Emotional stress recognition using a new fusion link between electroencephalogram and peripheral signals

  • Seyyed Abed Hosseini Mail Center of Excellence on Soft Computing and Intelligent Information Processing AND Department of Electrical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
  • Mohammad Ali Khalilzadeh Research Center of Biomedical Engineering, Islamic Azad University, Mashhad Branch, Mashhad, Iran
  • Mohammad Bagher Naghibi-Sistani Center of Excellence on Soft Computing and Intelligent Information Processing AND Department of Electrical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran
  • Seyyed Mehran Homam Department of Medical, Islamic Azad University, Mashhad Branch, Mashhad, Iran
Keywords:
Electroencephalogram, Emotional Stress, Signal Processing, Recognition, Support Vector Machine

Abstract

Background: This paper proposes a new emotional stress assessment system using multi-modal bio-signals. Electroencephalogram (EEG) is the reflection of brain activity and is widely used in clinical diagnosis and biomedical research.
Methods: We design an efficient acquisition protocol to acquire the EEG signals in five channels (FP1, FP2, T3, T4 and Pz) and peripheral signals such as blood volume pulse, skin conductance (SC) and respiration, under images induction (calm-neutral and negatively excited) for the participants. The visual stimuli images are selected from the subset International Affective Picture System database. The qualitative and quantitative evaluation of peripheral signals are used to select suitable segments of EEG signals for improving the accuracy of signal labeling according to emotional stress states. After pre-processing, wavelet coefficients, fractal dimension, and Lempel-Ziv complexity are used to extract the features of the EEG signals. The vast number of features leads to the problem of dimensionality, which is solved using the genetic algorithm as a feature selection method.
Results: The results show that the average classification accuracy is 89.6% for two categories of emotional stress states using the support vector machine (SVM).
Conclusion: This is a great improvement in results compared to other similar researches. We achieve a noticeable improvement of 11.3% in accuracy using SVM classifier, in compared to previous studies. Therefore, a new fusion between EEG and peripheral signals are more robust in comparison to the separate signals.

References

1. Hosseini SA. Quantification of EEG signals for evaluation of emotional stress level [MSc Thesis]. Mashhad, Iran: Islamic Azad University, Mashhad Branch; 2009.
2. Ruffman T, Henry JD, Livingstone V, Phillips LH. A meta-analytic review of emotion recognition and aging: implications for neuropsychological models of aging. Neurosci Biobehav Rev 2008; 32(4): 863-81.
3. Chanel G. Emotion assessment for affective computing based on brain and peripheral signal [PhD. Thesis]. Geneva, Switzerland: University of Geneva; 2009.
4. Seymour B, Dolan R. Emotion, decision making, and the amygdala. Neuron 2008; 58(5): 662-71.
5. Hosseini SA, Naghibi-Sistani MB, Rahati- quchani S. Analysis of psychophysiological and EEG signals for evaluation of emotional stress states. Proceedings of the 12th Iranian Students Conference on Electrical Engineering; 2009 Aug 13; Tabriz, Iran. [In Persian].
6. Ko KE, Yang HC, Sim KB. Emotion recognition using EEG signals with relative power values and Bayesian network. International Journal of Control, Automation and Systems 2009; 7(5): 865-70.
7. Cornelius RR. Theoretical approaches to emotion. Proceedings of the International Speech Communication Association Workshop on Speech and Emotion; 2000 Sep 5-7; Newcastle, Northern Ireland; 2000. p. 3-10.
8. Robert Horlings R. Emotion recognition using brain activity. Proceedings of the 9th International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing; 2008; New York, NY.
9. Ortony A, Turner TJ. What's basic about basic emotions? Psychol Rev 1990; 97(3): 315-31.
10. Chanel G, Ansari-Asl K, Pun T. Valence- arousal evaluation using physiological signals in an emotion recall paradigm. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics 2007 Oct 7-10; Montreal, Que.
11. Hosseini SA, Khalilzadeh MA. Emotional stress recognition system using EEG and psychophysiological signals: Using new labelling process of EEG signals in emotional stress state. Proceedings of the International Conference on Biomedical Engineering and Computer Science (ICBECS); 2010 Apr 23-25; Wuhan, China; 2010. p. 90-5.
12. Xiang Y, Tso SK. Detection and Classification of flows in Concrete Structure using Bispectra and neural networks. NDT&E International ed. 2002.
13. Yaacob S, Rizon M, Nagarajan R. FCM Clustering of Human Emotions using Wavelet based Features from EEG. Transactions ofBiomedical Soft Computing and Human Sciences(IJBSCHS) 2009; 14(2): 35-40.
14. Motie-Nasrabadi A. Quantitative and Qualitative Evaluation of Consciousness Variation and Depth of Hypnosis through Intelligent Processing of EEG signals [PhD Thesis]. Tehran, Iran: Amirkabir University of Technology; 2004.
15. Zhai J, Barreto A. Stress Detection in Computer Users Based on Digital Signal Processing of Noninvasive Physiological VariablesProceedings of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2006 31 Aug-3Sep; New York City, NY; 2006. p. 1355-8.
16. McFarland RA. Relationship of skin temperature changes to the emotions accompanying music. Biofeedback Self Regul 1985; 10(3): 255-67.
17. Chanel G, Kierkels JJM, Soleymani M, Pun T. Short-term emotion assessment in a recall paradigm. International Journal of Human- Computer Studies 2009; 67(8): 607-27.
18. Aftanas LI, Reva NV, Varlamov AA, Pavlov SV, Makhnev VP. Analysis of evoked EEG synchronization and desynchronization in conditions of emotional activation in humans: temporal and topographic characteristics. Neurosci Behav Physiol 2004; 34(8): 859-67.
19. Hosseini SA, Khalilzadeh MA, Homam SM, Azarnoosh M. Emotional stress detection using nonlinear and higher order spectra features in EEG signal. Journal of Electrical Eng 2010; 39 (2).
20. Kim KH, Bang SW, Kim SR. Emotion recognition system using short-term monitoring of physiological signals. Med Biol Eng Comput 2004; 42(3): 419-27.
21. Takahashi K. Remarks on Emotion Recognition from Bio-Potential Signals. Proceedings of the 2nd International Conference on Autonomous Robots and Agents; 2004 Dec 13-15; Palmerston North, New Zealand.
22. Schaaff K, Schultz T. Towards Emotion Recognition from Electroencephalographic Signals. 3rd International Conference on Affective Computing and Intelligent Interaction; 2009 Sep 10-12; Amsterdam, Netherlands.
23. Bradley M, Lang PJ. The International affective digitized sounds (IADS) stimuli, instruction manual and affective ratings. Gainesville, FL: NIMH Center for the Study of Emotion and Attention; 1999.
24. Kaplan HI, Sadock BJ. Kaplan and Sadock's Synopsis of Psychiatry: Behavioral Sciences, Clinical Psychiatry. 8th ed. Philadelphia, PA: Williams & Wilkins; 1998.
25. Thought Technology Ltd. FlexComp System with/ BioGraph Infiniti Software - T7555M [Online]. [cited 2015]; Available from: URL: http://thoughttechnology.com/index.php/fle xcomp-system-with-biograph-infiniti- software-t7555m.html http://www.thoughttechnology.com/flexinf. htm
26. Savran A, Ciftci K, Chanel G, Cruz Mota J, Hong Viet L, Sankur B, et al. EmotionDetection in the Loop from Brain Signals and Facial Images [Online]. [cited 2006]; Available from: URL: www.enterface.net/enterface06/docs/results/ reports/project7.pdf
27. Ritz T, Dahme B, Dubois AB, Folgering H, Fritz GK, Harver A, et al. Guidelines for mechanical lung function measurements in psychophysiology. Psychophysiology 2002; 39(5): 546-67.
28. Wilhelm FH, Pfaltz MC, Grossman P. Continuous electronic data capture of physiology, behavior and experience in real life: towards ecological momentary assessment of emotion. Interacting with Computers 2006; 18(2): 171-86.
29. Wan RD, Woo LJ. Feature Extraction and Emotion Classification Using Bio-signal", Transactions on engineering, computingand technology 2004; 2: 317-20.
30. Kernel-Machines [Online]. [cited 2009]; Available from: URL: http://www.kernel- machines.org/software.
31.Chang CC, Lin CJ. LIBSVM A Library for Support Vector Machines [Online]. [cited 2009]; Available from: URL:http://www.csie.ntu.edu.tw/~cjlin/libsvm/
32. Esteller R, Vachtsevanos G, Echauz J, Litt Finite Sequences. Information Theory, 2015; 22(1): 75-81.
33. Lempel A, Ziv J. On the Complexity of Finite Sequences. Information Theory, 2015; 22(1): 75-81.
34. Kaspar F, Schuster HG. Easily calculable measure for the complexity of spatiotemporal patterns. Phys Rev A 1987; 36(2): 842-8.
35. Haupt RL, Haupt SE. Practical Genetic Algorithms. 2nd ed. New Jersey, NJ: John Wiley & Sons; 2004.
Published
2015-10-14
How to Cite
1.
Hosseini SA, Khalilzadeh MA, Naghibi-Sistani MB, Homam SM. Emotional stress recognition using a new fusion link between electroencephalogram and peripheral signals. Curr J Neurol. 14(3):142-151.
Section
Special Articles