On the use of ARMAX approach for handwriting system modelization

Modeling handwriting system allows studying movements of the hand and its control signals as integrated electromyographic signals (IEMG) which are detected during muscle contraction involved in the act of writing. Reconstruction of muscle stimuli from written application can have a very important impact especially for the design of support systems for the disabled. In this paper, we propose a new mathematical model to estimate this muscle signal based on identification parameters of a discrete time system, using Auto-Regressive Average with eXternal inputs (ARMAX) models and the Recursive Least Squares algorithm (RLS).