The paper analyses disadvantages of standard feature generation and their standardization for image recognition by Pulse Coupled Neural Network (PCNN). The aim of research was to propose a new form of feature value calculation that improves significantly the quality of generated features. It is part of algorithm for feature generation by optimized PCNN.
The paper aims to present multidimensional data clustering using neural networks. Data processing in the multidimensional space requires considerable time and high compute complexity in general, therefore it is recommended to transform the data processing from high dimensional space into feature space with lower dimension. Presented approach uses the neural network model that consists of optimized model Pulse Coupled Neural Network (OM-PCNN) for dimension reduction and Projective Adaptive Resonance Theory (PART) for clustering. The proposed model of these two neural networks introduces the effective system for classification of the multidimensional data via clustering.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.