FusedTSNet: An automated nocturnal sleep sound classification method based on a fused textural and statistical feature generation network

Abstract

Nowadays, many people have suffered from sleep disorders. These diseases affect daily life and can disrupt sanity. Sleep disorders/diseases can be diagnosed by using nocturnal sleep sounds. This work presents an automated nocturnal sound classification method. The proposed nocturnal sound classification method can be used in the automated sleep disease diagnosis process. To propose a highly accurate and cognitive method, a fused feature generation network is proposed. The proposed fused feature generation network extracts both textural features and statistical features together. Therefore, this method is called as fused textural and statistical feature generation network (FusedTSNet). One-dimensional discrete wavelet transform (DWT) is employed to create levels and 7-leveled DWT is applied to nocturnal sounds. Here, DWT is utilized as a pooling/decomposition method to create a multileveled feature generation network. By using the ReliefF iterative neighborhood component analysis (RFINCA), the most valuable features are selected. To demonstrate the success of the FusedTSNet and RFINCA based nocturnal sound classification method, conventional classifiers are used. The proposed FusedTSNet and RFINCA based nocturnal sound classification method were tested on a collected nocturnal sound dataset. This dataset has 700 sounds in 7 classes. Our method achieved a 98.0% classification rate on this dataset. This work clearly indicates that the automated sleep behavior detection can be developed and the success of the proposed FusedTSNet and RFINCA based sound classification method is obviously shown. (C) 2020 Elsevier Ltd. All rights reserved.