Non-intrusive Physiological Monitoring for Automated Stress Detection in Human-Computer Interaction Armando Barreto 1,2 , Jing Zhai 1 , and Malek Adjouadi 1,2 1 Electrical and Computer Engineering Department 2 Biomedical Engineering Department Florida International University Miami, Florida, USA {barretoa, jzhai002, adjouadi}@fiu.edu Abstract. Affective Computing, one of the frontiers of Human-Computer Interaction studies, seeks to provide computers with the capability to react appropriately to a user’s affective states. In order to achieve the required on- line assessment of those affective states, we propose to extract features from physiological signals from the user (Blood Volume Pulse, Galvanic Skin Response, Skin Temperature and Pupil Diameter), which can be processed by learning pattern recognition systems to classify the user’s affective state. An initial implementation of our proposed system was set up to address the detection of “stress” states in a computer user. A computer-based “Paced Stroop Test” was designed to act as a stimulus to elicit emotional stress in the subject. Signal processing techniques were applied to the physiological signals monitored to extract features used by three learning algorithms: Naïve Bayes, Decision Tree and Support Vector Machine to classify relaxed vs. stressed states. Keywords: Stress Detection, Affective Computing, Physiological Sensing, Bio- signal Processing, Machine Learning. 1 Introduction New developments in human-computer interaction technology seek to broaden the character of the communication between the humans and computers. Picard [1] has pointed out the lack of responsivity to the affective states of users in contemporary human-computer interactions. Affective Computing concepts seek to empower computer systems to react appropriately to the affective states of the user. This, however, requires de development of methods to obtain reliable real-time assessment of the affective states experienced by the user. Several approaches for measuring affective states in the users have been tried, such as the identification of facial expressions, in isolation, or in combination with speech understanding and body gesture recognition [2]. Another approach for recognizing affect is through the monitoring of physiological signals [3]. Some previous attempts to recognize emotions from physiological changes have focused on variables that can be monitored