Skip to main content

Robotics and Autonomous Systems Lab
at Vanderbilt

Physiological Data Processing and Physiology-based Emotion Recognition

Personnel: Dayi Bian, Esube Bekele, Zachary Warren, & Nilanjan Sarkar.

Goals/Objectives:

  1. Explore physiological response differences when people exposed to various stimuli and use physiological features to build emotional recognition models

Outline:

The physiological signals were collected using the Biopac MP150 physiological data acquisition system with a sampling rate of 1000 Hz. The acquired physiological signals were broadly classified as cardiovascular activities including electrocardiogram (ECG), photoplethysmogram (PPG); electrodermal activities (EDA) including tonic and phasic responses from galvanic skin response (GSR); electromyogram (EMG) activities from Corrugator Supercilii, Zygomaticus Major, and Upper Trapezius muscles; respiration and skin temperature.

The physiological signals were used in several projects for different purposes. Generally, we processed physiological data in two ways: 1) extract features and use standard statistical analysis method to explore differences among different conditions (e.g., pre vs. post, Autism Spectrum Disorder (ASD) group vs. Typically Developing (TD) group, etc.); 2) use extracted features to build machine learning models for predicting different emotion states (e.g., engagement, anxiety, etc.).

Publications:

  1. D. Bian, Z. Zheng, A. Swanson, A. Weitlauf, Z. Warren, and N. Sarkar, “Physiology-based Affect Recognition during Driving in Virtual Environment for Autism Intervention,” 2nd International Conference on Physiological Computing Systems, 2015.
  2. L. Zhang, J. Wade, D. Bian, J. Fan, A. Swanson, A. Weitlauf, Z. Warren, and N. Sarkar, “Cognitive load measurement in a Virtual Reality-based Driving System for Autism Intervention,” IEEE Transactions on Affective Computing, 2016.
  3. D. Bian, J. Wade, Z. Warren, and N. Sarkar, “Online Engagement Detection and Task Adaptation in a Virtual Reality Based Driving Simulator for Autism Intervention,” in International Conference on Universal Access in Human-Computer Interaction, 2016, pp. 538-547.
  4. E. Bekele, J. Wade, D. Bian, J. Fan, A. Swanson, Z. Warren, and N. Sarkar, “Multimodal adaptive social interaction in virtual environment (MASI-VR) for children with Autism spectrum disorders (ASD),” in Virtual Reality (VR), 2016 IEEE, 2016, pp. 121-130.