Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.

Abstract: A process for using temperature measurements to determine health metrics includes: a) using a first temperature sensor of a wearable device to obtain a first set of measurements at a first location on a user's body over a time period; b) using a second temperature sensor of the wearable device to obtain a second set of measurements at a second location on the user's body over the time period; c) processing the measurements to identify changes in temperature over the time period, determining a first health metric based on the changes, and outputting an indication of the first health metric; and d) processing the measurements to compare the temperature at the first location at a given time point to the temperature at the second location at the given time point, determining a second health metric based on the comparison, and outputting an indication of the second health metric.

Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.

Abstract: A system includes a wearable device and a computing device. The wearable device includes one or more sensors for generating first use data corresponding to use of the wearable device by a user. The computing device includes a processor, a memory, and a display device. The processor is configured to receive the first use data; compute a first use metric associated with the user based on the first use data; and compare the first use metric to a first threshold metric. Based on the comparing, the processor is further configured to update a user score by a first score amount; compute a second score amount and a second threshold metric; and provide a first indication of the user score, the second threshold metric, and the second score amount on the display device.

Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.

Abstract: A method of manufacturing an insert system for footwear includes assembling electronic components. The electronic components include a sensor array having physiological sensors. Each physiological sensor includes a first high resistance layer configured to be in contact with a second high resistance layer when no force is applied to the sensor. The method further includes positioning the sensor array between a first layer and a base layer. An insert system for footwear includes a first layer, a base layer, a sensor array between the first and base layers, and a circuit board. The sensor array includes physiological sensors. Each physiological sensor includes a first high resistance layer in contact with a second high resistance layer when no force is applied to the sensor. The circuit board can transmit signals external to the system to trigger an alert being issued to a user, based on an output of the sensor array.

Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.

Abstract: A method and system for activity classification. A pressure sensor receives input data resulting from physical activity of a subject performing an activity. The input data includes pressure data from at least one pressure sensor, and may include other data acquired through other types of sensors. A deep learning neural network is applied to the input data for identifying the activity. The neural network is trained with reference to training data from a training database. The training data may include empirical data from a database of previous data of corresponding activities, synthesized data prepared from the empirical data or simulated data. The training data may include data from physical activity of the subject being monitored by the system. Different aspects of the neural network may be trained with reference to the training data, and some aspects may be locked or opened depending on the application and the circumstances.

Abstract: A hands-free, heads up and discrete system and method for controlling a peripheral device using foot gestures is provided. The system includes a foot-based sensory device that includes one or more sensors, such as pressure sensors, gyroscopes, and accelerometers, that receive sensory information from a user's foot, interpret the information as being linked to specific commands, and transmit the commands to at least one display device for controlling the display device. The system also includes a feedback system for providing tactile, visual and/or auditory feedback to the user based on the actions performed, information provided by the display device and/or information provided from another user.

Abstract: A method and assembly for acquiring pressure data. A pressure sensor is applied to a target surface on an individual. A calibrator and a processing element are in communication with the pressure sensor. Processing element receives pressure data and provides an integrated pressure value over a measurement time period. The integrated pressure value is compared to an alert value and to a change condition value. Where an alert value is exceeded, an alert is transmitted to an output device for display. Where a change condition value is exceeded, a measurement parameter of the pressure sensor is changed, or the calibrator is applied to the pressure sensor to recalibrate the pressure sensor to a recalibrated pressure range.

Abstract: A method and assembly for acquiring pressure data. A pressure sensor is applied to a target surface on an individual. A calibrator and a processing element are in communication with the pressure sensor. Processing element receives pressure data and provides an integrated pressure value over a measurement time period. The integrated pressure value is compared to an alert value and to a change condition value. Where an alert value is exceeded, an alert is transmitted to an output device for display. Where a change condition value is exceeded, a measurement parameter of the pressure sensor is changed, or the calibrator is applied to the pressure sensor to recalibrate the pressure sensor to a recalibrated pressure range.