本論文應用最佳化演算法對中級解析度成像分光輻射度計(Moderate Resolution Imaging Spectroradiometer, MODIS)影像進行分類。MODIS的觀測資料從可見光至紅外線，共有36個頻道可以使用。在傳統方法上經常使用亮度溫度(Brightness Temperature, BT)方法將影像分成四個種類，其中包括低雲、中雲、高雲及無雲，然而傳統方法在分類雲之邊緣及薄雲上的效果有限。因此，在本研究中使用MODIS的四個頻道組成偽色彩影像，並且採用基因演算法(Genetic Algorithm, GA)、粒子群(Particle Swarm Optimization, PSO)演算法及自我學習粒子群(Self-Learning Particle Swarm Optimization, SLPSO)演算法去提高分類性能。最後，將以多筆資料結果來進行比對。經實驗證明，我們所提出的方法可以有效分辨雲之種類，並且能有效的辨識出雲的邊緣及薄雲。

This paper mainly applies the optimization algorithms to the satellite image classification. The images are based on the Moderate Resolution Imaging Spectroradiometer (MODIS). The data of observation of MODIS have 36 channels can be used from visible to infrared. Traditionally, the images are classified into four classes by brightness temperature (BT) method, including low clouds, middle clouds, high clouds, non-clouds. However, this method has limited effect on classifying the edge of the cloud and thin cloud. Therefore, in this research, we use four channels of MODIS to constitute pseudo-color image, and we adopt genetic algorithm (GA), particle swarm optimization (PSO) and self-learning particle swarm optimization (SLPSO) to improve the performance. Finally, we will compare multiple results of data. Simulation results demonstrate that the proposed methods can effectively i) classify the categories of cloud, ii) distinguish the edge of the cloud, and iii) find out the thin cloud.

[1] M. P. Weinreb, R. Xie, J. H. Lienesch, and D. S. Crosby, “Destriping GOESM image by matching empirical distribution functions,” Remote Sensing of Environment, vol. 29, pp. 185-195, 1989.
[2] K. Komeza, E. N. Juszczak, P. Di, Barba, P. Napieralski, J. P. Lecointe, and N. Hihat, “Using the FEM meshes adaption and genetic algorithms for identification of permeability in normal direction of anisotropic sheets,” IEEE Trans. Magnetic, vol. 48, no. 2, pp. 211-214, 2012.
[3] Y. Okamoto, Y. Tominaga, and S. Sato, “Topological design for 3D optimization using the combination of multistep genetic algorithm with design space reduction and nonconforming mesh connection,” IEEE Trans. Magnetics, vol. 48, no. 2, pp. 515-518, 2012.
[4] H. Liang, S. An, J. Wang, Y. Zhou, H. Fan, P. Krebs, and J. Zhou, “Optimizing time multiplexing auto-stereoscopic displays with a genetic algorithm,” Journal of Display Technology, vol. 10, no. 8, pp. 695-699, 2014.
[5] Y. Fu, M. Ding, and C. Zhou, “Phase angle encoded and quantum behaved particle swarm optimization applied to three-dimensional route planning for UAV,” IEEE Trans. System Man and Cybernetics Part A: Systems and Humans, vol. 42, no. 2, pp. 511-526, 2012.
[6] S. Grubisic, W. P. Carpes, J. P. A. Bastos, and G. Santos, “Association of a PSO optimizer with a quasi-3d ray-tracing propagation model for mono and multi-criterion antenna positioning in indoor environments,” IEEE Trans. Magnetics, vol. 49, no. 5, pp. 1645-1648, 2013.
[7] W. Xu, B. Y. Duan, P. Li, N. Hu, and Y. Qiu, “Multiobjective particle swarm optimization of boresight error and transmission loss for airborne radomes,” IEEE Trans. Antennas and Propagation, vol. 62, no. 11, pp. 5880-5885, 2014.
[8] H. Wei and X. S. Tang, “A genetic-algorithm-based explicit description of object contour and its ability to facilitate recognition,” IEEE Trans. Cybernetics, vol. 45, no. 10, pp. 2558-2571, 2015.
[9] S. K. Mylonas, D. G. Stavrakoudis, J. B. Theocharis, and P. A. Mastorocostas, “Classification of remotely sensed images using the genesis fuzzy segmentation algorithm,” IEEE Trans. Geoscience and Remote Sensing, vol. 53, no. 10, pp. 5352-5376, 2015.
[10] H. Gao, W. B. Xu, J. Sun, and Y. L. Tang, “Multilevel thresholding for image segmentation through an improved quantum-behaved particle swarm algorithm,” IEEE Trans. Instrumentation and Measurement, vol. 59, no. 4, pp. 934-946, 2010.
[11] C. Y. Chang, Y. F. Lei, C. H. Tseng, and S. R. Shih, “Thyroid segmentation and volume estimation in ultrasound images,” IEEE Trans. Biomedical Engineering, vol. 57, no. 6, pp. 1348-1357, 2010.
[12] R. Poli, J. Kennedy, and T. Blackwell, “Particle swarm optimization: an overview,” Swarm Intelligence, vol. 1, no. 1, pp. 33-58, 2007.
[13] J. J. Liang, A. K. Qin, P. N. Suganthan, and S. Baska, “Comprehensive learning particle swarm optimizer for global optimization of multimodal functions,” IEEE Trans. Evolutionary Computation, vol. 10, no. 3, pp. 281-295, 2006.
[14] C. Li, S. Yang, and T. T. Nguyen, “A self-learning particle swarm optimizer for global optimization problems,” IEEE Trans. Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 42, no. 3, pp. 627-646, 2012.
[15] M. D. King, Y. J. Kaufman, W. P. Menzel, and D. Tanre, “Remote sensing of cloud, aerosol, and water vapor properties from the moderate resolution imaging spectrometer (MODIS),” IEEE Trans. Geoscience and Remote Sensing, vol. 30, no. 1, pp. 2-27, 1992.
[16] S. A. Ackerman, K. I. Strabala, W. P. Menzel, R. A. Frey, C. C. Moeller, and L. E. Gumley, “Discriminating clear sky from clouds with MODIS,” Journal of Geophysical Research, vol. 103, no. D24, pp. 32,141-32,157, 1998.
[17] Y. J. Zheng, H. F. Ling, J. Y. Xue, and S. Y. Chen, “Population classification in fire evacuation: a multiobjective particle swarm optimization approach,” IEEE Trans. Evolutionary Computation, vol. 18, no. 1, pp. 70-81, 2014.
[18] Z. Zhang, K. Long, J. Wang, and F. Dressler, “On swarm intelligence inspired self-organized networking: its bionic mechanisms designing principles and optimization approaches,” IEEE Communications Surveys & Tutorials, vol. 16, no. 1, pp. 513-537, 2014.
[19] J. Sun, V. Palade, X. J. Wu, W. Fang, and Z. Wang, “Solving the power economic dispatch problem with generator constraints by random drift particle swarm optimization,” IEEE Trans. Industrial Informatics, vol. 10, no. 1, pp. 222-232, 2014.
[20] T .H. S. Li, Y. H. Wang, C. C. Chen, and C. J. Lin, “A fast color information setup using EP-like PSO for manipulator grasping color objects,” IEEE Trans. Industrial Informatics, vol. 10, no. 1, pp. 645-654, 2014.
[21] W. Hu, J. Gao, Y. Wang, O. Wu, S. Maybank, “Online adaboost-based parameterized methods for dynamic distributed network intrusion detection,” IEEE Trans. Cybernetics, vol. 44, no. 1, pp. 66-82, 2014.
[22] J. H. Holland, “Genetic algorithms and the optimal allocation of trials,” Society for Industrial and Applied Mathematics(SIAM) Journal on Computing, vol. 2, no. 2, pp. 88-105, 1973.
[23] S. M. R. Islam, M. A. Ahsan, and B. C. Ghosh, “Optimization of power system operation with static var compensator applying ACO algorithm,” International Conf. Electrical Information and Communication Technology(EICT), Khulna, Bangladesh, Feb. 13-15 2013, pp. 1-6.
[24] W. Y. Tao, and Y. J. Huang, “Research on disposal station location problem based on genetic and simulated annealing algorithm,” International Conf. Computational and Information Sciences, Shiyang, China, June 21-23 2013, pp. 1897-1900.
[25] L. Xu, Y. P. Li, and J. Xuan, “Based on tabu search and particle swarm optimization algorithms solving job shop scheduling optimization problems,” International Conf. Digital Manufacturing & Automation, Qingdao, China, June 29-30 2013, pp. 322-324.
[26] A. A. Tahir, “A system based on ratio images and quick probabilistic neural network for continuous cloud classification,” IEEE Trans. Geoscience and Remote Sensing, vol. 49, no. 12, pp. 5008-5015, 2011.
[27] C. Li and S. Yang, “An adaptive learning particle swarm optimizer for function optimization,” IEEE Congress on Evolutionary Computation, Trondheim, Norway, May 18-21 2009, pp. 381-388.
[28] A. E. Eiben, R. Hinterding, and Z. Michalewicz, “Parameter control in evolutionary algorithms,” IEEE Trans. Evolutionary Computation, vol. 3, no. 2, pp. 124-141, 1999.
[29] D. E. Goldberg, “Probability matching, the magnitude of reinforcement, and classifier system bidding,” Journal on Machine Learning, vol. 5, no. 4, pp. 407-425, 1990.
[30] C. Li, S. Yang, and I. A. Korejo, “An adaptive mutation operator for particle swarm optimization,” Centre for Computational Intelligence, pp. 165-170. 2008.
[31] D. Thierens, “An adaptive pursuit strategy for allocating operator probabilities,” in Proc. Conf. Genetic and Evolutionary Computation Conference(GECCO), New York, USA, June 25 2005, pp. 1539-1546.
[32] N. Otsu, “A threshold selection method from gray level histograms,” IEEE Trans. Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979.
[33] S. Liu, L. Zhang, Z. Zhang, C. Wang, and B. Xiao, “Automatic cloud detection for all-sky images using superpixel segmentation,” IEEE Trans. Geoscience and Remote Sensing Letters, vol. 12, no. 2, pp. 354-358, 2015.
[34] S. Liu, Z. Zhang, B. Xiao, and X. Cao, “Ground-based cloud detection using automatic graph cut,” IEEE Trans. Geoscience and Remote Sensing Letters, vol. 12, no. 6, pp. 1342-1346, 2015.
[35] S. U. Khan, S. Y. Yang, L. Y. Wang, and L. Liu, “A modified particle swarm optimization algorithm for global optimizations of inverse problems,” IEEE Trans. Magnetics, vol. 52, no. 3, 2016.
[36] Y. W. Jeong, J. B. Park, S. H. Jang, and K. Y. Lee, “A new quantum-inspired binary pso: application to unit commitment problems for power systems,” IEEE Trans. Power Systems, vol. 25, no. 3, pp. 1486-1495, 2010.