Attention-Based Transfer Learning for Efficient Obstructive Sleep Apnea (OSA) Classification on Snore Sound
Polysomnography (PSG) is currently the gold-standard technique for classifying sleep apnea disorders. Yet, it is costly and requires an expert to score the severity, making it impractical for self-screening and home use. Snore sound classification with Deep Learning (DL) is a promising approach and...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11018873/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849319357802348544 |
|---|---|
| author | Apichada Sillaparaya Yuttapong Jiraraksopakun Kosin Chamnongthai Apichai Bhatranand |
| author_facet | Apichada Sillaparaya Yuttapong Jiraraksopakun Kosin Chamnongthai Apichai Bhatranand |
| author_sort | Apichada Sillaparaya |
| collection | DOAJ |
| description | Polysomnography (PSG) is currently the gold-standard technique for classifying sleep apnea disorders. Yet, it is costly and requires an expert to score the severity, making it impractical for self-screening and home use. Snore sound classification with Deep Learning (DL) is a promising approach and has gained increasing interest due to its relationship with abnormal breathing conditions in both time and frequency domains. This study proposes an attention-based transfer learning model for non-invasive detection of obstructive sleep apnea (OSA) using audio signals. Mel-spectrograms and MFCC features were input into the MobileNetV3-Large to extract deep features. A modified SENet was implemented to provide suitable channel attention for the extracted features. The attention-based features are then classified into normal and abnormal snore events. The study evaluates model performance using 10-fold cross-validation on sound data of the 70 adult OSA patients of an open-source PSG-Audio dataset. Results show that utilizing both Mel-Spectrogram and MFCCs as input features significantly enhances classification performance compared to single-feature models. In addition, the MobileNetV3-Large with modified SENet significantly outperforms the combination of other pre-trained and attention mechanisms. Specifically, the proposed model provides an accuracy of <inline-formula> <tex-math notation="LaTeX">$92.576\pm 0.910$ </tex-math></inline-formula>%, a sensitivity of <inline-formula> <tex-math notation="LaTeX">$92.906\pm 1.928$ </tex-math></inline-formula>%, a specificity of <inline-formula> <tex-math notation="LaTeX">$92.269\pm 2.740$ </tex-math></inline-formula>%, a precision of <inline-formula> <tex-math notation="LaTeX">$92.173\pm 3.024$ </tex-math></inline-formula>%, and an F1-score of <inline-formula> <tex-math notation="LaTeX">$92.486\pm 1.326$ </tex-math></inline-formula>% on the binary classification. Its performance also shows statistically significant improvement when benchmarked with other existing OSA classification models. Our proposed model demonstrates suitable potential for portable device-based sleep apnea monitoring applications. |
| format | Article |
| id | doaj-art-bbfb246f52e44923b4c6b4980b159e53 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-bbfb246f52e44923b4c6b4980b159e532025-08-20T03:50:31ZengIEEEIEEE Access2169-35362025-01-011311387911388910.1109/ACCESS.2025.357520311018873Attention-Based Transfer Learning for Efficient Obstructive Sleep Apnea (OSA) Classification on Snore SoundApichada Sillaparaya0https://orcid.org/0009-0001-6615-0349Yuttapong Jiraraksopakun1https://orcid.org/0000-0003-0143-978XKosin Chamnongthai2https://orcid.org/0000-0003-1509-5754Apichai Bhatranand3https://orcid.org/0000-0002-3468-918XElectronics and Telecommunication Engineering Department, Faculty of Engineering, King Mongkut’s University of Technology Thonburi, Bangkok, ThailandElectronics and Telecommunication Engineering Department, Faculty of Engineering, King Mongkut’s University of Technology Thonburi, Bangkok, ThailandElectronics and Telecommunication Engineering Department, Faculty of Engineering, King Mongkut’s University of Technology Thonburi, Bangkok, ThailandElectronics and Telecommunication Engineering Department, Faculty of Engineering, King Mongkut’s University of Technology Thonburi, Bangkok, ThailandPolysomnography (PSG) is currently the gold-standard technique for classifying sleep apnea disorders. Yet, it is costly and requires an expert to score the severity, making it impractical for self-screening and home use. Snore sound classification with Deep Learning (DL) is a promising approach and has gained increasing interest due to its relationship with abnormal breathing conditions in both time and frequency domains. This study proposes an attention-based transfer learning model for non-invasive detection of obstructive sleep apnea (OSA) using audio signals. Mel-spectrograms and MFCC features were input into the MobileNetV3-Large to extract deep features. A modified SENet was implemented to provide suitable channel attention for the extracted features. The attention-based features are then classified into normal and abnormal snore events. The study evaluates model performance using 10-fold cross-validation on sound data of the 70 adult OSA patients of an open-source PSG-Audio dataset. Results show that utilizing both Mel-Spectrogram and MFCCs as input features significantly enhances classification performance compared to single-feature models. In addition, the MobileNetV3-Large with modified SENet significantly outperforms the combination of other pre-trained and attention mechanisms. Specifically, the proposed model provides an accuracy of <inline-formula> <tex-math notation="LaTeX">$92.576\pm 0.910$ </tex-math></inline-formula>%, a sensitivity of <inline-formula> <tex-math notation="LaTeX">$92.906\pm 1.928$ </tex-math></inline-formula>%, a specificity of <inline-formula> <tex-math notation="LaTeX">$92.269\pm 2.740$ </tex-math></inline-formula>%, a precision of <inline-formula> <tex-math notation="LaTeX">$92.173\pm 3.024$ </tex-math></inline-formula>%, and an F1-score of <inline-formula> <tex-math notation="LaTeX">$92.486\pm 1.326$ </tex-math></inline-formula>% on the binary classification. Its performance also shows statistically significant improvement when benchmarked with other existing OSA classification models. Our proposed model demonstrates suitable potential for portable device-based sleep apnea monitoring applications.https://ieeexplore.ieee.org/document/11018873/Obstructive sleep apnea (OSA)snore sounddeep learning (DL)OSA classificationtransfer learning |
| spellingShingle | Apichada Sillaparaya Yuttapong Jiraraksopakun Kosin Chamnongthai Apichai Bhatranand Attention-Based Transfer Learning for Efficient Obstructive Sleep Apnea (OSA) Classification on Snore Sound IEEE Access Obstructive sleep apnea (OSA) snore sound deep learning (DL) OSA classification transfer learning |
| title | Attention-Based Transfer Learning for Efficient Obstructive Sleep Apnea (OSA) Classification on Snore Sound |
| title_full | Attention-Based Transfer Learning for Efficient Obstructive Sleep Apnea (OSA) Classification on Snore Sound |
| title_fullStr | Attention-Based Transfer Learning for Efficient Obstructive Sleep Apnea (OSA) Classification on Snore Sound |
| title_full_unstemmed | Attention-Based Transfer Learning for Efficient Obstructive Sleep Apnea (OSA) Classification on Snore Sound |
| title_short | Attention-Based Transfer Learning for Efficient Obstructive Sleep Apnea (OSA) Classification on Snore Sound |
| title_sort | attention based transfer learning for efficient obstructive sleep apnea osa classification on snore sound |
| topic | Obstructive sleep apnea (OSA) snore sound deep learning (DL) OSA classification transfer learning |
| url | https://ieeexplore.ieee.org/document/11018873/ |
| work_keys_str_mv | AT apichadasillaparaya attentionbasedtransferlearningforefficientobstructivesleepapneaosaclassificationonsnoresound AT yuttapongjiraraksopakun attentionbasedtransferlearningforefficientobstructivesleepapneaosaclassificationonsnoresound AT kosinchamnongthai attentionbasedtransferlearningforefficientobstructivesleepapneaosaclassificationonsnoresound AT apichaibhatranand attentionbasedtransferlearningforefficientobstructivesleepapneaosaclassificationonsnoresound |