Abstract
The issue of band selection is extremely important in dealing with the plague of dimensionality in hyperspectral images. This study offers a hybrid band selection strategy based on the split-and-merge concept. This novel technique provides suitable band subgroups based on entropy and mutual information utilizing a fuzzy rule-based system without dismissing the real relevance of the band information. Then, using ant colony optimization, it finds the most promising hyperspectral bands from these subsets. On three prominent hyperspectral image data sets, four state-of-the-art techniques are compared with the suggested method to assess the importance of the proposed band selection strategy. In terms of kappa coefficient and overall accuracy, this approach outperforms others significantly.










Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Aviris—airborne visible/infrared imaging spectrometer [online]. http://aviris.jpl.nasa.gov/
Chang CI, Du Q, Sun TL, Althouse MLG (1999) A joint band prioritization and band decorrelation approach to band selection for hyperspectral image classification. IEEE Trans Geosci Remote Sens 37(6):2631–2641
Lashkia G, Anthony L (2004) Relevant, irredundant feature selection and noisy example elimination. IEEE Trans Syst Man Cybern B Cybern 34(2):888–897
Shannon E (1948) A mathematical theory of communication. Bell Syst Tech J 27(3):379–423
Huang R, He M (2005) Band selection based on feature weighting for classification of hyperspectral data. IEEE Geosci Remote Sens Lett 2(2):156–159
Hazra J, Dutta ARCP (2017) A hybrid approach for band selection of hyperspectral images. In: Hybrid intelligence for image analysis and understanding. Wiley. Chap. 11, pp 263–282
Zhang L, Zhong BHJGY (2007) Dimensionality reduction based on clonal selection for hyperspectral imagery. IEEE Geosci Remote Sens Lett 45(12):4172–4186
Feng J, Jiao XZLC, Sun T (2014) Hyperspectral band selection based on trivariate mutual information and clonal selection. IEEE Trans Geosci Remote Sens 52(7):4092–4105
Patra S, Prahlad Modi LB (2015) Hyperspectral band selection based on rough set. IEEE Trans Geosci AND Remote Sens 53(10):5495–5503
Jia S, Guihua Tang JZQL (2016) A novel ranking-based clustering approach for hyperspectral band selection. IEEE Trans Geosci AND Remote Sens 54(1):88–102
Habermann M, Fremont V, Shiguemori EH (2019) Supervised band selection in hyperspectral images using single-layer neural networks. Int J Remote Sens:1–12
Bajcsy P, Groves P (2004) Methodology for hyperspectral band selection. Photogramm Eng Remote Sens 70:793–802
Tan K, Du P (2011) Combined multi-kernel support vector machine and wavelet analysis for hyperspectral remote sensing image classification. Chin Opt Lett 9(1):11003–11006
Du Q, Yang H (2008) Similarity-based unsupervised band selection for hyperspectral image analysis. IEEE Geosci Remote Sens Lett 5(4):564–568
Yang H, D Q, Chen G (2011) Unsupervised hyperspectral band selection using graphics processing units. IEEE J Sel Top Appl Earth Observ Remote Sens 4(3):660–668
Cariou C, Chehdi SLMK (2011) Bandclust: an unsupervised band reduction method for hyperspectral remote sensing. IEEE Geosci Remote Sens Lett 8(3):565–569
Lei L, Prasad JEFS, Bruce LM (2012) Locality preserving dimensionality reduction and classification for hyperspectral image analysis. IEEE Trans Geosci Remote Sens 50(4):1185–1198
Agarwal A, El-Ghazawi HEAT, Le-Moigne J (2007) Efficient hierarchical-pca dimension reduction for hyperspectral imagery. Proc IEEE Int Symp Signal Process Inf Technol: 353–356
Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(22):2323–2326
Chang CI, Wang S (2006) Constrained band selection for hyperspectral imagery. IEEE Trans Geosci Remote Sens 44(6):1575–1585
Martinez-Uso A, Pla JMSF, Garcia-Sevilla P (2007) Clustering based hyperspectral band selection using information measures. IEEE Trans Geosci Remote Sens 45(12):4158–4171
Martinez-Uso A, Pla JMSF, Garcia-Sevilla P (2012) Clustering based hyperspectral band selection using information measures. IEEE Trans Geosci Remote Sens 5(2):531–543
Mitra P, C M, Pal, S K (2002) Unsupervised feature selection using feature similarity. IEEE Trans Pattern Anal Mach Intell 24(3):301–312
Ma JP, Zheng ZB, Tong QX, Zheng LF (2003) An application of genetic algorithms on band selection for hyperspectral image classification. In: Proceedings of the 2nd international conference on machine learning and cybernetics, pp 2810–2813
Yu S, De Backer S, Scheunders P (2002) Genetic feature selection combined with composite fuzzy nearest neighbour classifiers for hyperspectral satellite imagery. Pattern Recogn Lett: 183–190
Zhou S, Zhang JP, Su BK (2009) Feature selection and classification based on ant colony algorithm for hyperspectral remote sensing images. In: 2nd international congress on image and signal processing, CISP ’09, pp 1–4
Firpi HA, Goodman E (2004) Swarmed feature selection. In: Proceedings of the 33rd applied imagery pattern recognition workshop (AIPR’04), pp 112–118
Ding S, Chen L (2009) Classification of hyperspectral remote sensing images with support vector machines and particle swarm optimization. In: Proceedings of the international conference on information engineering and computer science, pp 1–5
Huang R, Li X (2008) Band selection based on evolution algorithm and sequential search for hyperspectral classification. In: Proceedings of the international conference on audio, language and image processing(ICALIP’08), pp 1270–1273
Samadzadegan F, Partovi T (2010) Feature selection based on ant colony algorithm for hyperspectral remote sensing images. In: 2010 2nd workshop on hyperspectral image and signal processing: evolution in remote sensing (WHISPERS), pp 1–4
Liu X, Yu C, Cai Z (2010) Differential evolution based band selection in hyperspectral data classification. In: Proceedings of the international symposium on intelligence computation and applications (ISICA’10), pp 86–94
Khushaba RN, Al-Ani A, AlSukker A, Al-Jumaily A (2008) A combined ant colony and differential evolution feature selection algorithm. In: Proceedings of the international conference on ant colony optimiztion and swarm intelligence (ANTS 2008), pp 1–12
Aditi Roy C, Joydev Hazra KD, Dutta P (2020) Proceedings of research and applications in artificial intelligence, advances in intelligent systems and computing 1355. Comparative study of the effect of different fitness functions in PSO algorithm on band selection of hyperspectral imagery (2020). https://doi.org/10.1007/978-981-16-1543-6_9
Chang CI, Wu CC, Liu KH, Chen HM, Chen CC, Wen CH (2015) Progressive band processing of linear spectral unmixing for hyperspectral imagery. IEEE J Sel Top Appl Earth Observ Remote Sens 8(6):2583–2597
Gong M, Mingyang Zhang YY (2016) Unsupervised band selection based on evolutionary multiobjective optimization for hyperspectral images. IEEE Trans Geosci Remote Sens 54(1):544–557
Zhu G, Yuancheng Huang JLZBFX (2016) Unsupervised hyperspectral band selection by dominant set extraction. IEEE Trans Geosci Remote Sens 54(1):227–239
Xu Y, Qian Du NHY (2017) Particle swarm optimization-based band selection for hyperspectral target detection. IEEE Geosci Remote Sens Lett 14(4):554–558
Jiao L, Jie Feng FLTS, Zhang X (2015) Semisupervised affinity propagation based on normalized trivariable mutual information for hyperspectral band selection. IEEE J Sel Top Appl Earth Observ Remote Sens 8(6):2760–2773
Bai J, Shiming Xiang LS, Pan C (2015) Semisupervised pair-wise band selection for hyperspectral images. IEEE J Sel Top Appl Earth Observ Remote Sens 8(6):2798–2813
Arushi Gupta SS (2020) Comparative analysis of ant colony and particle swarm optimization algorithms for distance optimization. Procedia Comput Sci 173:245–253
AbWahab MN, Nefti-Meziani S, Atyabi A (2015) A comprehensive review of swarm optimization algorithm. PLoS ONE. https://doi.org/10.1371/journal.pone.0122827
Guo G, Wang H, Bell D, Bi Y (2004) Knn model-based approach in classification
Loh W-Y (2011) Classification and regression trees. WIREs Data Min Knowl Discov 1:14–23
Dorigo M, Birattari M, Stutzle T (2006) Ant colony optimization. IEEE Comput Intell Mag 1(4):28–39. https://doi.org/10.1109/MCI.2006.329691
Author information
Authors and Affiliations
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chowdhury, A.R., Hazra, J., Dasgupta, K. et al. Fuzzy rule-based hyperspectral band selection algorithm with ant colony optimization. Innovations Syst Softw Eng 20, 161–174 (2024). https://doi.org/10.1007/s11334-021-00432-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11334-021-00432-4