An artificial neural network (ANN) based software package for classification of remotely sensed data
| Autor: | K. K. Mohanty, Tapan Majumdar |
|---|---|
| Rok vydání: | 1996 |
| Předmět: |
Artificial neural network
business.industry Computer science Computer Science::Neural and Evolutionary Computation Pattern recognition Spectral bands computer.software_genre Software package ComputingMethodologies_PATTERNRECOGNITION Multilayer perceptron Learning rule Feature (machine learning) Artificial intelligence Data mining Computers in Earth Sciences business computer Information Systems |
| Zdroj: | Computers & Geosciences. 22:81-87 |
| ISSN: | 0098-3004 |
| DOI: | 10.1016/0098-3004(95)00059-3 |
| Popis: | This paper presents a package of C programs for classification of remotely sensed data using an artificial neural network (ANN) approach. The ANN used is a multilayer perceptron trained through the generalized delta learning rule. The software package is generalized in nature and can handle any number of input units (spectral bands), output units (feature classes) and hidden layers. Different numbers of hidden neurons also can be considered in various hidden layers. An application of the software package for classification of IRS-1A LISS-I images also has been demonstrated. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect