# Deep Convolutional Neural Network-Based Detection of Gait Abnormalities in Parkinson’s Disease Using Fewer Plantar Sensors in a Smart Insole

## TL;DR

This paper introduces a deep learning model that detects gait abnormalities in Parkinson’s disease using fewer sensors in smart insoles, improving accuracy and practicality.

## Contribution

A novel CNN model that achieves high accuracy with fewer sensors for PD gait detection.

## Key findings

- The CNN model achieved 90.35% accuracy using only 8 out of 32 plantar sensors.
- The model outperformed conventional CNNs by approximately 10% in classification accuracy.
- Processing each foot independently improved detection of gait asymmetries in PD patients.

## Abstract

Early diagnosis of Parkinson’s disease (PD) is crucial for slowing its progression. Gait analysis is increasingly used to detect early symptoms, with smart insoles emerging as a cost-effective and convenient tool for daily monitoring. However, smart insoles have practical limitations, including durability concerns, limited battery life, and difficulties in minimizing the number of sensors. In this study, we designed a novel deep convolutional neural network model for accurately detecting abnormal gaits in patients with PD using a reduced number of sensors embedded in smart insoles. The proposed convolutional neural network (CNN) model was trained on a gait dataset collected from a total of 29 participants, including 13 healthy individuals, 9 elderly individuals, and 7 patients with Parkinson’s disease (PD). Instead of combining plantar pressure data from both feet, the model processes each foot independently through sequential layers to better capture gait asymmetries. The proposed CNN model achieved a classification accuracy of 90.35% using only 8 of the 32 plantar pressure sensors in the smart insole, outperforming a conventional CNN model by approximately 10%. The experimental results demonstrate the potential of our CNN model for effectively detecting abnormal gait patterns in patients with PD while minimizing sensor requirements, enhancing the practicality and efficiency of smart insoles for real-world use.