Journal of information and
communication convergence engineering
(J. Inf. Commun. Converg. Eng.)

Gait analysis plays a pivotal role in clinical diagnostics and aids in the detection and evaluation of various disorders and disabilities. Traditional methods often rely on intricate video systems or pressure mats to assess gait. Previous studies have demonstrated the potential of artificial intelligence (AI) in gait analysis using techniques, such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. However, these methods often encounter challenges related to high dimensionality, temporal dependencies, and variability in gait patterns, making accurate and efficient classification difficult. To address these challenges, this study introduces a simple one-dimensional (1D) CNN model designed to analyze ground reaction force (GRF) patterns and classify individuals as healthy or suffering from gait disorders. The model achieved a remarkable classification accuracy of 98.65% in distinguishing healthy individuals from those with gait disorders, demonstrating significant improvements over the existing models. This performance is bolstered by the attention mechanism and standardization techniques that enhance robustness and accuracy.

Keywords: Attention mechanism, Convolutional neural networks (CNN), Gait analysis, Ground reaction force (GRF), Gaiter dataset