## Abstract

A recently proposed neural network architecture, the parallel consensual neural network (PCNN), is applied in classification of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks and the output responses from the stage networks are then weighted and combined to make a decision. In this paper a new approach is proposed to compute the input transforms for the PCNN. This approach uses wavelet packets. The experimental results obtained with the proposed approach show that the wavelet packet PCNN outperforms a conjugate-gradient backpropagation network and conventional statistical methods in terms of overall classification accuracy.

Original language | English |
---|---|

Pages | 5-13 |

Number of pages | 9 |

Publication status | Published - 1995 |

Event | Proceedings of the 1995 Artificial Neural Networks in Engineering, ANNIE'95 - St.Louis, MO, USA Duration: 12 Nov 1995 → 15 Nov 1995 |

### Conference

Conference | Proceedings of the 1995 Artificial Neural Networks in Engineering, ANNIE'95 |
---|---|

City | St.Louis, MO, USA |

Period | 12/11/95 → 15/11/95 |