Aniket Bera and Dinesh Manocha Receive the 2020 Brain and Behavior Initiative Seed Grant
Assistant Research Professor Aniket Bera and Paul Chrisman Iribe Professor of Computer Science, Dinesh Manocha recently received a grant from the UMD Brain and Behavior Initiative (BBI) for the project titled “Learning Age and Gender Adaptive Gait Motor Control-based Emotion Using Deep Neural Networks and Affective Modeling. ” The project seeks to develop automated AI-based techniques for perceiving human emotions based on kinematic and kinetic variables—that is, based on both the contextual and intrinsic qualities of human motion. The proposed research will examine the role of age and gender on gait-based emotion recognition using deep learning.
The project was one of six interdisciplinary projects that received BBI seed funding this year.
The proposed study is focused towards identifying and classifying human emotion based on a person’s gait and is in alignment with the mission of UMD’s new President, Dr. Darryll Pines, to “plan for a different and more equitable future [and to] play a transformative role in tackling the issues facing our global community and work to improve the health and well-being of people in the state of Maryland and around the world.”
The study aims to develop an automated artificial intelligence based technique for perceiving human emotions based on kinematic and kinetic variables—that is, based on both the contextual and intrinsic qualities of human motion.
“With this project, we want to explore how aging and depression affect body language and kinematic expressions and help understand and model the relationship between mental health, emotional well-being, and health disparity based on gender in the elderly,” said Bera.
The proposed research will examine the role of age and gender on gait-based emotion recognition using deep learning. After collecting full-body gaits across age and gender in a motion-capture lab.
Bera and Manocha will collaborate with Jae Kun Shim, a professor of kinesiology who specializes in neuromechanics, to develop an automated, artificial intelligence-based technique for perceiving human emotions.
The Department welcomes comments, suggestions and corrections. Send email to editor [-at-] cs [dot] umd [dot] edu.