New framework for hyperspectral band selection using modified wind-driven optimization algorithm
- 26 April 2019
- journal article
- research article
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 40 (20) , 7852-7873
Abstract
The presence of irrelevant and highly correlated spectral bands significantly reduces the classification accuracy of the hyperspectral images. Therefore, the selection of suitable bands from the set of available spectral bands plays a crucial role in improving the classification accuracy. In this paper, a novel band selection approach is proposed based on nature inspired meta-heuristic algorithm to mitigate the effect of curse of dimensionality. Wind-driven optimization (WDO), among other meta-heuristic algorithms, has proven to be more efficient in solving global optimization problems. However, WDO is prone to premature convergence when solving the global optimization problem due to loss of diversity of air particles. Therefore, a modified WDO (MWDO) is proposed for band selection, which is able to avoid the premature convergence and control the exploration–exploitation search trade-off. Finally, in order to further improve the performance of the classification, the selected bands are fed into the deep learning architecture to extract the high-level useful features. The experiments are carried on three widely used standard datasets such as Indian Pines, Pavia University, and Salinas. The experimental results show that the proposed approach selects an optimal subset of bands with good convergence characteristics and provide high classification accuracy with fewer bands in comparison with other approaches. The proposed method achieves an overall accuracy of 93.26%, 94.76%, and 95.96% for Indian Pines, Pavia University, and Salinas datasets, respectively.Keywords
This publication has 31 references indexed in Scilit:
- Gray Wolf Optimizer for hyperspectral band selectionApplied Soft Computing, 2016
- Unsupervised Band Selection Based on Evolutionary Multiobjective Optimization for Hyperspectral ImagesIEEE Transactions on Geoscience and Remote Sensing, 2015
- Deep Learning-Based Classification of Hyperspectral DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Optimized Hyperspectral Band Selection Using Particle Swarm OptimizationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Hyperspectral Imaging in the Medical Field: Present and FutureApplied Spectroscopy Reviews, 2013
- Self-adaptive differential evolution for feature selection in hyperspectral image dataApplied Soft Computing, 2013
- Recent advances in hyperspectral image processingGeo-spatial Information Science, 2012
- An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machineKnowledge-Based Systems, 2011
- A new optimizer using particle swarm theory2002
- On the mean accuracy of statistical pattern recognizersIEEE Transactions on Information Theory, 1968