R. Ebrahimpour, S. Sarhangi, F. Sharifizadeh,
Volume 7, Issue 4 (12-2011)
Abstract
This paper presents the results of Persian handwritten word recognition based on Mixture of Experts technique. In the basic form of ME the problem space is automatically divided into several subspaces for the experts, and the outputs of experts are combined by a gating network. In our proposed model, we used Mixture of Experts Multi Layered Perceptrons with Momentum term, in the classification Phase. We produce three different Mixture of Experts structure. Experimental result for proposed method show an error rate reduction of 6.42 % compare to the mixture of MLPs experts. Comparison with some of the most related methods indicates that the proposed model yields excellent recognition rate in handwritten word recognition.
M. R. Ramezani-Al, A. Vahidian Kamyad, N. Pariz,
Volume 11, Issue 2 (6-2015)
Abstract
Uncertain switched linear systems are known as an important class of control systems. Performance of these systems is affected by uncertainties and its stabilization is a main concern of recent studies. Existing work on stabilization of these systems only provides asymptotical stabilization via designing switching strategy and state-feedback controller. In this paper, a new switching strategy and a state-feedback control law are designed to exponentially stabilize Uncertain Discrete-Time Switched Linear Systems (UDSLS), considering a given infinite-horizon cost function. Our design procedure consists of three steps. First, we generalize the exponential stabilization theorem of nonlinear systems to UDSLS. Second, based on the Common Lyapunov Function technique, a new stabilizing switching strategy is presented. Third, a sufficient condition on the existence of state-feedback controller is provided in the form of Linear Matrix Inequality. Besides, convergence rate is obtained and the upper bound of the cost is calculated. Finally, effectiveness of the proposed method is verified via numerical example.
