A CMFFP-tree algorithm to mine complete multiple fuzzy frequent itemsets |
| |
| Affiliation: | 1. Innovative Information Industry Research Center (IIIRC), School of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, HIT Campus Shenzhen University Town Xili, Shenzhen 518055, PR China;2. Department of Computer Science and Information Engineering, National University of Kaohsiung, Kaohsiung 811, Taiwan, ROC;3. Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung 804, Taiwan, ROC;1. Centre of Excellence for Fundamental Studies in Structural Engineering, Iran University of Science and Technology, Narmak, Tehran 16, Iran;2. Department of Civil Engineering, University of Zanjan, Zanjan, Iran;1. Department of Applied Mathematics with Oceanology and Computer Programming, Vidyasagar University, Midnapore, West Bengal 721102, India;2. Department of Mathematics, Sidho Kanho Birsha University, Purulia, West Bengal 723101, India;1. Mathematics Department, Faculty of Science, Universiti Teknologi Malaysia, Skudai, Johor Bahru 81310, Johor, Malaysia;2. Faculty of Computer Science, Universiti Tun Hussein Onn Malaysia, Batu Pahat 86400, Johor, Malaysia;1. National Research Council (CNR), Institute of Cognitive Sciences and Technologies, Via Gaifami 18, 95028 Catania, Italy;2. School of Information Systems, Computing and Mathematics, Brunel University, Uxbridge, Middlesex UB8 3PH, United Kingdom;3. Department of Computing Engineering, University of La Laguna, 38271 Santa Cruz de Tenerife, Spain;1. Department of Information Management, National Chung Cheng University, Chiayi 62102, Taiwan, ROC;2. Department of Information Management, National Central University, Jhongli 32001, Taiwan, ROC;3. Chiayi Chang Gung Memorial Hospital, Chiayi 61363, Taiwan, ROC |
| |
| Abstract: | In the past, many algorithms were proposed to adopt fuzzy-set theory for discovering fuzzy association rules from quantitative databases. The fuzzy frequent pattern (FFP)-tree and the compressed fuzzy frequent pattern (CFFP)-tree algorithms were respectively proposed to mine the incomplete fuzzy frequent itemsets from the tree-based structures. In the past, multiple fuzzy frequent pattern (MFFP)-tree algorithm was proposed to keep more linguistic terms for mining fuzzy frequent itemsets. Since the MFFP-tree algorithm inherits the property of the FFP-tree algorithm, numerous tree nodes are thus required to build the MFFP-tree structure for mining the desired multiple fuzzy frequent itemsets. In this paper, the compressed multiple fuzzy frequent pattern (CMFFP)-tree algorithm is designed to keep not only the linguistic term with maximum membership value but also the other frequent linguistic terms for mining the completely fuzzy frequent itemsets. In the designed CMFFP-tree algorithm, the multiple frequent linguistic terms are sorted in descending order of their occurrence frequencies to build the CMFFP-tree structure. The construction process is the same as the CFFP-tree algorithm except more information are kept for later mining process to discover the completely fuzzy frequent itemsets. Each node in the CMFFP-tree uses the additional array to keep the membership values of its prefix path by intersection operation. A CMFFP-mine algorithm is also designed to efficiently mine the multiple fuzzy frequent itemsets from the developed CMFFP-tree structure. Experiments are then conducted to show the performance of the proposed CMFFP-tree algorithm in terms of execution time and the number of tree nodes, compared to those of the MFFP-tree and CFFP-tree algorithms. |
| |
| Keywords: | Data mining Fuzzy set Quantitative database Multiple linguistic terms Fuzzy frequent itemsets Frequent pattern tree |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
