Simulation of multi-criteria mean Clustering method for satellite imagery of Bogd Khan mountain of Mongolia
DOI:
https://doi.org/10.5564/pmas.v65i04.5236Keywords:
cluster, clustering methods, remote sensing dataAbstract
Traditionally, a variety of unsupervised methods have been used for analyzing remotely-sensed imagery. Although popular clustering techniques such as K-means, Mini-Batch K-means, and Fuzzy C-means are widely applied, their classification accuracy is often limited. This study proposes a new clustering method, called Multi-Criteria Mean Clustering (MCMC), to classify and extract forest areas from remote sensing images. The proposed method is based on a multi-criteria optimization framework, and leverages Pareto-optimal solutions arising from multiple clustering objectives. We show that K-means and Mini-Batch K-means can be viewed as specific instances of the proposed MCMC approach. For experimental evaluation, Root Mean Square Error (RMSE), Structural Similarity Index (SSIM), Overall Accuracy (OA), and Intersection over Union (IU) were used to assess performance. The results demonstrate that the proposed MCMC method provides more accurate and reliable classification, achieving lower RMSE, higher SSIM, higher OA, and higher IU compared to conventional clustering techniques. The study area is Bogd Khan Mountain, located in Central Mongolia, on the southern fringes of Ulaanbaatar. Sentinel-2B remote sensing data were employed for this research, and all computational experiments were conducted in Python Jupyter Notebook.
Downloads
5
References
1. Camps-Valls, G., “Machine learning in remote sensing data processing,” IEEE International Workshop on Machine Learning for Signal Processing, pp. 1-6, 2009. https://doi.org/10.1109/MLSP.2009.5306233.
2. Sisodiya, N., Dube, N., Thakkar, P., “Next-generation artificial intelligence techniques for satellite data processing,” In Artificial Intelligence Techniques for Satellite Image Analysis, Springer, Vol. 24, pp. 235-254, 2020. https://doi.org/10.1007/978-3-030-24178-0_11.
3. Han, J., Pei, M., Kamber, M., “Data Mining: Concepts and Techniques,” Elsevier, New York, 2011.
4. X. Wu, X. Zhu, G. Q. Wu, and W. Ding, “Data mining with big data,” IEEE Transaction on Knowledge and Data Engineering, vol. 26, no. 1, pp. 97-107, 2014. https://doi.org/10.1109/tkde.2013.109.
5. Jain, A., Murty, M., Flynn, P., “Data Clustering: A Review,” CM Computing Surveys, Vol. 31, no. 3, pp. 264-323, 1999. https://doi.org/10.1145/331499.331504.
6. A. S. Shirkhorshidi, S. Aghabozorgi, T. Y. Wah, and T. Herawan, “Big Data Clustering: A Review,” Lecture Notes in Computer Science, vol. 8583, pp. 707-720, 2014. https://doi.org/10.1007/978-3-319-09156-3_49.
7. Jain, A., Duin, R., Mao, J., “Statistical Pattern Recognition: A Review,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no.1, pp. 4-37, 2000. https://doi.org/10.1109/34.824819.
8. D. T. Nguyen, L. Chen, and C. K. Chan, “Clustering with Multi-viewpoint-Based Similarity Measure,” IEEE Transactions on Knowledge and Data Engineering, vol. 24, no. 6, pp. 988-1001, 2012. https://doi.org/10.1109/tkde.2011.86.
9. Hamerly, G., Elkan, C., “Learning the K in K-means,” In The Seventh Annual Conference on Neural Information Processing Systems, 2003.
10. C. Chen, L. Pau, and P. Wang, “Hand book of Pattern Recognition and Computer Vision , Eds., World Scientific, Singapore, pp. 3-32. R.Dubes, “Cluster analysis and related issue”.
11. Coleman, G., Andrews, H., “Image Segmentation by Clustering,” In Proceedings of IEEE, vol. 67, pp. 773-785, 1979. https://doi.org/10.1109/proc.1979.11327.
12. Jain, A., Dubes, R., “Algorithms for Clustering Data,” Prentice Hall, New Jersey, USA, 1988.
13. Turi, R.H., “Clustering-Based Color Image Segmentation,” PhD Thesis, Monash University, Australia, 2001.
14. Kaukoranta, T., Franti, P., Nevalainen. O., “A New Iterative Algorithm for VQ Codebook Generation,” International Conference on Image Processing, pp. 589-593, 1998. https://doi.org/10.1109/icip.1998.723533.
15. Baek, S., Jeon, B., Lee. D., Sung. K., “Fast Clustering Algorithm for Vector Quantization,” Electronics Letters, vol. 34, no. 2, pp. 151-152, 1998. https://doi.org/10.1049/el:19980217.
16. Xiang, Z., “Color Image Quantization by Minimizing the Maximum Inter-cluster Distance,” ACM Transactions on Graphics, vol. 16, no. 3, pp. 260-276, 1997. https://doi.org/10.1145/256157.256159.
17. D. L. Olson and D. Delen, “Advanced Data Mining Techniques,” Springer, 1st edition, 2008.
18. Judd, D., Mckinley, P., Jain, A., “Large-scale Parallel Data Clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, pp. 871-876, 1998. https://doi.org/10.1109/34.709614.
19. Bezdek, J., “A Convergence Theorem for the Fuzzy ISODATA Clustering Algorithms,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 2, pp. 1-8, 1980. https://doi.org/10.1109/tpami.1980.4766964.
20. Bezdek, J., “Pattern Recognition with Fuzzy Objective Function Algorithms,” Plenum Press, 1981. https://doi.org/10.1007/978-1-4757-0450-1.
21. Amarsaikhan, D., Munkh-Erdene, A., Enkhjargal, D., Nyamjargal, E., Tsogzol, G., “Forest change study in Mongolia using optical and microwavers,” First International Conference on Climate Change and Environment in Central and North-East Asia, October, 2022.
22. Nyamjargal, E., Amarsaikhan, D., Munkh-Erdene, A., Enkhjargal, D., Battsengel, V., Bolorchuluun, Ch., “Object-based classification of mixed forest types in Mongolia,” Geocarto International, 35:14, 1615-1626, 2020. https://doi.org/10.1080/10106049.2019.1583775.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Bayanjargal Darkhijav, Davaajargal Jargalsaikhan, Munkh-Erdene Altangerel, Enkhbat Rentsen
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on any research article in the Proceedings of the Mongolian Academy of Sciences is retained by the author(s).
The authors grant the Proceedings of the Mongolian Academy of Sciences a license to publish the article and identify itself as the original publisher.
Articles in the Proceedings of the Mongolian Academy of Sciences are Open Access articles published under a Creative Commons Attribution 4.0 International License CC BY.
This license permits use, distribution and reproduction in any medium, provided the original work is properly cited.
