Business Intelligence

Comparitive Study of Probabilistic Neural Network and Radial Basis Functional Link Neural Network in Time Series Data Mining

Download Now Free registration required

Executive Summary

This paper proposes a comparative analysis between Radial Basis Functional Link Network (RBFLN) - a combination of radial basis functions with the random vector functional link nets with Probabilistic Neural Network (PNN).The novel Stransform based neural classifier scheme is used for time series data mining of power quality events occurring due to power signal disturbances. The extracted features from Discrete Wavelet Transform (DWT) and S-Transform (ST) are used in Probabilistic Neural Network (PNN), and proposed radial basis functional link network for pattern classification and data mining which can be used for subsequent knowledge discovery.

  • Format: PDF
  • Size: 488.18 KB