Deep Learning Framework Applied for Predicting Anomaly of Respiratory\n Sounds

2020/12/25 by Dat Ngo, Lam Pham, Ngo, Dat +9 · 1 citation
Computer Science · Medicine · #Audio and Speech Processing (eess.AS) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Phonocardiography and Auscultation Techniques #Respiratory and Cough-Related Research #Sound (cs.SD) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2012.13668

openalex publication_date 2020/12/25 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

This paper proposes a robust deep learning framework used for classifying\nanomaly of respiratory cycles. Initially, our framework starts with front-end\nfeature extraction step. This step aims to transform the respiratory input\nsound into a two-dimensional spectrogram where both spectral and temporal\nfeatures are well presented. Next, an ensemble of C- DNN and Autoencoder\nnetworks is then applied to classify into four categories of respiratory\nanomaly cycles. In this work, we conducted experiments over 2017 Internal\nConference on Biomedical Health Informatics (ICBHI) benchmark dataset. As a\nresult, we achieve competitive performances with ICBHI average score of 0.49,\nICBHI harmonic score of 0.42.\n

Cited by

• A Multi-Stage Hybrid CNN-Transformer Network for Automated Pediatric Lung Sound Classification

Related

• Robust Deep Learning Framework For Predicting Respiratory Anomalies and\n Diseases
• An Ensemble of Deep Learning Frameworks Applied For Predicting Respiratory Anomalies
• CNN-MoE based framework for classification of respiratory anomalies and\n lung disease detection
• Inception-Based Network and Multi-Spectrogram Ensemble Applied For Predicting Respiratory Anomalies and Lung Diseases
• Deep auscultation: Predicting respiratory anomalies and diseases via recurrent neural networks