Data Mining Task Optimization with Soft Computing Approach
- 17 Downloads
The data mining task optimization (DMTO) is one of the emerging research areas in the branch of data mining. We discuss the data mining tasks as classification and clustering. The optimization of these tasks is done using soft computing methods. The soft computing is also a new term coined for optimization problems. The classification task is achieved using the support vector machine and results optimized with particle swarm optimization and simplified swarm optimization with exchange local strategy (SSO with ELS). The clustering task is achieved using the kernel fuzzy c-means (KFCM) and results optimized using particle swarm optimization (PSO) and intelligent firefly algorithm (IFA). The results of both the tasks are worked out in the same paper. The results obtained outperform the existing approach SVM with PSO with cuckoo search (CS) and PSO with social spider optimization (SSO) for classification, KFCM with PSO with Bacteria Foraging Optimization (BFO) for clustering in data mining task optimization framework.
KeywordsData mining task optimization Soft computing Classification Clustering Support vector machine Kernel fuzzy c-means
- 1.Fayyad, U., G. Piatesky-Shapiro, and P. Smyth. 1996. From Data Mining to Knowledge Discovery in Databases. AI Magzine 17 (3): 37–54.Google Scholar
- 2.Beni, G., and J. Wang. 1989. Cellular Robotic Systems. http://en.wikipedia.org/wiki/Swarm_intelligence.
- 3.Graves, D., and W. Pedrycz. 2010. Kernel-Based Fuzzy Clustering and Fuzzy Clustering: A Comparative Experimental Study. In Fuzzy Sets and Systems, 522–543.Google Scholar
- 4.Bae, Changseok, Wei-Chang Yeh, Noorhaniza Wahid, Yuk Ying Chung, and Yao Liu. 2012. A New Simplified Swarm Optimization (SSO) Using Exchange Local Search Scheme. International Journal of Innovative computing, Information and Control (IJICIC) 8 (6): 4391–4406.Google Scholar
- 5.Liu, Xiaoyong, and Hui Fu. 2014. PSO-Based Support Vector Machine with Cuckoo Search Technique for Clinical Disease Diagnoses, 1–7. Hindawi Publishing Corporation.Google Scholar
- 6.Yang, Xin-She, and Suash Deb. 2009. Cuckoo Search via Levy Flights. IEEE, 210–214.Google Scholar
- 8.Liu, Yao, Yuk Ying Chung, and Wei Chang Yeh. 2012. Simplified Swarm Optimization with Sorted Local Search for Golf Data Classification. In IEEE World Congress on Computational Intelligence.Google Scholar
- 9.Marr, J. 2003. Comparison of Several Clustering Algorithms for Data Rate Compression of LPC Parameters. In IEEE International Conference on Acoustics Speech, and Signal Processing, vol. 6, 964–966.Google Scholar
- 10.Wong, K.C., and G.C.L. Li. 2008. Simultaneous Pattern and Data Clustering for Pattern Cluster Analysis. IEEE Transaction on Knowledge and Data Engineering 20: 911–923 (Los Angeles, USA).Google Scholar
- 11.Kora, P., and S.R. Kalva. 2015. Hybrid Bacterial Foraging and Particle Swarm Optimization for detecting Bundle Branch Block, SpringerPlus, vol. 4, no. 1.Google Scholar
- 12.Korani, W.M. 2008. Bacterial Foraging Oriented by Particle Swarm Optimization Strategy for PID Tuning. In Proceedings of the 2008 GECCO Conference Companion on Genetic and Evolutionary Computation—GECCO ’08.Google Scholar
- 13.Fateen, S.E.K., and A. Bonilla-Petriciolet. 2013. Intelligent Firefly Algorithm for Global Optimization. In Studies in Computational Intelligence, 315–330.Google Scholar
- 14.Yang, X.-S. 2014. Firefly Algorithms, Nature-Inspired Optimization Algorithms, 111–127.Google Scholar
- 15.UCI Machine Learning Repository. http://archive.ics.uci.edu/ml.