Open-set lung sound recognition model based on conditional Gaussian capsule network and variational time-frequency feature reconstruction

作     者：Zhang, Yixuan Zhang, Jingye Shi, Lukui 

作者机构：Hebei Univ Technol Sch Artificial Intelligence Tianjin 300401 Peoples R China 

出 版 物：《BIOMEDICAL SIGNAL PROCESSING AND CONTROL》 (生物医学信号处理与控制)

年 卷 期：2024年第87卷第PartB期

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 10[医学] 

基　　金：Natural Science Foundation of Hebei Province [F2020202008] Hebei Province Graduate Innovation Funding Project [CXZZSS2022055] Tianjin Science and Technology Key RD Program [20YFZCGX00490] 

主　　题：Lung sound recognition Open-set recognition Variational autoencoder Feature reconstruction 

摘      要：Lung sound auscultation is an essential method for diagnosing lung diseases;however, most existing lung sound recognition methods fail to identify classes that are unknown in training. Thus, we proposed an open-set lung sound recognition model based on the conditional Gaussian capsule network and variational time- frequency feature reconstruction. The proposed model incorporates an inference network, a cubic encoder, an attention module, a classifier, a cubic decoder, and a generative network. First, the inference network is employed to extract the time-frequency features of lung sounds at a single time step. Then, the variational distribution of lung sounds is computed using the capsule network and optimized to approximate the Gaussian model of the class to which the sample belongs according to the labels. Time-frequency synchronized feature extraction and reconstruction are performed on the entire lung sound sample using the cubic encoder and cubic decoder. Finally, we utilize the generative network to refactor the lung sound features for open-set recognition. The proposed model was evaluated experimentally on a combined dataset using two different category assignment schemes. The results demonstrate that the proposed model achieved accuracies of 82.31% and 88.47%, respectively, thereby outperforming existing methods.