نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد، گروه مهندسی پزشکی، دانشگاه بین‌المللی امام رضا (ع)، مشهد، ایران / مرکز تحقیقات فناوری‌های زیستی و سلامت، دانشگاه بین‌المللی امام رضا (ع)، مشهد، ایران

2 استادیار، گروه مهندسی پزشکی، دانشگاه بین‌المللی امام رضا (ع)، مشهد، ایران / مرکز تحقیقات فناوری‌های زیستی و سلامت، دانشگاه بین‌المللی امام رضا (ع)، مشهد، ایران

10.22041/ijbme.2022.552263.1766

چکیده

اختلالات اضطرابی از شایع­ترین و ناتوان‌کننده­ترین اختلالات روانی در سراسر جهان به شمار می­آیند. از طرف دیگر از سال 2019 با شیوع کووید-19 اضطراب بین مردم و به خصوص کادر درمان افزایش پیدا کرده است. در حال حاضر اضطراب (زمانی که علائم کافی و شدید باشد) با استفاده از پرسش‌نامه و توسط افراد متخصص تشخیص داده می­شود. برای رفع این کاستی، اخیرا توجه محققان به استفاده از سیگنال­های مغزی جلب شده است. به همین منظور مطالعه‌ی حاضر با هدف تشخیص اضطراب با استفاده از سیگنال مغزی انجام شده است. نوآوری این مطالعه استفاده از نقشه‌ی آشوب‌گون چبیشف برای اولین بار در تحلیل سیگنال‌های بیولوژیکی است. در این مطالعه از پایگاه داده‌ی DASPS استفاده شده که شامل الکتروانسفالوگرام 14 کاناله از 23 نفر (10 مرد و 13 زن با میانگین سنی 30 سال) است. از نمرات آزمون خودارزیابی آدمک برای تقسیم اضطراب به دو و چهار سطح استفاده شده است. ابتدا داده­ها نرمال‌سازی شده و سپس نقشه‌ی آشوب‌گون بازسازی و به 128 نوار تقسیم شده است. چگالی نقاط در هر یک از نوارها محاسبه شده است. دو شاخص حداکثر چگالی و نمونه‌ی مربوط به آن به عنوان ویژگی در نظر گرفته شده است. در نهایت ویژگی‌ها به 5 روش شامل ویژگی 1 تمام کانال­ها، نگاشت ویژگی 1 تمام کانال­ها با استفاده از تجزیه و تحلیل اجزای اصلی (PCA)، ویژگی 2 تمام کانال­ها، نگاشت ویژگی 2 تمام کانال­ها با استفاده از PCA و هر ویژگی-هر کانال به طور جداگانه به دو طبقه­بند ماشین بردار پشتیبان (SVM) و K-نزدیک‌ترین همسایه (K-NN) اعمال شده است. نتایج حاکی از حداکثر صحت 75/93% برای تشخیص دو سطح اضطراب و 15/96% برای تشخیص چهار سطح اضطراب است. علاوه بر این، عمل‌کرد K-NN از SVM بهتر بوده است. در نتیجه می­توان الگوریتم پیشنهادی را به عنوان یک رویکرد مناسب برای تشخیص اضطراب معرفی کرد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

A New EEG Processing Approach using the Chebyshev Chaotic Map: Application in Anxiety Classification

نویسندگان [English]

  • Faezeh Daneshmand-Bahman 1
  • Ateke Goshvarpour 2

1 M.Sc. Student, Department of Biomedical Engineering, Imam Reza International University, Mashhad, Razavi Khorasan, Iran / Health Technology Research Center, Imam Reza International University, Mashhad, Iran

2 Assistant Professor, Department of Biomedical Engineering, Imam Reza International University, Mashhad, Razavi Khorasan, Iran / Health Technology Research Center, Imam Reza International University, Mashhad, Iran

چکیده [English]

Anxiety disorders are one of the most common and debilitating mental disorders worldwide. On the other hand, since 2019, with the outbreak of Covid-19, anxiety has increased among people, especially the medical staff. Currently, anxiety is diagnosed (when the symptoms are severe enough) using a questionnaire by a specialist. To resolve this shortcoming, researchers have recently paid attention to the use of brain signals. Consequently, the present study aimed to diagnose anxiety using brain signals. The novelty of this study is the use of the Chebyshev chaotic map for the first time in biological signal analysis. It used the DASPS database, which includes a 14-channel electroencephalogram (EEG) of 23 people (10 men and 13 women, with a mean age of 30 years). The self-assessment manikin scores were used to divide anxiety into two and four levels. First, the data were normalized. Then, the chaotic map was reconstructed and divided into 128 strips. The density of points in each of the strips was calculated. Two indicators were considered as features, (1) maximum density and (2) its corresponding sample. Finally, features were applied to Support Vector Machines (SVM) and k-Nearest Neighbors (K-NN) in 5 ways, (1) feature 1 of all channels, (2) feature1 mapping of all channels using principal component analysis (PCA), (3) feature 2 of all channels, (4) feature 2 mapping of all channels using PCA and (5) each feature - each channel separately. The results show a maximum accuracy of 93.75% for diagnosing two levels of anxiety and 96.15% for diagnosing four levels of anxiety. In addition, K-NN outperformed SVM. Accordingly, the proposed algorithm can be introduced as a suitable approach for diagnosing anxiety.

کلیدواژه‌ها [English]

  • Chebyshev Chaotic Map
  • Anxiety
  • Principal Component Analysis
  • Electroencephalogram
  • Classification
  1. W. Murrough, S. Yaqubi, S. Sayed, & D. S. Charney, “Emerging drugs for the treatment of anxiety” Expert opinion on emerging drugs, 20(3), 393-406, September, 2015.
  2. Cartwright-Hatton, K. McNicol & E. Doubleday, “Anxiety in a neglected population: Prevalence of anxiety disorders in pre-adolescent children” Clinical psychology review, 26(7), 817-833, 2006.
  3. Bandelow, S. Michaelis & D. Wedekind, “Treatment of anxiety disorders” Dialogues in clinical neuroscience, Vol. 19, No. 2, 2017.
  4. Millet, J. Longworth & J. Arcelus, “Prevalence of anxiety symptoms and disorders in the transgender population: A systematic review of the literature” International Journal of Transgenderism, 18(1), 27-38, 2017.
  5. Bandelow & S. Michaelis, “Epidemiology of anxiety disorders in the 21st century” Dialogues in clinical neuroscience, Vol. 17, No. 3, 327-335, 2022.
  6. S. McGinnis, E. W. McGinnis, J. Hruschak, N. L. Lopez-Duran, K. Fitzgerald, K. L. Rosenblum & M. Muzik, “Wearable sensors and machine learning diagnose anxiety and depression in young children” In 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI) (pp. 410-413). IEEE, March, 2018.
  7. Özdin & Ş. Bayrak Özdin, “Levels and predictors of anxiety, depression and health anxiety during COVID-19 pandemic in Turkish society: The importance of gender” International Journal of Social Psychiatry, 66(5), 504-511, 2020.
  8. Beesdo, S. Knappe & D. S. Pine, “Anxiety and anxiety disorders in children and adolescents: developmental issues and implications for DSM-V” Psychiatric Clinics, 32(3), 483-524, 2009.
  9. K. Hofmeijer-Sevink, N. M. Batelaan, H. J. van Megen, B. W. Penninx, D. C. Cath, M. A. van den Hout & A. J. van Balkom, “Clinical relevance of comorbidity in anxiety disorders: a report from the Netherlands Study of Depression and Anxiety (NESDA)” Journal of affective disorders, 137(1-3), 106-112, 2012.
  10. E. McKnight, S. S.Monfort, T. B. Kashdan, D. V. Blalock & J. M. Calton, “Anxiety symptoms and functional impairment: A systematic review of the correlation between the two measures” Clinical psychology review, 45, 115-130, 2016.
  11. Daneshmand-Bahman & A. Goshvarpour, “Classification of EEG Signals in Two Levels of Normal and Anxious Using Nonlinear Features” Journal of Cognitive Psychology, 9 (3):54-69, 2021 [Persian].
  12. Baghdadi, Y. Aribi, R. Fourati, N. Halouani, P. Siarry & A. M. Alimi (2019), “DASPS: A Database for Anxious States based on a Psychological Stimulation” Computer Vision and Pattern Recognition (cs.CV), arXiv preprint arXiv:1901.02942.
  13. Xie, B. Yang, X. Lu, M. Zheng, C. Fan, X. Bi & Y. Li, “Anxiety and depression diagnosis method based on brain networks and convolutional neural networks” In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 1503-1506). IEEE, July 2020.
  14. Giannakakis, D. Grigoriadis & M. Tsiknakis, “Detection of stress/anxiety state from EEG features during video watching.” In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 6034-6037). IEEE, August, 2015.
  15. A. Klados, N. Pandria, A. Athanasiou & P. D. Bamidis, “An automatic EEG based system for the recognition of math anxiety.” In 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS) (pp. 409-412). IEEE, June, 2017.
  16. Friedman, J. Claassen & L. J. Hirsch, “Continuous electroencephalogram monitoring in the intensive care unit.” Anesthesia & Analgesia, 109(2), 506-523, 2009.
  17. Craik, Y. He & J. L. Contreras-Vidal, “Deep learning for electroencephalogram (EEG) classification tasks: a review.” Journal of neural engineering, 16(3), 031001, 2019.
  18. Jijun, Z. Peng, X. Ran & D. Lei, The portable P300 dialing system based on tablet and Emotiv Epoc headset. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 566-569). IEEE, August, 2015.
  19. Duvinage, T. Castermans, M. Petieau, T. Hoellinger, G. Cheron & T. Dutoit, “Performance of the Emotiv Epoc headset for P300-based applications.” Biomedical engineering online, 12(1), 1-15, 2013.
  20. M. Bynion & M. T. Feldner, “Self-assessment manikin.” Encyclopedia of personality and individual differences, 4654-4656, 2020.
  21. K. Singh, K. Verma & A. S. Thoke, “Investigations on impact of feature normalization techniques on classifier's performance in breast tumor classification.” International Journal of Computer Applications, 116(19), 2015.
  22. Wang, G. Xu & G. Xu, “A provably secure anonymous biometrics-based authentication scheme for wireless sensor networks using chaotic map.” IEEE Access, 7, 101596-101608 (2019).
  23. Anuragi, D. S. Sisodia & R. B. Pachori, “Epileptic-seizure classification using phase-space representation of FBSE-EWT based EEG sub-band signals and ensemble learners.” Biomedical Signal Processing and Control, 71, 103138 (2022).
  24. Darjani & H. Omranpour, “Phase space elliptic density feature for epileptic EEG signals classification using metaheuristic optimization method.” Knowledge-Based Systems, 205, 106276 (2020).
  25. Z. Soroush, K. Maghooli, S. K. Setarehdan & A. M. Nasrabadi, “Emotion recognition using EEG phase space dynamics and Poincare intersections.” Biomedical Signal Processing and Control, 59, 101918 (2020).
  26. I. Abdelfatah, N. M. Abdal-Ghafour & M. E. Nasr, “Secure VANET Authentication Protocol (SVAP) Using Chebyshev Chaotic Maps for Emergency Conditions.” IEEE Access, 10, 1096-1115(2021).
  27. Wang, D. Luan & X. Bao, “Cryptanalysis of an image encryption algorithm using Chebyshev generator.” Digital Signal Processing, 25, 244-247(2014).
  28. Shakiba, “Generating dynamical S-boxes using 1D Chebyshev chaotic maps.” Journal of Computing and Security, 7(1), 1-17, 2020.
  29. Gan, Z. Li, J. Li, X. Wang & Z. Cheng, “Compressive sensing using chaotic sequence based on Chebyshev map.” Nonlinear Dynamics, 78(4), 2429-2438 (2014).
  30. Zhang, H. Wang & Y. Gao, “C2MP: Chebyshev chaotic map-based authentication protocol for RFID applications.” Personal and Ubiquitous Computing, 19(7), 1053-1061(2015).
  31. M. S. Hasan & A. M. Abdulazeez, “A review of principal component analysis algorithm for dimensionality reduction.” Journal of Soft Computing and Data Mining, 2(1), 20-30, 2021.
  32. R. Naik, “Advances in principal component analysis: research and development. Springer.” Springer, 2017.
  33. Liu, B. Song, S. Zhang & X. Liu, “A novel principal component analysis method for the reconstruction of leaf reflectance spectra and retrieval of leaf biochemical contents.” Remote Sensing, 9(11), 1113, 2017.
  34. Yadav & S. Shukla, “Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification.” In 2016 IEEE 6th International conference on advanced computing (IACC) (pp. 78-83). IEEE, February, 2016.
  35. Zeng, “On the confusion matrix in credit scoring and its analytical properties.” Communications in Statistics-Theory and Methods, 49(9), 2080-2093, 2020.
  36. Y. Hu, M. W. Huang, S. W. Ke & C. F Tsai, “The distance function effect on k-nearest neighbor classification for medical datasets.” SpringerPlus, 5(1), 1-9, 2016.
  37. A. Abu Alfeilat, A. B. Hassanat, O. Lasassmeh, A. S. Tarawneh, M. B. Alhasanat, H. S. Eyal Salman & V. S. Prasath, “Effects of distance measure choice on k-nearest neighbor classifier performance: a review.” Big data, 7(4), 221-248 (2019).
  38. Jain, S. Narayan, P. Balaji, A. Bhowmick & R. K. Muthu, “Speech emotion recognition using support vector machine.” arXiv preprint arXiv:2002.07590(2020).
  39. Huang, N. Cai, P. P. Pacheco, S. Narrandes, Y. Wang & W. Xu, “Applications of support vector machine (SVM) learning in cancer genomics.” Cancer genomics & proteomics, 15(1), 41-51(2018).
  40. Ramedani, M. Omid, A. Keyhani, S. Shamshirband & B. Khoshnevisan, “Potential of radial basis function based support vector regression for global solar radiation prediction.” Renewable and Sustainable Energy Reviews, 39, 1005-1011(2014).
  41. Massullo, G. A. Carbone, B. Farina, A. Panno, C. Capriotti, M. Giacchini, ... & C. Imperatori, “Dysregulated brain salience within a triple network model in high trait anxiety individuals: A pilot EEG functional connectivity study.” International Journal of Psychophysiology, 157, 61-69 (2020).
  42. V. Bocharov, G. G. Knyazev, A. N. Savostyanov, A. E. Saprygin, E. A. Proshina & S. S. Tamozhnikov, “Relationship of Depression, Anxiety, and Rumination Scores with EEG Connectivity of Resting State Networks.” Human Physiology, 47(2), 123-127 (2021).