Subscribe Now Subscribe Today
Research Article
 

A New Fuzzy Combination Method Based on Parametric Triangle Norm



Jia Pengtao and Liang Shuhui
 
ABSTRACT

Triangular norms can improve the generalization capability of pattern classification problems, so they are introduced to improve the performance of ensemble learning. This study pays attention to the different impacts of base classifiers and put forward a new fuzzy combination method for ensemble learning. It is based on parametric triangle norms. Firstly, a new combination model was constructed. The base learners in it are set with different weights. Secondly, a set of fuzzy combination rules were generated according to the parametric triangle norms. Thirdly, genetic algorithm was used as the parameters estimation module of the new fuzzy rules. Finally, experiments were conducted on seven different datasets from the University of California, Irvine machine learning repository (UCI). The experimental results show that the fuzzy rules generated by the new combination method have better performance than the base learners and the fixed combination rules. And when set proper weights to base learners, the new fuzzy rules obtain better performance than the ones set a same weight to base learners.

Services
Related Articles in ASCI
Similar Articles in this Journal
Search in Google Scholar
View Citation
Report Citation

 
  How to cite this article:

Jia Pengtao and Liang Shuhui, 2013. A New Fuzzy Combination Method Based on Parametric Triangle Norm. Information Technology Journal, 12: 7754-7757.

DOI: 10.3923/itj.2013.7754.7757

URL: https://scialert.net/abstract/?doi=itj.2013.7754.7757

REFERENCES
Bay, S.D., 1998. Combining Nearest Neighbor Classifiers through Multiple Feature Subsets. In: Proceeding 15th International Conference on Machine Learning, Shavlik, J. (Ed.). Morgan Kaufmann, San Francisco, pp: 37-45.

Chitra, A. and S. Uma, 2010. An ensemble model of multiple classifiers for time series prediction. Int. J. Comput. Theory Eng., 2: 454-458.
CrossRef  |  

Duda, R.O., P.E. Hart and D.G. Stork, 2001. Pattern Classification. 2nd Edn., John Wiley and Sons, New York.

Farahbod, F. and M. Eftekhari, 2012. Comparison of different t-norm operators in classification problems. Int. J. Fuzzy Logic Syst., 2: 33-39.
CrossRef  |  

Kittler, J., M. Hatef, R.P.W. Duin and J. Matas, 1998. On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell., 20: 226-239.
CrossRef  |  

Ko, A.H.R., R. Sabourin and A.S. Britto Jr., 2008. From dynamic classifier selection to dynamic ensemble selection. Pattern Recognit., 41: 1718-1731.
Direct Link  |  

Mizumoto, M., 1989. Pictorial representations of fuzzy connectives, part I: Cases of t-norms, t-conorms and averaging operators. Fuzzy Sets Syst., 31: 217-242.
CrossRef  |  

Newman, D.J., S. Hettich, C. Blake and C. Merz, 1998. UCI Repository of Machine Learning Databases. Department of Information and Computer Science, University of California, Berleley, CA.

Tsoumakas, G., I. Partalas and I. Vlahavas, 2008. A taxonomy and short review of ensemble selection. Proceedings of the 18th European Conference on Artificial Intelligence, July 21-25, 2008, Patras, Greece, pp: 1-6.

Zhou, Z.H., 2009. Ensemble Learning. In: Encyclopedia of Biometrics, Li, S.Z. and A. Jain (Eds.). Springer, Berlin, pp: 270-273.

©  2019 Science Alert. All Rights Reserved