Optimal Band Selection Using Evolutionary Machine Learning to Improve the Accuracy of Hyper-spectral Images Classification: a Novel Migration-Based Particle Swarm Optimization

In the domain of real-world concept learning, feature selection plays a crucial role in accelerating learning processes and enhancing the quality of classification concepts, particularly in remote sensing image classification. Traditional methods often exhibit weaknesses such as instability, sensitivity to noise, and a lack of consideration for feature dependencies when selecting informative spectral features from hyper-spectral (HS) images. Recent studies have recommended the utilization of meta-heuristic algorithms to address these limitations. However, most of these approaches overlook the correlation between spectral bands. To tackle these challenges, we propose a novel migration-based particle swarm optimization (MBPSO) algorithm that surpasses previous methods in terms of exploitation and exploration and considers spectral band correlation to prevent the inclusion of unnecessary bands. The variance-based J1 criteria are employed as the fitness function for MBPSO, while a support vector machine (SVM) is utilized as the classifier. To evaluate the performance of our proposed method against other optimization algorithms, we conducted experiments using four HS datasets, namely Indian Pine, Pavia University, Salinas, and Washington Mall. Numerical evaluations encompassing class accuracy, overall accuracy, kappa coefficient, execution time, stability, Wilcoxon test, and convergence rate were performed. The results indicate that our proposed algorithm achieves superior numerical outcomes compared to other algorithms, while requiring fewer features to attain higher accuracy. The algorithm’s higher speed, reduced computational time, and avoidance of additional features in the solution can be attributed to the presence of the conditional mutation operator within the MBPSO algorithm.