Handwritten Chinese trajectories prediction with an improved flat function-link neural networks and Kalman filter

This paper proposed an improved flat functional-link neural network (FFNN) to predict handwritten Chinese moving trajectories. To solve the prediction problem of a non-stationary time series, convectional neural networks need a lot of time and samples to train, where FFNN can solve this problem very well. Considering the structure of Chinese characters, the paper makes improvements for FFNN, and promising experimental results have been obtained. Furthermore a comparison is performed between the predictions of the Flat NN and a Kalman filter. Experiments suggest that the improved FFNN predictor works better for the prediction of trajectories of handwritten Chinese characters.

[1]  R. Mehra.  On the identification of variances and adaptive Kalman filtering , 1970 .

[2]  W. J. Hadden,et al.  A Comparison of , 1971 .

[3]  Pjw Rayner,et al.  A new connectionist model based on a non-linear adaptive filter , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[4]  Sheng Chen,et al.  Parallel recursive prediction error algorithm for training layered neural networks , 1990 .

[5]  Y. Takefuji,et al.  Functional-link net computing: theory, system architecture, and functionalities , 1992, Computer.

[6]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[7]  V. Ramamurti,et al.  A hybrid technique to enhance the performance of recurrent neural networks for time series prediction , 1993, IEEE International Conference on Neural Networks.

[8]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[9]  H. Johnson.  Relationship between user models in HCI and AI : Human-computer interaction , 1994 .

[10]  C. L. Philip Chen,et al.  A rapid supervised learning neural network for function interpolation and approximation , 1996, IEEE Trans. Neural Networks.

[11]  C. L. Philip Chen,et al.  A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[12]  Andreas Charitou,et al.  Comparative analysis of artificial neural network models: application in bankruptcy prediction , 1999 .

[13]  Andreas Charitou,et al.  ANNALS OF OPERATIONS RESEARCH , 2000 .

[14]  A.H. Sayed,et al.  Comparison of robust estimation and Kalman filtering applied to fingertip tracking in human-machine interfaces , 2001, Conference Record of Thirty-Fifth Asilomar Conference on Signals, Systems and Computers (Cat.No.01CH37256).

[15]  Ahmed Rubaai,et al.  Online training of parallel neural network estimators for control of induction motors , 2001 .

[16]  Pietro Perona,et al.  Visual Input for Pen-Based Computers , 2002, IEEE Trans. Pattern Anal. Mach. Intell..