نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 کارشناسی‌ارشد، دانشکده‌ی مهندسی برق، واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران

2 استادیار، دانشکده‌ی مهندسی برق، واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران

3 دانشیار، مرکز تحقیقاتی ریزشبکه‌های هوشمند، واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران

10.22041/ijbme.2020.119841.1551

چکیده

اثر اصلی، عمده و کوتاه‌مدت مصرف الکل روی سیستم اعصاب مرکزی است. مصرف مشروبات الکلی باعث ایجاد ناتوانی در مغز شده به طوری که مصرف زیاد آن باعث فلج شدن فعالیت­های مغزی، دستگاه تنفس و در نتیجه مرگ می‌شود. در این مقاله به منظور تشخیص مصرف الکل، سیگنال الکتروانسفالوگرام (EEG) 20 فرد شرکت کننده شامل 10 فرد الکلی و 10 فرد کنترل در 64 کانال مورد بررسی قرار گرفته است. به منظور تحلیل سیگنال EEG، ویژگی­های فرکانسی و غیرفرکانسی شامل طیف توان زیرباندها، آنتروپی جایگشتی، آنتروپی تقریبی، بعد فراکتال کتز و پتروشن استخراج شده است. برای بررسی تفاوت معنادار بین دو گروه الکل و کنترل از تحلیل آماری و از شاخص دﯾﻮﯾﺲ-ﺑﻮﻟﺪﯾﻦ (DB) برای انتخاب بهترین کانال جهت ایجاد تفکیک بین سیگنال EEG افراد الکلی و کنترل استفاده شده است. نتایج به دست آمده نشان می­دهد که در بین ویژگی­های فرکانسی، توان فرکانسی دومین زیرباند پایین آلفادر افراد الکلی کاهش یافته و با توجه به شاخص DB، کانال CP3 بهترین تفکیک‌پذیری را بین گروه الکل و کنترل داشته است. هم‌چنین در بین ویژگی­های غیرفرکانسی، بعد فراکتال کتز در افراد گروه کنترل افزایش یافته و کانال FP2 بهترین تفکیک‌پذیری را داشته است. در ادامه با استفاده از طبقه­بند k-نزدیک‌ترین همسایه (KNN) با ویژگی­های توان فرکانسی دومین زیرباند پایین آلفا و بعد فراکتال کتز به ترتیب دقت‌های 71% و 93% به دست آمده است. بر اساس نتایج به دست آمده نشان داده شده که بهترین ویژگی‌ تفکیک کننده‌ی دو گروه الکل و کنترل، بعد فراکتال کتز و بهترین کانال FP2 است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Classification of Alcoholic and Non-Alcoholic Individuals based on Frequency and Non-Frequency Features of Electroencephalogram Signal

نویسندگان [English]

  • Maryam Dorvashi 1
  • Neda Behzadfar 2
  • Ghazanfar Shahgholian 3

1 M.Sc., Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran

2 Assistant Professor, Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran

3 Associate Professor, Smart Microgrid Research Center, Najafabad Branch, Islamic Azad University, Najafabad, Iran

چکیده [English]

Consumption of alcohol contributes to disorders in brain. In this study, in order to detect the consumption of alcohol, electroencephalogram (EEG) signal of 20 participants (10 alcoholic and 10 control subjects) recorded by 64 channels was investigated. Frequency and non-frequency features of EEG signal including power spectrum of signal, permutation entropy, approximate entropy, Katz fractal dimension and Petrosion fractal dimension were extracted to analyses the EEG signal. Statistical analysis was used to investigate the significant differences between the alcohol and control groups. The Davis-Bouldin (DB) criterion was used to select the best channel distinguishing between the alcoholic and non-alcoholic EEG signal. Results showed that between frequency features, power of lower2 alpha frequency decreased in alcoholic individuals and regarding the DB criterion, the CP3 channel (DB=1.7638) showed the best discr­imi­na­tion between the alcohol and control groups. Also, among the non-frequency features, the Katz fractal dimension increased in the control group and FP2 channel (DB = 0.862) had the best discrimination. Eventually, power of Lower2-alpha frequency band and Katz fractal dimension fed into the nearest neighbor classifier (KNN), 71% and 93% accuracy were achieved, respectively. According to the results, it can be concluded that the best feature and channel discriminating between alcohol and control groups is the Katz fractal dimension and FP2 channel.

کلیدواژه‌ها [English]

  • Electroencephalogram signal
  • statistical analysis
  • Classification
  • Data Analysis
[1]   خدابخشی م.ر.، دوائی‌مرکزی ا.ح.، "تحلیل دینامیکی و دو شاخگی‌‌های مدل تودة نورونی جانسن-ریت و کاربرد آن در توصیف حملات صرعی"،  فصل نامه علمی پژوهشی مهندسی پزشکی زیستی، س.: 11، ش.: 1، ص.: 81-63، بهار 1396.
[2]   علی‌پور صفار ا.، شمسی م.، "ارزیابی بخش‌بندی توأم با تصحیح میدان بایاس تصاویر MR مغز انسان توسط روش‌های تنظیم سطح و مؤلفه‌های ذاتی ضرب‌شونده"، مجله پردازش سیگنال پیشرفته، س.: 3، ش.: 1، ص.: 75-67، تابستان 1398.
[3]   R. Willoughby, M. Zambotti, F. C. Baker, I. M. Colrain, "Evoked K-complexes and altered inte‌rac‌t‌i‌on between the central and autonomic nervous sys‌t‌ems during sleep in alcohol use disorder", Alcohol, Vol. 84, pp. 1-7, May 2020.
[4]   P. Wang, J. Hu, "A hybrid model for EEG-based gender recognition", Cogn Neurodyn, Vol. 13, pp. 541–554, 2019.
[5]   Anuragi, D. S. S. Sisodia, "Empirical wavelet transform based automated alcoholism detecting using EEG signal features", Biomedical Signal Processing and Control, Vol. 57, pp. 1-14, March 2020.
[6]   P. Mohanty, P. Siddharth, K. B. Swain, R. K. Patnaik, "Driver assistant for the detection of drow‌s‌iness and alcohol effect", Proceeding of the IEEE/ICSSS, pp. 279-283, Chennai, India, May 2017.
[7]   Hickie, B. Whitwell, "Alcohol and the teenage brain: safest to keep them apart", Brain and Mind Research Institute, University of Sydney, 2009.
[8]   M. Berglund, "Cerebral blood flow in chronic alcoholics", Alcoholism: Clinical and Experiment‌a‌l Research, Vol. 5, No. 2, pp. 295-303, 1981.
[9]   M. Oishi, Y. Mochizuki, E. Shikata, "Corpus callosum atrophy and cerebral blood flow in chronic alcoholics", Journal of the Neurological Sciences, Vol. 162, No. 1, pp. 51-55, Jan. 1999.
[10]قدسی س.، محمدزاده ه.، آقاجان ح.، "تحلیل اتصالات مغزی برای پیش بینی وقوع حملات تشنج صرعی با استفاده از سیگنال‌های الکتروانسفالوگرافی"، فصل نامه علمی پژوهشی مهندسی پزشکی زیستی، س.: 13، ش.: 3، ص.: 360-351، پاییز 1398.
[11]M. Gorgoni, A. D'Atri, S. Scarpelli, F. Reda, L. De Gennaro, "Sleep electroencephalography and brain mat-uration: developmental trajectories and the rela‌t‌i‌on with cognitive functioning", Sleep Medicine, Vol. 66, pp. 33-50, Feb. 2020.
[12]G. M. Opie, L. A. Otieno, M. Pourmajidian, J. G. Semmler, S. K. Sidhu , "Older adults differentially modulate transcranial magnetic stimulation–electroencephalography measures of cortical inhib‌iti‌on during maximal single-joint exercise", Neuro‌sci‌ence, Vol. 425, pp. 181-193, Jan. 2020.
[13]زاهدی حقیقی س.س.، سخایی س.م.، دلیری م.ر.، "تشخیص حالت‌های احساسی مبتنی بر EEG با استفاده از شبکه یادگیری عمیق"، فصل نامه علمی پژوهشی مهندسی پزشکی زیستی، س.: 13، ش.: 2، ص.: 160-151، تابستان 1398.
[14]W. Al-salman, Y. Li, P. Wen, M. Diykh, "An efficient approach for EEG sleep spindles detection based on fractal dimension coupled with time frequency image", Biomedical Signal Processing and Control, Vol. 41, pp. 210-221, March 2018.
[15]P. Zarjam, J. Epps, F. Chen, N. H. Lovell, "Classification of working memory load using wavelet complexity features of EEG signals", Proceeding of the ICONIP, pp. 692-699, Berlin, Heidelberg, 2012.
[16]F. Riaz, S. Khadim, R. Rauf, M. Ahmad, S. Jabbar, J. Chaudhry, "A validated fuzzy logic inspire‌d driver distraction evaluation system for road safety using artif‌ici‌al human driver emotion", Computer Networks, Vol. 143, pp. 62-73, Oct. 2018.
[17]S. J. Brislin, J. E. Hardee, M. E. Martz, L. M. Co‌p‌e, M. M. Heitzeg,, "Alcohol expectancies med‌iate the association between the neural response to e‌motional words and acohol consump‌i‌n", Drug and Alcohol Dependence, Vol. 2091, Article 1078‌8‌‌2, April 2020.
[18]E. Malar, M. Gauthaam, M. Kalaikamal, S. Muthukrishnan, "The EEG based driver safety system", International Journal of Engineering and Technology, Vol. 4, No. 3, pp. 340-343, June 2012.
[19]R. F. Kaplan, B. C. Glueck, M. N. Hesselbrock,  H. R. Jr, "Power and coherence analysis of the EEG in hospitalized alcoholics and nonalcoholic controls", Journal of Studies on Alcohol, Vol. 46, No. 2, pp. 122-127, Mar. 1985.
[20]H. Wang, F. He, J. Du, C. Liu, H. Zhao, "Effect of alcohol-dependent EEG on the traffic signal recognition", Proceeding of the IEEE/ITAB, pp. 395-396, Shenzhen, China, May 2008.
[21]W. Di, C. Zhihua, F. Ruifang, L. Guangyu, L. Tian, "Notice of retraction: Study on human brain after consuming alcohol based on EEG signal", Proce‌edi‌ng of the IEEE/ICCSIT, Vol. 5, pp. 406-409, Chengdu, China, July 2010.
[22]R. Cao, H. Deng, Z. Wu, G. Liu, H. Guo, J. Xiang, "Decreased synchronization in alcoholics using EEG", IRBM, Vol. 38, No. 2, pp. 63-70, April 2017.
[23]M. A. Shooshtari, S. K. Setarehdan, "Selection of optimal EEG channels for classification of signals correlated with alcohol abusers", Proceeding of the IEEE/ICOSP, pp. 1-4, Beijing, China, Oct. 2010.
[24]V. Bajaj, Y. Guo, A. Sengur, S. Siuly, and O. F. Alcin, "A hybrid method based on time–frequency images for classification of alcohol and control EEG signals," Neural Computing and Applications, vol. 28, no. 12, pp. 3717-3723, 2017. 
[25]Anuragi and D. S. S. Sisodia, "Empirical wavelet transform based automated alcoholism detecting using EEG signal features," Biomedical Signal Processing and Control, vol. 57, p. 101777, 2020.
[26]G. Gopan, N. Sinha, D. Babu, "Hybrid features based classification of alcoholic and non-alcoholic EEG", Proceeding of the IEEE/CONECCT, pp. 1-6, Bangalore, India, July 2015.
[27]H. Begleiter, L. Ingber, "EEG database data set" Neurodynamics Laboratory, State University of New York Health Center Brooklyn, New York 1993:UCI.
[28]J. G. Snodgrass, M. Vanderwart, "A standardized set of 260 pictures: norms for name agreement, image agreement, familiarity, and visual comple‌xity", Journal of Experimental Psychology: Human Learning and Memory, Vol. 6, No. 2, pp. 174-215, 1980.
[29]N. Behzadfar, S. M. P. Firoozabadi, K. Badie, "Low-complexity discriminative feature selection from eeg before and after short-term memory task", Clinical EEG and Neuroscience, Vol. 47, No. 4, pp. 291-297, 2016.
[30]Kraus, C. Cadle, S. Simon-Dack, "EEG alpha acti‌vity is moderated by the serial order effect duri‌ng divergent thinking", Biological Psychology, Vol. 145, pp. 84-95, July 2019.
[31]P. Zarjam, J. Epps, F. Chen, N. H. Lovell, "Classification of working memory load using wavelet complexity features of EEG signals", International Conference on Neural Information Processing, 2012: Springer, pp. 692-699.
[32]S. M. Pincus, "Approximate entropy as a measure of system complexity", Proceedings of the National Academy of Sciences, vol. 88, no. 6, pp. 2297-2301, 1991.
[33]W. Klimesch, "EEG alpha and theta oscillations reflect cognitive and memory performance: A review and analysis", Brain research Reviews, Vol. 29, No. 2-3, pp. 169-195, April 1999.
[34]N. Druesne-Pecollo, B. Tehard, Y. Mallet, M. Gerber, T. Norat, S. Hercberg, P. Latino-Martel, "Alc‌o‌hol and genetic polymorphisms: Effect on risk of alcohol-related cancer", The lancet onco‌logy, Vol. 10, No. 2, pp. 173-180, 2009.
[35]R. Shalbaf, H. Behnam, H. J. Moghadam, "Moni‌tor‌ing depth of anesthesia using combination of EEG measure and hemodynamic variables", Cogn‌itive Neurodynamics, Vol. 9, No. 1, pp. 41-51, 2015.
[36]H. Siamaknejad, C. K. Loo, W. S. Liew, "Fractal dimension methods to determine optimum EEG electrode placement for concentration estimation," Neural Computing and Applications, Vol. 31, No. 3,pp 945–953, March 2019.
[37]G. Rodriguez-Bermudez, P. J. Garcia-Laencina, "Analysis of EEG signals using nonlinear dynam‌ics and chaos: A review," Applied Mathematics and Information Sciences, Vol. 9, no. 5, pp. 2309-2321, 2015.
[38]Martins, A. Duarte, J. Dantas, J. C. Principe, "A new clustering separation measure based on negentropy", Journal of Control, Automation and Electrical Systems, Vol. 26, pp. 28–45, 2015.
[39]V. Konok, A. Marx, T. Faragó, "Attachment styles in dogs and their relationship with separation-related disorder– A questionnaire based clust‌eri‌n‌g‌", Applied Animal Behaviour Science, Vol. 213, pp. 81-90, April 2019.
[40]L. Davies, D. W. Bouldin, "A cluster separation measure", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. PAMI-1, No. 2, pp. 224-227, April 1979.
[41]Yazdani, S. K. Setarehdan, "Classification of EEG signals correlated with alcohol abusers", Proceeding of the IEEE/ISSPA,pp. 1-4, Sharjah, United Arab,Feb. 2007.
[42]W. Mumtaz, P. L. Vuong, L. Xia, A. S. Malik, R. B. A. Rashid, "An EEG-based machine learning method to screen alcohol use disorder",Cogn Neurodyn. Vol. 11, No. 2, pp. 161–171, April 2017.
[43]H. F. Moselhy, G. Georgiou, and A. Kahn, "Frontal lobe changes in alcoholism: a review of the literature", Alcohol and alcoholism, vol. 36, no. 5, pp. 357-368, 2001.
[44]K. Mittal, G. Aggarwal, P. Mahajan, "Performance study of K-nearest neighbor classifier and K-means clustering for predicting the diagnostic accuracy", International Journal of Information Technology, Vol. 11, No. 3, pp. 535-540, 2019.
[45]S. Bavkar, B. Iyer, S. Deosarkar, "Detection of alcoholism: an EEG hybrid features and ensemble subspace K-NN based approach", Distributed Computing and Internet Technology, Vol. 11319, pp. 161-168, 2019.
[46]W. Cherif, "Optimization of K-NN algorithm by clustering and reliability coefficients: application to breast-cancer diagnosis", Procedia Computer Science, Vol. 127, pp. 293-299, 2018.
[47]Yazdani and S. K. Setarehdan, "Classification of EEG signals correlated with alcohol abusers", Proceeding of the IEEE/ISSPA, pp. 1-4, Sharjah, United Arab Emirates, 2007.
[48]X. Li, Z. Deng, and J. Zhang, "Function of EEG temporal complexity analysis in neural activities measurement", Advances in Neural Networks, Vol. 5551, pp. 209-218, 2009.
[49]Dousset, H. Kajosch, A. Ingels, E. Schroder, C. Kornreich, S. Campanella, "Preventing Relapse in Alcohol Disorder with EEG-neurofeedback as a neuromodulation technique: A review and new insights regarding its application", Addictive Beha‌vi‌ors, Vol. 106, pp. 1-6, Article 106391, 2020.