Classification of Kidney Lesions Using Bee Swarm Optimization

  • Authors

    • Hima Bindu G
    • Prasad Reddy Pvgd
    • M Ramakrishna Murty
    • S Pallam Setty
    2018-06-08
    https://doi.org/10.14419/ijet.v7i2.33.17905
  • Bee Swarm Optimization, regularization parameter, Support Vector Machine, kernel function.
  • Support Vector Machine (SVM) is extensively used in classification due to its prominent features and better generalisation performance. The classification accuracy is highly dependent on the SVM parameters which are currently selected manually. Therefore, the necessity of an automated, fast and reliable approach to determine optimal SVM parameter and produce high classification accuracy has become important requirement for computer aided detection and diagnostic systems. In the current work, SVM parameters are tuned using Bee Swarm Optimization (BSO) approach to find the probability of achieving better classification accuracy. The approach is studied with two kernel function of SVM – polynomial and Gaussian radial basis function. The algorithm is implemented and executed on kidney CT images for classification of kidney lesions. The BSO-SVM Classification results are compared with SVM classification results obtained on the same dataset and it is found that BSO-SVM classification using BSO optimised SVM parameters produced higher classification accuracy.

     

     

  • References

    1. [1] Selvaraj, Cholavendhan, R. Siva Kumar, and M. Karnan. "A survey on application of bio-inspired algorithms." International Journal of Computer Science and Information Technologies 5.1 (2014): 366-70.

      [2] Ren, Yuan, and Guangchen Bai. "Determination of optimal SVM parameters by using GA/PSO." JCP 5, no. 8 (2010): 1160-1168.

      [3] Liu, Xiaoyong, and Hui Fu. "PSO-based support vector machine with Cuckoo search technique for clinical disease diagnoses." The Scientific World Journal 2014 (2014).

      [4] Chen, Hui-Ling, Bo Yang, Gang Wang, Su-Jing Wang, Jie Liu, and Da-You Liu. "Support vector machine based diagnostic system for breast cancer using swarm intelligence." Journal of medical systems 36, no. 4 (2012): 2505-2519.

      [5] Akbari, Reza, Alireza Mohammadi, and Koorush Ziarati. "A novel bee swarm optimization algorithm for numerical function optimization." Communications in Nonlinear Science and Numerical Simulation 15, no. 10 (2010): 3142-3155.

      [6] Holland, John Henry. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press, 1992.

      [7] Jones, Karl O. "Comparison of genetic algorithm and particle swarm optimization." In Proceedings of the International Conference on Computer Systems and Technologies. 2005.

      [8] Karaboga, Dervis, and Bahriye Basturk. "A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm." Journal of global optimization39, no. 3 (2007): 459-471.

      [9] Karaboga, Dervis, and Bahriye Akay. "A comparative study of artificial bee colony algorithm." Applied mathematics and computation 214, no. 1 (2009): 108-132.

      [10] Drias, Habiba, Souhila Sadeg, and Safa Yahi. "Cooperative bees swarm for solving the maximum weighted satisfiability problem." In International Work-Conference on Artificial Neural Networks, pp. 318-325. Springer, Berlin, Heidelberg, 2005.

      [11] Yu, Hwanjo, and Sungchul Kim. "Svm tutorial—classification, regression and ranking." In Handbook of Natural computing, pp. 479-506. Springer Berlin Heidelberg, 2012.

      [12] Jakkula, Vikramaditya. "Tutorial on support vector machine (svm)." School of EECS, Washington State University 37 (2006).

      [13] Vapnik V. The nature of statistical learning theory. Springer science & business media; 2013 Jun 29.

      [14] Vapnik, Vladimir Naumovich. "An overview of statistical learning theory." IEEE transactions on neural networks 10, no. 5 (1999): 988-999.

      [15] Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods. Cambridge university press; 2000 Mar 23.

      [16] Huang, Cheng-Lung, and Chieh-Jen Wang. "A GA-based feature selection and parameters optimization for support vector machines." Expert Systems with applications 31, no. 2 (2006): 231-240.

      [17] Lin, Shih-Wei, Kuo-Ching Ying, Shih-Chieh Chen, and Zne-Jung Lee. "Particle swarm optimization for parameter determination and feature selection of support vector machines." Expert systems with applications 35, no. 4 (2008): 1817-1824.

      [18] Akbari, Reza, Alireza Mohammadi, and Koorush Ziarati. "A powerful bee swarm optimization algorithm." In Multitopic Conference, 2009. INMIC 2009. IEEE 13th International, pp. 1-6. IEEE, 2009.

      [19] Lahari, Kannuri, M. Ramakrishna Murty, and Suresh C. Satapathy. "Partition based clustering using genetic algorithm and teaching learning based optimization: performance analysis." In Emerging ICT for Bridging the Future-Proceedings of the 49th Annual Convention of the Computer Society of India CSI Volume 2, pp. 191-200. Springer, Cham, 2015.

      [20] Murty, M. Ramakrishna, J. V. R. Murthy, PVGD Prasad Reddy, Anima Naik, and Suresh Chandra Satapathy. "Performance of teaching learning based optimization algorithm with various teaching factor values for solving optimization problems." In Proceedings of the International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA) 2013, pp. 207-216. Springer, Cham, 2014.

      [21] Binitha S. and Sathya, S.S., 2012. A survey of bio inspired optimization algorithms. International Journal of Soft Computing and Engineering, 2(2), pp.137-151.

  • Downloads

  • How to Cite

    Bindu G, H., Reddy Pvgd, P., Ramakrishna Murty, M., & Pallam Setty, S. (2018). Classification of Kidney Lesions Using Bee Swarm Optimization. International Journal of Engineering & Technology, 7(2.33), 1046-1052. https://doi.org/10.14419/ijet.v7i2.33.17905