Method and system for activity classification
Inventors
Cheng, Chun Hing • EVERETT, Julia Breanne • PURDY, MICHAEL TODD • STEVENS, Travis Michael • VIBERG, DAVID ALLAN • YEE, DALE BARRY
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11526749-B2
Publication Date
2022-12-13
Expiration Date
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.
Core Innovation
The invention relates to classifying an activity of a subject using pressure sensor input data. Input data resulting from the activity includes pressure data generated during the activity, and a deep learning neural network is applied to the input data based on weights and biases to produce classified activity data.
The invention further relates to training the deep learning neural network by updating the weights and biases. The training updates the deep learning neural network based on classified activity data and includes confirming a defined activity to obtain classified actual activity data and computing a loss function versus the classified activity data to mitigate the loss.
The invention also supports training data that includes synthetic input data generated from empirical input data. It further supports processing the input using time window segmentation and event detection filtering, including weighted time windows and event windowing. The system communicates the classified activity data to a user via display, tactile stimulation, storing, and related communications.
Claims Coverage
The document includes two independent claims: a method claim and a system claim. Together, they cover pressure-data-based activity classification with a deep learning neural network that is applied to input data and trained to update weights and biases, with communication of the resulting classified activity data to a user.
Pressure-data activity classification using a deep learning neural network
receiving input data of the subject resulting from the activity, the input data including pressure data; applying a deep learning neural network to the input data based on weights and biases, resulting in classified activity data
Training by updating weights and biases
training the deep learning neural network for updating the weights and biases
Communicating classified activity data to a user
communicating the classified activity data to a user
Pressure-sensor system with neural-network-based classification
a sensor module comprising a pressure sensor, the sensor module for generating input data during the activity, the input data including pressure data; a processor configured for receiving the input data, the processor configured for executing a method comprising: applying a deep learning neural network to the input data based on weights and biases, resulting in classified activity data; training the neural network for updating the weights and biases
Across the independent claims, the inventive core is pressure-data input for activity classification using a deep learning neural network driven by weights and biases, with training that updates the weights and biases, and communication of the resulting classified activity data to a user.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?