Recognizing Different Foot Deformities Using FSR Sensors by Static Classification of Neural Networks

Abstract

Sensing insole systems are a promising technology for various applications in healthcare and sports. They can provide valuable information about the foot pressure distribution and gait patterns of different individuals. However, designing and implementing such systems poses several challenges, such as sensor selection, calibration, data processing, and interpretation. This paper proposes a sensing insole system that uses force-sensitive resistors (FSRs) to measure the pressure exerted by the foot on different regions of the insole. This system classifies four types of foot deformities: normal, flat, over-pronation, and excessive supination. The classification stage uses the differential values of pressure points as input for a feedforward neural network (FNN) model. Data acquisition involved 60 subjects diagnosed with the studied cases. The implementation of FNN achieved an accuracy of 96.6% using 50% of the dataset as training data and 92.8% using only 30% training data. The comparison with related work shows good impact of using the differential values of pressure points as input for neural networks compared with raw data.