Osama Mahmoud Othman
ABSTRACT
Instance-reduction methods have successfully been used to find suitable representative instances from data, which can help in reducing the size of the retained instances. The Ant Colony Optimization (ACO) has been successfully applied in solving several types of combinatorial optimization problems. ACO simulates the natural behaviour of ants, especially their mechanisms of adaptation and cooperation. In this paper, a new instance reduction technique is presented which applies ACO principle. Comparing to other well-known methods we showed that applying the new instance reduction method on different datasets leads to a statistically significant lower number of generated instances, and achieved the best results in terms of predictive accuracy.
- Angiulli F. 2005. Fast condensed nearest neighbor rule, Technical report. In Proceedings of the 22nd International Conference on Machine Learning, Bonn, Germany. Google Scholar
Digital Library
- Babu, T. R. and Murty, M. N. 2001. Comparison of genetic algorithm based prototype selection schemes. Pattern Recognition, Vol. 34, pp. 523--525.Google ScholarCross Ref
- Bonabeau, E., Dorigo, M. and Theraulez, G. 1999. Swarm Intelligence: From natural to artificial intelligence, Oxford University Press, New York. Google ScholarDigital Library
- Brighton H. and Mellish C. 2002. Advances in instance selection for instance-based learning algorithms. Data mining and knowledge discovery, vol. 6, no. 2, pp. 153--172. Google ScholarDigital Library
- Cover, T. and Hart, P. 1967. Nearest neighbor pattern classification. In IEEE Transaction. Volume (13) Issue 1, pp. 21--27. Google ScholarDigital Library
- D. L. Wilson. 1972. Asymptotic properties of nearest neighbor rules Using Edited Data. IEEE Transactions on Systems, Man, and Cybernetics, vol. 2 no.3: pp. 408--421, 1972.Google ScholarCross Ref
- Fayed, H. A. and Atiya A. F. (2009). A novel template reduction approach for the K-nearest neighbor method. IEEE Transactions On Neural Networks, vol. 20, N. 5, pp. 890--896. Google ScholarDigital Library
- Gadodiya, S.V. and Chandak, M.B. 2013. Prototype Selection Algorithms for kNN Classifier: A Survey. in International Journal of Advanced Research in Computer and Communication Engineering Vol.2, Issue 12, December 2013.Google Scholar
- Gates, G. W. (1972). The reduced nearest neighbor rule. Institute of Electrical and Electronics Engineers Transactions on Information theory, Vol. 18 No. 3, pp. 431--433. Google ScholarDigital Library
- Grochowski M. and Jankowski N. 2004. Comparison of instance selection algorithms. ii. results and comments, LNCS 3070, pp. 580--585.Google ScholarCross Ref
- Hart, P. E. (1968). The condensed nearest neighbor rules. Institute of Electrical and Electronics Engineers Transactions on Information Theory, Vol. 14 No. 3, pp. 515--516. Google ScholarDigital Library
- I. Tomek, An experiment with the edited nearest-neighbor rule. IEEE Transactions on Systems, Man, and Cybernetics, vol. 6 no. 6: pp. 448--452, 1976.Google Scholar
- K. El Hindi and M. Alakhras. 2009. Eliminating border instance to avoid overfitting. eds. Antonio P Alakhras, Alma dos Reis. Proceeding of Intelligent Systems and Agents. pp 93--99. IADIS press Algarve, Portugal, 2009.Google Scholar
- Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Mellish, C. (ed.), Proceedings of 14th International Joint Conference on Artificial Intelligence, Morgan Kaufmann. San Francisco, CA, pp. 1137--1143. Google ScholarDigital Library
- K. Zhao, S Zhou, J. Guan, A. Zhou C-Pruner: An improved instance pruning algorithm. In Proceedings of the 2th International Conference on Machine Learning and Cybernetics, vol. 1, pp. 94--99, 2003, Sheraton Hotel, Xi'an, China: Piscataway, NJ: IEEE, 2003.Google Scholar
- Nikolaidis K., Wu Q.H. and Goulermas J.Y. 2011. A class boundary preserving algorithm for data condensation. Pattern Recognition, vol. 44, pp. 704--715. Google ScholarDigital Library
- Olvera-Lopez J.A., Kittler J. and Carrasco-Ochoa J.A. 2010. A review of instance selection methods. Journal of Artificial Intelligence Review, Springer Netherlands, vol.34, no.2, pp. 133--143. Google ScholarDigital Library
- Ritter, G. L., Woodruff, H. B., Lowry, S. R. and Isenhour, T. L. 1975. An algorithm for a selective nearest neighbor decision rule. IEEE Transactions on Information Theory, Vol. 21 No. 6, pp. 665--669. Google ScholarDigital Library
- Sun X. and Chan P. K. (2014), An Analysis of Instance Selection for Neural Networks to Improve Training Speed. 13th International Conference on Machine Learning and Applications, Detroit, MI, USA. Google ScholarDigital Library
- Wilson, D. L. and Martinez, T. (1997). Instance pruning technique, Fisher, D. M. (ed.), Machine Learning. Proceedings of the Fourteenth International Conference (ICML'97), Morgan Kauffmann, San Francisco, CA, pp. 403--411. Google ScholarDigital Library
- Wilson, D. L. and Martinez, T. 2000. Reduction techniques for instance based learning algorithms. Machine Learning, Vol. 38 No. 3, pp. 257--286. Google ScholarDigital Library
Index Terms
- Instance-Reduction Method based on Ant Colony Optimization
Recommendations
A new hybrid method based on Particle Swarm Optimization, Ant Colony Optimization and 3-Opt algorithms for Traveling Salesman Problem
The Traveling Salesman Problem (TSP) is one of the standard test problems used in performance analysis of discrete optimization algorithms. The Ant Colony Optimization (ACO) algorithm appears among heuristic algorithms used for solving discrete ...
Particle swarm optimizer, ant colony strategy and harmony search scheme hybridized for optimization of truss structures
A heuristic particle swarm ant colony optimization (HPSACO) is presented for optimum design of trusses. The algorithm is based on the particle swarm optimizer with passive congregation (PSOPC), ant colony optimization and harmony search scheme. HPSACO ...
Ant colony optimization theory: a survey
Research on a new metaheuristic for optimization is often initially focused on proof-of-concept applications. It is only after experimental work has shown the practical interest of the method that researchers try to deepen their understanding of the ...
Comments