區間資料之穩健式模糊C均值聚類演算法

Robust Fuzzy C-Means Clustering Algorithm for Interval Data

朱致宇(Chih-Yu Chu)

指導教授 ： 楊敏生

中原大學/理學院/應用數學研究所/碩士(2018年)

https://doi.org/10.6840/cycu201800251

摘要

摘要
在模糊聚類中，模糊C均值(FCM)演算法是應用最為廣泛的聚類方法。各種基於FCM的擴展演算法在過去許多文獻中被發表出來。然而，FCM及其擴展的演算法通常會因為需要事先給定群集數量而受到起始值和參數的選擇的影響，儘管有一些方法可以解決FCM的上述問題，但在沒有模糊指標m且事先不給定聚類數量和參數的情況下，FCM沒辦法同時達到穩健於起始值與參數的選擇。FCM也存在著對區間型態的測量尺度進行分群的限制。在本篇論文中，我們將穩健式學習模糊C均值聚類演算法(其根據於模糊C均值演算法) 拓展到區間資料並稱之為區間資料之穩健式模糊C均值聚類演算法（I-RLFCM），以顯示I-RLFCM演算法在區間資料集的有效性。

關鍵字

模糊聚類 ； 模糊C均值 ； 穩健式學習FCM ； 聚類個數 ； 區間資料 ； 區間資料之穩健式模糊C均值

並列摘要

Abstract
In fuzzy clustering, the fuzzy c-means (FCM) algorithm is the most widely used clustering method. Many extensions of FCM had been proposed in the literature. However, the FCM algorithm and its extensions are usually affected by initializations and parameter selection with a number of clusters to be given a priori. Although there were some works to solve these problems in FCM, there is no work for FCM to be simultaneously robust to initializations and parameter selection under free of the fuzziness index m without a given the number of clusters and parameters in priori. The FCM also have a restriction for classify the interval type of measurement scale. In this thesis, we extend the robust-learning fuzzy c-means clustering algorithm to interval data and called it robust-learning fuzzy c-means clustering algorithm for interval data (I-RLFCM) where based on the fuzzy c-means algorithm to demonstrate the effectiveness of the I-RLFCM algorithm for interval datasets.

並列關鍵字

Fuzzy clustering ； Fuzzy c-means ； Robust-learning FCM ； number of clusters ； interval data ； Robust-learning Fuzzy c-means for interval data

參考文獻

References

[1] L. Kaufman, P.J. Rousseeuw, Finding Groups in Data: An Introduction to Cluster Analysis, Wiley, New York, 1990.

[2] G.J. McLachlan and K.E. Basford, Mixture Models: Inference and Applications to clustering, Marcel Dekker, New York, 1988.

[3] A.P. Dempster, N.M. Laird, D.B. Rubin, Maximum likelihood from incomplete data via the EM algorithm (with discussion), Journal of the Royal Statistical Society: Series B (Methodological) 39 (1977) 1-38.

[4] J. MacQueen, Some methods for classification and analysis of multivariate observations, Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability 1 (1967) 281-297, University of California Press.