Spiking neural network classification for spike train analysis of physiotherapy movements

Fadilla ‘Atyka Nor Rashid (Universiti Tun Hussein Onn Malaysia)
Nor Surayahani Suriani (Universiti Tun Hussein Onn Malaysia)

Bulletin of Electrical Engineering and Informatics
Vol 9, No 1: February 2020

Classifying gesture or movements nowadays become a demanding business as the technologies of sensor rose. This has enchanted many researchers to actively investigated widely within the area of computer vision. Rehabilitation exercises is one of the most popular gestures or movements that being worked by the researchers nowadays. Rehab session usually involves experts that monitored the patients but lacking the experts itself made the session become longer and unproductive. This works adopted a dataset from UI-PRMD that assembled from 10 rehabilitation movements. The data has been encoded into spike trains for spike patterns analysis. Next, we tend to train the spike trains into Spiking Neural Networks and resulting into a promising result. However, in future, this method will be tested with other data to validate the performance, also to enhance the success rate of the accuracy.