Snoring Sounds Classification of OSAHS Patients Based on Model Fusion

Abstract

Obstructive sleep apnea hypopnea syndrome (OSAHS) is a prevalent and detrimental chronic condition. The conventional diagnostic approach for OSAHS is intricate and costly. Snoring is one of the most typical and easily obtained symptom of OSAHS patients. In this study, a series of acoustic features are extracted from snoring sounds. A fused model that integrates a deep neural network, K-nearest neighbors (KNN), and a random under sampling boost algorithm is proposed to classify snoring sounds of simple snorers (SSSS), simple snoring sounds of OSAHS patients (SSSP), and apnea-hypopnea snoring sounds of OSAHS patients (APSP). The ReliefF algorithm is employed to select features with high relevance in each classification model. A hard voting strategy is implemented to obtain an optimal fused model. Results show that the proposed fused model achieves commendable performance with an accuracy rate of 85.76%. It demonstrates the effectiveness and validity of assisting in diagnosing OSAHS patients based on the analysis of snoring sounds.