Assessing handwriting task difficulty levels through kinematic features: a deep-learning approach

Introduction: Handwriting is a complex task that requires coordination of motor, sensory, cognitive, memory, and linguistic skills to master. The extent these processes are involved depends on the complexity handwriting task. Evaluating difficulty challenging problem since it relies subjective judgment experts. Methods: In this paper, we propose machine learning approach for evaluating level tasks. We two convolutional neural network (CNN) models single- multilabel classification where single-label based mean expert evaluation while predicts distribution experts’ assessment. trained with dataset containing 117 spatio-temporal features from stylus hand kinematics, which recorded all letters Arabic alphabet. Results: While achieve decent accuracy (96% 88% respectively) using features, kinematics do not significantly influence performance models. Discussion: proposed capable extracting meaningful samples predicting their levels accurately. has potential be used personalize tools provide automatic quality handwriting.