RESUMEN
Handwriting learning disabilities, such as dysgraphia, have a serious negative impact on children's academic results, daily life and overall well-being. Early detection of dysgraphia facilitates an early start of targeted intervention. Several studies have investigated dysgraphia detection using machine learning algorithms with a digital tablet. However, these studies deployed classical machine learning algorithms with manual feature extraction and selection as well as binary classification: either dysgraphia or no dysgraphia. In this work, we investigated the fine grading of handwriting capabilities by predicting the SEMS score (between 0 and 12) with deep learning. Our approach provided a root-mean-square error of less than 1 with automatic instead of manual feature extraction and selection. Furthermore, the SensoGrip smart pen SensoGrip was used, i.e., a pen equipped with sensors to capture handwriting dynamics, instead of a tablet, enabling writing evaluation in more realistic scenarios.
