Current Science

Open Access Open Access  Restricted Access Subscription Access

Classification of Remote Sensed Data Using Hybrid Method Based on Ant Colony Optimization with Electromagnetic Metaheuristic


Affiliations
1 Department of Electronics and Communication Engineering, GSSS Institute of Engineering and Technology for Women, Mysuru 570 016, India
2 Department of Electronics and Communication Engineering, ATME College of Engineering, Mysuru 570 028, India
3 PES Institute of Technology and Management, Shivamogga 577 204, India
4 Department of Electronics and Communication Engineering, Malnad College of Engineering, Hassan 573 202, India
 

In this study, a hybrid configuration of electromagnetic metaheuristic algorithm (EM) with Pachycondyla apicalis (API) ant algorithm (inspired by the behaviour of real ant colony Pachycondyla apicalis) belonging to ant colony optimization (ACO) called EMAPI algorithm is presented for remote sensing data classification. The traditional per-pixel classification method identifies the classes using spectral variance and ignores the spatial distribution of pixels. It requires training data to be normally distributed in the pixels corresponding to land use/land cover classes and creates a lot of confusion between classes within a remote sensed (RS) data. The proposed algorithm is an integrated strategy structure to achieve advantages of global and local search ability of EM and API algorithms respectively. The objective consists of improving overall accuracy of the classified results of RS data. This method can overcome intermixing with regard to scrub land with cultivated areas and build-up land with palm groves. The proposed algorithm is tested on objective functions well used in the literature and EMAPI is used for supervised land cover classification. Results of EMAPI algorithm over 6 classes showed an improvement of 8% in overall classification accuracy (OCA) for EM technique and improvement of 3% in OCA for API algorithm.

Keywords

Ant Colony Optimization, API Algorithm, Electromagnetic Metaheuristic, Data Classification, Hybrid Metaheuristic.
User
Notifications
Font Size

  • Melgani, F. and Serpico, S. B., A statistical approach to the fusion of spectral and spatio-temporal contextual information for the classification of remote sensing images. Pattern Recognit. Lett., 2002, 23(9), 1053–1061; doi:10.1016/S0167-8655(02)00052-1.

  • Bruzzone, I. and Cossu, R., A multiple-cascade-classifier system for a robust and partially updating of land-cover maps. IEEE Trans. Geosci. Remote Sensing, 2002, 40(9), 1984–1996; doi: 10.1109/TGRS.2002.803794.

  • Bardossy, A. and Samaniego, L., Fuzzy rule-based classification of remotely sensed imagery. IEEE Trans. Geosci. Remote Sensing, 2002, 40(2), 362–374; doi:10.1109/36.992798.

  • Shankar, B. U., Saroj, K. and Ashish, G., Wavelet-fuzzy hybridization: feature-extraction and land-cover classification of remote sensing images. Appl. Soft Comput., 2011, 11, 2999–3011; doi:10.1016/j.asoc.2010.11.024.

  • Giacinto, G., Roli, F. and Bruzzone, L., Combination of neural and statistical algorithms for supervised classification of remotesensing images. Pattern Recognit. Lett., 2000, 21, 385–397; doi:10.1016/S0167-8655(00)00006-4.

  • Du, P., Tan, K. and Xing, X., A novel binary tree support vector machine for hyperspectral remote sensing image classification. Opt. Commun., 2012, 285, 3054–3060; doi:10.1016/j.optcom.2012.02.092.

  • Zheng, J., Cui, Z., Liu, A. and Jia, Y., A K-means remote sensing image classification method based on adaboost. natural computation. ICNC ’08. 2008, vol. 4, pp. 27–32; doi:10.1109/ICNC.2008.903.

  • Jayanth, J., Ashok Kumar, T. and Shiva Prakash Koliwad, Assessing different change detection technique to detect land cover changes in coastal region of Mangalore. Int. J. Earth Sci. Eng., 2014, 7(5), 1696–1703.

  • Jayanth, J., Ashok Kumar, T., Shiva Prakash Koliwad and Srikrishnashastry, Identification of land cover changes in the coastal area of Dakshina Kannada district, south India, during the year 2004–2008. Egyptian J. Remote Sensing Space Sci., 2016, 117–128 (EJRS, ISSN:1110-9823).

  • Yang, H., Du, Q. and Chen, G., Particle swarm optimization-based hyperspectral dimensionality reduction for urban land cover classification. IEEE J. Sele Topics Appl. Earth Observ. Remote Sensing, 2012, 5(2), 544–554; doi:10.1109/JSTARS.2012.2185822.

  • Liu, X., Li, X., Liu, L. and Ai, B., An innovative method to classify remote-sensing images using ant colony optimization. IEEE Trans. Geosci. Remote Sensing, 2008, 46(12), 24–28; doi:10.1109/TGRS.2008.2001754.

  • Atanassova, V., Fidanova, S., Popchev, I. and Chountas, P., Generalized nets, ACO algorithms and genetic algorithms, Monte Carlo methods and applications. In Eighth IMACS Seminar on Monte Carlo Methods, 2011, vol. 29, pp. 39–46.

  • Dorigo, M. and Blumb, C., Ant colony optimization theory: A survey. Theor. Comput. Sci., 2005, 344, 243–278; doi:10.1016/j.tcs.2005.05.020.

  • Jayanth, J., Koliwad, S. and Ashok Kumar, T., Classification of remote sensed data using artificial bee colony algorithm. Egyptian J. Remote Sensing Space Sci., 2015, 119–126; doi:10.1016/j.ejrs.2015.03.001.

  • Ciornei, I. and Kyriakides, E., Hybrid ant colony-genetic algorithm (gaapi) for global continuous optimization. IEEE Trans. Systems. Man. Cybernetics – Part B, 2012, 42(1), 234–245; doi: 10.1109/TSMCB.2011.2164245.

  • Zhong, Y., Zhang, L., Huang, B. and Li, P., An unsupervised artificial immune classifier for multi/hyperspectral remote sensing imagery. IEEE Trans. Geosci. Remote Sensing, 2006, 44(2), 420–431; doi:10.1109/TGRS.2005.861548.

  • Plaza, A. and Chang, C. I., Computer architectures for remote sensing overview and case study. In High Performance Computing in Remote Sensing (eds Plaza, A. and Chang, C.-I.), Chapman & Hall/CRC Press, Computer & Information Science Series, 2007, pp. 9–41.

  • Xu, M. and Wei, C., Remotely sensed image classification by complex network eigenvalue and connected degree. Comput. Math. Methods Med., 2012, 1–9; http://dx.doi.org/10.1155/2012/632703

  • Talbi, E. G., Hybrid metaheuristics. Stud. Comput. Intell., 2013, 434, XXVI, 458, p. 109 illus; doi:10.1007/978-3-642-30671-6.

  • Talbi, E. G., A taxonomy of hybrid metaheuristics. J. Heur., 2002, 8, 541–564; doi:10.1023/A:1016540724870.

  • Georgieva, A. and Jordanov, I., Hybrid metaheuristics for global optimization using low-discrepancy sequences of points. Comput. Op. Res., 2010, 37(3), 456–469; doi:10.1016/j.cor.2008.07.004.

  • Torn, A. and Zilinskas, A., Global optimization. Lecture Notes in Computer Science, Springer-Verlag, 1989, p. 350; doi:10.1007/3-540-50871-6.

  • Fidanova, S., Paprzycki, M. and Roeva, O., Hybrid GA-ACO algorithm for a model parameters identification problem. Proceedings of the 2014 Federated Conference on Computer Science and Information Systems, 2014, pp. 413–420; doi:10.15439/2014F373.

  • Ho, S. L., Yang, S. and Machado, J. M., A modified ant colony optimization algorithm modeled on tabu-search methods. IEEE Trans. Magnet., 2006, 42(4), 1195–1198; doi:10.1109/TMAG.2006.871425.

  • Birbil, S. I. and Fang, S. C., An electromagnetism-like mechanism for global optimization. J. Global Opt., 2003, 25, 263–282; doi: 10.1023/A:1022452626305.

  • Monmarché, N., Venturini, G. and Slimane, M., On how pachycondyla apicalis ants suggest a new search algorithm. Future Gener. Comp. Syst., 2000, 16, 937–946; doi:10.1016/S0167-739X(00)00047-9.

  • Fresneau, D., Individual foraging and path fidelity in a ponerine ant, Paris, 1985, 32(2), 109–116; doi:10.1007/BF02224226.

  • Jayanth, J., Ashok Kumar, T. and Shiva Prakash Koliwad, Comparative analysis of image fusion techniques for remote sensing, International conference on advanced machine learning technologies and applications (AMLTA 2012), Cairo, Egypt, 8–10 December 2012. Proceedings of the Communication in Computer Information Science (eds Hassanien, A. E. et al.), Springer, Berlin/ Heidelberg, Germany, 2012, vol. 322, pp. 111–117.

  • Fresneau, D., Biologie et comportement social d’une fourmi ponérine néotropicale (Pachycondyla apicalis). Ph D thesis, Thèse d’Etat, Laboratoire d’Ethologie Expérimentale et Comparée, Université de Paris XIII, France, 1994.

  • Filipovic, V., Kartelj, A. and Matic, D., An electromagnetism metaheuristic for solving the maximum betweenness problem. Appl. Soft Comput., 2013, 13, 1303–1313; doi:10.1016/j.asoc.2012.10.015.

  • Naji-Azimi, N., Toth, P. and Galli, L., An electromagnetism metaheuristic for the unicost set covering problem. Euro. J. Operat. Res., 2010, 205, 290–300; doi:10.1016/j.ejor.2010.01.035.


Abstract Views: 293

PDF Views: 91




  • Classification of Remote Sensed Data Using Hybrid Method Based on Ant Colony Optimization with Electromagnetic Metaheuristic

Abstract Views: 293  |  PDF Views: 91

Authors

J. Jayanth
Department of Electronics and Communication Engineering, GSSS Institute of Engineering and Technology for Women, Mysuru 570 016, India
V. S. Shalini
Department of Electronics and Communication Engineering, ATME College of Engineering, Mysuru 570 028, India
T. Ashok Kumar
PES Institute of Technology and Management, Shivamogga 577 204, India
Shivaprakash Koliwad
Department of Electronics and Communication Engineering, Malnad College of Engineering, Hassan 573 202, India

Abstract


In this study, a hybrid configuration of electromagnetic metaheuristic algorithm (EM) with Pachycondyla apicalis (API) ant algorithm (inspired by the behaviour of real ant colony Pachycondyla apicalis) belonging to ant colony optimization (ACO) called EMAPI algorithm is presented for remote sensing data classification. The traditional per-pixel classification method identifies the classes using spectral variance and ignores the spatial distribution of pixels. It requires training data to be normally distributed in the pixels corresponding to land use/land cover classes and creates a lot of confusion between classes within a remote sensed (RS) data. The proposed algorithm is an integrated strategy structure to achieve advantages of global and local search ability of EM and API algorithms respectively. The objective consists of improving overall accuracy of the classified results of RS data. This method can overcome intermixing with regard to scrub land with cultivated areas and build-up land with palm groves. The proposed algorithm is tested on objective functions well used in the literature and EMAPI is used for supervised land cover classification. Results of EMAPI algorithm over 6 classes showed an improvement of 8% in overall classification accuracy (OCA) for EM technique and improvement of 3% in OCA for API algorithm.

Keywords


Ant Colony Optimization, API Algorithm, Electromagnetic Metaheuristic, Data Classification, Hybrid Metaheuristic.

References





DOI: https://doi.org/10.18520/cs%2Fv113%2Fi02%2F284-291