Learn More
This paper presents a quantum-based algorithm for evolving artificial neural networks (ANNs). The aim is to design an ANN with few connections and high classification performance by simultaneously optimizing the network structure and the connection weights. Unlike most previous studies, the proposed algorithm uses quantum bit representation to codify the(More)
In this paper the non-stationary power signal prediction by using quantum neural network (QNY) is proposed. The signals with fuzziness are expected to be classged clearly for enhancing the learning eflciency of neural network due to the hidden units with various g,-aded levels in QNN structure. For a comparison, all experLwents are also performed by using(More)
This paper proposed the design of T-S fuzzy control for magnetic levitation systems. The maglev systems are linearized at the equilibrium point first. Then the error state equations are derived and the proportional integral (PI) controller is applied to eliminate the steady-state tracking error. The nonlinear dynamic equations of the magnetic levitation(More)
This paper presents a novel evolutionary algorithm based on a hybrid of Taguchi method and particle swarm optimization (PSO), and thus is called HTPSO. First, the nonlinear nano-positioning system is approximated by the TakagiSugeno (T-S) fuzzy model. Second, the parallel distributed compensation (PDC) is designed to control the piezoelectric system. Last,(More)