Feature Selection for Hyperspectral Data Classification Using Double Parallel Feedforward Neural Networks
Double parallel feedforward neural network (DPFNN) based approach is proposed for dimensionality reduction, which is one of very significant problems in multi- and hyperspectral image processing and is of high potential value in lunar and Mars exploration, new earth observation system, and biomedical engineering etc. Instead of using sequential search like most feature selection methods based on neural network (NN), the new approach adopts feature weighting strategy to cut down the computational cost significantly. DPFNN is trained by a mean square error function with regulation terms which can improve the generation performance and classification accuracy. Four experiments are carried out to assesses the performance of DPFNN selector for high-dimensional data classification. The first three experiments with the benchmark data sets are designed to make comparison between DPFNN selector and some NN based selectors. In the fourth experiment, hyperspectral data, that is an airborne visible/infrared imaging spectrometer (AVIRIS) data set, is used to compare DPFNN selector with widely used forward sequential search methods using the Maximum Likelihood classifier (MLC) as criterion. Experiments show the effectiveness of the new feature selection method based on DPFNNs.
KeywordsFeature Selection Hide Neuron Feature Subset Feature Selection Method Hyperspectral Data
Unable to display preview. Download preview PDF.
- 1.Hughes, G.F.: On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inform. Theory 14 (1968)Google Scholar
- 3.Swain, P., King, R.: Two effective feature selection criteria for multispectral remote sensing. In: Proceedings of the 1st International Joint Conference on Pattern Recognition, Washington, DC, pp. 536–540 (1973)Google Scholar
- 5.Sheffer, D., Ultchin, Y.: Comparison of band selection results using different class separation measures in various day and night conditions. In: Proc. SPIE, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery IX, vol. 5093, pp. 452–461 (2003)Google Scholar
- 8.Das, S.: Filters, wrappers and a boosting-based hybrid for feature selection. In: Proc. 18th International Conference on Machine Learning, pp. 74–81 (2001)Google Scholar
- 12.Kavzoglu, T., Mather, P.M.: The use of feature selection techniques in the context of artificial neural networks. In: Proceedings of the 26th Annual Conference of the Remote Sensing Society, Leicester, UK, (2000)Google Scholar
- 16.Fu, X.J., Wang, L.P.: A ga-based novel rbf classifier with class-dependent features. In: Proceedings of the 2002 Congress on Evolutionary Computation CEC 2002, vol. 2, pp. 1890–1894. IEEE Press, Los Alamitos (2002)Google Scholar
- 20.He, M.: Theory, application and related problems of double parallel feedforward neural networks. PhD thesis, Xidian University, Xi’an (1993)Google Scholar
- 21.He, M., Bao, Z.: Neural network and information processing system: limited precision design theory. Northwestern Polytechnical University publisher, Xi’an (1998)Google Scholar
- 22.He, M., Xia, J.: High dimensional multispectral image fusion: classification by neural network. In: Proc. SPIE, Image Processing and Pattern Recognition in Remote Sensing, vol. 4898, pp. 36–43 (2003)Google Scholar
- 23.He, M.: Multispectral image processing (invited lecture). IEEE Singapore Section, Singapore (2004)Google Scholar