SYSTEMS AND METHODS FOR MEASURING ENERGY EXPENDITURE OF AN INDIVIDUAL
Various methods and apparatuses for measuring a state parameter of an individual using signals based on one or more sensors are disclosed. In one embodiment, a first set of signals is used in a first function to determine how a second set of signals is used in one or more second functions to predict the state parameter. In another embodiment, first and second functions are used where the state parameter or an indicator of the state parameter may be obtained from a relationship between the first function and the second function. The state parameter may, for example, include calories consumed or calories burned by the individual. Various methods for making such apparatuses are also disclosed.
This application is a continuation of co-pending U.S. patent application Ser. No. 10/682,293 filed Oct. 9, 2003, which claims the benefit of U.S. Provisional Application No. 60/417,163 filed on Oct. 9, 2002.
BACKGROUND1. Field
The present invention relates to methods and apparatuses for measuring a state parameter of an individual using signals based on one or more sensors. The present invention also relates to various methods for making such apparatuses.
2. Description of the Related Art
Research has shown that a large number of the top health problems in society are either caused in whole or in part by an unhealthy lifestyle. More and more, our society requires people to lead fast paced, achievement oriented lifestyles that often result in poor eating habits, high stress levels, lack of exercise, poor sleep habits and the inability to find the time to center the mind and relax. Recognizing this fact, people are becoming increasingly interested in establishing a healthier lifestyle.
Traditional medicine, embodied in the form of an HMO or similar organizations, does not have the time, the training, or the reimbursement mechanism to address the needs of those individuals interested in a healthier lifestyle. There have been several attempts to meet the needs of these individuals, including a perfusion of fitness programs and exercise equipment, dietary plans, self help books, alternative therapies, and most recently, a plethora of health information web sites on the Internet. Each of these attempts are targeted to empower the individual to take charge and get healthy. Each of these attempts, however, addresses only part of the needs of individuals seeking a healthier lifestyle and ignores many of the real barriers that most individuals face when trying to adopt a healthier lifestyle. These barriers include the fact that the individual is often left to himself or herself to find motivation, to implement a plan for achieving a healthier lifestyle, to monitor progress, and to brainstorm solutions when problems arise; the fact that existing programs are directed to only certain aspects of a healthier lifestyle, and rarely come as a complete package; and the fact that recommendations are often not targeted to the unique characteristics of the individual or his life circumstances.
SUMMARYThe present invention relates to an apparatus for measuring a state parameter of an individual including a processor, at least two sensors in electronic communication with the processor, at least one of the sensors being a physiological sensor, and a memory for storing software executable by the processor. The software includes instructions for collecting a plurality of sensor signals from the at least two sensors, and utilizing a first set of signals based on one or more of the plurality of sensor signals in a first function, the first function determining how a second set of signals based on one or more of the plurality of sensor signals is utilized in one or more second functions, each of the one or more second functions having an output, wherein one or more of the outputs are used to predict the state parameter of the individual.
The present invention also relates to a method of measuring a state parameter of an individual, including collecting a plurality of sensor signals from at least two sensors in electronic communication with a sensor device worn on a body of the individual, at least one of the sensors being a physiological sensor, and utilizing a first set of signals based on one or more of the plurality of sensor signals in a first function, the first function determining how a second set of signals based on one or more of the plurality of sensor signals is utilized in one or more second functions, each of the one or more second functions having an output, wherein one or more of the outputs are used to predict the state parameter of the individual.
In one embodiment of either the apparatus or method, the first function recognizes one or more contexts based on the first set of signals and one or more of the second functions is chosen based on the one or more recognized contexts. The outputs of the chosen second functions are used to predict the state parameter of the individual. In another embodiment, the first function recognizes each of a plurality of contexts based on the first set of signals and each of the one or more second functions corresponds to one of the contexts. The first function assigns a weight to each of the one or more second functions based on a recognition probability associated with the corresponding context, and the outputs of the one or more second functions and the weights are used to predict the state parameter of the individual. The outputs may be combined in a post processing step to predict the state parameter. In addition, in either the apparatus or the method, the state parameter may be caloric expenditure the second functions may be regression algorithms, the contexts may comprise rest and active and, the first function may comprise a naïve Bayesian classifier. Where the state parameter is caloric expenditure, caloric consumption data for the individual may be generated and information based on the caloric expenditure data and the caloric consumption data may be displayed, such as energy balance data, rate of weight loss or gain, or information relating to one or more goals of the individual.
In one embodiment of the apparatus, the processor and the memory are included in a wearable sensor device. In another embodiment, the apparatus includes a wearable sensor device, the processor and the memory being included in a computing device located separately from the sensor device, wherein the sensor signals are transmitted from the sensor device to the computing device.
The present invention also relates to a method of making software for an apparatus for measuring a state parameter of an individual including providing a first sensor device, the first sensor device receiving a plurality of signals from at least two sensors, using the first sensor device to create a first function and one or more second functions, each of the one or more second functions having an output, the first function utilizing a first set of signals based on one or more of the plurality of sensor signals to determine how a second set of signals based on one or more of the plurality of sensor signals is utilized in the one or more second functions, wherein one or more of the outputs are used to predict the state parameter of the individual. The method further includes creating the software including instructions for: (i) receiving a second plurality of signals collected by a second sensor device substantially structurally identical to the first sensor device for a period of time; (ii) utilizing a third set of signals based on one or more of the second plurality of sensor signals in the first function to determine how a fourth set of signals based on one or more of the second plurality of sensor signals is utilized in the one or more second functions; and (iii) utilizing the one or more outputs produced by the one or more second functions from the fourth set of signals to predict the state parameter of the individual. In the method, the step of using the sensor device to create the first function and the one or more second functions may include gathering a first set of the plurality of signals under conditions where the state parameter is present, contemporaneously gathering gold standard data relating to the state parameter, and using one or more machine learning techniques to generate the first function and the one or more second functions from the first set of the plurality of signals and the gold standard data. In addition, A the first function may recognize one or more contexts based on the first set of signals and one or more of the second functions may be chosen based on the one or more recognized contexts, wherein the outputs of the chosen second functions are used to predict the state parameter of the individual. Alternatively, the first function may recognize each of a plurality of contexts based on the first set of signals and each of the one or more second functions may correspond to one of the contexts, wherein the first function assigns a weight to each of the one or more second functions based on a recognition probability associated with the corresponding context, and wherein the outputs of the one or more second functions and the weights are used to predict the state parameter of the individual.
One specific embodiment of the present invention relates to a method of measuring energy expenditure of an individual including collecting a plurality of sensor signals from at least two of a body motion sensor, a heat flux sensor, a skin conductance sensor, and a skin temperature sensor, each in electronic communication with a sensor device worn on a body of the individual, and utilizing a first set of signals based on one or more of the plurality of sensor signals in one or more functions to predict the energy expenditure of the individual. The utilizing step may include utilizing the first set of signals in a first function, the first function determining how a second set of signals based on one or more of the plurality of sensor signals is utilized in one or more second functions, each of the one or more second functions having an output, wherein one or more of the outputs are used to predict the energy expenditure of the individual. In addition, the collecting step may include collecting the plurality of sensor signals from a body motion sensor, a heat flux sensor, and a skin conductance sensor, the second set of signals comprising a heat flux high gain average variance (HFvar), a vector sum of transverse and longitudinal accelerometer SADs (VSAD), and a galvanic skin response low gain (GSR), wherein the second functions have the form of A*VSAD+B*HF+C*GSR+D*BMR+E, wherein A, B, C, D and E are constants and BMR is a basal metabolic rate for the individual.
The present invention also relates to an apparatus for measuring energy expenditure of an individual including a processor, at least two of a body motion sensor, a heat flux sensor, a skin conductance sensor, and a skin temperature sensor in electronic communication with the processor, and a memory storing software executable by the processor. The software includes instructions for collecting a plurality of sensor signals from the at least two of a body motion sensor, a heat flux sensor, a skin conductance sensor, and a skin temperature sensor, and utilizing a first set of signals based on one or more of the plurality of sensor signals in one or more functions to predict the energy expenditure of the individual. The utilizing instruction may include utilizing the first set of signals in a first function, the first function determining how a second set of signals based on one or more of the plurality of sensor signals is utilized in one or more second functions, each of the one or more second functions having an output, wherein one or more of the outputs are used to predict the energy expenditure of the individual. The collecting instruction may include collecting the plurality of sensor signals from a body motion sensor, a heat flux sensor, and a skin conductance sensor, the second set of signals comprising a heat flux high gain average variance (HFvar), a vector sum of transverse and longitudinal accelerometer SADs (VSAD), and a galvanic skin response low gain (GSR), wherein the second functions have the form of A*VSAD+B*HF+C*GSR+D*BMR+E, wherein A, B, C, D and E are constants and BMR is a basal metabolic rate for the individual.
The present invention also relates to a method of making software for an apparatus for measuring energy expenditure of an individual, including providing a first sensor device, the first sensor device receiving a plurality of signals from at least two of a body motion sensor, a heat flux sensor, a skin conductance sensor, and a skin temperature sensor, and using the first sensor device to create one or more functions that predict the energy expenditure of the individual using a first set of signals based on one or more of the plurality of sensor signals. The method further includes creating the software including instructions for: (i) receiving a second plurality of signals collected by a second sensor device substantially structurally identical to the first sensor device for a period of time, the second sensor device receiving the second plurality of signals from at least two of a body motion sensor, a heat flux sensor, a skin conductance sensor, and a skin temperature sensor; and (ii) utilizing a second set of signals based on one or more of the second plurality of sensor signals in the one or more functions to predict the energy expenditure of the individual. The step of using the sensor device to create the one or more functions may include gathering a first set of the plurality of signals under conditions where energy expenditure data for the individual is present, contemporaneously gathering gold standard data relating to the energy expenditure data for the individual, and using one or more machine learning techniques to generate the one or more functions from the first set of the plurality of signals and the gold standard data. In addition, the utilizing instruction may include utilizing the second set of signals in a first function, the first function determining how a third set of signals based on one or more of the second plurality of sensor signals is utilized in one or more second functions, each of the one or more second functions having an output; wherein one or more of the outputs are used to predict the energy expenditure of the individual.
In yet another embodiment, the present invention relates to an apparatus for automatically measuring a first state parameter of an individual, including a processor, one or more sensors for generating one or more signals over a period of time, the processor receiving the one or more signals, and a memory storing software executable by the processor. The software includes instructions for inputting one or more signal channels based on the one or more signals into a first function having a first output that predicts one or more second state parameters of the individual and either the first state parameter or an indicator of the first state parameter, wherein the first state parameter may be obtained from the indicator based on a first relationship between the first state parameter and the indicator, inputting the one or more signal channels into a second function having a second output that predicts the one or more second state parameters but not the first state parameter or the indicator of the first state parameter, and obtaining either the first state parameter or the indicator from the first and second outputs based on a second relationship between the first function and the second function, and, if the indicator is obtained, obtaining the first state parameter from the indicator based on the first relationship.
The present invention also relates to a method of automatically measuring a first state parameter of an individual, including collecting for a period of time one or more signals from one or more sensors in electronic communication with a sensor device worn on a body of the individual, inputting one or more signal channels based on the one or more signals into a first function having a first output that predicts one or more second state parameters of the individual and either the first state parameter or an indicator of the first state parameter, wherein the first state parameter may be obtained from the indicator based on a first relationship between the first state parameter and the indicator, inputting the one or more signal channels into a second function having a second output that predicts the one or more second state parameters but not the first state parameter or the indicator of the first state parameter, and obtaining either the first state parameter or the indicator from the first and second outputs based on a second relationship between the first function and the second function, and, if the indicator is obtained, obtaining the first state parameter from the indicator based on the first relationship.
In either the method or the apparatus, the first state parameter may be a number of calories consumed by the individual during the period of time. In such an embodiment, the indicator may include a first effect on the body of food consumed, and in particular, the indicator may be the thermic effect of food. In the case of thermic effect of food, the first output may comprise total energy expenditure, wherein the one or more second state parameters include basal metabolic rate, activity energy expenditure and adaptive thermogenesis, and the first state parameter may be obtained from the indicator by dividing the indicator by 0.1. In one specific embodiment, the software further includes instructions for generating caloric expenditure data for the individual for the period of time from one or more of the one or more signal channels and displaying information based on the caloric expenditure data and the number of calories consumed by the individual. The apparatus may include a display, such as part of a separate I/O device, for displaying the information based on the caloric expenditure data and the number of calories consumed by the individual.
In yet another embodiment, the present invention relates to a method of making software for an apparatus for automatically measuring a first state parameter of an individual. The method includes providing a first sensor device, the first sensor device receiving one or more signals from one or more sensors, using the first sensor device to create a first function having a first output that predicts one or more second state parameters of the individual and either the first state parameter or an indicator of the first state parameter, wherein the first state parameter may be obtained from the indicator based on a first relationship between the first state parameter and the indicator, the first function taking as inputs one or more signal channels based on the one or more signals, and using the first sensor device to create a second function having a second output that predicts the one or more second state parameters but not the first state parameter or the indicator of the first state parameter, the second function taking as inputs the one or more signal channels. The method further includes creating the software including instructions for: (i) receiving a second one or more signals collected by a second sensor device substantially structurally identical to the first sensor device for a period of time; (ii) inputting a second one or more signal channels based on the second one or more signals into the first function and the second function for generating the first output and the second output, respectively; and (iii) obtaining either the first state parameter or the indicator from the first and second outputs generated in the inputting step based on a second relationship between the first function and the second function, and, if the indicator is obtained, obtaining the first state parameter from the indicator based on the first relationship. The step of using the sensor device to create the first function may include gathering a first set of the one or more signals under conditions where the second state parameters and either the first state parameter or the indicator are present, contemporaneously gathering gold standard data relating to the second state parameters and either the first state parameter or the indicator, and using one or more machine learning techniques to generate the first function from the first set of one or more signals and the gold standard data, and the step of using the sensor device to create the second function may include gathering a second set of the one or more signals under conditions where neither the first state parameter nor the indicator are present, contemporaneously gathering second gold standard data relating to the second state parameters but not the first state parameter or the indicator, and using one or more machine learning techniques to generate the second function from the second set of one or more signals and the second gold standard data.
In still another alternate embodiment, the present invention relates to a method of measuring caloric consumption of an individual for a time period, including determining a weight differential for the individual between a beginning of the time period and an end of the time period, multiplying the weight differential by a constant, such as 3500, to obtain a caloric differential, measuring a caloric expenditure of the individual for the time period using a wearable sensor device having one or more sensors, and determining the caloric consumption from the caloric differential and the caloric expenditure. The step of measuring the caloric expenditure may comprises collecting a plurality of sensor signals from at least two sensors in electronic communication with the sensor device, at least one of the sensors being a physiological sensor, and utilizing a first set of signals based on one or more of the plurality of sensor signals in a first function, the first function determining how a second set of signals based on one or more of the plurality of sensor signals is utilized in one or more second functions, each of the one or more second functions having an output, wherein one or more of the outputs are used to predict the caloric expenditure.
Further features and advantages of the present invention will be apparent upon consideration of the following detailed description of the present invention, taken in conjunction with the following drawings, in which like reference characters refer to like parts, and in which:
In general, according to the present invention, data relating to the physiological state, the lifestyle and certain contextual parameters of an individual is collected and transmitted, either subsequently or in real-time, to a site, preferably remote from the individual, where it is stored for later manipulation and presentation to a recipient, preferably over an electronic network such as the Internet. Contextual parameters as used herein means parameters relating to the environment, surroundings and location of the individual, including, but not limited to, air quality, sound quality, ambient temperature, global positioning and the like. Referring to
Sensor device 10 generates data indicative of various physiological parameters of an individual, such as the individual's heart rate, pulse rate, beat-to-beat heart variability, EKG or ECG, respiration rate, skin temperature, core body temperature, heat flow off the body, galvanic skin response or GSR, EMG, EEG, EOG, blood pressure, body fat, hydration level, activity level, oxygen consumption, glucose or blood sugar level, body position, pressure on muscles or bones, and UV radiation exposure and absorption. In certain cases, the data indicative of the various physiological parameters is the signal or signals themselves generated by the one or more sensors and in certain other cases the data is calculated by the microprocessor based on the signal or signals generated by the one or more sensors. Methods for generating data indicative of various physiological parameters and sensors to be used therefor are well known. Table 1 provides several examples of such well known methods and shows the parameter in question, the method used, the sensor device used, and the signal that is generated. Table 1 also provides an indication as to whether further processing based on the generated signal is required to generate the data.
The types of data listed in Table 1 are intended to be examples of the types of data that can be generated by sensor device 10. It is to be understood that other types of data relating to other parameters can be generated by sensor device 10 without departing from the scope of the present invention.
The microprocessor of sensor device 10 may be programmed to summarize and analyze the data. For example, the microprocessor can be programmed to calculate an average, minimum or maximum heart rate or respiration rate over a defined period of time, such as ten minutes. Sensor device 10 may be able to derive information relating to an individual's physiological state based on the data indicative of one or more physiological parameters. The microprocessor of sensor device 10 is programmed to derive such information using known methods based on the data indicative of one or more physiological parameters. Table 2 provides examples of the type of information that can be derived, and indicates some of the types of data that can be used therefor.
Additionally, sensor device 10 may also generate data indicative of various contextual parameters relating to the environment surrounding the individual. For example, sensor device 10 can generate data indicative of the air quality, sound level/quality, light quality or ambient temperature near the individual, or even the global positioning of the individual. Sensor device 10 may include one or more sensors for generating signals in response to contextual characteristics relating to the environment surrounding the individual, the signals ultimately being used to generate the type of data described above. Such sensors are well known, as are methods for generating contextual parametric data such as air quality, sound level/quality, ambient temperature and global positioning.
A digital signal or signals representing certain physiological and/or contextual characteristics of the individual user may be used by microprocessor 20 to calculate or generate data indicative of physiological and/or contextual parameters of the individual user. Microprocessor 20 is programmed to derive information relating to at least one aspect of the individual's physiological state. It should be understood that microprocessor 20 may also comprise other forms of processors or processing devices, such as a microcontroller, or any other device that can be programmed to perform the functionality described herein.
The data indicative of physiological and/or contextual parameters can, according to one embodiment of the present invention, be sent to memory 22, such as flash memory, where it is stored until uploaded in the manner to be described below. Although memory 22 is shown in
The uploading of data from sensor device 10 to central monitoring unit 30 for storage can be accomplished in various ways. In one embodiment, the data collected by sensor device 10 is uploaded by first transferring the data to personal computer 35 shown in
Once the data is received by personal computer 35, it is optionally compressed and encrypted by any one of a variety of well known methods and then sent out over a local or global electronic network, preferably the Internet, to central monitoring unit 30. It should be noted that personal computer 35 can be replaced by any computing device that has access to and that can transmit and receive data through the electronic network, such as, for example, a personal digital assistant such as the Palm VII sold by Palm, Inc., or the Blackberry 2-way pager sold by Research in Motion, Inc.
Alternatively, the data collected by sensor device 10, after being encrypted and, optionally, compressed by microprocessor 20, may be transferred to wireless device 50, such as a 2 way pager or cellular phone, for subsequent long distance wireless transmission to local telco site 55 using a wireless protocol such as e mail or as ASCII or binary data. Local telco site 55 includes tower 60 that receives the wireless transmission from wireless device 50 and computer 65 connected to tower 60. According to the preferred embodiment, computer 65 has access to the relevant electronic network, such as the Internet, and is used to transmit the data received in the form of the wireless transmission to the central monitoring unit 30 over the Internet. Although wireless device 50 is shown in
Sensor device 10 may be provided with a button to be used to time stamp events such as time to bed, wake time, and time of meals. These time stamps are stored in sensor device 10 and are uploaded to central monitoring unit 30 with the rest of the data as described above. The time stamps may include a digitally recorded voice message that, after being uploaded to central monitoring unit 30, are translated using voice recognition technology into text or some other information format that can be used by central monitoring unit 30.
In addition to using sensor device 10 to automatically collect physiological data relating to an individual user, a kiosk could be adapted to collect such data by, for example, weighing the individual, providing a sensing device similar to sensor device 10 on which an individual places his or her hand or another part of his or her body, or by scanning the individual's body using, for example, laser technology or an iStat blood analyzer. The kiosk would be provided with processing capability as described herein and access to the relevant electronic network, and would thus be adapted to send the collected data to the central monitoring unit 30 through the electronic network. A desktop sensing device, again similar to sensor device 10, on which an individual places his or her hand or another part of his or her body may also be provided. For example, such a desktop sensing device could be a blood pressure monitor in which an individual places his or her arm. An individual might also wear a ring having a sensor device 10 incorporated therein. A base, not shown, could then be provided which is adapted to be coupled to the ring. The desktop sensing device or the base just described may then be coupled to a computer such as personal computer 35 by means of a physical or short range wireless connection so that the collected data could be uploaded to central monitoring unit 30 over the relevant electronic network in the manner described above. A mobile device such as, for example, a personal digital assistant, might also be provided with a sensor device 10 incorporated therein. Such a sensor device 10 would be adapted to collect data when mobile device is placed in proximity with the individual's body, such as by holding the device in the palm of one's hand, and upload the collected data to central monitoring unit 30 in any of the ways described herein.
Furthermore, in addition to collecting data by automatically sensing such data in the manners described above, individuals can also manually provide data relating to various life activities that is ultimately transferred to and stored at central monitoring unit 30. An individual user can access a web site maintained by central monitoring unit 30 and can directly input information relating to life activities by entering text freely, by responding to questions posed by the web site, or by clicking through dialog boxes provided by the web site. Central monitoring unit 30 can also be adapted to periodically send electronic mail messages containing questions designed to elicit information relating to life activities to personal computer 35 or to some other device that can receive electronic mail, such as a personal digital assistant, a pager, or a cellular phone. The individual would then provide data relating to life activities to central monitoring unit 30 by responding to the appropriate electronic mail message with the relevant data. Central monitoring unit 30 may also be adapted to place a telephone call to an individual user in which certain questions would be posed to the individual user. The user could respond to the questions by entering information using a telephone keypad, or by voice, in which case conventional voice recognition technology would be used by central monitoring unit 30 to receive and process the response. The telephone call may also be initiated by the user, in which case the user could speak to a person directly or enter information using the keypad or by voice/voice recognition technology. Central monitoring unit 30 may also be given access to a source of information controlled by the user, for example the user's electronic calendar such as that provided with the Outlook product sold by Microsoft Corporation of Redmond, Wash., from which it could automatically collect information. The data relating to life activities may relate to the eating, sleep, exercise, mind centering or relaxation, and/or daily living habits, patterns and/or activities of the individual. Thus, sample questions may include: What did you have for lunch today? What time did you go to sleep last night? What time did you wake up this morning? How long did you run on the treadmill today?
Feedback may also be provided to a user directly through sensor device 10 in a visual form, for example through an LED or LCD or by constructing sensor device 10, at least in part, of a thermochromatic plastic, in the form of an acoustic signal or in the form of tactile feedback such as vibration. Such feedback may be a reminder or an alert to eat a meal or take medication or a supplement such as a vitamin, to engage in an activity such as exercise or meditation, or to drink water when a state of dehydration is detected. Additionally, a reminder or alert can be issued in the event that a particular physiological parameter such as ovulation has been detected, a level of calories burned during a workout has been achieved or a high heart rate or respiration rate has been encountered.
As will be apparent to those of skill in the art, it may be possible to Adownload@ data from central monitoring unit 30 to sensor device 10. The flow of data in such a download process would be substantially the reverse of that described above with respect to the upload of data from sensor device 10. Thus, it is possible that the firmware of microprocessor 20 of sensor device 10 can be updated or altered remotely, i.e., the microprocessor can be reprogrammed, by downloading new firmware to sensor device 10 from central monitoring unit 30 for such parameters as timing and sample rates of sensor device 10. Also, the reminders/alerts provided by sensor device 10 may be set by the user using the web site maintained by central monitoring unit 30 and subsequently downloaded to the sensor device 10.
Referring to
Central monitoring unit 30 includes network storage device 100, such as a storage area network or SAN, which acts as the central repository for data. In particular, network storage device 100 comprises a database that stores all data gathered for each individual user in the manners described above. An example of a suitable network storage device 100 is the Symmetrix product sold by EMC Corporation of Hopkinton, Mass. Although only one network storage device 100 is shown in
Middleware servers 95a through 95c, a suitable example of which is the 22OR Dual Processor sold by Sun Microsystems, Inc. of Palo Alto, Calif., each contain software for generating and maintaining the corporate or home web page or pages of the web site maintained by central monitoring unit 30. As is known in the art, a web page refers to a block or blocks of data available on the World-Wide Web comprising a file or files written in Hypertext Markup Language or HTML, and a web site commonly refers to any computer on the Internet running a World-Wide Web server process. The corporate or home web page or pages are the opening or landing web page or pages that are accessible by all members of the general public that visit the site by using the appropriate uniform resource locator or URL. As is known in the art, URLs are the form of address used on the World-Wide Web and provide a standard way of specifying the location of an object, typically a web page, on the Internet. Middleware servers 95a through 95c also each contain software for generating and maintaining the web pages of the web site of central monitoring unit 30 that can only be accessed by individuals that register and become members of central monitoring unit 30. The member users will be those individuals who wish to have their data stored at central monitoring unit 30. Access by such member users is controlled using passwords for security purposes. Preferred embodiments of those web pages are described in detail below and are generated using collected data that is stored in the database of network storage device 100.
Middleware servers 95a through 95c also contain software for requesting data from and writing data to network storage device 100 through database server 110. When an individual user desires to initiate a session with the central monitoring unit 30 for the purpose of entering data into the database of network storage device 100, viewing his or her data stored in the database of network storage device 100, or both, the user visits the home web page of central monitoring unit 30 using a browser program such as Internet Explorer distributed by Microsoft Corporation of Redmond, Wash., and logs in as a registered user. Load balancer 90 assigns the user to one of the middleware servers 95a through 95c, identified as the chosen middleware server. A user will preferably be assigned to a chosen middleware server for each entire session. The chosen middleware server authenticates the user using any one of many well known methods, to ensure that only the true user is permitted to access the information in the database. A member user may also grant access to his or her data to a third party such as a health care provider or a personal trainer. Each authorized third party may be given a separate password and may view the member user's data using a conventional browser. It is therefore possible for both the user and the third party to be the recipient of the data.
When the user is authenticated, the chosen middleware server requests, through database server 110, the individual user's data from network storage device 100 for a predetermined time period. The predetermined time period is preferably thirty days. The requested data, once received from network storage device 100, is temporarily stored by the chosen middleware server in cache memory. The cached data is used by the chosen middleware server as the basis for presenting information, in the form of web pages, to the user again through the user's browser. Each middleware server 95a through 95c is provided with appropriate software for generating such web pages, including software for manipulating and performing calculations utilizing the data to put the data in appropriate format for presentation to the user. Once the user ends his or her session, the data is discarded from cache. When the user initiates a new session, the process for obtaining and caching data for that user as described above is repeated. This caching system thus ideally requires that only one call to the network storage device 100 be made per session, thereby reducing the traffic that database server 110 must handle. Should a request from a user during a particular session require data that is outside of a predetermined time period of cached data already retrieved, a separate call to network storage device 100 may be performed by the chosen middleware server. The predetermined time period should be chosen, however, such that such additional calls are minimized Cached data may also be saved in cache memory so that it can be reused when a user starts a new session, thus eliminating the need to initiate a new call to network storage device 100.
As described in connection with Table 2, the microprocessor of sensor device 10 may be programmed to derive information relating to an individual's physiological state based on the data indicative of one or more physiological parameters. Central monitoring unit 30, and preferably middleware servers 95a through 95c, may also be similarly programmed to derive such information based on the data indicative of one or more physiological parameters.
It is also contemplated that a user will input additional data during a session, for example, information relating to the user's eating or sleeping habits. This additional data is preferably stored by the chosen middleware server in a cache during the duration of the user's session. When the user ends the session, this additional new data stored in a cache is transferred by the chosen middleware server to database server 110 for population in network storage device 100. Alternatively, in addition to being stored in a cache for potential use during a session, the input data may also be immediately transferred to database server 110 for population in network storage device 100, as part of a write-through cache system which is well known in the art.
Data collected by sensor device 10 shown in
Referring to
Third parties such as insurance companies or research institutions may be given access, possibly for a fee, to certain of the information stored in mirror network storage device 120. Preferably, in order to maintain the confidentiality of the individual users who supply data to central monitoring unit 30, these third parties are not given access to such user's individual database records, but rather are only given access to the data stored in mirror network storage device 120 in aggregate form. Such third parties may be able to access the information stored in mirror network storage device 120 through the Internet using a conventional browser program. Requests from third parties may come in through CSU/DSU 70, router 75, firewall 80 and switch 85. In the embodiment shown in
As will be apparent to one of skill in the art, instead of giving these third parties access to the backup data stored in mirror network storage device 120, the third parties may be given access to the data stored in network storage device 100. Also, instead of providing load balancer 130 and middleware servers 135a through 135c, the same functionality, although at a sacrificed level of performance, could be provided by load balancer 90 and middleware servers 95a through 95c.
When an individual user first becomes a registered user or member, that user completes a detailed survey. The purposes of the survey are to: identify unique characteristics/circumstances for each user that they might need to address in order to maximize the likelihood that they will implement and maintain a healthy lifestyle as suggested by central monitoring unit 30; gather baseline data which will be used to set initial goals for the individual user and facilitate the calculation and display of certain graphical data output such as the Health Index pistons; identify unique user characteristics and circumstances that will help central monitoring unit 30 customize the type of content provided to the user in the Health Manager's Daily Dose; and identify unique user characteristics and circumstances that the Health Manager can guide the user to address as possible barriers to a healthy lifestyle through the problem-solving function of the Health Manager.
The specific information to be surveyed may include: key individual temperamental characteristics, including activity level, regularity of eating, sleeping, and bowel habits, initial response to situations, adaptability, persistence, threshold of responsiveness, intensity of reaction, and quality of mood; the user's level of independent functioning, i.e., self-organization and management, socialization, memory, and academic achievement skills; the user's ability to focus and sustain attention, including the user's level of arousal, cognitive tempo, ability to filter distractions, vigilance, and self-monitoring; the user's current health status including current weight, height, and blood pressure, most recent general physician visit, gynecological exam, and other applicable physician/healthcare contacts, current medications and supplements, allergies, and a review of current symptoms and/or health-related behaviors; the user's past health history, i.e., illnesses/surgeries, family history, and social stress events, such as divorce or loss of a job, that have required adjustment by the individual; the user's beliefs, values and opinions about health priorities, their ability to alter their behavior and, what might contribute to stress in their life, and how they manage it; the user's degree of self-awareness, empathy, empowerment, and self-esteem, and the user's current daily routines for eating, sleeping, exercise, relaxation and completing activities of daily living; and the user's perception of the temperamental characteristics of two key persons in their life, for example, their spouse, a friend, a co-worker, or their boss, and whether there are clashes present in their relationships that might interfere with a healthy lifestyle or contribute to stress.
Each member user will have access, through the home web page of central monitoring unit 30, to a series of web pages customized for that user, referred to as the Health Manager. The opening Health Manager web page 150 is shown in
Located on the opening Health Manager web page 150 is Health Index 155. Health Index 155 is a graphical utility used to measure and provide feedback to member users regarding their performance and the degree to which they have succeeded in reaching a healthy daily routine suggested by central monitoring unit 30. Health Index 155 thus provides an indication for the member user to track his or her progress. Health Index 155 includes six categories relating to the user's health and lifestyle: Nutrition, Activity Level, Mind Centering, Sleep, Daily Activities and How You Feel. The Nutrition category relates to what, when and how much a person eats and drinks. The Activity Level category relates to how much a person moves around. The Mind Centering category relates to the quality and quantity of time a person spends engaging in some activity that allows the body to achieve a state of profound relaxation while the mind becomes highly alert and focused. The Sleep category relates to the quality and quantity of a person's sleep. The Daily Activities category relates to the daily responsibilities and health risks people encounter. Finally, the How You Feel category relates to the general perception that a person has about how they feel on a particular day. Each category has an associated level indicator or piston that indicates, preferably on a scale ranging from poor to excellent, how the user is performing with respect to that category.
When each member user completes the initial survey described above, a profile is generated that provides the user with a summary of his or her relevant characteristics and life circumstances. A plan and/or set of goals is provided in the form of a suggested healthy daily routine. The suggested healthy daily routine may include any combination of specific suggestions for incorporating proper nutrition, exercise, mind centering, sleep, and selected activities of daily living in the user's life. Prototype schedules may be offered as guides for how these suggested activities can be incorporated into the user's life. The user may periodically retake the survey, and based on the results, the items discussed above will be adjusted accordingly.
The Nutrition category is calculated from both data input by the user and sensed by sensor device 10. The data input by the user comprises the time and duration of breakfast, lunch, dinner and any snacks, and the foods eaten, the supplements such as vitamins that are taken, and the water and other liquids consumed during a relevant, pre-selected time period. Based upon this data and on stored data relating to known properties of various foods, central monitoring unit 30 calculates well known nutritional food values such as calories and amounts of proteins, fats, carbohydrates, vitamins, etc., consumed.
The Nutrition Health Index piston level is preferably determined with respect to the following suggested healthy daily routine: eat at least three meals; eat a varied diet consisting of 6-11 servings of bread, pasta, cereal, and rice, 2-4 servings fruit, 3-5 servings of vegetables, 2-3 servings of fish, meat, poultry, dry beans, eggs, and nuts, and 2-3 servings of milk, yogurt and cheese; and drink 8 or more 8 ounce glasses of water. This routine may be adjusted based on information about the user, such as sex, age, height and/or weight. Certain nutritional targets may also be set by the user or for the user, relating to daily calories, protein, fiber, fat, carbohydrates, and/or water consumption and percentages of total consumption. Parameters utilized in the calculation of the relevant piston level include the number of meals per day, the number of glasses of water, and the types and amounts of food eaten each day as input by the user.
Nutritional information is presented to the user through nutrition web page 160 as shown in
The Activity Level category of Health Index 155 is designed to help users monitor how and when they move around during the day and utilizes both data input by the user and data sensed by sensor device 10. The data input by the user may include details regarding the user's daily activities, for example the fact that the user worked at a desk from 8 a.m. to 5 p.m. and then took an aerobics class from 6 p.m. to 7 p.m. Relevant data sensed by sensor device 10 may include heart rate, movement as sensed by a device such as an accelerometer, heat flow, respiration rate, calories burned, GSR and hydration level, which may be derived by sensor device 60 or central monitoring unit 30. Calories burned may be calculated in a variety of manners, including: the multiplication of the type of exercise input by the user by the duration of exercise input by the user; sensed motion multiplied by time of motion multiplied by a filter constant; or sensed heat flux multiplied by time multiplied by a filter constant.
The Activity Level Health Index piston level is preferably determined with respect to a suggested healthy daily routine that includes: exercising aerobically for a pre-set time period, preferably 20 minutes, or engaging in a vigorous lifestyle activity for a pre-set time period, preferably one hour, and burning at least a minimum target number of calories, preferably 205 calories, through the aerobic exercise and/or lifestyle activity. The minimum target number of calories may be set according to information about the user, such as sex, age, height and/or weight. Parameters utilized in the calculation of the relevant piston level include the amount of time spent exercising aerobically or engaging in a vigorous lifestyle activity as input by the user and/or sensed by sensor device 10, and the number of calories burned above pre-calculated energy expenditure parameters.
Information regarding the individual user's movement is presented to the user through activity level web page 200 shown in
The Mind Centering category of Health Index 155 is designed to help users monitor the parameters relating to time spent engaging in certain activities which allow the body to achieve a state of profound relaxation while the mind becomes focused, and is based upon both data input by the user and data sensed by the sensor device 10. In particular, a user may input the beginning and end times of relaxation activities such as yoga or meditation. The quality of those activities as determined by the depth of a mind centering event can be measured by monitoring parameters including skin temperature, heart rate, respiration rate, and heat flow as sensed by sensor device 10. Percent change in GSR as derived either by sensor device 10 or central monitoring unit 30 may also be utilized.
The Mind Centering Health Index piston level is preferably calculated with respect to a suggested healthy daily routine that includes participating each day in an activity that allows the body to achieve profound relaxation while the mind stays highly focused for at least fifteen minutes. Parameters utilized in the calculation of the relevant piston level include the amount of time spent in a mind centering activity, and the percent change in skin temperature, heart rate, respiration rate, heat flow or GSR as sensed by sensor device 10 compared to a baseline which is an indication of the depth or quality of the mind centering activity.
Information regarding the time spent on self reflection and relaxation is presented to the user through mind centering web page 250 shown in
The Sleep category of Health Index 155 is designed to help users monitor their sleep patterns and the quality of their sleep. It is intended to help users learn about the importance of sleep in their healthy lifestyle and the relationship of sleep to circadian rhythms, being the normal daily variations in body functions. The Sleep category is based upon both data input by the user and data sensed by sensor device 10. The data input by the user for each relevant time interval includes the times the user went to sleep and woke up and a rating of the quality of sleep. As noted in Table 2, the data from sensor device 10 that is relevant includes skin temperature, heat flow, beat-to-beat heart variability, heart rate, pulse rate, respiration rate, core temperature, galvanic skin response, EMG, EEG, EOG, blood pressure, and oxygen consumption. Also relevant is ambient sound and body movement or motion as detected by a device such as an accelerometer. This data can then be used to calculate or derive sleep onset and wake time, sleep interruptions, and the quality and depth of sleep.
The Sleep Health Index piston level is determined with respect to a healthy daily routine including getting a minimum amount, preferably eight hours, of sleep each night and having a predictable bed time and wake time. The specific parameters which determine the piston level calculation include the number of hours of sleep per night and the bed time and wake time as sensed by sensor device 10 or as input by the user, and the quality of the sleep as rated by the user or derived from other data.
Information regarding sleep is presented to the user through sleep web page 290 shown in
The Activities of Daily Living category of Health Index 155 is designed to help users monitor certain health and safety related activities and risks and is based entirely on data input by the user. The Activities of Daily Living category is divided into four sub categories: personal hygiene, which allows the user to monitor activities such as brushing and flossing his or her teeth and showering; health maintenance, that tracks whether the user is taking prescribed medication or supplements and allows the user to monitor tobacco and alcohol consumption and automobile safety such as seat belt use; personal time, that allows the user to monitor time spent socially with family and friends, leisure, and mind centering activities; and responsibilities, that allows the user to monitor certain work and financial activities such as paying bills and household chores.
The Activities of Daily Living Health Index piston level is preferably determined with respect to the healthy daily routine described below. With respect to personal hygiene, the routine requires that the users shower or bathe each day, brush and floss teeth each day, and maintain regular bowel habits. With respect to health maintenance, the routine requires that the user take medications and vitamins and/or supplements, use a seat belt, refrain from smoking, drink moderately, and monitor health each day with the Health Manager. With respect to personal time, the routine requires the users to spend at least one hour of quality time each day with family and/or friends, restrict work time to a maximum of nine hours a day, spend some time on a leisure or play activity each day, and engage in a mind stimulating activity. With respect to responsibilities, the routine requires the users to do household chores, pay bills, be on time for work, and keep appointments. The piston level is calculated based on the degree to which the user completes a list of daily activities as determined by information input by the user.
Information relating to these activities is presented to the user through daily activities web page 330 shown in
The How You Feel category of Health Index 155 is designed to allow users to monitor their perception of how they felt on a particular day, and is based on information, essentially a subjective rating, that is input directly by the user. A user provides a rating, preferably on a scale of 1 to 5, with respect to the following nine subject areas: mental sharpness; emotional and psychological well being; energy level; ability to cope with life stresses; appearance; physical well being; self-control; motivation; and comfort in relating to others. Those ratings are averaged and used to calculate the relevant piston level.
Referring to
Referring again to
Opening Health Manager web page 150 also may include Daily Dose section 157 which provides, on a daily time interval basis, information to the user, including, but not limited to, hyperlinks to news items and articles, commentary and reminders to the user based on tendencies, such as poor nutritional habits, determined from the initial survey. The commentary for Daily Dose 157 may, for example, be a factual statement that drinking 8 glasses of water a day can reduce the risk of colon cancer by as much as 32%, accompanied by a suggestion to keep a cup of water by your computer or on your desk at work and refill often. Opening Health Manager web page 150 also may include a Problem Solver section 158 that actively evaluates the user's performance in each of the categories of Health Index 155 and presents suggestions for improvement. For example, if the system detects that a user's Sleep levels have been low, which suggest that the user has been having trouble sleeping, Problem Solver 158 can provide suggestions for way to improve sleep. Problem Solver 158 also may include the capability of user questions regarding improvements in performance. Opening Health Manager web page 150 may also include a Daily Data section 159 that launches an input dialog box. The input dialog box facilitates input by the user of the various data required by the Health Manager. As is known in the art, data entry may be in the form of selection from pre defined lists or general free form text input. Finally, opening Health Manager web page 150 may include Body Stats section 161 which may provide information regarding the user's height, weight, body measurements, body mass index or BMI, and vital signs such as heart rate, blood pressure or any of the identified physiological parameters.
Referring to
Elastic strap 415 is used to removably affix armband sensor device 400 to the individual's upper arm. As seen in
In order to wear armband sensor device 400, a user inserts each end 427 of elastic strap 415 into a respective thru-hole 420 of flexible wing body 410. The user then places his arm through the loop created by elastic strap 415, flexible wing body 410 and computer housing 405. By pulling each pull tab 429 and engaging Velcro hook patches 428 with Velcro loops 416 at a desired position along bottom surface 426 of elastic strap 415, the user can adjust elastic strap 415 to fit comfortably. Since Velcro hook patches 428 can be engaged with Velcro loops 416 at almost any position along bottom surface 426, armband sensor device 400 can be adjusted to fit arms of various sizes. Also, elastic strap 415 may be provided in various lengths to accommodate a wider range of arm sizes. As will be apparent to one of skill in the art, other means of fastening and adjusting the size of elastic strap may be used, including, but not limited to, snaps, buttons, or buckles. It is also possible to use two elastic straps that fasten by one of several conventional means including Velcro, snaps, buttons, buckles or the like, or merely a single elastic strap affixed to wings 418.
Alternatively, instead of providing thru-holes 420 in wings 418, loops having the shape of the letter D, not shown, may be attached to ends 425 of wings 418 by one of several conventional means. For example, a pin, not shown, may be inserted through ends 425, wherein the pin engages each end of each loop. In this configuration, the D-shaped loops would serve as connecting points for elastic strap 415, effectively creating a thru-hole between each end 425 of each wing 418 and each loop.
As shown in
Top portion 435 and bottom portion 440 of computer housing 405 sealingly mate along groove 436 into which O-ring 437 is fit, and may be affixed to one another by screws, not shown, which pass through screw holes 438a and stiffeners 438b of bottom portion 440 and apertures 439 in PCB 445 and into threaded receiving stiffeners 451 of top portion 435. Alternately, top portion 435 and bottom portion 440 may be snap fit together or affixed to one another with an adhesive. Preferably, the assembled computer housing 405 is sufficiently water resistant to permit armband sensor device 400 to be worn while swimming without adversely affecting the performance thereof.
As can be seen in
Electrical coupling between heat flux sensor 460, GSR sensors 465, and PCB 445 may be accomplished in one of various known methods. For example, suitable wiring, not shown, may be molded into bottom portion 440 of computer housing 405 and then electrically connected, such as by soldering, to appropriate input locations on PCB 445 and to heat flux sensor 460 and GSR sensors 465. Alternatively, rather than molding wiring into bottom portion 440, thru-holes may be provided in bottom portion 440 through which appropriate wiring may pass. The thru-holes would preferably be provided with a water tight seal to maintain the integrity of computer housing 405.
Rather than being affixed to raised platform 430 as shown in
As shown in
Armband sensor device 400 may be adapted to be activated for use, that is collecting data, when either of GSR sensors 465 or heat flux sensor 460 senses a particular condition that indicates that armband sensor device 400 has been placed in contact with the user's skin. Also, armband sensor device 400 may be adapted to be activated for use when one or more of heat flux sensor 460, GSR sensors 465, accelerometer 495 or 550, or any other device in communication with armband sensor device 400, alone or in combination, sense a particular condition or conditions that indicate that the armband sensor device 400 has been placed in contact with the user's skin for use. At other times, armband sensor device 400 would be deactivated, thus preserving battery power.
Computer housing 405 is adapted to be coupled to a battery recharger unit 480 shown in
Also provided inside battery recharger unit 480 is RF transceiver 483 adapted to receive signals from and transmit signals to RF transceiver 565 provided in computer housing 405 and shown in
As shown in
PCB 445 may include three-axis accelerometer 550 instead of or in addition to two-axis accelerometer 495. The three-axis accelerometer outputs a signal to processing unit 490. A suitable example of three-axis accelerometer is the μPAM product sold by I.M. Systems, Inc. of Scottsdale, Ariz. Three-axis accelerometer 550 is preferably tilted in the manner described with respect to two-axis accelerometer 495.
PCB 445 also includes RF receiver 555 that is coupled to processing unit 490. RF receiver 555 may be used to receive signals that are output by another device capable of wireless transmission, shown in
The fact that RF Transceiver 565 may be used for wirelessly uploading data from and wirelessly downloading data to armband sensor device 400 is advantageous because it eliminates the need to remove armband sensor device 400 to perform these functions, as would be required with a physical connection. For example, if armband sensor device 400 was being worn under the user's clothing, requiring removal of armband sensor device 400 prior to uploading and/or downloading data increases user inconvenience. In addition, the wearing of armband sensor device 400 has an effect on the user's skin and underlying blood vessels, which in turn may effect any measurements being made with respect thereto. It may be necessary for a period of time during which armband sensor device 400 is worn by the user to elapse before a steady state is achieved and consistent, accurate measurements can be made. By providing armband sensor device 400 with wireless communications capability, data can be uploaded and downloaded without disturbing an established steady state equilibrium condition. For example, programming data for processing unit 490 that controls the sampling characteristics of armband sensor device 400 can be downloaded to armband sensor device 400 without disturbing the steady state equilibrium condition.
In addition, antenna 560 and RF transceiver 565 permit armband sensor device 400 to communicate wirelessly with other devices capable of wireless communication, i.e., transmit information to and receive information from those devices. The devices may include, for example, devices that are implanted in the body of the person using armband sensor device 400, such as an implantable heart pacemaker or an implantable insulin dispensing device, for example the MiniMed® 2007 implantable insulin pump sold by MiniMed Inc. of Northridge, Calif., devices worn on the body of the person using armband sensor device 400, or devices located near the person using armband sensor device 400 at any particular time, such as an electronic scale, a blood pressure monitor, a glucose monitor, a cholesterol monitor or another armband sensor device 400. With this two-way wireless communication capability, armband sensor device 400 may be adapted to transmit information that activates or deactivates such a device for use or information that programs such a device to behave in a particular way. For example, armband sensor device 400 may be adapted to activate a piece of exercise equipment such as a treadmill and program it to operate with certain parameters that are dictated or desired by or optimal for the user of armband sensor device 400. As another example, armband sensor device 400 may be adapted to adjust a computer controlled thermostat in a home based on the detected skin temperature of the wearer or turn off a computer controlled lighting system, television or stereo when the wearer is determined to have fallen asleep.
Vibrating motor 455 is coupled to processing unit 490 through vibrator driver 570 and provides tactile feedback to the wearer. Similarly, ringer 575, a suitable example of which is the Model SMT916A ringer sold by Projects Unlimited, Inc. of Dayton, Ohio, is coupled to processing unit 490 through ringer driver 580, a suitable example of which is the Model MMBTA14 CTI darlington transistor driver sold by Motorola, Inc. of Schaumburg, Illinois, and provides audible feedback to the wearer. Feedback may include, for example, celebratory, cautionary and other threshold or event driven messages, such as when a wearer reaches a level of calories burned during a workout.
Also provided on PCB 445 and coupled to processing unit 490 is momentary switch 585. Momentary switch 585 is also coupled to button 470 for activating momentary switch 585. LEDs 475, used to provide various types of feedback information to the wearer, are coupled to processing unit 490 through LED latch/driver 590.
Oscillator 595 is provided on PCB 445 and supplies the system clock to processing unit 490. Reset circuit 600, accessible and triggerable through a pin-hole in the side of computer housing 405, is coupled to processing unit 490 and enables processing unit 490 to be reset to a standard initial setting.
Rechargeable battery 450, which is the main power source for the armband sensor device 400, is coupled to processing unit 490 through voltage regulator 605. Finally, memory functionality is provided for armband sensor device 400 by SRAM 610, which stores data relating to the wearer of armband sensor device 400, and flash memory 615, which stores program and configuration data, provided on PCB 445. SRAM 610 and flash memory 615 are coupled to processing unit 490 and each preferably have at least 512K of memory.
In manufacturing and assembling armband sensor device 400, top portion 435 of computer housing 405 is preferably formed first, such as by a conventional molding process, and flexible wing body 410 is then overmolded on top of top portion 435. That is, top portion 435 is placed into an appropriately shaped mold, i.e., one that, when top portion 435 is placed therein, has a remaining cavity shaped according to the desired shape of flexible wing body 410, and flexible wing body 410 is molded on top of top portion 435. As a result, flexible wing body 410 and top portion 435 will merge or bond together, forming a single unit. Alternatively, top portion 435 of computer housing 405 and flexible wing body 410 may be formed together, such as by molding in a single mold, to form a single unit. The single unit however formed may then be turned over such that the underside of top portion 435 is facing upwards, and the contents of computer housing 405 can be placed into top portion 435, and top portion 435 and bottom portion 440 can be affixed to one another. As still another alternative, flexible wing body 410 may be separately formed, such as by a conventional molding process, and computer housing 405, and in particular top portion 435 of computer housing 405, may be affixed to flexible wing body 410 by one of several known methods, such as by an adhesive, by snap-fitting, or by screwing the two pieces together. Then, the remainder of computer housing 405 would be assembled as described above. It will be appreciated that rather than assembling the remainder of computer housing 405 after top portion 435 has been affixed to flexible wing body 410, the computer housing 405 could be assembled first and then affixed to flexible wing body 410.
Referring to
As shown schematically in
As indicated by reference numbers 720 and 725, information comprising data indicative of various physiological and/or contextual parameters and data derived therefrom may be input into stand alone sensor device 700 through interaction with other devices. In addition, information such as handshake data or data indicative of various physiological and/or contextual parameters and data derived therefrom may be output from stand alone sensor device 700 to such other devices. According to one embodiment, the interaction is in the form of wireless communication between stand alone sensor device 700 and another device capable of wireless communication by way of a wireless transceiver provided in stand alone sensor device 700, such as wireless transceiver 565 shown and described in connection with
As shown schematically in
Also, computing device 750 may in turn be used to control other devices, such as the lights or thermostat in a home, based on data output by stand alone sensor device 700, such as the fact that the wearer has fallen asleep or the fact that the wearer's skin temperature has reached a certain level. In other words, stand alone sensor device 700, and in particular its processor, may be adapted to cause a computing device 750 to trigger an event upon detection of one or more physiological and/or contextual conditions by stand alone sensor device 700. Alternatively, stand alone sensor device 700 may be adapted to cause a computing device 750 to trigger an event based upon information received from another computing device 750.
Stand alone sensor device 700 may be adapted to interact with and influence an interactive electronic media device, such as a video game, or non-interactive electronic media device, such as on a display device such as a DVD or digital video disc player playing a digitally recorded movie. For example, stand alone sensor device 700 may be adapted to transmit information relating to the physiological state of the wearer to the video game, which in turn adjusts the characteristics of the game, such as the level of difficulty. As another example, stand alone sensor device 700 may be adapted to transmit information relating to the physiological state of the wearer to the device displaying the digitally recorded movie which in turn adjusts the characteristics, such as the outcome, of the movie.
Furthermore, stand alone sensor device 700 may include location sensing device 765, such as an ultrasonic or a radio-frequency identification tag, for enabling a computing device 750 to detect the geographic location of stand alone sensor device 700, such as the location of stand alone sensor device 700 within a defined space such as a building. In one embodiment, a location indication causes computing device 750 to trigger an event, such as lowering the temperature in a room corresponding to the indicated location, preferably based on the detection by stand alone sensor device 700 of one or more physiological conditions of the wearer, such as skin temperature. In another embodiment, the location indication causes computing device 750 to trigger an event, such as lowering the temperature in a room corresponding to the indicated location, if stand alone sensor device 700 detects one or more physiological conditions, such as a skin temperature of the wearer being above a certain level. In addition, the input means of the computing device, such as the mouse and keyboard of a personal computer, the keypad of a cell phone or pager, or the touch screen of a personal digital assistant, may be used to manually input information into stand alone sensor device 700.
The different modes of output may be used in combination to provide different types and levels of information to a user. For example, stand alone sensor device 700 could be worn by an individual while exercising and an LED or a tone can be used to signal that a goal of a certain number of calories burned has been reached. The user could then transmit additional data wirelessly from stand alone sensor device 700 to a computing device 750 such as a cell phone after he or she is finished exercising to view data such as heart rate and/or respiration rate over time.
As a further alternative embodiment of the present invention, rather than the processor provided in stand alone sensor device 700 being programmed and/or otherwise adapted to generate the derived data and to include the utilities and algorithms necessary to create analytical status data, computing device 750 could be so programmed. In this embodiment, stand alone sensor device 700 collects and/or generates the data indicative of various physiological and/or contextual parameters of the user, the data manually input by the user, and/or data input as a result of device-to-device interaction shown at 720 and 725, all of which is stored in the memory provided in stand alone sensor device 700. This data is then periodically uploaded to computing device 750 which in turn generates derived data and/or analytical status data. Alternatively, the processor of stand alone sensor device 700 could be programmed to generate the derived data with computing device 750 being programmed and/or otherwise adapted to include the utilities and algorithms necessary to create analytical status data based on data indicative of one or more physiological and/or contextual parameters, data derived therefrom, data manually input by the user and/or data input as a result of device-to-device interaction shown at 720 and 725 uploaded from stand alone sensor device 700. As still a further alternative, the processor of stand alone sensor device 700 could be programmed and/or otherwise adapted to include the utilities and algorithms necessary to create analytical status data based on data indicative of one or more physiological and/or contextual parameters, data derived therefrom, data manually input by the user and/or data input as a result of device-to-device interaction shown at 720 and 725 uploaded from stand alone sensor device 700 with computing device 750 being programmed to generate the derived data. In either alternative, any or all of the data indicative of physiological and/or contextual parameters of the user, the data derived therefrom, the data manually input by the user, the data input as a result of device-to-device interaction shown at 720 and 725 and the analytical status data may then be viewed by the user using the output means of the programmed computing device 750 or another computing device 750 to which the data is downloaded. In the latter alternative, everything but the analytical status data may also be output by stand alone sensor device 700 as described herein.
Computing device 750 in these alternative embodiments may be connected to an electronic network, such as the Internet, to enable it to communicate with central monitoring unit 30 or the like. The programming of computing device 750 that enables it to generate the derived data and/or the analytical status data may, with such a configuration, be modified or replaced by downloading the relevant data to computing device 750 over the electronic network.
As still a further alternative embodiment, computing device 750 may be provided with a custom written plug-in adapted to provide data display functionality through use of a well known browser program. In this embodiment, stand alone sensor device 700 collects and/or generates the data indicative of various physiological and/or contextual parameters of the user, the derived data, the data input by the user, data input as a result of device-to-device interaction shown at 720 and 725, and/or analytical status data based thereon and uploads this data to computing device 750. The plug-in provided in computing device 750 then generates appropriate display pages based on the data which may be viewed by the user using the browser provided with computing device 750. The plug-in may be modified/updated from a source such as central monitoring unit 30 over an electronic network such as the Internet.
Referring to
As can be seen most readily in
GSR Sensors 825, heat flux, skin interface component 835, skin temperature skin interface component 840, or any other sensing component that comes into contact with the skin may be provided with a plurality of microneedles for, among other things, enhancing electrical contact with the skin and providing real time access to interstitial fluid in and below the epidermis, which access may be used to measure various parameters such as pH level of the skin through electrochemical, impedance based or other well known methods. Microneedles enhance electrical contact by penetrating the stratum corneum of the skin to reach the epidermis. Such microneedles are well known in the art and may be made of a metal or plastic material. Prior art microneedles are described in, for example, U.S. Pat. No. 6,312,612 owned by the Procter and Gamble Company. Based on the particular application, the number, density, length, width at the point or base, distribution and spacing of the microneedles will vary.
Referring to
Still referring to
Heat Flux=K(T2−T1)
The combination of PCB 860 and heat flux thermistors 890A and 890B are thus a form of a heat flux sensor One advantage of the configuration of the apparatus for measuring heat flux shown in
As shown in
Battery monitor 945, preferably comprising a voltage divider with low pass filter to provide average battery voltage, monitors the remaining power level of rechargeable battery 950. Rechargeable battery 950 is preferably a LiIon/LiPolymer 3.7 V Cell. Rechargeable battery 950, which is the main power source for sensor device 800, is coupled to processing unit 900 through voltage regulator 955. Rechargeable battery 950 may be recharged either using recharger 960 or USB cable 965, both of which may be coupled to sensor device 800 through USB interface 970. Preferably, USB interface 970 is hermetically sealable, such as with a removable plastic or rubber plug, to protect the contacts of USB interface 970 when not in use.
PCB 860 further includes skin temperature thermistor 870 for sensing the temperature of the skin of the wearer of sensor device 800, and near-body ambient temperature thermistor 880 for sensing the ambient temperature in the area near the body of the wearer of sensor device 800. Each of these components is biased and coupled to processing unit 900 through A/D converter 915.
According to a specific embodiment of sensor device 800, PCB 860 may include one or both of an ambient light sensor and an ambient sound sensor, shown at 975 in
PCB 860 further includes RF transceiver 990, coupled to processing unit 900, and antenna 995 for wirelessly transmitting and receiving data to and from wireless devices in proximity to sensor device 800. RF transceiver 990 and antenna 995 may be used for transmitting and receiving data to and from a device such as a treadmill being used by a wearer of sensor device 800 or a heart rate monitor worn by the wearer of sensor device 800, or to upload and download data to and from a computing device such as a PDA or a PC. In addition, RF transceiver 990 and antenna 995 may be used to transmit information to a feedback device such as a bone conductivity microphone worn by a fireman to let the fireman know if a condition that may threaten the fireman's safety, such as hydration level or fatigue level, has been sensed by sensor device 800. As described in detail in connection with
As shown in
Sensor device 800 may also be provided with sensors in addition to those shown in
The sensing apparatus as taught by the '005 patent is an example of what shall be referred to herein as a non-ECG heart parameter sensor, meaning that it has the following two qualities: (1) it does not need to make measurements across the torso using at least two contact separated by some distance; and (2) it does not measure electrical activity of the heart. The sensing apparatus as taught by the '005 patent has been shown to be capable of detecting heart rate information and information relating to individual beats of the heart with high reliability under certain circumstances, depending primarily on factors including the proximity of the apparatus to the heart, the level of ambient noise, and motion related sound artifacts caused by the movement of the body. As a result, the sensing apparatus as taught by the '005 patent is most reliable when worn in an ambient environment with a low level of ambient noise and when the body is not moving.
Certain characteristics, sensors and sensing capabilities of sensor device 800 are able to improve the reliability and accuracy of an acoustic-based non-ECG heart parameter sensor 1012 such as the sensing apparatus as taught by the '005 patent that is incorporated therein or coupled thereto. For example, in one specific embodiment, sensor device 800 is particularly suited to be worn on the upper arm. The upper arm is a good location for a sensor device 800 having an acoustic-based non-ECG heart parameter sensor 1012 incorporated therein because it is near the heart and provides a space for sensor device that allows it to be unobtrusive and comfortable to wear. In addition, ambient sound sensor shown at 975 in
Several methodologies for performing the filtering or subtracting of signals described herein are known to those of ordinary skill in the art. Such filtering or subtracting of signals used in connection with the monitoring of disparate signal, some used for noise cancellation and some used for their direct measure, is also known as data integration.
Sensor device 800 may also be used to put parameters around and provide a context for the readings made by a non-ECG heart parameter sensor 1012 so that inaccurate reading can be identified and compensated for. For example, sensor device 800 may be used to detect real time energy expenditure of the wearer as well as the type of activity in which the wearer is engaging, such as running or riding a bike. Thus, as another example of how the sensors and sensing capabilities of sensor device 800 may be used to increase the reliability and accuracy of a non-ECG heart parameter sensor 1012 through data integration, the energy expenditure and activity type information can be used to provide a context in which the heart related parameters detected by the non-ECG heart parameter sensor 1012 can be assessed and possibly filtered. For example, if sensor device 800 detects that a person is burning 13 calories per minute and is biking, and the non-ECG heart parameter sensor 1012 is indicating that the wearer's heart rate is 60 beats per minute, then it is highly likely that further filtration of the signal from the non-ECG heart parameter sensor 1012 is necessary.
Other well known non-ECG heart parameter sensing devices include, for example, those based on micro-power impulse radar technology, those based on the use of piezo-electric based strain gauges, and those based on plethysmography, which involves the measurement of changes in the size of a body part as modified by the circulation of blood in that part. It will be appreciated that the performance of these devices may also be enhanced through the use of data integration as described herein.
Another sensor that may be incorporated into the sensor device 800 measures the pressure with which sensor device 800 is held against the body of the wearer. Such a sensor could be capacitive or resistive in nature. One such instantiation places a piezo-resistive strain gauge on the back of the enclosure to measure the small deflection of the plastic as increasing force is applied. Data gathered from such a sensor can be used to compensate the readings of other sensors in sensor device 800 according to the readings of such a sensor.
Also provided on PCB 860 and coupled to processing unit 900 is switch 1015. Switch 1015 is also coupled to button 1020 provided on housing 805. Button 1020, by activating switch 1015, may be used to enter information into sensor device 800, such as a time stamp to mark the occurrence of an event such taking medication. Preferably, button 1020 has a tactile, positive d-tent feedback when depressed, and a concave shape to prevent accidental depression. Also, in the embodiment shown in
Oscillator 1030 is provided on PCB 860 and supplies the system clock to processing unit 900. Reset circuit 1035 is coupled to processing unit 900 and enables processing unit to be reset to a standard initial setting.
Finally, non-volatile data storage device 1040, such as a FLASH memory chip, is provided for storing information collected and/or generated by sensor device 800. Preferably, data storage device 1040 includes at least 128K of memory. Non-volatile program storage device 1045, such as a FLASH ROM chip, is provided for storing the programs required to operate sensor device 800.
As an alternative, a microprocessor with integral A/D converters, data storage, and program storage may be substituted for processing unit 900, A/D converter 915, data storage device 1040 and non-volatile memory 1045. A suitable example of such a microprocessor is the Texas Instruments Model MSP430 processor.
Any component forming a part of sensor device 800 that comes in contact with the wearer's skin should not, in a preferred embodiment, degrade in durometer, elasticity, color or other physical or chemical properties when exposed to skin oils, perspiration, deodorant, suntan oils or lotions, skin moisturizers, perfume or isopropyl alcohol. In addition, such components preferably are hypoallergenic.
Referring to
According to a particular embodiment, housing 805 is provided with first magnetic switch 1070 and second magnetic switch 1075, each on PCB 860. Provided on or inside flexible section 810, such as by an insert molding technique, is magnet 1080. Magnet 1080 is positioned on or inside flexible section 810 such that it aligns with and thereby activates one of first magnetic switch 1080 and second magnetic switch 1075 when housing 805 is attached to flexible section 810. In the embodiment shown in
Referring to
Referring to
Referring to
It will be appreciated that, in the embodiment where sensor device 1201 is stand alone sensor device 700, I/O device 1200 may perform the manual data entry functions indicated by and described in connection with reference numeral 715 in
As known in the art, a number of configurations exist for constructing I/O device 1200 so that button 1215 and dial 1220 may be used to input information into I/O device 1200. Such buttons and dials are commercially available from Duraswitch Industries, Inc. located in Mesa, Ariz. under the names PUSHGATE™ pushbutton and thiNcoder™ ROTOR, respectively. U.S. Pat. No. 5,666,096, the disclosure of which is incorporated herein by reference, is owned by Duraswitch Industries, Inc. and describes the rotary switch technology used in the thiNcoder™ ROTOR switch. The '096 patent describes a rotary switch including a bottom substrate layer and a top membrane layer separated by a non-conductive spacer. The internal surface of the membrane layer carries a set of electrodes which define the spaced contacts of at least one electrical switch. The membrane layer also carries an electrically conductive metallic armature, in the form of a flat circular disc, that is received in an annular opening provided in the spacer. The switch further includes a rotatable actuating knob that carries a coupler in its underside. The coupler is a magnet which may be molded or otherwise entrapped in the knob. The coupler forces the armature against the internal surface of the membrane by means of the magnetic field originating from the coupler. The coupler functions both to create the switch contact pressure as well as to drag the armature from one contact to another when a user rotates the knob. In operation, when the knob is rotated, the coupler rotates with the knob and, by virtue of the magnetic coupling between the coupler and the armature, the armature rotates with the knob as well. As the armature rotates, it moves into and out of shorting contact with the contact or contacts on the membrane. When the armature is in shorting contact with a contact, the corresponding switch is closed. As will be appreciated by those of skill in the art, various encoding schemes are known for converting the actuation of one or more switches into information that may be used by a processor or other device coupled to the switch.
Alternatively, U.S. Pat. No. 6,225,980 B1, the disclosure of which is incorporated herein by reference, describes a rotary dial input device for portable computers including an insulating member overlying a printed circuit board, a spine rigidly connected to the printed circuit board, a rotatable dial, a switch ring carried by the dial and a snap ring rigidly connected to the dial. The dial, the switch ring and the snap ring rotate together around the periphery of the spine. The switch ring carries at least two magnets located 180° apart, and a plurality of Hall effect sensors are mounted on the printed circuit board and lie just under the surface of the insulating material. The position of the magnets relative to any of the Hall effect sensors may be used to generate an output signal based on the position of the dial. The '980 patent also describes a spring-based mechanism for enabling the dial to be moved between first and second vertical positions, wherein the springs biases the dial toward the first vertical position and downward pressure is required to move the dial toward the second vertical position. An additional magnet is included on a flexible arm carried by the switch ring. Upon movement of the dial from the first vertical position to the second vertical position, the magnet is moved in a direction toward another Hall effect sensor mounted on the printed circuit board. This Hall effect sensor produces a signal whenever the dial is depressed, which signal may be used to control the associated portable computer. The '980 patent further states that a momentary switch may be provided, such as in the center of the dial, for producing another computer control signal.
According to the '980 patent, the multiple switch rotary dial input device described therein, that generates signals from the rotation of the dial and the depression of the dial and/or a momentary switch, may be used in place of conventional mouse input devices as a mechanism for controlling and entering information into a computer. For example, the '980 patent states that the dial may be rotated to scroll through a list of items appearing on a display device of the computer, and the dial or monetary switch may be depressed to select an identified item. In the preferred embodiment, the dial cannot be depressed while it is being rotated and vice versa.
As another example, U.S. Pat. No. 5,959,611, the disclosure of which is incorporated herein by reference, describes a portable computer system including a CPU, an input interface, a display and an input device, wherein the input device comprises a rotary switch or dial and three on/off switches. The rotary switch may be a 16 position, binary coded rotary switch which outputs a four-digit gray code representing the position of the switch. As is known in the art, a gray code is a special binary encoding scheme in which adjacent numbers or positions have codes that differ in only one bit position. The on/of switches may be momentary push button switches positioned so as to surround the rotary switch.
The input interface translates the rotational movement of the rotary switch and the depressions of the on/off switches into data appropriately formatted for the CPU. Specifically, four conductors carry a first input signal produced by the rotary switch indicative of its position, and each of three separate conductors carry second input signals generated by depression of each of the on/off switches. The '611 patent states that the first input signal may be used to sequentially identify, through rotation of the dial, information appearing on the display, and the second input signals may be used to select an identified piece of information. The input interface may be implemented using a PIC microcontroller that is programmed to encode the first and second input signals into, for example, an eight bit byte transmitted to the CPU consisting of one byte for each switch depression and every turn of the rotary switch. Such an eight bit byte, according to the '611 patent, consists of six significant bits. Bits 5 and 6 represent the rotary switch turning clockwise and counterclockwise, respectively. If one of those bits is set to one, thereby indicating either a clockwise or counter-clockwise rotation, then bits 1 through 4 represent the gray code input signal. If both of those bits are set to zero, then bits 1 through 4 represent the depression of one of four possible on/off switches, only three of which are actually in use in the device described in the '611 patent. In other words, if any of bits 1 through 4 is set to one, then the corresponding switch was just depressed.
As is known in the art, particular portions or zones of a computer display showing a particular character, word or image can be selected, using a mouse or other input device, to cause the computer to perform an action. The '611 patent refers to such zones as hot spots. According to the '611 patent, a user can sequentially identify or step through hot spots provided on the display by rotating the rotary switch in a clockwise direction. Rotation of the rotary switch in a counter-clockwise direction enables the user to step through the hot spots in the reverse order. When the desired hot spot is identified, such as by being made bold or otherwise highlighted, any one of the on/off switches may be depressed to select the identified hot spot, thereby causing the computer to perform an action. Thus, the input device described in the '611 patent may be used to input information into and control a computer much like a conventional mouse.
If at step 6600 a selection was made, process control proceeds with step 7400 to determine if a system command had been invoked. If not, the type of hot spot is checked at step 7600, the relevant code is executed, and the screen is redrawn at step 6200. If, on the other hand, a system command is invoked at step 7400, at step 7800 an execution of the next screen or previous screen, as appropriate, is performed and the appropriate screen is redrawn at step 6200. Thereafter, process control returns to step 6400 to await additional user input. In this manner, the rotation of the rotary switch coupled with operation of the push-button switches controls the hot spots and ultimately controls the information displayed on the display and the actions taken by the computer. Those of ordinary skill in the art will recognize that the process illustrated in
Thus, as is known in the art and as taught by, for example, the '980 and '611 patents, dial 1220 may be used to step through or toggle between or among various input or command or control possibilities presented on LCD 1210 by selectively rotating dial 1220 in either the clockwise or counter-clockwise direction. As dial 1220 is rotated, the various input or command or control possibilities are highlighted. Highlighted items may be selected and a corresponding action commenced by pressing button 1215, or alternatively dial 1220 itself, in which case dial 1220 acts as both a dial and a button as those terms are used herein such that the device in question would be considered to have both a dial and a button. One alternate example of dial 1220 is the knob on the side of a watch that rotates about the side external surface of the watch.
As an alternative to dial 1220, one or more buttons, such as an up button and a down button or left and right buttons, may be used to step through or toggle between or among various input or command or possibilities presented on LCD 1210. In this embodiment, button 1215 may still be used to select and commence a highlighted items. As a further alternative, I/O device 1200 may be provided with voice recognition software and voice commands may be used to step through or toggle between or among various input or command or possibilities presented on LCD 1210. Voice commands may also be used to select and commence a highlighted items. As still a further alternate embodiment, voice commands in combination with voice recognition software may be used to directly enter information, such as nutrition information described below, into I/O device 1200.
Referring to
The calories burned data that is displayed by I/O device 1200 may, according to one embodiment of the present invention, be generated by sensor device 1201 from the physiological and/or contextual parameters it detects and thereafter transmitted to I/O device 1200 for storage, use in appropriate calculations and/or display. The calories burned data may also be generated using data that is input by the user in addition to the detected parameters. Furthermore, the caloric consumption data that is displayed by I/O device 1200 may, according to one embodiment of the present invention, be generated, preferably by I/O device 1200 but also by sensor device 1201, from data input into I/O device 1200 by the individual relating to foods consumed (as described elsewhere herein, caloric consumption data may also be generated using various detected parameters in addition to information that is input manually). Specifically, I/O device 1200 may be provided with access to a user accessible database of foods and corresponding caloric value. Such a database may be provided as part of I/O device 1200 itself, as in the case of the preferred embodiment of the present invention, or I/O device 1200 may be able to access a database stored and maintained on a computing device located separately from the I/O device such as through short or long distance wireless or wired communications. Referring to
Although
It is also possible to enter nutrition information in a considerably simplified manner in any of several potential forms, including single dimensional point systems, single dimensional categorical rating systems, and multi-dimensional categorical rating systems. For a simple example of a single-dimensional point system, the user may select from a 7 point scale, where each point value corresponds to a rough approximation of the relative size of the meal in relation to the user's normal sized meal. For an example of a categorical system, the user may select from the set {tiny, small, medium, large, and super-size} when describing a meal. An example of a multi-dimensional categorical system is the grid system described below.
For each of these systems, the users are asked to score each meal (including snacks) according to the choice of scoring system. The user's classification of the meal, as identified by a classification identifier chosen by the user, is used as an input to an algorithm that estimates the caloric content of the meal. The algorithm that does this calculation may take other factors into consideration, including, but not limited to, the time of day, the day of the week, the season, whether the day is a holiday, the user's past meal habits, the raw or derived values from a body monitoring product such as sensor device 1201, demographic information, and trends in the user's reporting of data. The algorithm may be a simple look-up table where each classification identifier is associated with a caloric amount, but can be more complicated as well.
Referring to
This system of quick caloric entry has been tested and verified in both an in-house pilot study with ten subjects over several months conducted by the assignor of the present application and a brief three-day study of 41 participants. In both studies, the following method was used. For each subject, the data from all of the other subjects was used to generate caloric estimates for each grid category for each meal type. The estimates from that aggregate information were then compared to the computed caloric totals calculated from full diet diary entries.
Referring to
Another aspect of the invention is that of automatic adaptation of feedback given to the user by sensor device 1201 or I/O device 1200. The feedback given to the user in this invention (e.g. “you might want to run an extra 10 minutes today”) can be given exactly when appropriate by taking advantage of the system's ability to detect contexts and to auto-journal as describe elsewhere herein. For example, feedback for eating might be best given just before a meal, and exercise feedback might be best given right when the user is most likely to exercise. Furthermore, if the system has detected that the user has already jogged that day, then an alternate suggestion can be given. Finally, the user's response to feedback can be utilized to further adapt the choice of the given feedback. If the user never takes exercise suggestions, advice can focus instead on nutrition. If the user tends to respond better to feedback given in the morning, more feedback can be given in the morning. The method of noticing their response would be measured by adherence to the suggestions and by successful maintenance of a healthy eating balance, as well as by noticing the absence of “violent” responses such as hitting a button that turns feed back off, turning the device off, or abruptly taking off the device.
There are three main ways in which sensor device 1201 can calibrate itself to the user. First, the device can use an initial training or calibration period where the user performs some additional tasks to train the system. For example, the user can enter in a full diet diary in addition to the quick estimates, allowing the system to learn the user's own definitions for each meal classification. The user might additionally perform a program of activities (such as walking around the block for at least 10 minutes or resting for 20 minutes) in order to calibrate a subsystem for obtaining energy expenditure that may be provided in sensor device 1201 and obtain personalized parameters for the individual that are then used in later use of the system. The subsystem for obtaining energy expenditure may also be calibrated against gold standard data from, for example, a VO2 machine. The second method involves repeating the training procedures (or a subset thereof) every so often. One example of this would be for a glucose level prediction algorithm where, each week (for example), the user performs a finger-prick glucose test to calibrate the prediction system. The third method involved doing continual training while the user is using the system including sensor device 1201. For example, the system described above that utilizes discrepancies in predicted weights between the system's prediction and that reported by a scale to adjust the estimated caloric amounts for each category is an example of this type of training.
According to a further aspect of the present invention, the user can be queried to answer questions that the sensor device 1201 or I/O device 1200 can not figure out for itself, or about which it has too much uncertainty. For example, the sensor device 1201 or I/O device 1200 may have enough information to ask the user only a single question about breakfast, but may require more information for a morning snack that the user doesn't have every day. The system can ask the questions specifically when the range of its uncertainty about a quantity is too large, and can thus minimize the input required from the user.
According to a further aspect of the present invention, I/O device 1200, sensor device 1201 and a computing device such as a PC or a PDA may be used together as a weight management system. Specifically, I/O device 1200, such as a watch like device, is used to input and track information relating to calories consumed by an individual and sensor device 1201 is used to measure calories burned or expended by the individual. The caloric expenditure information measured by sensor device 1201 is transmitted, by wire or wirelessly, to I/O device 1200. I/O device 1200 then, based on the caloric consumption and caloric expenditure information, displays to the individual a current rate of weight loss or gain and/or an energy balance value on LCD 1210. According to a specific embodiment, sensor device 1201 assumes that the individual is inactive if sensor device 1201 is not being worn, and uses the individual's resting metabolic rate to calculate caloric expenditure during such period.
In one embodiment, the individual, for each meal, including snacks, rather than inputting a specific food or foods selected from a database as described in connection with
In a preferred embodiment, the computing device is provided with weight management software that enables the individual to input information relating to foods actually eaten during each meal using a database such as that shown in
In a preferred embodiment, I/O device 1200 is programmed to provide suggestions to the individual, in the form of information displayed on LCD 1210, on how to achieve the individual's weight goals. These suggestions are based on the caloric expenditure and caloric consumption data that is logged by I/O device 1200. For example, if the individual is currently below the target weight loss rate of, for example, 1 pound per week, I/O device 1200 may display a message that instructs the individual to walk for 55 minutes to bring the current weight loss rate up to 1 pound per week. The suggestions may be of many types, including, without limitation, actions for the individual to take, explanations for why the individual is experiencing certain things such as inability to lose weight, feedback regarding the individual progress toward goals, and/or relationships between or among the parameters being measured and/or reported by sensor device 1201 and/or I/O device 1200. The suggestions may self adjust or learn based on the individual's performance toward goals. The substance of the suggestions may come from a number of sources, such as sensor device 1201 and/or I/O device 1200 or a third party source, including a person such as a trainer or health care provider, a computing device such as a treadmill, or a remote computer, such as an Internet source.
As noted above, in one embodiment, I/O device 1200 displays a current weight loss or gain rate on display 1200. The current weight loss or gain rate that is displayed on I/O device 1200 may be a daily, weekly or monthly rate, or may be a rate calculated based on the total time remaining until the weight loss target date. I/O device 1200 may be programmed to selectively display each of these rates depending on the desires of the individual, such as by using dial 1220 or one or more buttons to toggle among these various options.
LCD 1210 and backlight 1350 for LCD 1210 are connected to processing unit 1300 through appropriate well known drivers 1355. Battery 1360, which may be disposable or rechargeable, provides power for I/O device 1200 and is connected to processing unit 1300 through voltage regulator 1365. Oscillator 1370 provides the system clock to processing unit 1300, and reset circuit 1375 enables processing unit 1300 to be reset to a standard initial setting. Finally, button 1215 and dial 1220 are electronically connected to processing unit 1300 according to any known means, such as those described in the '980 and '619 patents, which would enable button 1215 and dial 1220 to provide input or command or control signals to processing unit 1300.
According to an alternate embodiment of the present invention, I/O device 1200 may be adapted to operate on its own, without being in communication with sensor device 1201. In this embodiment, a user may enter information into I/O device 1200 as described herein and may use I/O device to store and track such information over time. For example, reference database 1315 may store food and activity related information and a user may enter caloric consumption and caloric expenditure or burn information as described in connection with
According to a further alternate embodiment of the present invention, I/O device 1200 may act as a hub or terminal for collection and, in a specific embodiment, processing data received from a variety of sources. For example, referring to
As seen in
According to one aspect of the present invention, I/O device 1200 stores a program or regimen preferably including a set of goals that may be established by set by the user or a third party such as a trainer or care giver. I/O device 1200 communicates with and is programmed to control an apparatus in the environment such as a treadmill or weight machine. Specifically, I/O device 1200 is able to communicate instructions to the apparatus for setting the apparatus up for the desired interaction/result, such as choosing treadmill programs or setting or weight machine weight amounts. While user interacts with the apparatus, I/O device 1200, being in communication with the apparatus, tracks the user's performance, preferably with respect to the program or regimen including goals. The tracking may be based on information received from the apparatus, such as repetitions on a weight machine or distances run on or heart rate measured by a treadmill, and may also be based on parameters being measured by sensor device 1201 or I/O device 1200 such as energy expenditure. I/O device 1200 may also adjust/control the apparatus the user is interacting with to maximize the performance toward the goal, such as by adjusting the treadmill angle and/or resistance to decrease heart rate or energy expenditure rate of the individual. Such adjustment may be important if, for example, the individual is a CVD patient that needs to watch how much they exert themselves. In addition, after the use of the apparatus is complete, I/O device 1200 can adjust the program or regimen so that the next time the user uses the apparatus, the program or regimen will have been adjusted to comply with the progress or lack of progress the person has made. This adjustment could also include free-living exercise and other information that gets collected between periods of use of the apparatus. For example, if the person walked the rest of the week according to their program or regimen, the next time they come to use the apparatus, instead of using the same now outdated program/regimen, the program/regimen is adjusted to meet the user's new capabilities. The principle just described could also apply to interaction with other types of equipment other than exercise equipment, such as medication dispensers, CPAP machines used in sleep therapy, or even a thermostat in the house.
Most health clubs include various devices for providing entertainment to users while they are exercising. For example, a health club may include a number of television monitors, with each monitor providing a different channel of programming. Users are able to listen to the audio portions accompanying the programming while exercising by plugging headphones into an access device provided adjacent to each piece of exercise equipment, and may use the access device to select among the audio portions of the various programming channels. Referring to
In addition, health club 1500 includes computing device 1515, which may be a PC or a server computer or the like. I/O device 1200 is adapted to be in electronic communication with computing device 1515 through communications connection 1230 to enable the data collected, stored and, in a specific embodiment, processed by I/O device 1200 to be transmitted to computing device 1515. For example, a wireless interface device in electronic communication with computing device 1515 could be placed near the front desk of health club 1500. As a user exits health club 1500, he or she could place I/O device 1200 in proximity with the wireless internet device and, either automatically or after a further step such as pressing a button, the data collected, stored and, in a specific embodiment, processed by I/O device 1200 while the user was in health club 1500 would be downloaded from I/O device 1200 and transmitted to computing device 1515. The data transmitted to computing device 1515 may also include data manually entered into I/O device 1200, such as caloric consumption data. As an alternative, the wireless interface device could be replaced by a docking station or a jack device that requires I/O device to be physically coupled thereto to establish an electronic communications path.
As seen in
Furthermore, I/O device 1200 may also be used to collect data from devices located outside of health club 1500 that have capabilities and functionality that are similar to exercise equipment 1505 or entertainment equipment 1510. For example, a user that normally exercises at health club 1500 may be out of town for a period of time and, while out of town, may exercise at another facility. I/O device 1200 may be used to collect data from exercise and/or entertainment equipment used at the other facility, provided such equipment has capabilities and functionality similar to that of exercise equipment 1505 and entertainment equipment 1510. I/O device 1200 may also be used to collect data when a user is exercising or watching or listening to some sort of programming, as described herein, at home using compatible equipment. In addition, I/O device 1200 can collect relevant information while the user is not at health club 1500 through ways other than from compatible equipment. For example, if a user takes a walk at home, I/O device 1200 could collect data relating to the walk from sensor device 1201 or from manual entry. When the user returns to health club 1500, he or she can transmit the data collected while he or she was away or while exercising or engaging in other activities at home to computing device 1515, thereby eliminating gaps in data collection that otherwise would have occurred while the user was away from health club 1500. By eliminating such gaps, a program being followed by the user or goals set by the user can be more accurately monitored and modified, for example by a personal trainer or though an artificial intelligence program or algorithm employed by I/O device 1200.
In one embodiment, I/O device 1200 would store information about the user including demographic information, identification information, musical preferences, and the type of program they are on, such as rehab, cardio, or fat burning. I/O device 1200 may also collect information about the specific room it was in while the person interacted in the club, when they entered and left the room and what machine they used. In one specific embodiment, a wireless system may be utilized in which I/O device 1200 could understand it's own location in the facility through means of triangulating off two other RF transceivers in the facility.
According to yet another aspect of the present invention, instead of a space or facility like a health club requiring all the infrastructure for all it's machines to be networked with one another, either wired or wirelessly, and with a central computer to collect information about and control the machines, people can take I/O device 1200 with them as they interact with the space and use it to communicate with the equipment using local (not long distance wireless, or wires), low power communication methods, so when they use equipment such as a treadmill, I/O device 1200 tracks the machine they were on, the use, how they performed, etc. I/O device 1200 may also select entertainment programs they want to watch and/or listen to. At the end of the session in the space or facility, the information can be downloaded to a specified site such as the central computer of the facility and/or a remote server. Thus, the space or facility avoided the need to establish a specific and costly infrastructure to connect up every piece of equipment in the facility. I/O device acts, instead, as an ad-hoc infrastructure as needed.
According to one embodiment of the present invention, sensor device 1201, which may be any one of sensor device 400 shown in
One aspect of the present invention relates to a sophisticated algorithm development process for creating a wide range of algorithms for generating information relating to a variety of variables from the data received from the plurality of physiological and/or contextual sensors on sensor device 1201. Such variables may include, without limitation, energy expenditure, including resting, active and total values, daily caloric intake, sleep states, including in bed, sleep onset, sleep interruptions, wake, and out of bed, and activity states, including exercising, sitting, traveling in a motor vehicle, and lying down, and the algorithms for generating values for such variables may be based on data from, for example, the 2-axis accelerometer, the heat flux sensor, the GSR sensor, the skin temperature sensor, the near-body ambient temperature sensor, and the heart rate sensor in the embodiment described above.
Note that there are several types of algorithms that can be computed. For example, and without limitation, these include algorithms for predicting user characteristics, continual measurements, durative contexts, instantaneous events, and cumulative conditions. User characteristics include permanent and semi-permanent parameters of the wearer, including aspects such as weight, height, and wearer identity. An example of a continual measurement is energy expenditure, which constantly measures, for example on a minute by minute basis, the number of calories of energy expended by the wearer. Durative contexts are behaviors that last some period of time, such as sleeping, driving a car, or jogging. Instantaneous events are those that occur at a fixed or over a very short time period, such as a heart attack or falling down. Cumulative conditions are those where the person's condition can be deduced from their behavior over some previous period of time. For example, if a person hasn't slept in 36 hours and hasn't eaten in 10 hours, it is likely that they are fatigued. Table 3 below shows numerous examples of specific personal characteristics, continual measurements, durative measurements, instantaneous events, and cumulative conditions.
It will be appreciated that the present invention may be utilized in a method for doing automatic journaling of a wearer's physiological and contextual states. The system can automatically produce a journal of what activities the user was engaged in, what events occurred, how the user's physiological state changed over time, and when the user experienced or was likely to experience certain conditions. For example, the system can produce a record of when the user exercised, drove a car, slept, was in danger of heat stress, or ate, in addition to recording the user's hydration level, energy expenditure level, sleep levels, and alertness levels throughout a day.
According to the algorithm development process, linear or non-linear mathematical models or algorithms are constructed that map the data from the plurality of sensors to a desired variable. The process consists of several steps. First, data is collected by subjects wearing sensor device 1201 who are put into situations as close to real world situations as possible (with respect to the parameters being measured), such that the subjects are not endangered and so that the variable that the proposed algorithm is to predict can, at the same time, be reliably measured using highly accurate medical grade lab equipment. This first step provides the following two sets of data that are then used as inputs to the algorithm development process: (i) the raw data from sensor device 1201, and (ii) the data consisting of the gold-standard labels measured with the more accurate lab equipment. For cases in which the variable that the proposed algorithm is to predict relates to context detection, such as traveling in a motor vehicle, the gold-standard data is provided by the subjects themselves, such as through information input manually into sensor device 1201, a PC, or otherwise manually recorded. The collected data, i.e., both the raw data and the corresponding gold standard label data, is then organized into a database and is split into training and test sets.
Next, using the data in the training set, a mathematical model is built that relates the raw data to the corresponding gold standard labeled data. Specifically, a variety of machine learning techniques are used to generate two types of algorithms: 1) algorithms known as feature detectors that produce a result that is highly correlated with the lab-measured level (e.g. VO2 level information from a metabolic cart, douglas bag, or doubly labeled water), and 2) algorithms known as context detectors that predict various contexts (e.g., running, exercising, lying down, sleeping, driving) useful for the overall algorithm. A number of well known machine learning techniques may be used in this step, including artificial neural nets, decision trees, memory-based methods, boosting, attribute selection through cross-validation, and stochastic search methods such as simulated annealing and evolutionary computation. After a suitable set of feature and context detectors are found, several well known machine learning methods are used to cross-validate the models using the training data and increase the quality of the models of the data. Techniques used in this phase include, but are not limited to, multilinear regression, locally weighted regression, decision trees, artificial neural networks, stochastic search methods, support vector machines, and model trees.
At this stage, the models make predictions on, for example, a minute by minute basis. Inter-minute effects are next taken into account by creating an overall model that integrates the minute by minute predictions. A well known or custom windowing and threshold optimization tool may be used in this step to take advantage of the temporal continuity of the data. Finally, the model's performance can be evaluated on the test set, which has not yet been used in the creation of the algorithm. Performance of the model on the test set is thus a good estimate of the algorithm's expected performance on other unseen data. Finally, the algorithm may undergo live testing on new data for further validation.
Further examples of the types of non-linear functions and/or machine learning method that may be used in the present invention include the following: conditionals, case statements, logical processing, probabilistic or logical inference, neural network processing, kernel based methods, memory-based lookup (kNN, SOMs), decision lists, decision-tree prediction, support vector machine prediction, clustering, boosted methods, cascade-correlation, Boltzmann classifier, regression trees, case-based reasoning, Gaussians, Bayes nets, dynamic Bayesian networks, HMMs, Kalman filters, Gaussian processes, algorithmic predictors (e.g. learned by evolutionary computation or other program synthesis tools).
Although one can view an algorithm as taking raw sensor values or signals as input, performing computation, and then producing a desired output, it is useful in one preferred embodiment to view the algorithm as a series of derivations that are applied to the raw sensor values. Each derivation produces a signal referred to as a derived channel. The raw sensor values or signals are also referred to as channels, specifically raw channels rather than derived channels. These derivations, also referred to as functions, can be simple or complex but are applied in a predetermined order on the raw values and, possibly, on already existing derived channels. The first derivation must, of course, only take as input raw sensor signals, but subsequent derivations can take as input previously derived channels. Note that one can easily determine, from the order of application of derivations, the particular channels utilized to derive a given derived channel. Also note that inputs that a user provides on an I/O device or in some fashion can also be included as raw signals which can be used by the algorithms. For example, the category chosen to describe a meal can be used by a derivation that computes the caloric estimate for the meal. In one embodiment, the raw signals are first summarized into channels that are sufficient for later derivations and can be efficiently stored. These channels include derivations such as summation, summation of differences, and averages. Note that although summarizing the high-rate data into compressed channels is useful both for compression and for storing useful features, it may be useful to store some or all segments of high rate data as well, depending on the exact details of the application. In one embodiment, these summary channels are then calibrated to take minor measurable differences in manufacturing into account and to result in values in the appropriate scale and in the correct units. For example, if, during the manufacturing process, a particular temperature sensor was determined to have a slight offset, this offset can be applied, resulting in a derived channel expressing temperature in degrees Celsius.
For purposes of this description, a derivation or function is linear if it is expressed as a weighted combination of its inputs together with some offset. For example, if FOO and BAR are two raw or derived channels, then all derivations of the form A*FOO+B*BAR+C, where A, B, and C are constants, is a linear derivation. A derivation is non-linear with respect to its inputs if it is not expressed as a weighted sum of the inputs with a constant offset. An example of a nonlinear derivation is as follows: if (FOO>7) then return BAR*9, else return (BAR*3.5+912). A channel is linearly derived if all derivations involved in computing it are linear, and a channel is nonlinearly derived if any of the derivations used in creating it are nonlinear. A channel nonlinearly mediates a derivation if changes in the value of the channel change the computation performed in the derivation, keeping all other inputs constant. According to a preferred embodiment of the present invention, the algorithms that are developed using this process will have the format shown conceptually in
Referring to
This algorithm development process may be used to create algorithms to enable sensor device 1201 to detect and measure various parameters, including, without limitation, the following: (i) when an individual is suffering from duress, including states of unconsciousness, fatigue, shock, drowsiness, heat stress and dehydration; and (ii) an individual's state of readiness, health and/or metabolic status, such as in a military environment, including states of dehydration, under-nourishment and lack of sleep. In addition, algorithms may be developed for other purposes, such as filtering, signal clean-up and noise cancellation for signals measured by a sensor device as described herein. As will be appreciated, the actual algorithm or function that is developed using this method will be highly dependent on the specifics of the sensor device used, such as the specific sensors and placement thereof and the overall structure and geometry of the sensor device. Thus, an algorithm developed with one sensor device will not work as well, if at all, on sensor devices that are not substantially structurally identical to the sensor device used to create the algorithm.
Another aspect of the present invention relates to the ability of the developed algorithms to handle various kinds of uncertainty. Data uncertainty refers to sensor noise and possible sensor failures. Data uncertainty is when one cannot fully trust the data. Under such conditions, for example, if a sensor, for example an accelerometer, fails, the system might conclude that the wearer is sleeping or resting or that no motion is taking place. Under such conditions it is very hard to conclude if the data is bad or if the model that is predicting and making the conclusion is wrong. When an application involves both model and data uncertainties, it is very important to identify the relative magnitudes of the uncertainties associated with data and the model. An intelligent system would notice that the sensor seems to be producing erroneous data and would either switch to alternate algorithms or would, in some cases, be able to fill the gaps intelligently before making any predictions. Determining when sensors have failed and when data channels are no longer reliable is a non-trivial task because a failed sensor can sometimes result in readings that may seem consistent with some of the other sensors and the data can also fall within the normal operating range of the sensor.
Clinical uncertainty refers to the fact that different sensors might indicate seemingly contradictory conclusions. Clinical uncertainty is when one cannot be sure of the conclusion that is drawn from the data. For example, the accelerometers might indicate that the wearer is motionless (leading toward a conclusion of “resting”), the galvanic skin response sensor might provide a very high response (leading toward “active”), and the heat flow sensor might indicate that the wearer is still dispersing substantial heat (leading toward “active”). How should these differing factors be assessed? An inferior system would simply try to vote among the sensors or use similarly unfounded methods to integrate the various readings. The present invention instead weights the important joint probabilities and determines the appropriate most likely conclusion (which might be, for this example, that the wearer is currently performing or has recently performed a low motion activity such as stationary biking).
According to a further aspect of the present invention, a sensor device such as sensor device 400 shown in
According to the preferred embodiment, f1 is developed using the algorithm development process described elsewhere herein which uses data, specifically the raw and derived channels X, derived from the signals collected by the sensor device, so-called gold standard data relating to U or Y and Z contemporaneously measured using a method taken to be the correct answer, for example highly accurate medical grade lab equipment, and various machine learning techniques to generate the algorithms from the collected data. The algorithm or function f1 is created under conditions where the indicator U or state parameter Y, whichever the case may be, is present. As will be appreciated, the actual algorithm or function that is developed using this method will be highly dependent on the specifics of the sensor device used, such as the specific sensors and placement thereof and the overall structure and geometry of the sensor device. Thus, an algorithm developed with one sensor device will not work as well, if at all, on sensor devices that are not substantially structurally identical to the sensor device used to create the algorithm.
Next, a second algorithm or function f2 is created using the sensor device that takes as inputs the raw and derived channels X and gives an output that predicts and is conditionally dependent on everything output by f1 except either Y or U, whichever the case may be and is conditionally independent of either Y or U, whichever the case may be. The idea is that certain of the raw and derived channels X from the one or more sensors make it possible to explain away or filter out changes in the raw and derived channels X coming from non-Y or non-U related events. This algorithm or function f2 may be expressed as follows:
Preferably, f2, like f1, is developed using the algorithm development process referenced above. f2, however, is developed and validated under conditions where U or Y, whichever the case may, is not present. Thus, the gold standard data used to create f2 is data relating to Z only measured using highly accurate medical grade lab equipment.
Thus, according to this aspect of the invention, two functions will have been created, one of which, f1, is sensitive to U or Y, the other of which, f2, is insensitive to U or Y. As will be appreciated, there is a relationship between f1 and f2 that will yield either U or Y, whichever the case may be. In other words, there is a function f3 such that f3 (f1, f2)=U or f3 (f1, f2)=Y. For example, U or Y may be obtained by subtracting the data produced by the two functions (U=f1−f2 or Y=f1−f2). In the case where U, rather than Y, is determined from the relationship between f1 and f2, the next step involves obtaining Y from U based on the relationship between Y and U. For example, Y may be some fixed percentage of U such that Y can be obtained by dividing U by some factor.
One skilled in the art will appreciate that in the present invention, more than two such functions (e.g. f1, f2, f3, . . . f_n-1) could be combined by a last function f_n in the manner described above. In general, this aspect of the invention requires that a set of functions is combined whose outputs vary from one another in a way that is indicative of the parameter of interest. It will also be appreciated that conditional independence (or dependence) as used here will be defined to be approximate (in)dependence rather than precise (in)dependence.
The method just described may, for example, be used to automatically measure and/or report the caloric consumption or intake of a person using the sensor device, such as that person's daily caloric intake, also known as DCI. Automatic measuring and reporting of caloric intake would be advantageous because other non-automated methods, such as keeping diaries and journals of food intake, are hard to maintain and because caloric information for food items is not always reliable or, as in the case of a restaurant, readily available.
It is known that total body metabolism is measured as total energy expenditure (TEE) according to the following equation:
TEE=BMR+AE+TEF+AT,
wherein BMR is basal metabolic rate, which is the energy expended by the body during rest such as sleep, AE is activity energy expenditure, which is the energy expended during physical activity, TEF is thermic effect of food, which is the energy expended while digesting and processing the food that is eaten, and AT is adaptive thermogenesis, which is a mechanism by which the body modifies its metabolism to extreme temperatures. It is estimated that it costs humans about 10% of the value of food that is eaten to process the food. TEF is therefore estimated to be 10% of the total calories consumed. Thus, a reliable and practical method of measuring TEF would enable caloric consumption to be measured without the need to manually track or record food related information. Specifically, once TEF is measured, caloric consumption can be accurately estimated by dividing TEF by 0.1 (TEF=0.1* Calories Consumed; Calories Consumed=TEF/0.1).
According to a specific embodiment of the present invention relating to the automatic measurement of a state parameter Y as described above, a sensor device as described above may be used to automatically measure and/or record calories consumed by an individual. In this embodiment, the state parameter Y is calories consumed by the individual and the indicator U is TEF. First, the sensor device is used to create f1, which is an algorithm for predicting TEE. f1 is developed and validated on subjects who ate food, in other words, subjects who were performing activity and who were experiencing a TEF effect. As such, f1 is referred to as EE(gorge) to represent that it predicts energy expenditure including eating effects. The gold standard data used to create f1 is a VO2 machine. The function f1, which predicts TEE, is conditionally dependent on and predicts the item U of interest, which is TEF. In addition, f1 is conditionally dependent on and predicts Z which, in this case, is BMR+AE+AT. Next, the sensor device is used to create f2, which is an algorithm for predicting all aspects of TEE except for TEF. f2 is developed and validated on subjects who fasted for a period of time prior to the collection of data, preferably 4-6 hours, to ensure that TEF was not present and was not a factor. Such subjects will be performing physical activity without any TEF effect. As a result, f2 is conditionally dependent to and predicts BMR+AE+AT but is conditionally independent of and does not predict TEF. As such, f2 is referred to as EE(fast) to represent that it predicts energy expenditure not including eating effects. Thus, f1 so developed will be sensitive to TEF and f2 so developed will be insensitive to TEF. As will be appreciated, in this embodiment, the relationship between f1 and f2 that will yield the indicator U, which in this case is TEF, is subtraction. In other words, EE (gorge)−EE (fast)=TEF.
Once developed, functions f1 and f2 can be programmed into software stored by the sensor device and executed by the processor of the sensor device. Data from which the raw and derived channels X can be derived can then be collected by the sensor device. The outputs of f1 and f2 using the collected data as inputs can then be subtracted to yield TEF. Once TEF is determined for a period of time such as a day, calories consumed can be obtained for that period by dividing TEF by 0.1, since TEF is estimated to be 10% of the total calories consumed. The caloric consumption data so obtained may be stored, reported and/or used in lieu of the manually collected caloric consumption data utilized in the embodiments described elsewhere herein, such as in connection with
Preferably, the sensor device in this embodiment is sensor device 800 shown in
As a limiting case of attempting to estimate TEF as described above, one can imagine the case where the set of additional state parameters Z is zero. This results in measuring TEF directly through the derivational process using linear and non-linear derivations described earlier. In this variation, the algorithmic process is used to predict TEF directly, which must be provided as the gold-standard training data.
As an alternative to TEF, any effect of food on the body, such as, for example, drowsiness, urination or an electrical effect, or any other signs of eating, such as stomach sounds, may be used as the indicator U in the method just described for enabling the automatic measurement of caloric consumption. The relationship between U and the state parameter Y, which is calories consumed, may, in these alternative embodiments, be based on some known or developed scientific property or equation or may be based on statistical modeling techniques.
As an alternate embodiment, DCI can be estimated by combining measurements of weight taken at different times with estimates of energy expenditure. It is known from the literature that weight change (measured multiple times under the same conditions so as to filter out effects of water retention and the digestive process) is related to energy balance and caloric intake as follows: (Caloric Intake−Energy Expenditure)/K=weight gain in pounds, where K is a constant preferably equal to 3500. Thus, given that an aspect of the present invention relates to a method and apparatus for measuring energy expenditure that may take input from a scale, the caloric intake of a person can be accurately estimated based on the following equation: Caloric Intake=Energy Expenditure+(weight gain in pounds*K). This method requires that the user weigh themselves regularly, but requires no other effort on their part to obtain a measure of caloric intake.
Also note also that DCI can be estimated using an algorithm that takes sensor data and attempts to directly estimate the calories consumed by the wearer, using that number of calories as the gold standard and the set of raw and derived channels as the training data. This is just an instance of the algorithmic process described above.
Another specific instantiation where the present invention can be utilized relates to detecting when a person is fatigued. Such detection can either be performed in at least two ways. A first way involves accurately measuring parameters such as their caloric intake, hydration levels, sleep, stress, and energy expenditure levels using a sensor device and using the two function (f1 and f2) approach described with respect to TEF and caloric intake estimation to provide an estimate of fatigue. A second way involves directly attempting to model fatigue using the direct derivational approach described in connection with
According to an alternate embodiment of the present invention, rather than having the software that implements f1 and f2 and determines U and/or Y therefrom be resident on and executed by the sensor device itself, such software may be resident on and run by a computing device separate from the sensor device. In this embodiment, the computing device receives, by wire or wirelessly, the signals collected by the sensor device from which the set of raw and derived channels X are derived and determines U and/or Y from those signals as described above. This alternate embodiment may be an embodiment wherein the state parameter Y that is determined by the computing device is calories consumed and wherein the indicator is some effect on the body of food, such as TEF. The computing device may display the determined caloric consumption data to the user. In addition, the sensor device may also generate caloric expenditure data as described elsewhere herein which is communicated to the computing device. The computing device may then generate and display information based on the caloric consumption data and the caloric expenditure data, such as energy balance data, goal related data, and rate of weight loss or gain data.
The terms and expressions which have been employed herein are used as terms of description and not as limitation, and there is no intention in the use of such terms and expressions of excluding equivalents of the features shown and described or portions thereof, it being recognized that various modifications are possible within the scope of the invention claimed. Although particular embodiments of the present invention have been illustrated in the foregoing detailed description, it is to be further understood that the present invention is not to be limited to just the embodiments disclosed, but that they are capable of numerous rearrangements, modifications and substitutions.
Claims
1. (canceled)
2. A method of measuring energy expenditure of an individual, comprising:
- collecting a plurality of sensor signals from at least two of a body motion sensor, a heat flux sensor, a skin conductance sensor, and a skin temperature sensor, each in electronic communication with a sensor device worn on a body of said individual; and
- utilizing a first set of signals based on one or more of said plurality of sensor signals in one or more functions to predict said energy expenditure of said individual.
3. A method according to claim 2, said collecting step comprising collecting said plurality of sensor signals from a body motion sensor, a heat flux sensor, and a skin conductance sensor.
4. A method according to claim 3, said body motion sensor being an accelerometer and said skin conductance sensor being a GSR sensor.
5. A method according to claim 2, said utilizing step comprising utilizing said first set of signals in a first function, said first function determining how a second set of signals based on one or more of said plurality of sensor signals is utilized in one or more second functions, each of said one or more second functions having an output; wherein one or more of said outputs are used to predict said energy expenditure of said individual.
6. A method according to claim 5, wherein said first function recognizes one or more contexts based on said first set of signals, wherein one or more of said second functions is chosen based on said one or more recognized contexts, and wherein said outputs of said chosen second functions are used to predict said energy expenditure of said individual.
7. A method according to claim 5, wherein said first function recognizes each of a plurality of contexts based on said first set of signals, wherein each of said one or more second functions corresponds to one of said contexts, wherein said first function assigns a weight to each of said one or more second functions based on a recognition probability associated with the corresponding context, and wherein said outputs of said one or more second functions and said weights are used to predict said energy expenditure of said individual.
8. A method according to claim 5, further comprising combining one or more of said outputs in a post processing step to predict said energy expenditure of said individual.
9. A method according to claim 5, wherein said second functions are regression algorithms.
10. A method according to claim 5, wherein said contexts comprise rest and active.
11. A method according to claim 5, wherein said first function comprising a naïve Bayesian classifier.
12. A method according to claim 5, said collecting step comprising collecting said plurality of sensor signals from a body motion sensor, a heat flux sensor, and a skin conductance sensor, said second set of signals comprising a heat flux high gain average variance (HFvar), a vector sum of transverse and longitudinal accelerometer SADs (VSAD), and a galvanic skin response low gain (GSR), wherein said second functions have the form of A*VSAD+B*HF+C*GSR+D*BMR+E, wherein A, B, C, D and E are constants and BMR is a basal metabolic rate for said individual.
13. An apparatus for measuring energy expenditure of an individual, comprising a processor;
- at least two of a body motion sensor, a heat flux sensor, a skin conductance sensor, and a skin temperature sensor in electronic communication with said processor; and
- a memory storing software executable by said processor, said software including instructions for: collecting a plurality of sensor signals from said at least two of a body motion sensor, a heat flux sensor, a skin conductance sensor, and a skin temperature sensor; and utilizing a first set of signals based on one or more of said plurality of sensor signals in one or more functions to predict said energy expenditure of said individual.
14. An apparatus according to claim 13, said collecting instruction comprising collecting said plurality of sensor signals from a body motion sensor, a heat flux sensor, and a skin conductance sensor.
15. An apparatus according to claim 14, said body motion sensor being an accelerometer and said skin conductance sensor being a GSR sensor.
16. An apparatus according to claim 13, said utilizing instruction comprising utilizing said first set of signals in a first function, said first function determining how a second set of signals based on one or more of said plurality of sensor signals is utilized in one or more second functions, each of said one or more second functions having an output; wherein one or more of said outputs are used to predict said energy expenditure of said individual.
17. An apparatus according to claim 16, wherein said first function recognizes one or more contexts based on said first set of signals, wherein one or more of said second functions is chosen based on said one or more recognized contexts, and wherein said outputs of said chosen second functions are used to predict said energy expenditure of said individual.
18. An apparatus according to claim 16, wherein said first function recognizes each of a plurality of contexts based on said first set of signals, wherein each of said one or more second functions corresponds to one of said contexts, wherein said first function assigns a weight to each of said one or more second functions based on a recognition probability associated with the corresponding context, and wherein said outputs of said one or more second functions and said weights are used to predict said energy expenditure of said individual.
19. An apparatus according to claim 16, said instructions further comprising combining said one or more outputs in a post processing step to predict said energy expenditure of said individual.
20. An apparatus according to claim 16, wherein said second functions are regression algorithms.
21. An apparatus according to claim 20, wherein said contexts comprise rest and active.
22. An apparatus according to claim 21, said first function comprising a naive Bayesian classifier.
23. An apparatus according to claim 21, wherein said collecting instruction comprising collecting said plurality of sensor signals from a body motion sensor, a heat flux sensor, and a skin conductance sensor, said second set of signals comprising a heat flux high gain average 15 variance (HFvar), a vector sum of transverse and longitudinal accelerometer SADs (VSAD), and a galvanic skin response low gain (GSR), wherein said second functions have the form of A*VSAD+B*HF+C*GSR+D*BMR+E, wherein A, B, C, D and E are constants and BMR is a basal metabolic rate for said individual.
Type: Application
Filed: Nov 18, 2013
Publication Date: Aug 7, 2014
Inventors: Eric Teller (Palo Alto, CA), Jonathan Farringdon (Pittsburgh, PA), David Andre (San Francisco, CA), Christopher Pacione (Pittsburgh, PA), John M. Stivoric (Pittsburgh, PA), Scott Safier (New York, NY), Raymond Pelletier (Ben Avon, PA), Suresh Vishnubhatla (Louisville, KY)
Application Number: 14/083,397
International Classification: A61B 5/00 (20060101); A61B 5/01 (20060101); A61B 5/053 (20060101); A61B 5/11 (20060101);
