Automated Learning Disabilities Identification at Early Education Level (T-0712) (MFN 5100)

Abstract

Students’ at all educational levels can suffer from many diseases and disorders that may hinder their carrier progression. Dyslexia is one such disorder that disrupts or delays development of mental map which is required to create prolonged understanding of fundamental concepts. There is a significant research work on such disorders in the medical science as well as in the psychological sciences. However, software engineering perspective as well as a study to see effectiveness for an automated process is missing. We have proposed an automated process supported by our handwriting analysis software identifying learning disorder at early education level. Students at early education level can be identified or screened out from their class assessment in an automated manner without them noticing providing a direct intervention method. The purpose of this research is to help diagnosis of this disease (intensity/level) in students through analysis of their handwriting so that they can be helped to overcome this problem. We have developed a software “Automated Learning Disorder Identification at Early Education Level” through class work analysis.