J.A. Jacko (Ed.): Human-Computer Interaction, Part I, HCII 2009, LNCS 5610, pp. 169–175, 2009. © Springer-Verlag Berlin Heidelberg 2009 A Method to Monitor Operator Overloading Dvijesh Shastri, Ioannis Pavlidis, and Avinash Wesley Computational Physiology Lab, Department of Computer Science, University of Houston, Houston, TX, 77204 {dshastri,ipavlidis,awesley}@uh.edu Abstract. This paper describes research that aims to quantify stress levels of operators who perform multiple tasks. The proposed method is based on the thermal signature of the face. It measures physiological function from a stand- off distance and therefore, it can unobtrusively monitor a machine operator. The method was tested on 11 participants. The results show that multi-tasking ele- vates metabolism in the supraorbital area, which is an indirect indication of in- creased mental load. This local metabolic change alters heat dissipation and thus, it can be measured through thermal imaging. The methodology could serve as a benchmarking tool in scenarios where an operator’s divided attention may cause harmful outcomes. A classic example is the case of a vehicle driver who talks on the cell phone. This stress measurement method when combined with user performance metrics can delineate optimal operational envelopes. Keywords: Human-Machine Interaction, divided attention, stress, thermal imaging. 1 Introduction In many occasions, machine operators simultaneously perform more than one task. When a combination of overlapping events demands critical decisions and rapid ac- tions, they raise the operator’s alertness. If this persists, it develops to stress that over- loads the operator. Stress due to operator’s divided attention may lead to degradation of his/her performance. This work aimed to analyze stress-induced change in facial physiology during di- vided attention situations. The supraorbital thermal signature emerged as the physio- logical variable of interest, which can be measured through thermal imaging. In fact, thermal imaging based stress monitoring is an increasingly popular approach [1] [2] [3]. In contrast to probe based stress monitoring methods, it is totally unobtrusive [7] [8]. Although concurrent performance of multiple tasks is part of human life, insuffi- cient research has been done to understand its effect on human emotional states and performance. The purpose of this study is to develop an effective tool to gauge stress load of operators engaging in multi-tasking. The experimental design focused on cell- phone communication during driving simulation [9][10][11] and was tested on 11 participants. However, other task pairs could have been chosen, such as reading in the presence of background distractions.