Neural computing: theory and practice
Neural computing: theory and practice
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Neural networks in designing fuzzy systems for real world applications
Fuzzy Sets and Systems
Computer Processing of Remotely-Sensed Images: An Introduction
Computer Processing of Remotely-Sensed Images: An Introduction
A soft computing approach for obtaining transition regions in satellite images
ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing
| Hi-index | 0.00 |
We present the results of a study of performance of neuro-fuzzy method derived from a generic model of a three-layer fuzzy perceptron, and compare it with conventional statistical and artificial intelligent methods: maximum likelihood and neural network. The land cover classification is performed using multispectral IKONOS satellite data of the part of Daejeon City in Korea. Land cover classification results of satellite image data are usually summarized as confusion matrices. The results of the classification and method comparison show that the neuro-fuzzy method is the most accurate. Thus, the neuro-fuzzy model is more suitable for classifying a mixed-composition area such as the natural environment of the Korean peninsula. And the neuro-fuzzy classifier is superior in its suppression of classification errors for mixed land cover signatures. The classified land cover information is important when the results of the classification are integrated into a geographical information system.