Abstract: A system for determining a location of an egress point in a plumbing system that includes a branched system of pipes within a building is provided. The system includes a first sensor that is configured to measure a first pressure signal as a function of time at a first location within the plumbing system, and a second sensor that is configured to measure a second pressure signal as a function of time at a second location within the plumbing system. The plumbing system includes multiple branch points between the first location and the second location. The system also includes a processor that is configured to determine a temporal difference between a first pressure drop in the first pressure signal and a second pressure drop in the second pressure signal, and use the temporal difference to determine an estimated location of the egress point in the plumbing system.

Abstract: Examples of apparatuses and methods described herein may provide personalized audio health sensing to identify individuals based on their health sounds. A microphone may receive an audio sample including speech utterance and cough. A computing device may process the audio sample and analyze the audio sample to predict whether the audio sample is produced by a known user. The computing device may include a neural network that processes and analyzes the audio sample.

Abstract: Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

Abstract: A system including a sensing device configured to (i) measure pressure of water in cold and hot water lines proximate to a fixture of a water system of a structure, and (ii) generate pressure measurement data representing the pressure of the water. The system also includes one or more processors. The system additionally includes one or more non-transitory computer readable media storing machine-executable instructions configured, when executed on the one or more processors, to perform detecting a non-cyclical pressure event corresponding to a water leak in the water system of the structure during a first time period based on an analysis of information comprising the pressure measurement data. Other embodiments are described.

Abstract: A motion sensor assembly may include a cover plate configured to be mounted to an electrical box. The cover plate may include a front surface configured to face away from the electrical box and a rear surface opposite the front surface. The cover plate may further include an aperture configured to receive a toggle or rocker type switch. A motion sensor may be coupled to the cover plate. A power source and processor may be operably coupled to the motion sensor. Furthermore, the processor may be operably coupled to a communication device.

Abstract: Embodiments of water sensors having multi-value outputs are disclosed. A water sensing circuit measures the impedance between two contacts of a water sensor and compares it with a reference signal. The impedance between two contacts varies depending on the wetness of the contacts, and so the sensing circuit may provide a measured wetness level. The water sensor may transmit measurements or other information wired or wirelessly. The water sensor may display indicia of measurements or other information via a display on a housing.

Abstract: Examples described herein include electronic devices which may serve as hemochromatic analyzers, leveraging sensors and computation available on the electronic devices themselves, such as smartphones and smartwatches. In this manner, minor to no hardware modification may be required to a mobile phone or other electronic device to allow the device to predict hemoglobin levels.

Abstract: A method including measuring pressure of water in a water system of a structure at a single location in the water system using a pressure sensor of a sensing device to generate pressure measurement data representing the pressure of the water as measured by the pressure sensor. The method also can include communicating the pressure measurement data to one or more processors. The method additionally can include detecting a non-cyclical pressure event corresponding to a water leak in the water system of the structure during a first time period based on an analysis of information including the pressure measurement data. The information analyzed in the analysis does not include flow measurement data that represents a total amount of flow of the water in the water system of the structure during the first time period. Other embodiments are described.

Abstract: A method and system for detecting small leaks in a plumbing system is disclosed. A temperature sensor coupled to the water in the plumbing system is used to determine if there is a leak. During times of inactivity for fixtures in the plumbing systems, a flow sensor might measure usage of water that would indicate a leak. For very small leaks, the flow is below a minimum measurable flow of the flow sensor. Embodiments of the invention measure temperature of water within a pipe coupled to the plumbing system. Temperature will generally decay in a particular predicable way when there is flow as the temperature of water upon entry to the building is lower than the air temperature within the building. Signal processing, machine learning and/or statistical approaches are used to analyze the temperature and optionally flow and/or pressure over time to determine when a leak is likely.

Abstract: A method and system for detecting small leaks in a plumbing system is disclosed. A temperature sensor coupled to the water in the plumbing system is used to determine if there is a leak. During times of inactivity for fixtures in the plumbing systems, a flow sensor might measure usage of water that would indicate a leak. For very small leaks, the flow is below a minimum measurable flow of the flow sensor. Embodiments of the invention measure temperature of water within a pipe coupled to the plumbing system. Temperature will generally decay in a particular predicable way when there is flow as the temperature of water upon entry to the building is lower than the air temperature within the building. Signal processing, machine learning and/or statistical approaches are used to analyze the temperature and optionally flow and/or pressure over time to determine when a leak is likely.

Abstract: A wrist-worn device heart-monitoring device is presented. The wrist-worn heart-monitoring device includes a radial tonometer configured to output a pressure signal indicating a pulse pressure wave at a user's wrist, two or more electrodes configured to output an electrical signal indicating a user's heart has been commanded to contract, and a microphone configured to output an audio signal indicating a closing of a user's aortic valve. The wrist-worn heart-monitoring device further includes a pulse transit time monitor configured to calculate a pre-ejection period of the user's heart based on at least the pressure, electrical, and audio signals, and calculate a pulse transit time based on at least the pre-ejection period, the pressure signal, and the electrical signal.

Abstract: An apparatus including a sensing device configured to be coupled to an electrical outlet is provided. The sensing device can include a data acquisition receiver configured to receive electrical noise via the electrical outlet when the sensing device is coupled to the electrical outlet. The electrical outlet can be electrically coupled to an electrical power infrastructure. One or more electrical devices can be coupled to the electrical power infrastructure and can generate at least a portion of the electrical noise on the electrical power infrastructure. The data acquisition receiver can be configured to convert the electrical noise into one or more first data signals. The apparatus also can include a processing module configured to run on a processor of a computational unit. The sensing device can be in communication with the computational unit.

Abstract: The various embodiments herein provide an energy harvester which can capacitively harvest stray electric field from low-voltage AC power lines without a physical grounding connection. The energy harvester comprises an inner electrode, an outer electrode and a circuit. The inner electrode forms an inner periphery of an upper portion of a harvester housing. The outer electrode forms an inner base of a lower portion of the harvester housing to provide a local ground reference. The circuit is housed within the lower portion of the harvester housing to direct stored energy and control an energy discharge.

Abstract: An apparatus including a sensing device configured to be coupled to an electrical outlet is provided. The sensing device can include a data acquisition receiver configured to receive electrical noise via the electrical outlet when the sensing device is coupled to the electrical outlet. The electrical outlet can be electrically coupled to an electrical power infrastructure. One or more electrical devices can be coupled to the electrical power infrastructure and can generate at least a portion of the electrical noise on the electrical power infrastructure. The data acquisition receiver can be configured to convert the electrical noise into one or more first data signals. The apparatus also can include a processing module configured to run on a processor of a computational unit. The sensing device can be in communication with the computational unit.

Abstract: In some embodiments, techniques for using machine learning to enable visible light pupilometry are provided. In some embodiments, a smartphone may be used to create a visible light video recording of a pupillary light reflex (PLR). A machine learning model may be used to detect a size of a pupil in the video recording over time, and the size over time may be presented to a clinician. In some embodiments, a system that includes a smartphone and a box that holds the smartphone in a predetermined relationship to a subject's face is provided. In some embodiments, a sequential convolutional neural network architecture is used. In some embodiments, a fully convolutional neural network architecture is used.

Abstract: Examples of systems and methods described herein may estimate the bilirubin level of an adult subject based on image data associated with a portion of the eye of the subject (e.g., a color of the sclera). Accessories are described which may facilitate bilirubin estimation, including sensor shields and calibration frames.

Abstract: A method and system for detecting small leaks in a plumbing system is disclosed. A temperature sensor coupled to the water in the plumbing system is used to determine if there is a leak. During times of inactivity for fixtures in the plumbing systems, a flow sensor might measure usage of water that would indicate a leak. For very small leaks, the flow is below a minimum measurable flow of the flow sensor. Embodiments of the invention measure temperature of water within a pipe coupled to the plumbing system. Temperature will generally decay in a particular predicable way when there is flow as the temperature of water upon entry to the building is lower than the air temperature within the building. Signal processing, machine learning and/or statistical approaches are used to analyze the temperature and optionally flow and/or pressure over time to determine when a leak is likely.

Abstract: Examples of the present invention utilize principal component analysis (PCA) to detect cough sounds in an audio stream. Comparison of all or portions of the audio stream with a cough model may be conducted. The cough model may include a number of basis vectors may be based on initial portions of known coughs. The initial portions may be non-user specific, and accordingly the cough model may be used to detect coughs across individuals. Moreover, examples of the present invention may reconstruct the cough sounds from stored features such that the cough sounds are reconstructed but the reconstruction techniques used may be insufficient to reconstruct speech sounds that may also have been recorded, which may increase user privacy.

Abstract: A system for classifying a user touch event by a user interacting with a device as an intended key is provided. For different hand postures (e.g., holding device with right hand and entering text with right thumb), the system provides a touch pattern model indicating how the user interacts using that hand posture. The system receives an indication of a user touch event and identifies the hand posture of the user. The system then determines the intended key based on the user touch event and a touch pattern model for the identified hand posture. A system is also provided for determining the amount a presser a user is applying to the device based on dampening of vibrations as measured by an inertial sensor. A system is provided that uses motion of the device as measured by an inertial sensor to improve the accuracy of text entry.

Abstract: A method and system for detecting small leaks in a plumbing system is disclosed. A temperature sensor coupled to the water in the plumbing system is used to determine if there is a leak. During times of inactivity for fixtures in the plumbing systems, a flow sensor might measure usage of water that would indicate a leak. For very small leaks, the flow is below a minimum measurable flow of the flow sensor. Embodiments of the invention measure temperature of water within a pipe coupled to the plumbing system. Temperature will generally decay in a particular predicable way when there is flow as the temperature of water upon entry to the building is lower than the air temperature within the building. Signal processing, machine learning and/or statistical approaches are used to analyze the temperature and optionally flow and/or pressure over time to determine when a leak is likely.