Affective assessment of computer users based on processing the pupil diameter signal

Detecting affective changes of computer users is a current challenge in human-computer interaction which is being addressed with the help of biomedical engineering concepts. This article presents a new approach to recognize the affective state (“relaxation” vs. “stress”) of a computer user from analysis of his/her pupil diameter variations caused by sympathetic activation. Wavelet denoising and Kalman filtering methods are first used to remove abrupt changes in the raw Pupil Diameter (PD) signal. Then three features are extracted from the preprocessed PD signal for the affective state classification. Finally, a random tree classifier is implemented, achieving an accuracy of 86.78%. In these experiments the Eye Blink Frequency (EBF), is also recorded and used for affective state classification, but the results show that the PD is a more promising physiological signal for affective assessment.

[1]  J. Beatty,et al.  The pupillary system. , 2000 .

[2]  S. Steinhauer,et al.  Sympathetic and parasympathetic innervation of pupillary dilation during sustained processing. , 2004, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[3]  Shu-Jen Steven Tsai.  Power Transformer Partial Discharge (PD) Acoustic Signal Detection using Fiber Sensors and Wavelet Analysis, Modeling, and Simulation , 2002 .

[4]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[5]  Ian H. Witten,et al.  Data mining - practical machine learning tools and techniques, Second Edition , 2005, The Morgan Kaufmann series in data management systems.

[6]  L. F. Bacher,et al.  Sensitivity of the rate of spontaneous eye blinking to type of stimuli in young infants. , 2009, Developmental psychobiology.

[7]  E. Vesterinen,et al.  Affective Computing , 2009, Encyclopedia of Biometrics.

[8]  Olaf Hochmuth,et al.  The Application of the Walsh Transform in Biosignal Processing , 1987 .

[9]  L. J. M. Rothkrantz,et al.  DETECTING STRESS USING EYE BLINKS AND BRAIN ACTIVITY FROM EEG SIGNALS , 2009 .

[10]  Paul C. Bressloff,et al.  Spontaneous oscillations in a nonlinear delayed-feedback shunting model of the pupil light reflex , 1998 .

[11]  George N. Votsis,et al.  Emotion recognition in human-computer interaction , 2001, IEEE Signal Process. Mag..

[12]  David A. Landgrebe,et al.  A survey of decision tree classifier methodology , 1991, IEEE Trans. Syst. Man Cybern..

[13]  Ilker Yaylali,et al.  Interictal spike detection using the Walsh transform , 2004, IEEE Transactions on Biomedical Engineering.

[14]  Charles Webster,et al.  Medical Affective Computing: Medical Informatics Meets Affective Computing , 1998, MedInfo.

[15]  W. Marsden.  I and J , 2012 .

[16]  Naphtali Rishe,et al.  Significance of Pupil Diameter Measurements for the Assessment of Affective State in Computer Users , 2007 .

[17]  Veikko Surakka,et al.  Pupil size variation as an indication of affective processing , 2003, Int. J. Hum. Comput. Stud..