Hybrid Validation of Handwriting Process Modelling

Handwriting process is one of the most complex processes of our biological repertory. Modelling such process remains difficult to implement. Several approaches were proposed in the literature. However, the validation results of these models remain less or more satisfactory. This paper deals with unconventional and conventional handwriting process characterization approaches based on the use of soft computing techniques namely the Radial Basis Function (RBF) neural networks and the use of mathematical models based on the recursive least squares algorithm. Modelling handwriting system as well as the hybrid validation of the proposed models constitutes the main contribution of this paper. The obtained simulation results of the hybrid validation models show a satisfactory agreement between responses of the developed models and the experimental Electromyographic signals (EMG) data then the efficiency of the proposed approaches. Applying the study is very interesting to elaborate a helpful system to those who suffer from physical handicaps.

[1]  Mohamed Benrejeb,et al.  Sur l’étude du processus d'écriture à la main. Approches classiques et non conventionnelles , 2005 .

[2]  Mohamed Benrejeb,et al.  RBF neural networks for handwriting process modelling , 2011, 2011 International Conference of Soft Computing and Pattern Recognition (SoCPaR).

[3]  Mohamed Benrejeb,et al.  On New RBF Neural Network Construction Algorithm for Classification , 2009 .

[4]  M Yasuhara,et al.  [Experimental studies of handwriting process]. , 1974, Iyo denshi to seitai kogaku. Japanese journal of medical electronics and biological engineering.

[5]  John S. MacDonald,et al.  Experimental studies of handwriting signals. , 1966 .

[6]  Frédéric de Coulon,et al.  Théorie et traitement des signaux , 1984 .

[7]  Nezha Maamri-Trigeassou.  Identification et commande des systèmes à représentation continue par la méthode des moments , 1991 .

[8]  J. Strackee,et al.  A handwriting simulator. , 1962, Physics in medicine and biology.

[9]  Mohamed Benrejeb.  Les réseaux de neurones. , 2006 .

[10]  Zheng Rong Yang,et al.  A novel radial basis function neural network for discriminant analysis , 2006, IEEE Transactions on Neural Networks.

[11]  Shimon Edelman,et al.  A model of handwriting , 2004, Biological Cybernetics.

[12]  Mohamed Benrejeb,et al.  Parametric identification of handwriting system based on RLS algorithm , 2011, 2011 11th International Conference on Control, Automation and Systems.

[13]  Panos J. Antsaklis,et al.  The dependence identification neural network construction algorithm , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).