Abstract: An apparatus for assessing heart failure can include an image sensor configured to capture image data of a patient, a sensor configured to capture sensor data for the patient, a memory configured to store the image data and the sensor data, and a processor coupled to the image sensor, the sensor, and the memory. The processor is configured to receive image data in response to detecting a biological condition from the sensor data, wherein the biological condition is indicative of psychophysiological health and cardiac health. The processor is further configured to detect a visual characteristic from the image data, wherein the visual characteristic is indicative of heart health, and, in response to detecting the visual characteristic, provide an indication that the patient is experiencing a worsening of heart failure.

Abstract: A system for evaluating health-related quality of life (HRQOL) can include a sensor adapted to generate sensor data for a user, a memory adapted to store the sensor data, and a processor coupled to the sensor and the memory. The processor can be configured to initiate executable operations including determining a first biological marker for the user from the sensor data, wherein the first biological marker is indicative of a first dimension of HRQOL, performing speech analysis on user provided speech to determine a second biological marker indicative of a second dimension of HRQOL. The processor is further configured to initiate executable operations including comparing the first biological marker and the second biological marker with a baseline for the first biological marker and a baseline for the second biological marker, respectively, and outputting a result of the comparing.

Abstract: Chronotherapeutic dosing can include receiving, using a processor, sensor data from a sensor for a user, wherein the sensor data is collected subsequent to the user starting a regimen for a medication, determining, using the processor, a biological marker from the sensor data, wherein the biological marker is correlated with the medication, and comparing, using the processor, the biological marker with an expected state of the biological marker based upon a dose time of the medication. Chronotherapeutic dosing can also include providing, using the processor, a notification indicating a result of the comparing.

Abstract: In particular embodiments, a method for determining a heart-rate variability (HRV) measurement of a user may include receiving, from a sensor of an electronic device of the user, heart sensor data, determining a noise level of the heart sensor data, and then adjusting the HRV measurement by an amount calculated based on the determined noise level. The sensor data may include data on a photoplethysmograph (PPG) signal over a noise-calculation time period.

Abstract: A method for monitoring a health characteristic of a user based on one or more biological measurements may include selecting a context from a plurality of contexts, each context corresponding to a baseline health value, and each context being defined by a plurality of recorded events each comprising one or more of repeated biological states, repeated user activity, or space-time coordinates of the user, and then monitoring the health characteristic of the user based on one or more bio-sensing measurements in comparison to the baseline health value corresponding to the selected context.

Abstract: A method for monitoring a stress level of a user may include determining, based on biological measurements on one or more physiological markers received in a first sampling mode, the stress level of the user, and then dynamically switching to a second sampling mode when it is determined that one or more of the physiological markers are above a threshold level, the second sampling mode being different from the first sampling mode.

Abstract: A method for determining a stress level of a user based on a sympathovagal balance (SVB) value calculated based on a set of measurement data may include determining a heart-rate variability (HRV) characteristic as a ratio involving a number of autonomic nervous system (ANS) activity markers within a first portion of the set of measurement data and the number of ANS activity markers within a second portion of the set of measurement data, and then determining the stress level of the user based on the HRV characteristic. The first and second portions of the set of measurement data may be selected based on a user-specific baseline SVB value that divides a histogram representation of the set of measurement data into the first and second portions.

Abstract: In one embodiment, one or more computer-readable non-transitory storage media embody software that is operable when executed to determine, based on cardiac-activity data, a shift in sympathovagal balance (SVB) during the period of time; obtain an emotional-state characteristic the emotional-state characteristic being based on brain-wave activity data; and determine, based on the SVB shift and the emotional-state characteristic, an estimate of an emotional state of the user during the period of time.

Abstract: In one embodiment, a method includes accessing an inverted index of a searchable set of objects including key words. The inverted index includes multiple lists each corresponding to a particular key word and identifying a particular subset of the objects including the particular key word. The method includes generating a binary decision diagram (BDD) for each of one or more of the lists. The BDD corresponds to the particular key word of the list, and each decision node of the BDD represents an object in the searchable set of objects including the particular key word of the list. The method includes storing each of one or more of the lists as its BDD. Storage of the BDD facilitates more efficient storage of the inverted index.

Abstract: According to one embodiment of the present invention, a method for selecting metadata for sensor data streams may be provided. The method may include receiving a first sensor data stream associated with a user. The first data stream may be generated by one or more sensors co-located with the user. A plurality of tags that are each associated with one or more sensor value ranges may be accessed. A first tag may be selected from the plurality of tags according to a relationship between the first sensor data stream and the one or more sensor value ranges associated with the first tag. The method may further include facilitating reporting of the first tag.

Abstract: In one embodiment, modeling topics includes accessing a corpus comprising documents that include words. Words of a document are selected as keywords of the document. The documents are clustered according to the keywords to yield clusters, where each cluster corresponds to a topic. A statistical distribution is generated for a cluster from words of the documents of the cluster. A topic is modeled using the statistical distribution generated for the cluster corresponding to the topic.

Abstract: A method of determining stress includes receiving a data signal including multiple consecutive RR intervals of a subject. The method may also include calculating heart rate variability (HRV) data for the subject from the data signal. The method may also include calculating an RR integral average (RRIA) from the HRV data, the RRIA indicating a stress level of the subject.

Abstract: A method of operating an image-sensing device includes detecting a trigger. The method also includes, in response to detecting the trigger, changing an operating mode of the image-sensing device from a first operating mode having a first spatial resolution and a first temporal resolution to a second operating mode having a second spatial resolution and a second temporal resolution. The second spatial resolution may be lower than the first spatial resolution and the second temporal resolution may be higher than the first temporal resolution. The method may also include capturing video data in the second operating mode, the video data having the second spatial resolution and the second temporal resolution.

Abstract: In particular embodiments, a method includes accessing data streams from a first group of physiological sensors monitoring a person, a second group of deconfounding sensors monitoring the person, and a third group of sensors monitoring a stressor, analyzing data sets collected from the person when the person is exposed and not exposed to the stressor, and determining a current stress factor for the stressor with respect to the person based on the analysis.

Abstract: In particular embodiments, a method includes analyzing a binary decision diagram (BDD) representing a data stream from a sensor to determine a compression rate of the BDD and indicating a sensor malfunction in the sensor if the compression rate of the BDD deviates from a specified compression rate range.

Abstract: In particular embodiments, a method includes accessing one or more physiological data streams, analyzing each physiological data stream in reference to a set of control parameters, and, if a data stream deviates from its control parameters, then transmitting a query to a mood sensor or a behavioral sensor.

Abstract: In particular embodiments, a method includes accessing a first binary decision diagram (BDD) representing data streams from sensors, selecting portions from the first BDD based on ease-of-analysis, and constructing a plurality of sub-BDDs by partitioning the first BDD, wherein the sub-BDDs comprises a first sub-BDD representing the selected portions, and second sub-BDDs representing the non-selected portions.

Abstract: A method of determining stress based on renal blood flow. The method includes receiving data indicating renal blood flow of a subject. The method also includes calculating a power spectrum of a signal derived from the data. The power spectrum indicates a stress level of the subject.

Abstract: According to certain embodiments, a set of samples of sensor data is accessed. The set of samples records medical measurements taken by one or more medical sensors. A characteristic function is generated from the set of samples. The characteristic function indicates whether a given sample is a member of the set of samples. One or more samples of the set of samples that are associated with a given medical annotation are identified according to the characteristic function.

Abstract: According to one embodiment of the present invention, a method for identifying the occurrence of an event from sensor data streams may be provided. The method may include accessing a plurality of sensor data streams generated by a plurality of sensor sets. Each sensor set may comprise one or more sensors. A sensor data stream may be associated with a user. The user may be co-located with a sensor set that generates the sensor data stream. A relationship between two or more sensor data streams of the plurality of sensor data streams may be identified. The method may further include determining, according to the relationship, that the plurality of sensor data streams corresponds to an event. A notification of an occurrence of the event may be sent.