This Article 
 Bibliographic References 
 Add to: 
Support Vector Machines to Define and Detect Agitation Transition
July-December 2010 (vol. 1 no. 2)
pp. 98-108
George E. Sakr, American University of Beirut, Beirut
Imad H. Elhajj, American University of Beirut, Beirut
Huda Abou-Saad Huijer, American University of Beirut, Beirut
The need to automate the detection of agitation and the detection of agitation transition for dementia patients is a significant facilitator for caregivers. This research aims at detecting the transitional phase toward agitation, as well as agitation detection of subjects, using soft computing techniques that do not require supervision beyond the training phase. Three vital signs are monitored: Heart Rate (HR), Galvanic Skin Response (GSR), and Skin Temperature (ST). These measures are fed into two proposed SVM architectures which are based on the definition of a new confidence measure: "Confidence-Based SVM” and "Confidence-Based Multilevel SVM.” Results show very high detection accuracy of agitation and agitation transition, a quick adaptation to the subject, and a strong correlation between the physiological signals monitored and the emotional states of the subjects. Another challenge that is successfully addressed in this paper is the ability to train the classifier on a limited group of subjects, and then test it on subjects not belonging to the training group. The result is a learning algorithm that is "Subject-Independent.”

[1] “DSM-IV: Diagnostic and Statistical Manual of Mental Disorders,” Am. Psychiatric Assoc. Task Force on DSM-IV, 1994.
[2] W. He, M. Sengupta, V. Velkoff, and K. DeBarros, “US Census Bureau, Current Population Reports, P23-209, 65+ in the United States: 2005,” US Govt. Printing Office, 2005.
[3] A. Rosenblatt, “The Art of Managing Dementia in the Elderly,” Cleveland Clinic J. Medicine, vol. 72, no. 3, p. 3, 2005.
[4] R. Picard, E. Vyzas, and J. Healey, “Toward Machine Emotional Intelligence: Analysis of Affective Physiological State,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1175-1191, Oct. 2001.
[5] W. Liao, W. Zhang, Z. Zhu, and Q. Ji, “A Real-Time Human Stress Monitoring System Using Dynamic Bayesian Network,” Proc. 2005 IEEE CS Conf. Computer Vision and Pattern Recognition, p. 70, June 2005.
[6] P. Ekman, “Expression and the Nature of Emotion,” Approaches to Emotion, vol. 3, pp. 319-343, Lawrence Erlbaum Assoc., 1984.
[7] L. Li and J. Chen, “Emotion Recognition Using Physiological Signals,” Advances in Artificial Reality and Tele-Existence, pp. 437-446, Springer, 2006.
[8] K. Kim, S. Bang, and S. Kim, “Emotion Recognition System Using Short-Term Monitoring of Physiological Signals,” Medical and Biological Eng. and Computing, vol. 42, no. 3, pp. 419-427, 2004.
[9] M. Murugappan, M. Rizon, R. Nagarajan, S. Yaacob, D. Hazry, and I. Zunaidi, “Time-Frequency Analysis of EEG Signals for Human Emotion Detection,” Proc. Fourth Kuala Lumpur Int'l Conf. Biomedical Eng., pp. 262-265, 2008.
[10] V. Fook, P. Thang, T. Htwe, Q. Qiang, A. Wai, M. Jayachandran, J. Biswas, and P. Yap, “Automated Recognition of Complex Agitation Behavior of Dementia Patients Using Video Camera,” Proc. Ninth Int'l Conf. e-Health Networking, Application and Services, pp. 68-73, 2007.
[11] L. Wenhui, Z. Weihong, Z. Zhiwei, and Q. Ji, “A Real-Time Human Stress Monitoring System Using Dynamic Bayesian Network,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, June 2005.
[12] T. Tamura, T. Fujimoto, and T. Togawa, “Quantitative Assessment of Behavior in Dementia Patients by Continuous Physical Activity Monitoring,” Proc. 19th Ann. Int'l Conf. IEEE Eng. in Medicine and Biology Soc., vol. 3, pp. 999-1002, 1997.
[13] J. Zhai and A. Barreto, “Stress Recognition Using Non-Invasive Technology,” Proc. 19th Int'l Florida Artificial Intelligence Research Soc. Conf., pp. 395-400, 2006.
[14] J. Stroop, “Studies of Interference in Serial Verbal Reactions,” J.Experimental Psychology, vol. 18, no. 6, pp. 643-662, 1935.
[15] G. Sakr, I. Elhajj, H. Huijer, C. Riley-Doucet, and D. Debnath, “Subject Independent Agitation Detection,” Proc. IEEE/ASME Int'l Conf. Advanced Intelligent Mechatronics, pp. 200-204, 2008.
[16] G. Sakr, I. Elhajj, and U. Wejinya, “Multi Level SVM for Subject Independent Agitation Detection,” Proc. IEEE/ASME Int'l Conf. Advanced Intelligent Mechatronics, pp. 538-543, 2009.
[17] R. Dishman, Y. Nakamura, M. Garcia, R. Thompson, A. Dunn, and S. Blair, “Heart Rate Variability, Trait Anxiety, and Perceived Stress among Physically Fit Men and Women,” Int'l J. Psychophysiology, vol. 37, no. 2, pp. 121-133, 2000.
[18] J. Lee, F. Pearce, A. Hibbs, R. Matthews, C. Morrissette, and R. Walter, “Evaluation of a Capacitively-Coupled, Non-Contact (through Clothing) Electrode or ECG Monitoring and Life Signs Detection for the Objective Force Warfighter,” http://ftp.rta. RTO/MP/RTO-MP-HFM-109//MP-HFM-109-25.pdf , 2010.
[19] M. Malik, J. Bigger, A. Camm, R. Kleiger, A. Malliani, A. Moss, and P. Schwartz, “Heart Rate Variability: Standards of Measurement, Physiological Interpretation, and Clinical Use,” European Heart J., vol. 17, no. 3, p. 354, 1996.
[20] D. Murray, “What Is Heart Rate Variability; and Is It Blunted by Tumor Necrosis Factor?” Chest, vol. 123, no. 3, p. 664, 2003.
[21] A. Kistler, C. Mariauzouls, and K. von Berlepsch, “Fingertip Temperature as an Indicator for Sympathetic Responses,” Int'l J. Psychophysiology, vol. 29, no. 1, pp. 35-41, 1998.
[22] K. Pearson, “LIII. On Lines and Planes of Closest Fit to Systems of Points in Space,” Philosophical Magazine, Series 6, vol. 2, no. 11, pp.559-572, 1901.
[23] V. Kecman, Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models. MIT Press, 2001.
[24] N. Aronszajn, Introduction to the Theory of Hilbert Spaces. Oklahoma Reasearch [sic] Foundation, 1950.
[25] V. Vapnik, Statistical Learning Theory. Wiley, 1998.
[26] C. Burges, “A Tutorial on Support Vector Machines for Pattern Recognition,” Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121-167, 1998.
[27] C. Spielberger, R. Gorsuch, and L. Edward, STAI Manual for the State-Trait Anxiety Inventory (“Self-Evaluation Questionnaire”). Consulting Psychologists Press, 1970.

Index Terms:
Agitation detection, agitation transition detection, support vector machines, confidence.
George E. Sakr, Imad H. Elhajj, Huda Abou-Saad Huijer, "Support Vector Machines to Define and Detect Agitation Transition," IEEE Transactions on Affective Computing, vol. 1, no. 2, pp. 98-108, July-Dec. 2010, doi:10.1109/T-AFFC.2010.2
Usage of this product signifies your acceptance of the Terms of Use.