Segmentation of textured images using Gibbs random fields
Computer Vision, Graphics, and Image Processing
Genetic algorithms + data structures = evolution programs (2nd, extended ed.)
Genetic algorithms + data structures = evolution programs (2nd, extended ed.)
Neural network classification of remote-sensing data
Computers & Geosciences
Genetic Algorithms and Investment Strategies
Genetic Algorithms and Investment Strategies
Artificial Immune Systems: A New Computational Intelligence Paradigm
Artificial Immune Systems: A New Computational Intelligence Paradigm
T-detector maturation algorithm with overlap rate
WSEAS Transactions on Computers
Adaptive hybrid immune detector maturation algorithm
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part II
Hi-index | 0.00 |
With the epidemic application of geographic information systems retaining remotely sensed data as layers, the accuracy assessment of the map generated from any remotely sensed data has been even more crucial. In recent, data mining has been widely applied in many areas. It means the methodologies and tools for the efficient new knowledge discovery from databases. In this paper, a immune algorithms based mining approach to accuracy assessment is proposed for extracting the decision rules including the predictors, the corresponding inequality and threshold values simultaneously so as to building a decision-making model with maximum prediction accuracy. Early many studies of handling the satellite-derived land-cover classification problems used the statistical related techniques. As the land-cover classification is highly nonlinear in nature, it is hard to develop a comprehensive model using conventional statistical approaches. Recently, numerous studies have demonstrated that neural networks (NNs) are more reliable than the traditional statistical approaches. The usefulness of using NNs have been reported in literatures but the most obstacle is the in the building and using the model in which the classification rules are hard to be realized. We compared our results against commercial GIS software, and we show experimentally that the proposed rule extraction approach is promising for improving land-cover classification accuracy and enhancing the modeling simplicity. In particular, our approach is capable of extracting rules which can be developed as a computer model for classification of satellite-derived land-cover potential like expert systems.