Stress Detection Based on Fusion of Multimodal Physiological signals using Dempster-Shafer Evidence Theory

Subject Areas : Renewable energy

Sara Majlesi ¹ , Mahdi Khezri ²

1 - Department of Electrical Engineering- Najafabad Branch, Islamic Azad University, Najafabad, Iran
2 - Digital Processing and Machine Vision Research Center- Najafabad Branch, Islamic Azad University, Najafabad, Iran

Received: 2021-06-18 Accepted : 2021-08-20 Published : 2021-12-22

Keywords: SVM Classifier, Stress detection, physiological signals, Dempster-Shafer fusion method,

Abstract :

Detecting and controlling stress levels in drivers is especially important to reduce the potential risks while driving. Accordingly, in this study, a detection system was presented to identify four levels of stress (low, neutral, high and very high) in drivers based on physiological signals. The proposed method used the drivedb database, which includes the recording of physiological signals from 17 healthy volunteers while driving on specific routes on city streets and highways. A set of statistical and entropy features along with morphological features that were calculated only for the ECG signals, were used. The calculated features were applied as inputs to the classification units to detect stress levels. Support vector machine (SVM), k nearest neighbors (kNN) and decision tree (DT) were evaluated as classification methods. The main purpose of this study was to improve the accuracy of stress level detectionusing the idea of classifiers fusion. To achieve this goal, the combination of individual classification units, each of which used only the features of one of the ECG, EMG and GSR signals, was performed by the Demster-Shafer method. Using genetic algorithm as feature selection method, SVM classifier and Dempster-Shafer fusion strategy, the best stress detection accuracy of 96.9% was obtained. While the highest detection accuracy among individual classifiers was 75% and obtained by a subsystem that used ECG features.The results show significant performance of the proposed method compared to previous studies that used the same dataset.

References:

[1] S.M. Ahmed, P.J. Hershberger, J.P. Lemkau, R. Rakel, D. Rakel, "Psychosocial influences on health", Textbook of Family Medicine E-Book,  Elsevier Health Sciences, March, 2011.

[2] L. Bowen, A. Smith, "Drive better, feel better: predicting well-being and driving behaviour in undergraduate psychology students", Advances in Social Sciences Research Journal, vol. 6, no. 2, pp. 302- 318, Feb. 2019 (doi: 10.14738/assrj.62.6221).

[3] J.A. Healey, R.W. Picard, "Detecting stress during real-world driving tasks using physiological sensors", IEEE Trans. on Intelligent Transportation Systems,vol. 6, no. 2, pp. 156-166, June 2005 (doi: 10.1109/T­ITS­.200­5.848368).

[4] A.O. Akmandor, N.K. Jha, "Keep the stress away with SoDA: Stress detection and alleviation system", IEEE Trans. on Multi-Scale Computing Systems, vol. 3, no. 4, pp. 269-282, Oct.-Dec. 2017 (doi:  10.1109/TMSC­S.2017.2703613)

[5] A. R. Subhani, W. Mumtaz, M. N. B. M. Saad, N. Kamel, A. S. Malik, "Machine learning framework for the detection of mental stress at multiple levels", IEEE Access, vol. 5, pp. 13545-13556, 2017 (doi: 10.1109/­AC­CESS.2017.2723622).

[6] M. Choi, G. Koo, M. Seo, S. W. Kim, "Wearable device-based system to monitor a driver’s stress, fatigue, and drowsiness", IEEE Trans. on Instrumentation Measurement, vol. 67, no. 3, pp. 634-645, Mar. 2017 (doi: 10.1109/TIM.2017.2779329).

[7] Y. Liu, S. Du, "Psychological stress level detection based on electrodermal activity", Behavioural brain research, vol. 341, pp. 50-53, Apr. 2018 (doi: 10.1016/j.bbr.2017.12.021).

[8]  M. D. Hssayeni, B. Ghoraani, "Multi-modal physiological data fusion for affect estimation using deep learning",  IEEE Access, vol. 9, pp. 21642-21652, 2021 (doi: 10.1109/ACCESS.2021.3055933).

[9] L. Rachakonda, S. P. Mohanty, E. Kougianos, P. Sundaravadivel, "Stress-lysis: A DNN-integrated edge device for stress level detection in the IoMT," IEEE Trans. on Consumer Electronics, vol. 65, no. 4, pp. 474-483, Nov. 2019 (doi: 10.1109/TCE.2019.2940472).

[10]  J. Healey, R. Picard, "SmartCar: detecting driver stress", Proceeding of the IEEE/ICPR, pp. 218-221, Barcelona, Spain, Sept. 2000 (doi: 10.1109/ICPR.2000.902898).

[11]  Y. Zhou, J. Kang, X. Zhang, "A cooperative coevolutionary approach to discretization-based feature selection for high-dimensional data", Entropy, vol. 22, no. 6, p. 613, June 2020 (doi: 10.3390/e22060613.).

[12] S. Karimi-Shahraki, M. Khezri, "Identification of ADHD patients using wavelet-based features of EEG signals", Journal of Intelligent Procedures in Electrical Technology, vol. 12, no. 47, pp. 1-11, Dec. 2021 (dor: 20.1001.1.23223871.1400.12.3.1.1) (in Persian).

[13] S. R. Safavian D. Landgrebe, "A survey of decision tree classifier methodology", IEEE Trans. on systems, man, cybernetics, vol. 21, no. 3, pp. 660-674, May-June. 1991 (doi: 10.1109/21.97458).

[14]  C. Reinders, H. Ackermann, M.Y. Yang, B. Rosenhahn, “Chapter4- Learning convolutional neural networks for object detection with very little training data", Multimodal Scene Understanding: Algorithms, Applications and Deep Learning Elsevie, pp. 65-10, 2019 (doi:10.1016/B978-0-12-817358-9.00010-X).

[15] N. Dashti, M. Khezri, "Recognition of motor imagery based on dynamic features of electroencephal-ography signals", Journal of Intelligent Procedures in Electrical Technology, vol. 11, no. 43, pp. 13-27, June 2020 (in Persian).

[16] T. Denœux, "Logistic regression, neural networks and Dempster–Shafer theory: A new perspective", Knowledge-Based Systems, vol. 176, pp. 54-67, Jul. 2019 (doi: 10.1016/j.knosys.2019.03.030).

[17]  G. Shafer, "A mathematical theory of evidence", Princeton university press, 1976.

[18] G. Mardanian, N. Behzadfar, “A new method for detection of breast cancer in mammography images using a firefly algorithm”, Journal of Intelligent Procedures in Electrical Technology, vol. 10, no. 40, pp. 23-32, March 2020 (in Persian).

[19]  J.-S. Wang, C.-W. Lin, Y.-T. C. Yang, "A k-nearest-neighbor classifier with heart rate variability feature-based transformation algorithm for driving stress recognition", Neurocomputing, vol. 116, pp. 136-143, Sept, 2013 (doi: 10.1016/j.neucom.2011.10.047).

[20] S. Pourmohammadi, A. Maleki, "A fuzzy C-means clustering approach for continuous stress detection during driving", Signal and Data Processing, vol. 14, no. 4, pp. 129-142, March 2018 (doi: 10.29252/jsd­p.14.4.129) (in Persian).

[21] M.F. Rizwan, R. Farhad, F. Mashuk, F. Islam, M.H. Imam, "Design of a biosignal based stress detection system using machine learning techniques", Proceeding of the IEEE/ ICREST, pp. 364-368, Dhaka, Bangladesh, Jan 2019 (doi: 10.1109/ICREST.2019.8644259).