استفاده از الگوریتم فراابتکاری کرم شب تاب در بهبود دقت طبقه بندی تصویر ماهواره ای, مطالعه موردی: شهر رفسنجان
محورهای موضوعی : زیرساخت اطلاعات مکانی و طبقه بندی
1 - عضو هیات علمی, گروه مهندسی عمران, دانشگاه فنی و حرفه ای، تهران، ایران
کلید واژه: ماشین بردار پشتیبان, کرم شبتاب, طبقه بندی, شبکه عصبی مصنوعی,
چکیده مقاله :
امروزه یکی از روش‌های تهیه‌ی نقشه کاربری و پوششی اراضی، استفاده از اطلاعات ماهواره‌ای و روش‌های سیستم اطلاعات مکانی است. داده‌های ماهواره‌ای به دلیل ارائه اطلاعات به روز و امکان پردازش تصاویر، در تهیه‌ی نقشه‌های پوششی اراضی از اهمیت بالایی برخوردارند. از سوی دیگر در سال‌های اخیر به طور وسیع و گسترده جهت طبقه‌بندی تصاویر ماهواره‌ای از روش‌های طبقه‌بندی پیشرفته از قبیل شبکه‌های عصبی مصنوعی، مجموعه‌های فازی و شبکه‌های هوشمند استفاده شده است. هدف از این تحقیق، بهبود دقت طبقه‌بنـدی تصـویر ماهواره‌ای با استفاده از یک الگوریتم فراابتکاری است. در این تحقیق، یک روش طبقه‌بندی جدید مبتنی بر الگوریتم کرم شبتاب به عنوان یک الگوریتم یادگیری تحت نظارت معرفی شده است. بـدین منظـور ابتدا با استفاده از دو الگوریتم طبقه‌بندی شبکه عصبی مصنوعی و ماشین‌های بـردار پشتیبان، تصـویر موردنظر طبقه‌بندی و نقشه‌ی پوششی اراضی آن تهیه شد. سپس مقادیر دقت و ضریب کاپا برای این دو الگـوریتم محاسبه گردید. در نهایت الگوریتم کرم شبتاب در نرم‌افزار پایتون برنامه‌نویسی شد و پس از ورود تصاویر به برنامه پایتون و مشاهده نتایج خروجی، مشخص شد که پارامترهای تابع هسته مرکزی روش بردار پشتیبان و تعداد نورون‌های روش شبکه عصبی مصنوعی بهبود داده شده است. در نهایت نتایج نشان داد که الگوریتم کرم شبتاب یک طبقه-بندی کننده مناسب است و قابلیت رقابت با بقیه روش‌ها را دارد. دقت کلی حاصل از طبقه‌بندی برای سنجنده ASTER با این الگوریتم، در طبقه‌بندی شبکه عصبی بـه میـزان ۱.۶ درصد و در طبقه‌بندی ماشین بردار پشتیبان به میزان ۳.۸ درصد افزایش یافت. همچنین مقایسه ضریب کاپا، دقت کاربر و دقت تولید کننده برای روش های ذکر شده در بخش نتایج و تحلیل شرح داده شده است.
Today, one of the methods of preparing land use and land cover is the use of satellite information and Geographic information systems methods. Also, satellite data is very important in preparing land use maps due to providing up-to-date and digital information and the possibility of image processing. On the other hand, in recent years, advanced classification methods such as artificial neural networks, fuzzy sets and intelligent networks have been widely used to classify satellite images. The aim of this study is to improve the classification accuracy of satellite imagery using a meta-heuristic algorithm. In this research, a new supervised learning classification method was introduced based on the firefly algorithm. For that purpose, two neural network classification algorithms and the support vector machines were used for land use map classification. Then the overall and kappa coefficient values for these two algorithms were calculated. Finally, the firefly algorithm was programmed in Python software, and after entering the images into the Python program, it was found that the parameters of the core function of the support vector method and the number of neurons in the neural network method were improved. The classification accuracy for the ASTER sensor with this algorithm increased by 1.6% in the neural network classification and by 3.8% in the support vector machine classification. Finally, the results showed that the firefly algorithm is a suitable classifier and can compete with other methods.
1. Abbaspour-Gilandeh, Y., Sabzi, S., Benmouna, B., García-Mateos, G., Hernández-Hernández, J. L., & Molina-Martínez, J. M. (2020). Estimation of the constituent properties of red delicious apples using a hybrid of artificial neural networks and artificial bee colony algorithm. Agronomy, 10(2), 267.
2. Alavipanah, K, M, Masoudi.2001. Land use Mapping Preparation Using TM satellite imaging Data and GIS (A case Study: Mork region of Fars province Natural Resources and Agricultural Journal.
3. Arekhi Saleh and Adibnejad. Mostafa, 2011, Evaluation of the efficiency of support vector machine algorithms for land use classification using Landsat ETM+ satellite imagery (case study: Ilam Dam), Natural Resources Department, Agriculture Sciences Faculty, University of Ilam, Scientific Journal of Research Pasture and Desert of Iran, Volume 18, Number 3, Page 420-440. (In Persian).
4. Baban, S. J. and M. Wan Yusof. (2001) Mapping land use/ cover distribution on a mountainous tropical island using remote sensing and GIS, International Journal Remote Sensing, 22:10, 1909–1918.
5. Barrett, E.C, and Curtic, L. F (1992). Introduction to Environmental Remote Sensing, Chapman & Hall, London.
6. Chen, K., Zhou, Y., Zhang, Z., Dai, M., Chao, Y., & Shi, J. (2016). Multilevel image segmentation based on an improved firefly algorithm. Mathematical Problems in Engineering.
7. Chen, Q., Chen, Y., & Jiang, W. (2016). Genetic particle swarm optimization–based feature selection for very-high-resolution remotely sensed imagery object change detection. Sensors, 16(8), 1204.
8. Chen, X., Wang, J., Sun, D., & Liang, J. (2008, October). A novel hybrid Evolutionary Algorithm based on PSO and AFSA for feedforward neural network training. In 2008 4th International Conference on Wireless Communications, Networking and Mobile Computing (pp. 1-5). IEEE.
9. Jansen L. J.M. and A. Di Gregorio. (2004) Obtaining land-use information from a remotely sensed land cover map: results from a case study in Lebanon, International Journal of Applied Earth Observation and Geoinformation, 5: 141–157.
10. Hossieni, S. 2002. Investigation on ability of ETM+ satellite image Data for land use mapping preparation (A case Study: Mazandaran province, Chamestan region). Msc Thesis,Tehran University.
11. Hung, H. J., O'Neill, R. T., Bauer, P., & Kohne, K. (1997). The behavior of the p-value when the alternative hypothesis is true. Biometrics, 11-22.
12. Hussain, S. F., Pervez, A., & Hussain, M. (2020). Co-clustering optimization using Artificial Bee Colony (ABC) algorithm. Applied Soft Computing, 97, 106725.
13. Huang, J., Lu, J., & Ling, C. X. (2003, November). Comparing naive Bayes, decision trees, and SVM with AUC and accuracy. In Third IEEE International Conference on Data Mining (pp. 553-556). IEEE.
14. Kattan, A., & Abdullah, R. (2011, January). A parallel & distributed implementation of the harmony search based supervised training of artificial neural networks. In 2011 Second International Conference on Intelligent Systems, Modelling and Simulation (pp. 277-283). IEEE.
15. Karaboga, D., & Akay, B. (2009). A comparative study of artificial bee colony algorithm. Applied mathematics and computation, 214(1), 108-132.
16. Karnan, S. M. (2014). Medical image segmentation using firefly algorithm and enhanced bee colony optimization. Bonfring Int. J. Adv. Image Process, 316-321.
17. Lee, Y. J., & Mangasarian, O. L. (2001). SSVM: A smooth support vector machine for classification. Computational optimization and Applications, 20(1), 5-22.
18. Liu, L., Zhao, D., Yu, F., Heidari, A. A., Li, C., Ouyang, J., ... & Pan, J. (2021). Ant colony optimization with Cauchy and greedy Levy mutations for multilevel COVID 19 X-ray image segmentation. Computers in biology and medicine, 136, 104609.
19. Montana, D. J., & Davis, L. (1989, August). Training feedforward neural networks using genetic algorithms. In IJCAI (Vol. 89, pp. 762-767).
20. Omran, M. G. (2009). Using opposition-based learning with particle swarm optimization and barebones differential evolution. Particle Swarm Optimization, 23, 343-384.
21. Okwuashi, O., & Ndehedehe, C. (2017). Tide modelling using support vector machine regression. Journal of Spatial Science, 62(1), 29-46.
22. Pirra, M., & Diana, M. (2019). A study of tour-based mode choice based on a support vector machine classifier. Transportation Planning and Technology, 42(1), 23-36.
23. Poursaee, A. (2018). Application of agent-based paradigm to model corrosion of steel in concrete environment. Corrosion Engineering, Science and Technology, 53(4), 259-264.
24. Ren, Z., Liu, T., & Liu, G. (2021). Classification and discrimination of real and fake blood based on photoacoustic spectroscopy combined with particle swarm optimized wavelet neural networks. Photoacoustics, 100278.
25. Shataee, Sh and A, Abdi, 2007. Land use mapping preparation in Zagros mountain region using ETM+ satellite images Data (A case study: Sarkan Watershed of Lorestan). Natural Resources and Agricultural Sciences Journal: 1(4):129-138.
26. Shilane, D., Martikainen, J., Dudoit, S., & Ovaska, S. J. (2008). A general framework for statistical performance comparison of evolutionary computation algorithms. Information Sciences, 178(14), 2870-2879.
27. Slowik, A., & Bialko, M. (2008, May). Training of artificial neural networks using differential evolution algorithm. In 2008 conference on human system interactions (pp. 60-65). IEEE.
28. Socha, K., & Blum, C. (2007). An ant colony optimization algorithm for continuous optimization: application to feed-forward neural network training. Neural computing and applications, 16(3), 235-247.
29. Su, H., Cai, Y., & Du, Q. (2016). Firefly-algorithm-inspired framework with band selection and extreme learning machine for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(1), 309-320.
30. Vallada, E., & Ruiz, R. (2010). Genetic algorithms with path relinking for the minimum tardiness permutation flowshop problem. Omega, 38(1-2), 57-67.
31. Wang, X. J., Gao, L., & Zhang, C. Y. (2008, September). Electromagnetism-like mechanism based algorithm for neural network training. In International Conference on Intelligent Computing (pp. 40-45). Springer, Berlin, Heidelberg.
32. Wijaya, A., 2005, Application of Multi-Stage Classification to Detect Illegal Logging with the Use of MultiSource Data, MSc. Thesis, ITC, Enschede, The Netherlands.
33. Xie, H., Zhang, L., Lim, C. P., Yu, Y., Liu, C., Liu, H., & Walters, J. (2019). Improving K-means clustering with enhanced firefly algorithms. Applied Soft Computing, 84, 105763.
34. Yang, X. S. (2009, October). Firefly algorithms for multimodal optimization. In International symposium on stochastic algorithms (pp. 169-178). Springer, Berlin, Heidelberg.
35. Yang, X. S. (2010). Engineering optimization: an introduction with metaheuristic applications. John Wiley & Sons.
36. Yang, X. S., & He, X. (2015). Swarm intelligence and evolutionary computation: overview and analysis. Recent advances in swarm intelligence and evolutionary computation, 1-23.
37. Yang, X. S., & Deb, S. (2010). Eagle strategy using Lévy walk and firefly algorithms for stochastic optimization. In Nature inspired cooperative strategies for optimization (NICSO 2010) (pp. 101-111). Springer, Berlin, Heidelberg.