بهینه‌سازی ابرپارامترهای مدل‌های ترکیبی یادگیری عمیق با رویکرد تشخیص آپنه خواب با استفاده از الگوریتم‌های هوش جمعی | ||
| پژوهش های نظری و کاربردی هوش ماشینی | ||
| مقاله 3، دوره 2، شماره 2، اسفند 1403، صفحه 31-48 اصل مقاله (1.73 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22034/abmir.2025.22637.1087 | ||
| نویسندگان | ||
| فرانک فتوحی قزوینی* 1؛ مریم بدیعی2 | ||
| 1استادیار دانشکده فنی و مهندسی، گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشگاه قم ، قم، ایران | ||
| 2دانشجوی کارشناسی ارشد دانشکده فنی و مهندسی، گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشگاه قم ، قم، ایران | ||
| چکیده | ||
| این مقاله به بررسی کارایی طبقه‌بندهای ترکیبی CNN-DRNN در شناسایی آپنه خواب با استفاده از سیگنال الکتروکاردیوگرام قلب (ECG) پرداخته است. در این مطالعه، مدل‌های مختلف شبکه‌های عصبی کانولوشنی ازجمله AlexNet، VGG16، VGG19 و ZFNet در ترکیب با مدل‌های شبکه عصبی بازگشتی عمیق شامل LSTM، GRU و BiLSTM مورد ارزیابی قرارگرفته است. این مدل‌ها با و بدون استفاده از بهینه‌سازهای هوش جمعی گورکن عسل و گرگ خاکستری برای تعیین مقادیر بهینه ابرپارامترها مقایسه شده‌اند. نتایج نشان می‌دهد که مدل ترکیبی AlexNet-GRU پس از اعمال هر دو بهینه‌ساز، بهترین عملکرد را با دقت ۹۵٪، نرخ تشخیص 61/97٪ و F-Score 37/93٪ ارائه کرده است. در این پژوهش، چالش بهینه‌سازی ابرپارامترها در مدل‌های یادگیری عمیق با استفاده از دو بهینه‌ساز گورکن عسل و گرگ خاکستری بررسی‌شده است. این بهینه‌سازها با الهام از رفتارهای طبیعت، تعامل غیرمستقیم میان عامل‌ها و توزیع هوشمند به حل این چالش کمک می‌کنند. البته، بهینه‌ساز گورکن عسل در مقایسه با گرگ خاکستری در انتخاب مقادیر بهینه ابرپارامترها عملکرد بهتری از خود نشان داده است. | ||
| کلیدواژه‌ها | ||
| آپنه خواب؛ بهینه‌ساز گورکن عسل؛ بهینه‌ساز گرگ خاکستری؛ شبکه عصبی پیچشی؛ شبکه عصبی بازگشتی عمیق | ||
| عنوان مقاله [English] | ||
| Optimization of Hyperparameters in Hybrid Deep Learning Models for Sleep Apnea Detection Using Swarm Intelligence Algorithms | ||
| نویسندگان [English] | ||
| Faranak Fotouhi-Ghazvini1؛ Maryam Badiee2 | ||
| 1Assistant Professor Department of Computer Engineering and IT, University of Qom, Qom, Iran | ||
| 2M.Sc Student Department of Computer Engineering and IT, University of Qom, Qom, Iran | ||
| چکیده [English] | ||
| This study investigates the efficiency of CNN-DRNN hybrid classifiers in detecting sleep apnea using electrocardiogram (ECG) signals. Various CNN models were evaluated, including AlexNet, VGG16, VGG19, and ZFNet, along with DRNN models such as LSTM, GRU, and BiLSTM. These models were compared with and without the application of swarm intelligence optimizers, namely the Honey Badger Algorithm (HBA) and Grey Wolf Optimizer (GWO), for optimizing hyperparameter values. The results demonstrated that the AlexNet-GRU hybrid model achieved the best performance after applying both optimizers, with an accuracy of 95%, a detection rate of 97.61%, and an F-Score of 93.37%.This research also explores the challenges of hyperparameter optimization in deep learning models using swarm intelligence-based optimizers. These optimizers, inspired by natural behaviors, facilitate problem-solving through intelligent distribution, indirect interactions among agents, and simplification of complex processes. Additionally, the findings revealed that HBA outperformed GWO in determining optimal hyperparameter values, leading to enhanced model performance. Overall, the study highlights the potential of integrating deep learning models with swarm intelligence optimizers to improve sleep apnea detection. | ||
| کلیدواژه‌ها [English] | ||
| Sleep Apnea, HoneyBadger Optimizer, GreyWolf Optimizer, Convolutional Neural Network, Deep Recurrent Neural Network | ||
| مراجع | ||
|
[1] A. K. Abasi, M. Aloqaily, and M. Guizani, “Optimization of CNN using modified honey badger algorithm for sleep apnea detection,” Expert Syst. Appl., vol. 229, p. 120484, 2023. [2] S. Ahmadzadeh, J. Luo, and R. Wiffen, “Review on biomedical sensors, technologies and algorithms for diagnosis of sleep disordered breathing: Comprehensive survey,” IEEE Rev. Biomed. Eng., vol. 15, pp. 4–22, 2020. [3] S. Akyol, M. Yildirim, and B. Alatas, “Multi-feature fusion and improved BO and IGWO metaheuristics based models for automatically diagnosing the sleep disorders from sleep sounds,” Comput. Biol. Med., vol. 157, p. 106768, 2023. [4] N. F. Alharbi and N. Hewahi, “Exploring deep neural network capability for intrusion detection using different mobile phones platforms,” Int. J. Comput. Digit. Syst., 2021. [5] A. A. Awad, A. F. Ali, and T. Gaber, “An improved long short term memory network for intrusion detection,” PLoS One, vol. 18, no. 8, p. e0284795, 2023. [6] M. Bahrami and M. Forouzanfar, “Sleep apnea detection from single-lead ECG: A comprehensive analysis of machine learning and deep learning algorithms,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–11, 2022. [7] A. Bhusal, A. Alsadoon, P. W. C. Prasad, N. Alsalami, and T. A. Rashid, “Deep learning for sleep stages classification: modified rectified linear unit activation function and modified orthogonal weight initialisation,” Multimed. Tools Appl., vol. 81, no. 7, pp. 9855–9874, 2022. [8] J. H. Che, B. W.-K. Ling, Q. Liu, and Q. Miao, “Variational mode decomposition-based sleep stage classification using multi-channel polysomnograms,” Signal Image Video Process., vol. 17, no. 4, pp. 1355–1363, 2023. [9] L. Chen, X. Zhang, and C. Song, “An automatic screening approach for obstructive sleep apnea diagnosis based on single-lead electrocardiogram,” IEEE Trans. Autom. Sci. Eng., vol. 12, no. 1, pp. 106–115, 2014. [10] A. Darwish, D. Ezzat, and A. E. Hassanien, “An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis,” Swarm Evol. Comput., vol. 52, p. 100616, 2020. [11] M. R. Falahzadeh, F. Farokhi, A. Harimi, and R. Sabbaghi-Nadooshan, “Deep convolutional neural network and gray wolf optimization algorithm for speech emotion recognition,” Circ. Syst. Signal Process., vol. 42, no. 1, pp. 449–492, 2023. [12] M. Hafezi et al., “Sleep apnea severity estimation from tracheal movements using a deep learning model,” IEEE Access, vol. 8, pp. 22641–22649, 2020. [13] P. Hamilton, “Open source ECG analysis,” in *Comput. Cardiol., pp. 101–104, IEEE, 2002. [14] U. Hanif et al., “Estimation of apneahypopnea index using deep learning on 3-D craniofacial scans,” IEEE J. Biomed. Health Inform., vol. 25, no. 11, pp. 4185–4194, 2021. [15] I. Jabłoński, R. Morello, and J. Mroczka, “The complexity and variability mapping for prediction and explainability of the sleep apnea syndrome,” IEEE Sens. J., vol. 21, no. 13, pp. 14203–14212, 2021. [16] J. L. Kelly et al., “Diagnosis of sleep apnoea using a mandibular monitor and machine learning analysis: one-night agreement compared to in-home polysomnography,” Front. Neurosci., vol. 16, p. 726880, 2022. [17] H. Korkalainen et al., “Accurate deep learning-based sleep staging in a clinical population with suspected obstructive sleep apnea,” IEEE J. Biomed. Health Inform., vol. 24, no. 7, pp. 2073–2081, 2019. [18] H. Korkalainen et al., “Detailed assessment of sleep architecture with deep learning and shorter epoch-to-epoch duration reveals sleep fragmentation of patients with obstructive sleep apnea,” IEEE J. Biomed. Health Inform., vol. 25, no. 7, pp. 2567–2574, 2020.
[19] G. Kouziokas, *Swarm Intelligence and Evolutionary Computation: Theory, Advances and Applications in Machine Learning and Deep Learning*. CRC Press, 2023. [20] M. Leo, G. M. Bernava, P. Carcagnì, and C. Distante, “Video-based automatic baby motion analysis for early neurological disorder diagnosis: state of the art and future directions,” Sensors, vol. 22, no. 3, p. 866, 2022. [21] N. Limbu et al., “A novel solution of deep learning for sleep apnea detection: enhancement of SC and elimination of GVICS,” Multimed. Tools Appl., vol. 81, no. 27, pp. 38569–38592, 2022. [22] H. W. Loh et al., “Automated detection of cyclic alternating pattern and classification of sleep stages using deep neural network,” Appl. Intell., vol. 52, no. 3, pp. 2903–2917, 2022. [23] S. N. Makhadmeh et al., “Recent advances in grey wolf optimizer, its versions and applications,” IEEE Access, 2023. | ||
|
آمار تعداد مشاهده مقاله: 423 تعداد دریافت فایل اصل مقاله: 328 |
||