Vassilis Athitsos               VLM Lab

Assessing Cognitive Skills in Children through Performance in Physical and Computer-based Tasks

picture 1 picture 2
picture 3 picture 4

Figure 1: A child performing a physical exercise, with results of skeletal tracking superimposed.

This project is conducted in collaboration with Professor Fillia Makedon at UTA, and Professors Morris Bell and Bruce Wexler at Yale. The project officially started in October 2016, and it is funded by NSF grants IIS-1565328 to UTA and IIS-1565310 to Yale. The goal is to develop automated methods for assessing cognitive skills in children, based on the children's performance in structured physical and computer-based tasks.

One key challenge in this project is developing human motion analysis algorithms that can assess how well children perform certain activities. Another key challenge is the design of data mining methods for discovering new knowledge about the role of physical exercise in cognitive training, and about correlations between individual metrics in physical and computer-based tasks. Since the start of the project, we have made several advances in addressing those challenges, as described in the publications listed at the end of this page.

One key outcome is the development of the ACTIVATE Test of Embodied Cognition (ATEC) by Dr. Bell. ATEC includes a sequence of physical exercises that can be used to assess the cognitive and neurological development of a child. ATEC also includes specifications on scoring the performance of children in these exercises. This 1-gigabyte slide presentation by Dr. Bell provides more information about ATEC. There is a shorter (1.37 MB) PDF version of this presentation, that does not include the videos.

At the same time, we have been developing computer vision and machine learning methods for analyzing the motion of children performing these exercises, and for providing automated scores. Research on those topics is ongoing. The following publications provide details of some of the outcomes we have achieved so far:


Vassilis Athitsos               VLM Lab