Neural network approach to multidimensional data classification via clustering
Roman Krakovský, Radoslav Forgáč · 2011
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.