Combining Evolutionary and Sequential Search Strategies for Unsupervised Feature Selection
The research presented in this paper aimed at development of a robust feature space exploration technique for unsupervised selection of its subspace for feature vectors classification. Experiments with synthetic and textured image data sets show that current sequential and evolutionary strategies are inefficient in the cases of large feature vector dimensions (reaching the order of 102) and multiple-class problems. Thus, the proposed approach utilizes the concept of hybrid genetic algorithm and adopts it for specific requirements of unsupervised learning.
KeywordsUnsupervised feature selection hybrid genetic algorithm texture analysis
Unable to display preview. Download preview PDF.
- 7.Morita, M., Sabourin, R., Bortolozzi, F., Suen, C.: Unsupervised feature selection using multi-objective genetic algorithms for handwritten word recognition. In: Seventh IEEE Conf. Document Analysis and Recognition, pp. 666–670 (2003)Google Scholar
- 10.Brodatz, P.: Textures. A Photographic Album for Artists and Designers. Dover, New York (1966)Google Scholar