UTA investigators use advanced computational approach to assess learning difficulties in children

University of Texas at Arlington researchers are using an advanced computational approach or artificial intelligence to help experts assess learning difficulties in children very early in their lives.

Professor Fillia Makedon and Associate Professor Vassilis Athitsos, both in the College of Engineering's Department of Computer Science and Engineering, received $1.27 million of a total $2.7 million National Science Foundation grant for the project. Yale University will receive the remainder of the grant.

This large, highly competitive NSF grant is awarded because of its huge potential impact in understanding and learning how to enhance the cognitive abilities of children.

Untreated cognitive disorders in children are a widely recognized challenging problem. Center for Disease Control statistics show that about 11 percent of American children ages 4 to 17 have Attention-Deficit/Hyperactivity Disorder. That is an increase of 42 percent of ADHD in just the last eight years, according to the CDC.

Makedon, who is the principal investigator and a Jenkins-Garrett Distinguished Professor, said the project uses the latest methods in computer vision, machine learning and data mining to assess several children while they are performing certain physical and computer exercises that are designed to produce executive function skills, and involve attention, decision-making and managing emotions. The data collected is then analyzed to generate recommendations for the best type of intervention.

"We believe that the proposed computational methods will help provide quantifiable early diagnosis and allow us to monitor progress over time. In particular, it will help children overcome learning difficulties and lead them to healthy and productive lives. Working with top neuroscientists and psychology experts, our aim is to develop new computer methods to help discover problems with the underlying neurocognitive processes," Makedon said. "The goal is to design a low-cost, easy-to-use systems that can be implemented in special education practices world-wide."

Makedon said that the proposed system builds upon many years of expertise and a track record of a strong interdisciplinary team.

"It also builds upon a large existing education program that was designed by top psychiatry experts, our Yale collaborators," she said.

During the past five years, the Makedon and Athitsos team has received three other large NSF grants which have built the computational foundation for this award.

At the heart of the project is a computer vision recognition and machine learning system that assesses children while they're performing certain physical and computer exercises. The data collected is analyzed to recognize patterns of inattention, hyperactivity or acting impulsively, two features common to executive function disorders, including ADHD. Monitoring and analyzing how children are behaving during such game-like exercises can be used to build a knowledge base that will enable health-care professionals to apply predictive methods and make recommendations for effective intervention.

Hong Jiang, chair of the Computer Science and Engineering Department, said this research is yet another example of the power of computer science in addressing real-world problems to empower the experts in making targeted decisions and providing for personalized intervention.

"Dr. Makedon is leading breakthrough research, building human-centric innovations that have wide applicability to improving the quality of life at home or the workplace, especially for people with special physical or cognitive needs," Jiang said. "This award now opens the road for larger funding efforts in areas that use evidence-based, data-driven approaches to improve the human condition, a priority of UTA's Strategic Plan 2020: Bold Solutions | Global Impact."