TY - GEN
T1 - Feature Fool Exploitation for Lightweight Anomaly Detection in Respiratory Sound
AU - Le, Kim Ngoc T.
AU - Bang, Sammy Yap Xiang
AU - Le, Duc Tai
AU - Choo, Hyunseung
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.
PY - 2023
Y1 - 2023
N2 - Respiratory sound auscultation with digital stethoscopes is a common technique for identifying lung disorders, however, it requires a qualified medical expert to interpret the sounds, and inter-listener variability results from subjectivity in interpretations. To improve diagnostic accuracy and enhance patient treatment, there is a growing need for automated detection of lung diseases. Deep neural networks (DNNs) have demonstrated substantial potential in addressing such challenges. However, DNNs demand a significant amount of data, and the largest available respiratory dataset, ICBHI, comprises only 6898 breathing cycles, which is insufficient to train a satisfactory DNN model. To address the issue, we propose a robust and lightweight model that employs a feature fool exploitation technique to identify respiratory anomalies. Next, we deploy two evaluation approaches to evaluate its performance: random 60/40 splitting and 5-fold cross-validation, against state-of-the-art methods, using the ICBHI dataset. Remarkably, our scheme outperforms existing approaches up to 18.26%, achieving impressive accuracy rates of 72.36% and 89.46%, using the two respective train/test splitting methods. The results show a significant improvement from our method over existing approaches, suggesting its promise for future respiratory healthcare technology research.
AB - Respiratory sound auscultation with digital stethoscopes is a common technique for identifying lung disorders, however, it requires a qualified medical expert to interpret the sounds, and inter-listener variability results from subjectivity in interpretations. To improve diagnostic accuracy and enhance patient treatment, there is a growing need for automated detection of lung diseases. Deep neural networks (DNNs) have demonstrated substantial potential in addressing such challenges. However, DNNs demand a significant amount of data, and the largest available respiratory dataset, ICBHI, comprises only 6898 breathing cycles, which is insufficient to train a satisfactory DNN model. To address the issue, we propose a robust and lightweight model that employs a feature fool exploitation technique to identify respiratory anomalies. Next, we deploy two evaluation approaches to evaluate its performance: random 60/40 splitting and 5-fold cross-validation, against state-of-the-art methods, using the ICBHI dataset. Remarkably, our scheme outperforms existing approaches up to 18.26%, achieving impressive accuracy rates of 72.36% and 89.46%, using the two respective train/test splitting methods. The results show a significant improvement from our method over existing approaches, suggesting its promise for future respiratory healthcare technology research.
KW - anomaly detection
KW - feature extraction
KW - ICBHI dataset
KW - lightweight
KW - respiratory sound
UR - https://www.scopus.com/pages/publications/85177856234
U2 - 10.1007/978-981-99-8296-7_40
DO - 10.1007/978-981-99-8296-7_40
M3 - Conference contribution
AN - SCOPUS:85177856234
SN - 9789819982950
T3 - Communications in Computer and Information Science
SP - 556
EP - 563
BT - Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications - 10th International Conference, FDSE 2023, Proceedings
A2 - Dang, Tran Khanh
A2 - Küng, Josef
A2 - Chung, Tai M.
PB - Springer Science and Business Media Deutschland GmbH
T2 - 10th International Conference on Future Data and Security Engineering, FDSE 2023
Y2 - 22 November 2023 through 24 November 2023
ER -
