2026 Vol.9 Feb.N01   

• Title: Research on Multimodal Feature-Based Deep Ensemble Learning for Sleep Apnea Detection
• Name: Yan Zhou*, Wenlu Zhang
• Company: Faculty of Engineering, Sias University ,ZhengZhou 451100 China
• Abstract:

  This study proposes a multi-feature fusion framework for automatic sleep apnea (SA) detection using electrocardiogram (ECG) signals. ECG segments are transformed into time–frequency representations via continuous wavelet transform (CWT) and processed by an Squeeze-and-Excitation Residual Network (SE-ResNet) to extract spatial features, while a Convolutional Neural Network – Long Short-Term Memory (CNN–LSTM) model captures temporal dependencies from ECG-derived sequences. The complementary features are fused and classified using a support vector machine (SVM). Experimental results on a public dataset demonstrate that the proposed method achieves superior performance (accuracy: 96.54%, precision: 95.26%, recall: 94.48%, F1-score: 94.87%, AUC: 97.51%), outperforming conventional single-model approaches. These results indicate that the proposed framework effectively exploits both temporal and time–frequency characteristics of ECG signals, providing a robust and promising solution for automated SA detection.

  
  

• Keyword: Sleep apnea; deep learning; CNN–LSTM; SE-ResNet; SVM
• DOI: 10.12250/jpciams2026090212
• Citation form: Yan Zhou*, Wenlu Zhang.Research on Multimodal Feature-Based Deep Ensemble Learning for Sleep Apnea Detection[J]. Computer Informatization and Mechanical System,2026,Vol.9,pp.

[1] S. Bakare, F. Olori, C. F. Okirie, H. Yousif, et al, Beyond obstructive sleep apnea: a systematic review of sexspecific links between diverse sleep disorders and cardiac arrhythmias, Sleep Science and Practice, vol. 10, Art. no. 2, 2026.

[2] Gottlieb D, Punjabi N. Diagnosis and Management of Obstructive Sleep Apnea: a Review. JAMA. 2020:323(14):1389–1400.

[3] Chi, H.T.K., Dabbs-Brown, A., Jurek-Loughrey, A. et al. Obstructive Sleep Apnea Prediction: A Comprehensive Review and Comparative Study. Mach Learn 115, 29 (2026).

[4] Liu, P., Qian, W., Zhang, H. et al. Automatic sleep stage classification using deep learning: signals, data representation, and neural networks. Artif Intell Rev 57, 301 (2024).

[5] Nandakumar, R., Arunachalam, R., Pugalenthi, R., etal. Automatic model of sleep apnea detection using optimized weighted fusion process of hybrid convolution (1D/2D) efficient attention network from EEG signals. EURASIP J. Adv. Signal Process. 2025, 18 (2025).

[6] Almarshad MA, Al-Ahmadi S, Islam S, Soudani A and BaHammam AS Transformer-based deep learning approach for obstructive sleep apnea detection using single-lead ECG. Front. Artif. Intell. 9:1727091 (2026).

[7] Yook S, Kim D, Gupte C, Joo EY, Kim H. Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity. Sleep Med. 2024 Feb: 114:211-219.

[8] Soonhyun Yook, Dongyeop Kim, Chaitanya Gupte, Eun Yeon Joo, Hosung Kim, Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity, Sleep Medicine, Volume 114, 2024, Pages 211-219.

[9] Park MJ, Choi JH, Kim SY, Ha TK. A deep learning algorithm model to automatically score and grade obstructive sleep apnea in adult polysomnography. Digit Health. 2024 Oct 17; 10:20552076241291707.

[10] Yifei Wang, Qi Liu, Fuli Min et al, PSG-MAE: Robust Multitask Sleep Event Monitoring using Multichannel PSG Reconstruction and Inter-channel Contrastive Learning, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 34, 274–286, 2025. 

[11] Biswarup Ganguly, Rajobrata Dasgupta, Debangshu Dey, A residual deep learning framework for sleep apnea diagnosis from single lead electrocardiogram signals: An explainable artificial intelligence approach, Engineering Applications of Artificial Intelligence, Volume 148, 2025, 110481.

[12] Padovano D, Martinez-Rodrigo A, Pastor JM, Rieta JJ, Alcaraz R. Deep Learning and Recurrence Information Analysis for the Automatic Detection of Obstructive Sleep Apnea. Applied Sciences. 2025; 15(1):433.

[13] Wang E, Koprinska I, Jeffries B. Sleep Apnea Prediction Using Deep Learning. IEEE J Biomed Health Inform. 2023 Nov;27(11):5644-5654.

[14] Lin C-Y, Wang Y-W, Setiawan F, et al, Sleep Apnea Classification Algorithm Development Using a Machine-Learning Framework and Bag-of-Features Derived from Electrocardiogram Spectrograms. Journal of Clinical Medicine. 2022; 11(1):192.

[15] Linh TTD, Trang NTH, Lin SY, Wu D, Liu WT, Hu CJ. Detection of preceding sleep apnea using ECG spectrogram during CPAP titration night: A novel machine-learning and bag-of-features framework. J Sleep Res. 2024 May;33(3):e13991.

[16] Sharma P, Jalali A, Majmudar M, Rajput KS, Selvaraj N. Deep-Learning based Sleep Apnea Detection using SpO2 and Pulse Rate. Annu Int Conf IEEE Eng Med Biol Soc. 2022 Jul;2022:2611-2614.

[17] Sadr N, de Chazal P, van Schaik A, Breen P. Sleep apnoea episodes recognition by a committee of ELM classifiers from ECG signal. Annu Int Conf IEEE Eng Med Biol Soc. 2015; 2015:7675-8.

[18] Rizal, A., Siregar, F.D.A.A., Fauzi, H.T. (2022). Obstructive sleep apnea (OSA) classification based on heart rate variability (HRV) on electrocardiogram (ECG) signal using support vector machine (SVM). Traitement du Signal, Vol. 39, No. 2, pp. 469-474.

[19] Kunyang Li, Weifeng Pan, Yifan Li, Qing Jiang, Guanzheng Liu, A method to detect sleep apnea based on deep neural network and hidden Markov model using single-lead ECG signal, Neurocomputing, Volume 294, 2018, Pages 94-101.

[20] Haifa Almutairi, Ghulam Mubashar Hassan and Amitava Datta, Classification of Obstructive Sleep Apnoea from single-lead ECG signals using convolutional neural and Long Short Term Memory networks, Biomedical Signal Processing and Control, Volume 69, 2021.