FOCUS Genetic-fuzzy mining with multiple minimum supports based on fuzzy clustering Chun-Hao Chen • Tzung-Pei Hong • Vincent S. Tseng Published online: 19 November 2010 Ó Springer-Verlag 2010 Abstract Data mining is the process of extracting desir- able knowledge or interesting patterns from existing databases for specific purposes. Most of the previous approaches set a single minimum support threshold for all the items and identify the relationships among transactions using binary values. In real applications, different items may have different criteria to judge their importance. In the past, we proposed an algorithm for extracting appropriate multiple minimum support values, membership functions and fuzzy association rules from quantitative transactions. It used requirement satisfaction and suitability of mem- bership functions to evaluate fitness values of chromo- somes. The calculation for requirement satisfaction might take a lot of time, especially when the database to be scanned could not be totally fed into main memory. In this paper, an enhanced approach, called the fuzzy cluster- based genetic-fuzzy mining approach for items with mul- tiple minimum supports (FCGFMMS), is thus proposed to speed up the evaluation process and keep nearly the same quality of solutions as the previous one. It divides the chromosomes in a population into several clusters by the fuzzy k-means clustering approach and evaluates each individual according to both their cluster and their own information. Experimental results also show the effective- ness and the efficiency of the proposed approach. Keywords Data mining  Fuzzy set  Genetic algorithm  Genetic-fuzzy mining  Fuzzy k-means  Clustering  Multiple minimum supports 1 Introduction Data mining is commonly used for inducing association rules from transaction data. An association rule is an expression X ? Y, where X is a set of items and Y is a single item. It means in the set of transactions, if all the items in X exist in a transaction, then Y is also in the transaction with a high probability (Agrawal and Srikant 1994). Most previous studies focused on binary-valued transaction data. Transaction data in real-world applica- tions, however, usually consist of quantitative values. Designing a sophisticated data-mining algorithm able to deal with various types of data presents a challenge to workers in this research field. Fuzzy set theory has been used in intelligent systems for a long time because of its simplicity and similarity to human reasoning (Chen et al. 2000; William Siler and James 2004; Zhang and Liu 2006). The theory has been applied in fields such as manufacturing, engineering, This is a modified and expanded version of the paper ‘‘Speeding up genetic-fuzzy mining by fuzzy clustering,’’ The IEEE International Conference on Fuzzy Systems, pp. 1695–1699, 2009. C.-H. Chen Department of Computer Science and Information Engineering, Tamkang University, Taipei 251, Taiwan, ROC e-mail: chchen@mail.tku.edu.tw T.-P. Hong (&) Department of Computer Science and Information Engineering, National University of Kaohsiung, Kaohsiung 811, Taiwan, ROC e-mail: tphong@nuk.edu.tw T.-P. Hong Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung 804, Taiwan, ROC V. S. Tseng Department of Computer Science and Information Engineering, National Cheng-Kung University, Tainan 701, Taiwan, ROC e-mail: tsengsm@mail.ncku.edu.tw 123 Soft Comput (2011) 15:2319–2333 DOI 10.1007/s00500-010-0664-1