Method and system for activity classification
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.
1. A method for classifying an activity of a subject comprising:
receiving input data of the subject resulting from the activity, wherein the activity comprises an activity indicative of an imminent fall, 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, wherein the classified activity data comprises classified predicted fall data;
training the deep learning neural network for updating the weights and the biases;
generating a fall prediction query using the classified predicted fall data, wherein the fall prediction query is negative or positive; and
communicating an alert to a user if the fall prediction query is positive.
2. The method of claim 1 , further comprising an event window, wherein the event window is of a duration in time equal to an identified event from within the input data.
3. The method of claim 2 , wherein the identified event is a single type of event or multiple types of events.
4. The method of claim 2 , further comprising updating the event window if the fall prediction query is negative, wherein updating the event window includes defining the event window for the input data, changing a selection feature for the event window, and/or progressing the event window to a next identified event.
5. The method of claim 1 , wherein training the deep learning neural network comprises:
confirming the activity, resulting in a defined activity, the defined activity comprising a defined activity indicative of an imminent fall, and corresponding classified actual activity data, the classified actual activity data comprising classified actual predicted fall data, wherein confirming the activity comprises:
monitoring the subject while the defined activity is performed;
receiving a confirmation input that the subject performed the defined activity;
defining a loss function between the classified actual activity data and the classified activity data; and
updating the weights and the biases for mitigating the loss function.
6. The method of claim 1 , wherein the input data further comprises personal and/or physical attributes of the subject; and the personal and/or physical attributes of the subject include health information from a database and/or self-inputted health information.
7. The method of claim 1 , wherein communicating the alert to the user comprises one or many of the following operations: displaying the alert visually, displaying the alert audibly, and generating a tactile or other neuroplastic stimulus, wherein the tactile or other neuroplastic stimulus causes an instinctive response in the subject to correct the activity indicative of an imminent fall or prompts the subject to correct the activity indicative of an imminent fall.
8. The method of claim 1 , wherein the user is the subject or a third party.
9. The method of claim 1 , further comprising identifying a risk level indicating a likelihood of a fall occurring.
10. The method of claim 1 , further comprising collecting additional input data after the activity indicative of an imminent fall;
detecting a recent fall of the subject using the additional input data; and
communicating a recent fall alert to emergency services or a caregiver.
11. A system for classifying an activity of a subject comprising:
a sensor module comprising a pressure sensor for collecting input data during the activity, wherein the activity comprises an activity indicative of an imminent fall, the input data comprising pressure data;
a processor included in a first device, configured for receiving the input data from the sensor module, wherein the processor is configured to:
apply a deep learning neural network to the input data based on weights and biases, resulting in classified activity data, wherein the classified activity data comprises classified predicted fall data;
train the deep learning neural network for updating the weights and the biases;
generate a fall prediction query using the classified predicted fall data, wherein the fall prediction query is negative or positive; and
communicate an alert to a user if the fall prediction query is positive.
12. The system of claim 11 , wherein the input data further comprises personal and/or physical attributes of the subject; and the personal and/or physical attributes of the subject include health information from a database and/or self-inputted health information.
13. The system of claim 11 , further comprising an alert output module, wherein the alert output module is used to communicate the alert to the user using one or many of the following operations: displaying the alert visually, displaying the alert audibly, and generating a tactile or other neuroplastic stimulus, wherein the tactile or other neuroplastic stimulus causes an instinctive response in the subject to correct the activity indicative of an imminent fall or prompts the subject to correct the activity indicative of an imminent fall.
14. The system of claim 13 , wherein the alert output module is located on a second device.
15. The system of claim 11 , wherein the user is the subject or a third party.
16. The system of claim 11 , wherein the processor is further configured to identify a risk level indicating a likelihood of a fall occurring.
17. The system of claim 11 , further comprising collecting additional input data after the activity indicative of an imminent fall, and wherein the processor is further configured to:
detect a recent fall of the subject using the additional input data; and
communicate a recent fall alert to emergency services or a caregiver.
18. The system of claim 11 , wherein the sensor module further comprises an accelerometer, a gyroscope, a seismograph, a thermometer, a humidity sensor, an altimeter, a GPS, a video camera, a heart rate sensor, an oxygen sensor, a breathing rate sensor, a blood glucose sensor, a fatigue measuring device, a limb position measuring device, a blood pressure monitor, an ECG, a lung function meter, an alcohol level sensor, drug level sensor, or any other type of sensor that measures a level of impairment.
19. The system of claim 11 , wherein the sensor module is located on a support matrix; wherein the support matrix is located for receiving the input data from different portions of the subject; and the weights and the biases are initially determined with reference to the location of the sensor module on the support matrix.
20. The system of claim 11 , wherein the sensor module is disposed on a wearable device worn underfoot.