ACDSA

Dr. Edison A. Roxas

University of Santo Tomas, Philippines

Education
Doctor of Philosophy in Electronics and Communications Engineering, De La Salle University – Manila, Philippines, 2018
Master of Science in Electronics and Communications Engineering, De La Salle University – Manila, Philippines, 2013
Bachelor of Science in Electronics and Communications Engineering, Technological Institute of the Philippines – Manila, Philippines, 1999

Research Interests:
Computer Vision, Data Science and Machine Learning, Digital Health, Intelligent Transport System, Smart and Precision Farming,

Program Leader:
iSULAT (Intelligent Stroke Utilization, Learning, Assessment and Testing): A Development of an Intelligent Quantitative Software-Based Handwriting Assessment and Testing System for Early Childhood Handwriting Evaluation
Project 1 – ISULAT WriteQuest: A Development of an Intelligent Quantitative Software-Based Children’s Handwriting Impairment Assessment with Gamification
Project 2 – ISULAT Sensory Patterns: AI-based Handwriting Analysis and Evaluation for Sensory Processing Difficulties

Title: An AI-Based Handwriting Analysis and Evaluation for Sensory Processing Difficulties

Abstract: Attention-Deficit/Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD) are neurodevelopmental conditions that significantly affect behavior, communication, motor coordination, and sensory processing. A frequently overlooked but critical concern among children with ADHD and ASD is Sensory Processing Difficulties (SPDs), which negatively impact daily functioning, academic performance, fine motor skills such as handwriting, and overall health by contributing to anxiety, fatigue, and behavioral dysregulation. SPDs typically manifest as hypersensitivity, hyposensitivity, or sensory-seeking behaviors, complicating the child’s ability to interpret and respond to sensory input. Current assessment tools while clinically validated, are often costly, time-consuming, and inaccessible, especially in low-resource communities. Thus, the study proposes the development of an alternative, intelligent, handwriting-based assessment system using a sensor-equipped pen to detect and quantify SPD characteristics. The system aims to provide a low-cost, accessible tool that integrates standard sensory metrics with handwriting analysis.