Sitting Posture Recognition Using a Spiking Neural Network

TL;DR

This paper presents a personalized smart chair system that uses a spiking neural network to accurately recognize 15 sitting postures from pressure data, aiming to improve sitting habits and comfort.

Contribution

It introduces a novel encoding algorithm for pressure data into spiking neural networks and demonstrates high classification accuracy for sitting postures.

Findings

Prediction accuracy of 88.52% for 15 sitting postures.

Effective encoding algorithm for pressure data into SNNs.

System successfully guides users towards proper sitting postures.

Abstract

To increase the quality of citizens' lives, we designed a personalized smart chair system to recognize sitting behaviors. The system can receive surface pressure data from the designed sensor and provide feedback for guiding the user towards proper sitting postures. We used a liquid state machine and a logistic regression classifier to construct a spiking neural network for classifying 15 sitting postures. To allow this system to read our pressure data into the spiking neurons, we designed an algorithm to encode map-like data into cosine-rank sparsity data. The experimental results consisting of 15 sitting postures from 19 participants show that the prediction precision of our SNN is 88.52%.