A research paper on detecting human mood using sensors in mobile devices from postdoctoral fellow Munirul Haque, Ph.D., in the laboratory of Ragib Hasan, Ph.D., assistant professor in the UAB Department of Computer and Information Sciences and founder of the SECuRE and Trustworthy Computing Lab (SECRETLab) at the University of Alabama at Birmingham, has been selected as the best paper at the Association for Computing Machinery’s 2013 International Conference on Research in Adaptive and Convergent Systems.
The paper, titled “Towards In Situ Affect Detection in Mobile Devices: A Multimodal Approach,” was one of just 73 papers out of 317 submitted that were accepted at the 2013 Research in Adaptive and Convergent Systems conference. Among the 73 papers accepted to the conference, Haque’s paper was selected for the Best Paper Award.
In this paper, Haque and his collaborators investigate affect detection in natural environment using sensors available in smartphones. They used a person’s facial expression and energy expenditure to classify that person’s affective state, or the human mood, by continuously capturing fine-grained accelerometer data for energy, and camera image for facial expression. The research found an important correlation between facial image and energy, which validates prior findings by another researcher in the field, James Russell, Ph.D., who first asserted that emotions are distributed in a two-dimensional circular space, containing arousal and valence dimensions.