Classification of Multi-spectral/Hyperspectral Data using Genetic Programming and Error-correcting Output Codes

@inproceedings{He2006, abstract = {Genetic programming (GP) and error-correcting output codes (ECOC) are combined to develop a new classification method (GP-ECOC) for the multi-class problem solving in this paper. Some additional improvements on the algorithm, modified codeword matrix and group division before classification, are also proposed to settle several existing problems in multi-spectral and hyperspectral data classification. Experimental tests using both multi-spectral and hyperspectral data are carried out for verification and illustration. It is observed from the obtained results that the classification precision with the newly proposed method is greatly enhanced compared with some existing methods using GP, and the proposed improvements are also effective. The algorithm of GP-ECOC and its improved versions can also be run on multi-terminals, which saves computational cost effectively}, author = {He, Mingyi and Zhang, Yifan and Xie, Yuzhen and Liang, Na and Wen, Changyun }, booktitle = {Industrial Electronics and Applications, 2006 1ST IEEE Conference on}, citeulike-article-id = {2762304}, doi = {http://dx.doi.org/10.1109/ICIEA.2006.257153}, journal = {Industrial Electronics and Applications, 2006 1ST IEEE Conference on}, pages = {1--6}, posted-at = {2008-05-06 20:06:14}, priority = {2}, title = {Classification of Multi-spectral/Hyperspectral Data using Genetic Programming and Error-correcting Output Codes}, url = {http://dx.doi.org/10.1109/ICIEA.2006.257153}, year = {2006} }

TY - CONF ID - He2006 L3 - citeulike-article-id:2762304 N2 - Genetic programming (GP) and error-correcting output codes (ECOC) are combined to develop a new classification method (GP-ECOC) for the multi-class problem solving in this paper. Some additional improvements on the algorithm, modified codeword matrix and group division before classification, are also proposed to settle several existing problems in multi-spectral and hyperspectral data classification. Experimental tests using both multi-spectral and hyperspectral data are carried out for verification and illustration. It is observed from the obtained results that the classification precision with the newly proposed method is greatly enhanced compared with some existing methods using GP, and the proposed improvements are also effective. The algorithm of GP-ECOC and its improved versions can also be run on multi-terminals, which saves computational cost effectively JF - Industrial Electronics and Applications, 2006 1ST IEEE Conference on EP - 6 TI - Classification of Multi-spectral/Hyperspectral Data using Genetic Programming and Error-correcting Output Codes T2 - Industrial Electronics and Applications, 2006 1ST IEEE Conference on SP - 1 AU - He, Mingyi AU - Zhang, Yifan AU - Xie, Yuzhen AU - Liang, Na AU - Wen, Changyun PY - 2006/// UR - http://dx.doi.org/10.1109/ICIEA.2006.257153 ER -