Optimizing ANN-Based Lyapunov Stability for Facial Expression Recognition as A Base Monitoring Neurological Disorders

Abstract

This study emphasizes the importance of facial expression recognition in identifying neurological problems in individuals with limited verbal communication abilities. Current evaluation methods are time-consuming and expensive, hindering medical professionals. To address these limitations, we present an improved artificial neural network based on Lyapunov Stability Theory (ANN-LST). By combining these methods, we overcome convergence issues while encountering overfitting problems with high dimensional data, affecting prediction and analysis. Our approach employs PCA for dimensionality reduction and feature extraction, effectively solving overfitting problems. The proposed model is evaluated using the JAFFE and our own databases, with accuracy (ACC) as the evaluation metric. Results demonstrate higher recognition rates and faster training speeds due to adaptive learning rate parameters and extraction of relevant feature information. The proposed system achieves a 13% higher success rate compared to face recognition systems using raw images alone. Overall, this model represents a significant advancement, offering promising applications for facial expression recognition in patients with neurological disorders