تشخیص آپنه انسدادی خواب با استفاده از الگوریتم خوشه بندی پوشش متوسط و تبدیل موجک
محورهای موضوعی : Electrical Engineering
1 - استادیار گروه برق دانشگاه آزاد واحد علی آباد کتول
کلید واژه: تخفیف علائم, حداقل مربعات بازگشتی ترکیبی, انتخاب علائم چند خوشه ای, آپنه انسدادی خواب,
چکیده مقاله :
به دلیل خطر بیش از حد این بیماری، تشخیص آپنه انسدادی خواب (OSA) یک موضوع مطالعاتی گرم است. در این مقاله، چند تکنیک پردازش علائم محاسباتی موثر و کم قیمت برای این امر مورد آزمایش قرار گرفته است که اثرات آنها با دستاوردهای فعلی در تشخیص OSA مورد بررسی و مقایسه قرار گرفته است. تبدیل موجک پیچیده دو درختی (DT-CWT) در این مقاله برای استخراج ضرایب ویژگی استفاده شده است. 8 ویژگی غیرخطی از آن ضرایب استخراج شده است که پس از آن استفاده از الگوریتم انتخاب مشخصه چند خوشه ای (MCFS) کاهش یافته است. توابع باقی مانده در یک شبکه ترکیبی RBF پیاده سازی می شوند که یک رقیب محاسباتی کوچک برای خانواده شبکه های خود دستگاه بردار پشتیبان (SVM) است. نتایج یک درصد تشخیص OSA مناسب نزدیک به 96٪ را با پیچیدگی تخفیف تقریباً یک سوم از تکنیک های مبتنی بر SVM که قبلا ارائه شده بود، تأیید کرد.
The detection of obstructive sleep apnea (OSA) has turn out to be a warm studies topic because of the excessive danger of this sickness. in this paper, we tested a few effective and low-price computational sign processing techniques for this undertaking and compared their effects with current achievements in OSA detection.
dual-tree complex wavelet transform (DT-CWT) is used in this paper to extract feature coefficients. 8 nonlinear features are extracted from those coefficients after which decreased the usage of a multi-cluster characteristic selection (MCFS) algorithm. The remaining functions are implemented to a hybrid "ok-approach, RLS" RBF network, which is a small computational rival for the support vector device (SVM) own family of networks.
The results confirmed a appropriate OSA detection percentage near 96% with a discounted complexity of virtually one-third of previously provided SVM-primarily based techniques.
symptom discount, hybrid recursive least squares okay-manner, multi cluster symptom choice, obstructive sleep apnea
1. Hilmisson H, Lange N, Duntley SP. Sleep apnea detection: Accuracy of using automated ECG analysis compared to manually scored polysomnography (apnea hypopnea index) Sleep Breath. 2019;23:125–33.
2. Janbakhshi P, Shamsollahi MB. Sleep apnea detection from single-lead ECG using features based on ECG-derived respiration (EDR) signals. IRBM. 2018;39:206–18.
3. Khandoker AH, Gubbi J, Palaniswami M. Automated scoring of obstructive sleep apnea and hypopnea events using short-term electrocardiogram recordings. IEEE Trans InfTechnol Biomed. 2009;13:1057–67. 4. Ma Y, Sun S, Zhang M, Guo D, Liu AR, Wei Y, et al. Electrocardiogram-based sleep analysis for sleep apnea screening and diagnosis. Sleep Breath. 2019;24:231–40.
5. Zarei A, Asl BM. Automatic detection of obstructive sleep apnea using wavelet transform and entropy-based features from single-lead ECG signal. IEEE J Biomed Health Inform. 2019;23:1011–21.
6. Hassan AR, Bashar SK, Bhuiyan MI. Computerized Obstructive Sleep Apnea Diagnosis from Single-Lead ECG Signals Using Dual-Tree Complex Wavelet Transform. IEEE Region Humanitarian Technology Conference (R-HTC, Dhaka, Bangladesh); 21-23 December. 2017
7. Nishad A, Pachori RB, Acharya UR. Application of TQWT based filterbank for sleep apnea screening using ECG signals. J Ambient IntellHumanizComput. 2018 doiorg/101007/s12652-018-0867-3.
8. Avcı C, Akbaş A. Sleep apnea classification based on respiration signals by using ensemble methods. Biomed Mater Eng. 2015;26(Suppl 1):S1703–10.
9. Rachim VP, Li G, Chung WY. Sleep apnea classification using ECG-signal wavelet-PCA features. Biomed Mater Eng. 2014;24:2875–82.
10. Cai D, Zhang C, He X. Unsupervised Feature Selection for Multi-Cluster Data.In Proceedings of 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2010:333–42.
11. Hassan AR, Haque MA. An expert system for automated identification of obstructive sleep apnea from single-lead ECG using random under sampling boosting. Neurocomputing. 2017;235:122–30.
12. Hassan AR, Haque MA. Computer-aided obstructive sleep apnea screening from single-lead electrocardiogram using statistical and spectral features and bootstrap aggregating. Biocybern Biomed Eng. 2016;36:256–66.
13. Hassan AR. Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting. Biomed Signal Proc Control. 2016;29:22–30.
14. Wang T, Lu C, Shen G, Hong F. Sleep apnea detection from a single-lead ECG signal with automatic feature-extraction through a modified LeNet-5 convolutional neural network. PeerJ. 2019;7:e7731.
15. Singh SA, Majumder S. A novel approach OSA detection using single lead ECG Scalogram based on deep neural network. J Mech Med Biol. 2019;19:1–18.
16. Urtnasan E, Park JU, Joo EY, Lee KJ. Automated detection of obstructive sleep apnea events from a single-lead electrocardiogram using a convolutional neural network. J Med Syst. 2018;42:104.
17. Wang X, Cheng M, Wang Y, Liu S, Tian Z, Jiang F, et al. Obstructive Sleep Apnea Detection using ECG-Sensor with Convolutional Neural Networks. Multimedia Tools and Application, First Online. 2018 Jun 18;
18. Wang T, Lu C, Shen G. Detection of sleep apnea from single-lead ECG signal using a time window artificial neural network. Hindawi Bio Med Res Int. 2019 Article ID 9768072. https://doiorg/101155/2019/9768072.
19. Hassan AR, Haque MA, et al. Computer-Aided Sleep Apnea Diagnosis from Single-Lead Electrocardiogram using Dual-Tree Complex Wavelet Transform and spectral features. Rajshahi, Bangladesh: 1st International Conference on Electrical & Electronic Engineering (ICEEE), RUET; 2015. Nov, 04-06.
20. Thomas M, Das MK, Ari S. Automatic ECG arrhythmia classification using dual-tree complex wavelet based features. Int J Electron Commun. 2015;69:715–21.
21. Rifkin RM. Everything Old is New Again: A Fresh Look at Historical Approaches in Machine Learning. Ph.D. Thesis, MIT. 2002
22. Haykin S. Neural Networks and Learning Machines.Pearson Education, Inc. Upper Saddle River, New Jersey: Prentice Hall; 2008. pp. 230–63.
23. Papini GB, Fonseca P, Margarito J, van Gilst MM, Overeem S, Bergmans JWM, et al. On the generalizability of ECG-based obstructive sleep apnea monitoring: Merits and limitations of the Apnea-ECG database. ConfProc IEEE Eng Med Biol Soc. 2018;2018:6022–5.
24. Zhang P, Peng J. SVM vs. Regularized Least Squares Classification Proceedings of the th International Conference on Pattern Recognition. Cambridge, UK: 2004. Aug,
25. Debnath R, Takahashi H. Learning Capability: Classical RBF Network vs SVM with Gaussian Kernel Proceedings of International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems. 2002:293–302.
