Dynamic Determination of Mixing Parameters in Fuzzy Clustering
This paper considers the simultaneous determination of data classification and linear regression models. The clustering criterion introduced in this paper includes two types of mixing parameters to make a balance between two objectives of clustering: the minimization of variances within clusters and the minimization of regression errors. The paper proposes an idea on dynamic determination of those parameters in the clustering process.
Key wordsFuzzy clustering fuzzy modeling mixing parameters
Unable to display preview. Download preview PDF.
- Dave, R. N. (1990). An adaptive fuzzy c-elliptotype clustering algorithm, Proceedings of NAFIPS 90: Quarter Century of Fuzziness, Vol. I, pp. 9–12.Google Scholar
- Phansalkar, G. & Dave, R. N. (1997). On generating solid models of mechanical parts through fuzzy clustering, Proceedings of FUZZ- IEEW 91, Vol. I, pp. 225–230.Google Scholar
- Ryoke, M. et al. (1996). Fuzzy modeling though adaptive fuzzy clustering, Proceedings of 4th conference of the European Congress on Fuzzy and Intelligent Technologies, Vol. 2, pp. 1416–1419.Google Scholar
- Takagi, T. h Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control, IEEE Trans, on Systems, Man and Cybernetics, Vol. SMC-15, No. 1, pp. 116–132.Google Scholar