Analysis of The Electrodermal Activity Signals for Different Stressors Using Empirical Mode Decomposition

Year 2020, Volume: 8 Issue: 2, 407 - 414, 26.05.2020

Ramis İleri , Fatma Latifoglu

https://doi.org/10.21541/apjes.601235

Cited By: 1

Abstract

In this study, Electrodermal Activity (EDA) signals were analyzed to evaluate the changes between physical stress, cognitive stress, and emotional stress. For this purpose, energy and variance properties of the EDA signals in the time domain were analyzed for each case and as short-time frames. In addition, the EDA signals were decomposed using the Empirical Mode Decomposition (EMD) method, and the sub-band signals were analyzed for each case. Further, the Short Time Fourier Transform (STFT) method was used to analyze the in the time-frequency domain of these signals. Also, according to obtained features, EDA signals were classified to determine the stages. Simulated results show that, the EDA and subband EDA signals were found to be significantly different in terms of cognitive stress (p<0.05). Also, the features obtained from the EMD subbands were classified using Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Multi-Layer Perceptron (MLP) methods for different situations and classifier performances were compared. In the classification of cognitive stress period and first rest period, the best classification performance was achieved as 97.36 %, 84,21 %, and 81,57 % using MLP, SVM and KNN classifier respectively compared to other situations.

Keywords

Electrodermal Activity (EDA), Empirical Mode Decomposition (EMD), Short Time Fourier Transform (STFT), Artifical Neural Network (ANN)

Analysis of The Electrodermal Activity Signals for Different Stressors Using Empirical Mode Decomposition

Abstract

Bu çalışmada, fiziksel stres, bilişsel stres ve duygusal stres arasındaki değişiklikleri değerlendirmek için Elektrodermal Aktivite (EDA) sinyalleri analiz edilmiştir. Bu amaçla, EDA sinyallerinin zaman ekseninde enerji ve varyans özellikleri, her bir durum için analiz edilmiştir. Ek olarak, EDA sinyalleri, Ampirik Kip Ayrışımı (AKA) yöntemi kullanılarak alt bandlara ayrıştırımış ve her bir stres durumu için alt bant sinyalleri analiz edilmiştir. Kısa Zamanlı Fourier Dönüşümü (STFT) yöntemi, bu sinyallerin zaman-frekans alanında analiz etmek için kullanılmıştır. Ayrıca, elde edilen özelliklere göre, farklı stres durumlarını belirlemek için EDA sinyalleri sınıflandırılmıştır. Elde edilen sonuçlar, EDA ve alt bant EDA sinyallerinin bilişsel stres açısından diğer stres durumlarından anlamlı derecede farklı olduğunu göstermiştir. Ayrıca, AKA alt bantlarından elde edilen özellikler, farklı durumlar için Destek Vektör Makineleri (DVM), K-En Yakın Komşular (KNN) ve Çok Katmanlı Algılayıcı (ÇKA) yöntemleri kullanılarak sınıflandırılmış ve sınıflandırıcı performansları karşılaştırılmıştır. Diğer durumlarla karşılaştırıldığında, bilişsel stres durumu ve ilk dinlenme periyodunun sınıflandırılmasında, en iyi sınıflandırma performansı MLP, SVM ve KNN sınıflandırıcısı kullanılarak sırasıyla % 97,36, % 84,21 ve % 81,57 olarak elde edilmiştir.

Keywords

Elektrodermal Aktivite (EDA), Ampirik Kip Ayrışımı (AKA), Kısa Zamanlı Fourier Dönüşümü (KZFD), Yapay Sinir Ağları(YSA)

References

• [1] Bouscein W., Electrodermal Activity. ,Newyork, Plenum Pres., pp 1-372, 1992.
• [2] Dolu N, Özbek H, Sporcularda Dikkat Düzeyindeki Hemisferik Farklılıkların Elektrodermal Aktivite İle Belirlenmesi, Erciyes Üniversitesi, Kayseri, 2009
• [3] Y. J. Kim, G. R. Jeon, S. S. Kim, W. Y. Jang, J. H. Kim, and S. W. Baik, “Implementation of Electrodermal Activity Measurement System using Algometer and Biopotential Measuring System”, International Conference on Chemistry, Antalya, 2014
• [4] Dolu N., “Sağlıklı Kişilerde ve Hipertiroidili Hastalarda Elektrodermal Aktivite Bulgularının İncelenmesi”, Uzmanlık Tezi, Erciyes Üniversitesi
• [5] Tarvainen, M.P., Karjalainen, P. A., Koistinen, A.S., Valkonen- Korhonen, M., 2000, “ Principal component analysis of galvanic skin responses “, Proceedingsof the 22" d Annual EMBS International Conference of the IEEE Engineering in Medicine and Biology Society Vols 1-4, Vol.22, July 23-28, Chicago IL., pp.3011- 3014
• [6] Xiong, J., 2010, “ Design of Health Relaxation System based on Biofeedback from Finger Sensors”, Innovative Computing & Communication, 2010 Intl Conf on and Information Technology & Ocean Engineering, 2010 Asia- Pacific Conf on (CICC-ITOE) , pp. 127-128
• [7] Bouscein W., Electrodermal Activity, Springer Science & Business Media, 2012
• [8] S. Zhang, S. Hu, H.H. Chao, X. Luo, O.M. Farr, C.-s.R. Li, Cerebral correlates of skin conductance responses in a cognitive task, NeuroImage, vol 62, pp 1489-1498, 2012
• [9] MM. Bradley, P.J. Lang, Motivation and Emotion, in Handbook of Psychophysiology, 2nd edition, Cambridge University Press, New York, pp. 581-607.,2006.
• [10] C. Setz, B. Arnrich, J. Schumm, R. La Marca, G. Tröster, and U. Ehlert, "Discriminating stress from cognitive load using a wearable EDA device.," IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society, vol. 14, no. 2, pp. 410-7, Mar. 2010
• [11] Rabavilas AD. Electrodermal activity in low and high alexithymic neurotic patients. Psychother Psychosom, vol 4, pp 47:101, 2006.
• [12] J.H Satterfield, M.E Dawson Electrodermal correlates of hyperactivity in children Psychophysiology, vol 8,pp. 191-197 , 1971
• [13] J. A. Healey and R. W. Picard, “Detecting stress during real-world driving tasks using physiological sensors,” IEEE Transactions in Intelligent Transportation Systems, vol. 6(2), pp. 156-166, 2005
• [14] Birjandtalab, Javad, Diana Cogan, Maziyar Baran Pouyan, and Mehrdad Nourani, A Non-EEG Biosignals Dataset for Assessment and Visualization of Neurological Status, 2016 IEEE International Workshop on Signal Processing Systems (SiPS), Dallas, TX, pp. 110-114., 2016. doi: 10.1109/SiPS.2016.27
• [15] Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101(23):e215-e220 [Circulation Electronic Pages; http://circ.ahajournals.org/content/101/23/e215]; 2000 (June 13).
• [16] Konstantin Dragomiretskiy, Dominique Zosso,Variational Mode Decomposition, IEEE Transactions on Signal Processing, Vol 62, No 3, pp. 531-544, February 2014.
• [17] Norden E. Huang, Zheng Shen, Steven R. Long, Manli C. Wu, Hsing H. Shih, Quanan Zheng, Nai-Chyuan Yen, Chi Chao Tung, Henry H. LiuProc. R. Soc. Lond. A. "The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis." Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, vol 454, pp 903-995, 1998. Doi: 10.1098/rspa.1998.0193.
• [18] Huang, N.E., Shen, Z. and Long, S.R, A new view of nonlinear water waves:The Hilbert Spectrum. Annu. Rev. Fluid Mech.,vol 454, pp 903–995,1999.
• [19] Huang, N.E., Wu, M.L., Long, S.R., Shen, S., Qu, W., Gloerson, P. and Fan, K. (2003) A confidence limit for the empirical mode decomposition and hilbert spectral analysis. Proc. Roy. Soc. London A., 31, 417–457
• [20] Rilling, G & Flandrin, Patrick & Gonçalves, Paulo. "On empirical mode decomposition and its algorithms." IEEE-EURASIP workshop on nonlinear signal and image processing 2003. NSIP-03. Grado, Italy. 8-11.
• [21] Erkaymaz, H., Özer, M. ve Orak, İ. M.,Detection of Directional Eye Movements Based on The Electrooculogram Signals Through an Artificial Neural Network, Chaos Solitons&Fractals, vol 56 ,pp 202- 208, 2015.
• [22] Charu C. Aggarwal,Neural Networks and Deep Learning : A Textbook,Cham, Switzerland, 2018
• [23] [25] https://towardsdatascience.com/knn-k-nearest-neighbors-1-a4707b24bd1d , Access date : 19.07.2019
• [24] Cortes, C. , & Vapnik, V. ,Support-vector networks. Machine Learning, vol 20 (3),pp 273–2, 1995
• [25] P. Ghaderyan, A. Abbasi, An efficient automatic workload estimation method based on electrodermal activity using pattern classifier combinations, Int. J. Psychophysiol. Vol 110, pp 91-101, 2016.
• [26] J. Kim, E. André, Emotion recognition based on physiological changes in music listening, IEEE Trans. Pattern Anal. Mach. Intell. Vol 30 (12) , pp 2067-2083, 2008.
• [27] W. Wen, G. Liu, N. Cheng, J. Wei, P. Shangguan, W. Huang, Emotion recognition based on multi-variant correlation of physiological signals, IEEE Trans. Affect. comput. vol 5 (2) ,pp 126-140, 2014.