Recognition System for Diagnosing Pneumonia and Bronchitis Using Children’s Breathing Sounds Based on Transfer Learning

作     者：Jianying Shi Shengchao Chen Benguo Yu Yi Ren Guanjun Wang Chenyang Xue 

作者机构：School of Information and Communication EngineeringHainan UniversityHaikou570228China School of Biomedical Information and EngineeringHainan Medical CollegeHaikou571199China Department of PediatricsHaikou Hospital of the Maternal and Child HealthHaikou570203China Wuhan National Laboratory for OptoelectronicsHuazhong University of Science and TechnologyWuhan430074China School of Instrument and ElectronicsNorth University of ChinaTaiyuan030051China 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第37卷第9期

页      面：3235-3258页

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：funded by the Scientific Research Starting Foundation of Hainan University(KYQD1882) the Flexible Introduction Scientific Research Starting Foundation of Hainan University(2020.11-2025.10) 

主　　题：Deep learning breath sounds transfer learning signal denoising 

摘      要：Respiratory infections in children increase the risk of fatal lung disease,making effective identification and analysis of breath sounds ***,most studies have focused on adults ignoring pediatric patients whose lungs are more vulnerable due to an imperfect immune system,and the scarcity of medical data has limited the development of deep learning methods toward reliability and high classification *** this work,we collected three types of breath sounds from children with normal(120 recordings),bronchitis(120 recordings),and pneumonia(120 recordings)at the posterior chest position using an off-the-shelf 3M electronic *** features were extracted from the wavelet denoised signal:spectrogram,mel-frequency cepstral coefficients(MFCCs),and Delta *** recog-nition model is based on transfer learning techniques and combines fine-tuned MobileNetV2 and modified ResNet50 to classify breath sounds,along with software for displaying analysis *** experiments on a real dataset demonstrate the effectiveness and superior performance of the proposed model,with average accuracy,precision,recall,specificity and F1 scores of 97.96%,97.83%,97.89%,98.89%and 0.98,respectively,achieving superior performance with a small *** proposed detection system,with a high-performance model and software,can help parents perform lung screening at home and also has the potential for a vast screening of children for lung disease.