Handwriting velocity modeling by sigmoid neural networks with Bayesian regularization

Writing is the language visual representation by a graphic signs system conventionally adopted by a community of people. The study of the handwriting process is an exploration of the properties of the biological system producing it and the main involved factors namely the nerve impulses generation, the pen displacement on a writing surface, etc. People with disabilities or suffering from various neurological diseases are facing so many difficulties resulting from problems located at the muscle stimuli or signals of the brain and which arise at the stage of writing. The handwriting velocity of a same writer or different writers varies according to different criteria: age, attitude, mood, writing surface, etc. Therefore, it is interesting to reconstruct an experimental basis records taking, as primary reference, the writing speed for different writers which would allow studying the global system during handwriting process. This paper deals with a new approach of the handwriting system modeling based on the velocity criterion through the exploitation of artificial neural networks and specifically the sigmoid neural networks as well as the Bayesian regularization principles.