مروری بر الگوریتم‌های یادگیری ماشین جهت تشخیص اوتیسم با استفاده از سیگنال EEG

شریفی مهرجرد, زهره; مومنی, هاجر; ادبی اردکانی, حبیب

doi:10.22052/scj.2023.248522.1110

مروری بر الگوریتم‌های یادگیری ماشین جهت تشخیص اوتیسم با استفاده از سیگنال EEG

نوع مقاله : مقاله مروری

نویسندگان

¹ گروه مهندسی برق، دانشگاه فنی و حرفه ای، تهران، ایران.

² گروه مهندسی برق، دانشگاه اردکان، اردکان، ایران.

³ گروه مهندسی برق، دانشگاه یزد، یزد، ایران.

10.22052/scj.2023.248522.1110

چکیده

بیماری اوتیسم یک اختلال عصبی و تکاملی است که اشخاص مبتلا به آن اغلب علایم یا رفتارهای محدود را نشان می‌دهند و بر اساس آزمون رفتاری تشخیص داده می‌شود. این اختلال عصبی با دیگر اختلالات عصبی مشابه می‌باشد، به این علت تشخیص بیماری اوتیسم کار پیچیده‌ای است. اگر بیماری در سنین کم و به موقع تشخیص داده شود، شدت بیماری و عوارض آن کم می‌شود. در سال‌های اخیر محققان با استفاده از بررسی سیگنال الکتروانسفالوگرافی (EEG) به تشخیص بیماری اوتیسم پرداخته‌اند. در تشخیص بیماری اوتیسم با استفاده از سیگنال EEG از الگوریتم‌های یادگیری ماشین استفاده شده که کاربر انسانی توانسته است با تجزیه و تحلیل ویژگی‌های استخراج شده با درصد دقت خوبی این بیماری را تشخیص دهد. در این پژوهش، الگوریتم‌های مورد استفاده در هر یک از مقالات، بررسی شده و نتایج به دست آمده از بررسی داده‌های متناسب با آنها مبنای ادامه کار برای پژوهش‌های آتی می‌باشد. در این پژوهش، ضمن بررسی روش‌های ارائه شده پیشین، مزایا و معایب روش‌ها بررسی می‌شوند. نتایج نشان می‌دهد که نقش روش‌های بکار گرفته شده به منظور پیش‌پردازش، استخراج و انتخاب ویژگی از روی تصاویر EEG و نوع طبقه‌بندها، عوامل موثر در دقت طبقه‌بندی می‌باشند. شبکه‌های عصبی کانولوشنی با توجه به ارائه بهترین نتایج دقت، بیشترین کاربرد را در مقایسه با سایر روش‌های مبتنی بر یادگیری داشته‌اند.

کلیدواژه‌ها

موضوعات

یادگیری ماشین

عنوان مقاله [English]

A review of machine learning algorithms to diagnose autism using the EEG signal

نویسندگان [English]

Zohreh Sharifi Mehrjard ¹
Hajar Momeni ²
Habib Adabi Ardekani ³

¹ Department of Electrical Engineering, Technical and Vocational University, Tehran, Iran.

² Department of Electrical Engineering, Ardakan University, Ardakan, Iran.

³ Department of Electrical Engineering, Yazd University, Yazd, Iran.

چکیده [English]

Autism is a neurological and developmental disorder in which individuals often show limited symptoms or behaviors and are diagnosed based on a behavioral test. This neurological disorder is similar to other neurological disorders; therefore, diagnosing autism is a complicated task. If the disease is diagnosed at an early age, the severity of the disease and its complications will be reduced. In recent years, researchers have used electroencephalography (EEG) to diagnose autism. In the diagnosis of autism using EEG signals, machine learning algorithms have been used, and the human user has been able to diagnose this disease with a good percentage of accuracy by analyzing the extracted features. In this paper, the algorithms used in each of the articles have been reviewed, and the results obtained from the corresponding data review are the basis for further research. While examining the previously presented methods, the advantages and disadvantages of the methods are examined. The results show that the role of the methods used for pre-processing, extracting and selecting features from EEG images and the type of classifiers are effective factors in classification accuracy. Convolutional neural networks have been the most popular compared to other learning-based methods due to their ability to provide the best accuracy results.

کلیدواژه‌ها [English]

Electroencephalography
Supervised learning
Autism
Deep learning
Machine learning

مراجع

[1] E. Grossi, G. Valbusa, and M. Buscema, “Detection of an autism EEG signature from only two EEG channels through features extraction and advanced machine learning analysis,” Clin. EEG Neurosci., vol. 52, no. 5, pp. 330-337, 2021, doi: 10.1177/1550059420982424.
[2] A. Tayyebi and B.C. Pijanowski, “Modeling multiple land use changes using ANN, CART and MARS: Comparing tradeoffs in goodness of fit and explanatory power of data mining tools,” Int. J. Appl. Earth Obs. Geoinform., vol. 28, pp. 102-116, 2014, doi: 10.1016/j.jag.2013.11.008.
[3] L.P. Coelho and W. Richert, Building machine learning systems with Python. Packt Publishing Ltd, 2015.
[4] J.S. Kumar and P. Bhuvaneswari, “Analysis of Electroencephalography (EEG) signals and its categorization–a study,” Proc. Eng., vol. 38, pp. 2525-2536, 2012, doi: 10.1016/j.proeng.2012.06.298.
[5] R. Radhamani, et al., “Computational analysis of cortical EEG biosignals and neural dynamics underlying an integrated mind-body relaxation technique,” Proc. Comput. Sci., vol. 171, pp. 341-349, 2020, doi: 10.1016/j.procs.2020.04.035.
[6] S.A. Samadi and R. Mcconkey, “The impact on Iranian mothers and fathers who have children with an autism spectrum disorder,” J. Intellect. Disabil. Res., vol. 58, no. 3, pp. 243-254, 2014, doi: 10.1111/jir.12005.
[7] H. Kantarjian and P.P. Yu, “Artificial intelligence, big data, and cancer,” JAMA Oncol., vol. 1, no. 5, pp. 573-574, 2015, doi:10.1001/jamaoncol.2015.1203.
[8] H. Veisi, H.R. Ghaedsharaf, and M. Ebrahimi, “Improving the Performance of Machine Learning Algorithms for Heart Disease Diagnosis by Optimizing Data and Features,” Soft Comput. J., vol. 8, no. 1, pp. 70-85, 2019, doi: 10.22052/8.1.70 [In Persian].
[9] A. Vasighi Zaker and S. Jalili, “Candidate disease gene prediction using One-Class classification,” Soft Comput. J., vol. 4, no. 1, pp. 74-83, 2015, dor: 20.1001.1.23223707.1394.4.1.60.8 [In Persian].
[10] S. Razzaghzadeh, P. Norouzi Kivi, and B. Panahi, “A hybrid algorithm based on Gossip architecture using SVM for task scheduling in cloud computing,” Soft Comput. J., vol. 9, no. 2, pp. 84-93, doi: 10.22052/scj.2021.242822.0 [In Persian].
[11] D. Dhall, R. Kaur, and M. Juneja, “Machine learning: a review of the algorithms and its applications,” in P. Singh, A. Kar, Y. Singh, M. Kolekar, and S. Tanwar, (eds) Proc. ICRIC 2019, Lecture Notes in Electrical Engineering, vol 597, Springer, Cham., 2020, doi: 10.1007/978-3-030-29407-6_5.
[12] S.B. Kotsiantis, I. Zaharakis, and P. Pintelas, “Supervised machine learning: A review of classification techniques,” in Proc. Conf. Emerg. Artif. Intell. Appl. Comput. Eng.: Real Word AI Syst. Appl. eHealth, HCI, Inf. Retr. Pervasive Technol., 2007, pp. 3-24.
[13] J.G. Carbonell, R.S. Michalski, and T.M. Mitchell, “An overview of machine learning,” Mach. Learn., vol. 1, pp. 3-23, 1983, doi: 10.1016/B978-0-08-051054-5.50005-4.
[14] X. Zhu and A.B. Goldberg, “Introduction to semi-supervised learning,” in Synthesis lectures on artificial intelligence and machine learning, Springer, Cham, 2009, doi: 10.1007/978-3-031-01548-9.
[15] X. Zhu, Semi-supervised learning literature survey, Computer Sciences TR 1530, University of Wisconsin, Madison, 2008.
[16] V. Nanduri and T.K. Das, “A Reinforcement Learning Model to Assess Market Power Under Auction-Based Energy Pricing,” IEEE Trans. Power Syst., vol. 22, no. 1, pp. 85-95, 2007, doi: 10.1109/TPWRS.2006.888977.
[17] R. Sutton and A.G. Barto, “Reinforcement learning,” J. Cogn. Neurosci., vol. 11, pp. 126-134, 1999.
[18] R. Polikar, “Ensemble learning,” in C. Zhang and Y. Ma, (eds) Ensemble Machine Learning, Springer, New York, NY, 2012, doi: 10.1007/978-1-4419-9326-7_1.
[19] D.W. Aha, D. Kibler, and M.K. Albert, “Instance-based learning algorithms,” Mach. Learn., vol. 6, pp. 37-66, 1991, doi: 10.1007/BF00153759.
[20] R. Vargas, A. Mosavi, and R. Ruiz, “Deep learning: a review,” Adv. Intell. Syst. Comput., vol. 5, no. 2, pp. 1-10, 2017.
[21] A.Chaddad, et al., “Can autism be diagnosed with artificial intelligence? A narrative review,” Diagnostics, vol. 11, no. 11, pp. 2032, 2021, doi: 10.3390/diagnostics11112032.
[22] G. Brihadiswaran, D. Haputhanthri, S. Gunathilaka, D. Meedeniya, and S. Jayarathna, “EEG-based processing and classification methodologies for autism spectrum disorder: A review,” J. Comput. Sci., vol. 15, no. 8, pp. 1161-1183, 2019, doi: 10.3844/jcssp.2019.1161.1183.
[23] Q. Mohi-ud-Din and A.K. Jayanthy, “Detection of Autism Spectrum Disorder from EEG signals using pre-trained deep convolution neural networks,” in 7th Int. Conf. Bio Signals Images Instrum. (ICBSII), Chennai, India, 2021, pp. 1-5, doi: 10.1109/ICBSII51839.2021.9445193.
[24] G.D. Varshini and R. Chinnaiyan, “Optimized machine learning classification approaches for prediction of autism spectrum disorder”, Ann. Autism. Dev. Disord., vol. 1, no. 1, pp. 1001, 2020.
[25] R. Djemal, K. AlSharabi, S. Ibrahim, and A. Alsuwailem, “EEG-based computer aided diagnosis of autism spectrum disorder using wavelet, entropy, and ANN,” BioMed Res. Int., vol. 2017, no. 1, p. 9816591, 2017, doi: 10.1155/2017/9816591.
[26] S. Ibrahim, R. Djemal, and A. Alsuwailem, “Electroencephalography (EEG) signal processing for epilepsy and autism spectrum disorder diagnosis,” Biocybern. Biomed. Eng., vol. 38, no. 1, pp. 16-26, 2018, doi: 10.1016/j.bbe.2017.08.006.
[27] S. Noachtar and J. Remi, “The role of EEG in epilepsy: a critical review,” Epilepsy Behav., vol. 15, no. 1, pp. 22-33, 2009, doi: 10.1016/j.yebeh.2009.02.035.
[28] S. Bhat, U.R. Acharya, H. Adeli, G.M. Bairy, and A. Adeli, “Automated diagnosis of autism: in search of a mathematical marker,” Rev. Neurosci., vol. 25, no. 6, pp. 851-861, 2014, doi: 10.1515/revneuro-2014-0036.
[29] Z.J. Peya, M.A.H. Akhand, J. Ferdous Srabonee, and N. Siddique, “EEG Based Autism Detection Using CNN Through Correlation Based Transformation of Channels' Data,” in IEEE Region 10 Symp. (TENSYMP), Dhaka, Bangladesh, 2020, pp. 1278-1281, doi: 10.1109/TENSYMP50017.2020.9230928..
[30] K. Hyde, et al., “Applications of supervised machine learning in autism spectrum disorder research: a review,” Rev. J. Autism Dev. Disord., vol. 6, pp. 128-146, 2019, doi: 10.1007/s40489-019-00158-x.
[31] H.A. Ardakani, M. Taghizadeh, and F. Shayegh, “Diagnosis of Autism Disorder Based on Deep Network Trained by Augmented EEG Signals,” Int. J. Neural Syst., vol. 32, no. 11, p. 2250046, 2022, doi: 10.1142/s0129065722500460.
[32] M.N.A. Tawhid, S. Siuly, H. Wang, F. Whittaker, K. Wang, and Y. Zhang, “A spectrogram image based intelligent technique for automatic detection of autism spectrum disorder from EEG,” PLoS One, vol. 16, no. 6, p. e0253094, 2021, doi: 10.1371/journal.pone.0253094.
[33] M. Baygin, et al., “Automated ASD detection using hybrid deep lightweight features extracted from EEG signals”, Comput. Biol. Med., vol. 134, p. 104548, 2021, doi: 10.1016/j.compbiomed.2021.104548.
[34] M. Ahmadlou, H. Adeli, and A. Adeli, “Fractality and a wavelet-chaos-neural network methodology for EEG-based diagnosis of autistic spectrum disorder,” J. Clin. Neurophysiol., vol. 27, no. 5, pp. 328-333, 2010, doi: 10.1097/WNP.0b013e3181f40dc8.
[35] W. Bosl, A. Tierney, H. Tager-Flusberg, and C. Nelson, “EEG complexity as a biomarker for autism spectrum disorder risk,” BMC Med., vol. 9, p. 18, 2011, doi: 10.1186/1741-7015-9-18.
[36] S. Boeve, “Can machine learning capture differences in EEG of infants at elevated likelihood and typical likelihood of Autism?”, Thesis for Master of Science, Theoretical and Experimental Psychology, Diss. Ghent University, 2022.
[37] Z.J. Peya, M.H.A. Akhand, J.F. Srabonee, and N. Siddique, “Autism Detection from 2D Transformed EEG Signal using Convolutional Neural Network,” J. Comput. Sci., vol. 18, no. 8, pp. 695-704, 2022, doi: 10.3844/jcssp.2022.695.704.
[38] K.M. Zubair, B.S. Mashkur, and N.M. Nor, “Early Detection on Autistic Children by Using EEG Signals,” Int. J. Percept. Cogn. Comput., vol. 8, no. 1, pp. 59-64, 2022.
[39] G.M. Kresnia and A.A. Parikesit, “Use of Artificial Intelligence in the Diagnostics of Autism Spectrum Disorder,” Cermin Dunia Kedokteran, vol. 49, no. 6, pp. 341-344, 2022, doi: 10.55175/cdk.v49i6.246
[40] B. Ari, N. Sobahi, O.F. Alcin, A. Sengur, and U.R. Acharya, “Accurate detection of autism using Douglas-Peucker algorithm, sparse coding based feature mapping and convolutional neural network techniques with EEG signals”, Comput. Biol. Med., vol. 143, p. 105311, 2022, doi: 10.1016/j.compbiomed.2022.105311.
[41] M. Liao, H. Duan, and G. Wang, “Application of machine learning techniques to detect the children with autism spectrum disorder,” J. Healthc. Eng., vol. 2022, no. 1, p. 9340027, 2022, doi: 10.1155/2022/9340027.
[42] S. Alhassan, A. Soudani, and M. Almusallam, “Energy-efficient EEG-based scheme for autism spectrum disorder detection using wearable sensors,” Sensors, vol. 23, no. 4, p. 2228, 2023, doi: 10.3390/s23042228.
[43] Q.M. Din and A.K. Jayanthy, “Wavelet Scattering Transform and Deep Learning Networks Based Autism Spectrum Disorder Identification Using EEG Signals,” Traitement du Signal, vol. 39, no. 6, p. 2069, 2022, doi: 10.18280/ts.390619
[44] S. Das, et al., “Machine learning approaches for electroencephalography and magnetoencephalography analyses in autism spectrum disorder: A systematic review,” Prog. Neuro-Psychopharmacol. Biol. Psychiatry, vol. 123, p. 110705, 2023, doi: 10.1016/j.pnpbp.2022.110705.
[45] D. Abdolzadegan, M.H. Moattar, and M. Ghoshuni, “A robust method for early diagnosis of autism spectrum disorder from EEG signals based on feature selection and DBSCAN method,” Biocybern. Biomed. Eng., vol. 40, no. 1, pp. 482-493, 2020, doi: 10.1016/j.bbe.2020.01.008.