Support vector machine classification of brain states exposed to social stress test using EEG-based brain network measures

• Autorzy: Lotfan Saeed , Shahyad Shima , Khosrowabadi Reza , Mohammadi Alireza , Hatef Boshra

Identyfikatory

DOI

10.1016/j.bbe.2018.10.008

• Języki publikacji: EN

Abstrakty

EN

Stress is one of the most significant health problems in the 21st century, and should be dealt with due to the costs of primary and secondary cares of stress-associated psychological and psychiatric problems. In this study, the brain network states exposed to stress were monitored based on electroencephalography (EEG) measures extracted by complex network analysis. To this regard, 23 healthy male participants aged 18–28 were exposed to a stress test. EEG data and salivary cortisol level were recorded for three different conditions including before, right after, and 20 min after exposure to stress. Then, synchronization likelihood (SL) was calculated for the set of EEG data to construct complex networks, which are scale reduced datasets acquired from multi-channel signals. These networks with weighted connectivity matrices were constructed based on original EEG data and also by using four different waves of the recorded signals including d, u, a, and b. In addition to these networks with weighted connectivity, networks with binary connectivity matrices were also derived using threshold T. For each constructed network, four measures including transitivity, modularity, characteristic path length, and global efficiency were calculated. To select the sensitive optimal features from the set of the calculated measures, compensation distance evaluation technique (CDET) was applied. Finally, multi-class support vector machine (SVM) was trained in order to classify the brain network states. The results of testing the SVM models showed that the features based on the original EEG, a and b waves have got better performances in monitoring the brain network states.

Słowa kluczowe

EN

trier social stress test; complex brain network; synchronization likelihood; support vector machine

PL

test stresu społecznego; sieć mózgowa; maszyna wektorów wsparcia

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 1
• Strony: 199--213
• Opis fizyczny: Bibliogr. 75 poz., rys., tab., wykr.

Twórcy

autor

Lotfan Saeed

• Department of Mechanical Engineering, University of Tabriz, Tabriz, Iran

autor

Shahyad Shima

• Neuroscience Research Centre, Baqiyatallah University of Medical Sciences, Tehran, Iran

autor

Khosrowabadi Reza

• Institute for cognitive and brain sciences, Shahid Beheshti University G.C., Tehran, Iran

autor

Mohammadi Alireza

• Neuroscience Research Centre, Baqiyatallah University of Medical Sciences, Tehran, Iran

autor

Hatef Boshra

• Neuroscience Research Centre, Baqiyatallah University of Medical Sciences, Tehran, Iran

Bibliografia

• [1] Vogel S, Schwabe L. Learning and memory under stress: implications for the classroom. npj Sci Learn 2016;1:16011.
• [2] Kudielka BM, Hellhammer DH, Kirschbaum C, Harmon- Jones E, Winkielman P. Ten years of research with the Trier Social Stress Test—revisited. Soc Neurosci 2007;56:83.
• [3] Sharma N, Gedeon T. Objective measures, sensors and computational techniques for stress recognition and classification: a survey. Comput Meth Programs Biomed 2012;108(3):1287–301.
• [4] Fuchs E, Flügge G. Social stress in tree shrews: effects on physiology, brain function, and behavior of subordinate individuals. Pharmacol Biochem Behav 2002;73(1):247–58.
• [5] Selye H. The stress of life; 1956.
• [6] Peters A, McEwen BS, Friston K. Uncertainty and stress: why it causes diseases and how it is mastered by the brain. Prog Neurobiol 2017;156:164–88. http://dx.doi.org/10.1016/j.pneurobio.2017.05.004.
• [7] Hutchison MG, Mainwaring L, Senthinathan A, Churchill N, Thomas S, Richards D. Psychological and physiological markers of stress in concussed athletes across recovery milestones. J Head Trauma Rehabil 2017;32(3):E38–48.
• [8] Foley P, Kirschbaum C. Human hypothalamus–pituitary– adrenal axis responses to acute psychosocial stress in laboratory settings. Neurosci Biobehav Rev 2010;35(1):91–6. http://dx.doi.org/10.1016/j.neubiorev.2010.01.010.
• [9] Maruyama Y, Kawano A, Okamoto S, Ando T, Ishitobi Y, Tanaka Y, et al. Differences in salivary alpha-amylase and cortisol responsiveness following exposure to electrical stimulation versus the Trier Social Stress Tests. PLoS One 2012;7(7):e39375. http://dx.doi.org/10.1371/journal.pone.0039375.
• [10] Mohammadi A, Asgar E, Maryam S, GolamHossein M, Shima S, Keyvan Y, et al. The persistent response to acute psychosocial stress. Biomed Signal Process Control 2018.
• [11] Dishman RK, Nakamura Y, Garcia ME, Thompson RW, Dunn AL, Blair SN. Heart rate variability, trait anxiety, and perceived stress among physically fit men and women. Int J Psychophysiol 2000;37(2):121–33.
• [12] Steptoe A, Marmot M. Impaired cardiovascular recovery following stress predicts 3-year increases in blood pressure. J Hypertens 2005;23(3):529–36.
• [13] Partala T, Surakka V. Pupil size variation as an indication of affective processing. Int J Human-Computer Stud 2003;59(1– 2):185–98.
• [14] Lundberg U. Stress, subjective and objective health. Int J Soc Welfare 2006;15(s1).
• [15] Katsis CD, Katertsidis N, Ganiatsas G, Fotiadis DI. Toward emotion recognition in car-racing drivers: a biosignal processing approach. IEEE Trans Syst Man Cybern Part A Syst Humans 2008;38(3):502–12.
• [16] Rothkrantz LJ, Wiggers P, Van Wees J-WA, van Vark RJ. Voice stress analysis. International Conference on Text, Speech and Dialogue; 2004. pp. 449–56.
• [17] Schindler K, Van Gool L, de Gelder B. Recognizing emotions expressed by body pose: a biologically inspired neural model. Neural Networks 2008;21(9):1238–46.
• [18] Pärkkä J, Merilahti J, Mattila EM, Malm E, Antila K, Tuomisto MT, et al. Relationship of psychological and physiological variables in long-term self-monitored data during work ability rehabilitation program. IEEE Trans Inform Technol Biomed 2009;13(2):141–51.
• [19] McEwen BS, Bowles NP, Gray JD, Hill MN, Hunter RG, Karatsoreos IN, et al. Mechanisms of stress in the brain. Nat Neurosci 2015;18(10):1353–63. http://dx.doi.org/10.1038/nn.4086.
• [20] Jeunet C, Lotte F, Mühl C. Design and validation of a mental and social stress induction protocol; 2014.
• [21] Brouwer A-M, Hogervorst MA. A new paradigm to induce mental stress: the Sing-a-Song Stress Test (SSST). Front Neurosci 2014;8:224.
• [22] Yaribeygi H, Panahi Y, Sahraei H, Johnston TP, Sahebkar A. The impact of stress on body function: a review. EXCLI J 2017;16:1057–72.
• [23] Stam CJ, Pritchard WS. Dynamics underlying rhythmic and non-rhythmic variants of abnormal, waking delta activity. Int J Psychophysiol 1999;34(1):5–20.
• [24] Janjarasjitt S, Scher M, Loparo K. Nonlinear dynamical analysis of the neonatal EEG time series: the relationship between sleep state and complexity. Clin Neurophysiol 2008;119(8):1812–23.
• [25] Ying J, Zhou D, Lin K, Gao X. Network analysis of functional brain connectivity driven by gamma-band auditory steady-state response in auditory hallucinations. J Med Biol Eng 2015;35(1):45–51.
• [26] Kaur M, Singh G. Classification of seizure prone EEG signal using amplitude and frequency based parameters of intrinsic mode functions. J Med Biol Eng 2017;37(4):540–53.
• [27] Wang J-H, Zuo X-N, Gohel S, Milham MP, Biswal BB, He Y. Graph theoretical analysis of functional brain networks: test–retest evaluation on short-and long-term resting-state functional MRI data. PLoS ONE 2011;6(7):e21976.
• [28] Ajilore O, Lamar M, Leow A, Zhang A, Yang S, Kumar A. Graph theory analysis of cortical–subcortical networks in late-life depression. Am J Geriatr Psychiatry 2014;22(2):195–206.
• [29] Stam CJ, Jones B, Nolte G, Breakspear M, Scheltens P. Small-world networks and functional connectivity in Alzheimer's disease. Cerebral Cortex 2006;17(1):92–9.
• [30] Al-shargie F, Tang TB, Badruddin N, Kiguchi M. Towards multilevel mental stress assessment using SVM with ECOC: an EEG approach. Med Biol Eng Comput 2018;56(1):125–36.
• [31] Subhani AR, Mumtaz W, Saad MNBM, Kamel N, Malik AS. Machine learning framework for the detection of mental stress at multiple levels. IEEE Access 2017;5:13545–56.
• [32] Gaurav, Anand RS, Kumar V. EEG-metric based mental stress detection. Network Biol 2018.
• [33] Howard GLD. Convergence and Hybrid Information Technology; 2012.
• [34] Putman P, Verkuil B, Arias-Garcia E, Pantazi I, van Schie C. EEG theta/beta ratio as a potential biomarker for attentional control and resilience against deleterious effects of stress on attention. Cogn Affect Behav Neurosci 2014;14(2):782–91.
• [35] Mohino-Herranz I, Gil-Pita R, Ferreira J, Rosa-Zurera M, Seoane F. Assessment of mental, emotional and physical stress through analysis of physiological signals using smartphones. Sensors 2015;15(10):25607–2.
• [36] Rubinov M, Sporns O. Complex network measures of brain connectivity: uses and interpretations. Neuroimage 2010;52 (3):1059–69.
• [37] Strogatz SH. Exploring complex networks. Nature 2001;410 (6825):268.
• [38] Newman ME. The structure and function of complex networks. SIAM Rev 2003;45(2):167–256.
• [39] Boccaletti S, Latora V, Moreno Y, Chavez M, Hwang D-U. Complex networks: structure and dynamics. Phys Rep 2006;424(4–5):175–308.
• [40] Alonso J, Romero S, Ballester M, Antonijoan R, Mañanas M. Stress assessment based on EEG univariate features and functional connectivity measures. Physiol Measure 2015;36 (7):1351.
• [41] Sadeghi MH, Lotfan S. Identification of non-linear parameter of a cantilever beam model with boundary condition non-linearity in the presence of noise: an NSI-and ANN-based approach. Acta Mechanica 2017;1–19.
• [42] Kirschbaum C, Pirke K-M, Hellhammer DH. The 'Trier Social Stress Test' – a tool for investigating psychobiological stress responses in a laboratory setting. Neuropsychobiology 1993;28(1–2):76–81.
• [43] Baum A, Contrada R. The handbook of stress science: biology, psychology, and health. Springer; 2010.
• [44] Zigmond MJ, Bloom FE. Fundamental neuroscience; 1999.
• [45] Dickerson SS, Kemeny ME. Acute stressors and cortisol responses: a theoretical integration and synthesis of laboratory research. Psychol Bull 2004;130(3):355.
• [46] Zahra R, Boshra H, Reza K, Golam-Hossein M. Stress functionally rewires the brain: an EEG based study. Front Comput 2018.
• [47] Fliege NJ. Multirate digital signal processing. New York: John Wiley; 1994.
• [48] Sanei S, Chambers JA. EEG signal processing. John Wiley Sons; 2013.
• [49] Friston KJ. Functional and effective connectivity in neuroimaging: a synthesis. Human Brain Mapp 1994;2(1– 2):56–78.
• [50] Friston KJ, Harrison L, Penny W. Dynamic causal modelling. Neuroimage 2003;19(4):1273–302.
• [51] Stam C, Van Dijk B. Synchronization likelihood: an unbiased measure of generalized synchronization in multivariate data sets. Physica D 2002;163(3–4):236–51.
• [52] Barttfeld P, Wicker B, Cukier S, Navarta S, Lew S, Sigman M. A big-world network in ASD: dynamical connectivity analysis reflects a deficit in long-range connections and an excess of short-range connections. Neuropsychologia 2011;49(2):254–63.
• [53] Buzug T, Pawelzik K, Von Stamm J, Pfister G. Mutual information and global strange attractors in Taylor–Couette flow. Physica D 1994;72(4):343–50.
• [54] Takens F. Detecting strange attractors in turbulence. Dynamical systems and turbulence, Warwick 1980. Springer; 1981. p. 366–81.
• [55] Theiler J. Spurious dimension from correlation algorithms applied to limited time-series data. Phys Rev A 1986;34 (3):2427.
• [56] Montez T, Linkenkaer-Hansen K, Van Dijk B, Stam C. Synchronization likelihood with explicit time-frequency priors. Neuroimage 2006;33(4):1117–25.
• [57] Watts DJ, Strogatz SH. Collective dynamics of 'small-world'networks. Nature 1998;393(6684):440.
• [58] Newman ME, Moore C, Watts DJ. Mean-field solution of the small-world network model. Phys Rev Lett 2000;84(14):3201.
• [59] Humphries MD, Gurney K. Network 'small-world-ness': a quantitative method for determining canonical network equivalence. PLoS One 2008;3(4):e0002051.
• [60] Onnela J-P, Saramäki J, Kertész J, Kaski K. Intensity and coherence of motifs in weighted complex networks. Phys Rev E 2005;71(6):065103.
• [61] Newman ME. Fast algorithm for detecting community structure in networks. Phys Rev E 2004;69(6):066133.
• [62] Reichardt J, Bornholdt S. Statistical mechanics of community detection. Phys Rev E 2006;74(1):016110.
• [63] Latora V, Marchiori M. Efficient behavior of small-world networks. Phys Rev Lett 2001;87(19):198701.
• [64] Lei Y, He Z, Zi Y, Chen X. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique. Mech Syst Signal Process 2008;22(2):419–35.
• [65] Subhani AR, Mumtaz W, Kamil N, Saad NM, Nandagopal N, Malik AS. MRMR based feature selection for the classification of stress using EEG. 2017 Eleventh International Conference on Sensing Technology (ICST), 4–6 December. 2017. pp. 1–4. http://dx.doi.org/10.1109/ICSensT.2017.8304499.
• [66] Sani MM, Norhazman H, Omar HA, Zaini N, Ghani SA. Support vector machine for classification of stress subjects using EEG signals. 2014 IEEE Conference on Systems, Process and Control (ICSPC 2014), 12–14 December. 2014. pp. 127–31. http://dx.doi.org/10.1109/SPC.2014.7086.243.
• [67] Luts J, Heerschap A, Suykens JA, Van Huffel S. A combined MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs with class probabilities and feature selection. Artif Intell Med 2007;40(2):87–102.
• [68] Kousarrizi MRN, Ghanbari AA, Gharaviri A, Teshnehlab M, Aliyari M. Classification of alcoholics and non-alcoholics via EEG using SVM and neural networks. 3rd IEEE International Conference on Bioinformatics and Biomedical Engineering, ICBBE 2009. 2009. pp. 1–4.
• [69] Meier TB, Desphande AS, Vergun S, Nair VA, Song J, Biswal BB, et al. Support vector machine classification and characterization of age-related reorganization of functional brain networks. Neuroimage 2012;60(1):601–13.
• [70] Manohar L, Ganesan K. Diagnosis of schizophrenia disorder in MR brain images using multi-objective BPSO based feature selection with fuzzy SVM. J Med Biol Eng 2017;1–16.
• [71] Fatima S, Mohanty A, Naikan V. Multiple fault classification using support vector machine in a machinery fault simulator. Vib Eng Technol Machinery 2015;1021–31.
• [72] Mohammad Taghi S-T, Mir Mohammad E, Saeed L, Hamed S. Cavitation intensity monitoring in an axial flow pump based on vibration signals using multi-class support vector machine. Proceedings of the Institution of Mechanical Engineers Part C: Journal of Mechanical Engineering Science 2017. http://dx.doi.org/10.1177/0954406217729416.
• [73] Fatima S, Guduri B, Mohanty A, Naikan V. Transducer invariant multi-class fault classification in a rotor-bearing system using support vector machines. Measurement 2014;58:363–74.
• [74] Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press; 2000.
• [75] Friedman J, Hastie T, Tibshirani R. The elements of statistical learning: Springer series in statistics, vol 1. Berlin: Springer; 2001.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).