A New Design of DSPACE Microcontroller-based Real-Time Digital Predictive Controller for Grid Connected Photovoltaic Power Conditioning System

Abstract: Object recognition system (ORS) is divided into two parts namely, feature extraction and classification. Feature Extraction part consists rotation, translation and scale (RTS) invariant features. These features are used to train fuzzy min-max neural network with compensatory neuron architecture (FMCN). MPEG7 shape database is used for experimentation. Fuzzy min-max classification neural network (FMN) proposed by Simpson uses the contraction method to eliminate the overlap. FMCN eliminate the contraction method, since it is found to be erroneous. The concept compensatory neurons are inspired from the reflex system of human brain which takes over the control in hazardous condition. Compensatory neurons are getting activated when the testing sample falls in the overlapped regions of different classes. The performance of FMCN is superior than FMN with respect to recognition rate.

Keywords: Object recognition, RTS, Neural network, FMN, FMCN.