Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476413Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Salwani Abdullah, Prof. Dr. | |
| dc.contributor.author | Kharrousheh Adnan Naim (P53698) | |
| dc.date.accessioned | 2023-10-06T09:18:02Z | - |
| dc.date.available | 2023-10-06T09:18:02Z | - |
| dc.date.issued | 2011-06-30 | |
| dc.identifier.other | ukmvital:85082 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476413 | - |
| dc.description | Clustering problem in data mining is a process that organizes a data set into a number of clusters such that the data in each cluster share a high degree of similarity while being very dissimilar to data from other clusters. This problem is defined as NP-hard optimization problems. Over last decades, a numerous of approaches have proposed to solve this problem, such as simulated annealing, genetic algorithm, ant colony and artificial bee colony. This thesis considers a modified tabu search algorithm as one of the methods to solve the clustering problem. The objective of this thesis is to present the modified tabu search algorithm that can be used to find the minimum sum-of-squares clustering problem. The heuristic algorithm that has been applied in this thesis is divided into two phases. The first phase is a constructive phase, which is responsible to generate an initial solution using K-means approach. Whilst, the second phase is an improvement phase, aims to enhance the solution quality that is obtained from the first phase. A modified tabu search algorithm is proposed as an improvement method, where two tabu lists are introduced. The first tabu list is used to keep the neighborhood structures, and the second tabu list is used to keep the moves. These two tabu lists are employed to prevent a cycle (get stuck with the same solution) through the search process. The proposed of modified tabu search algorithm was experimented and tested on five benchmark datasets that are available at the University of California at Irvine (UCI) Machine Learning Repository, which cover low, medium and high dimensions. Computational results show that the proposed approach was effective in finding the minimum distance between points and their centers in each cluster. Based on the comparative experiment results, we observed that the modified tabu search method outperforms the other two techniques i.e. k-means and a standard tabu search alone.,Master/ Sarjana | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
| dc.rights | UKM | |
| dc.subject | Data mining | |
| dc.title | Solving clustering problem in data mining using a modifired tabu search algorithm | |
| dc.type | theses | |
| dc.format.pages | 73 | |
| dc.identifier.callno | QA76.9.D343K482 2011 | |
| dc.identifier.barcode | 002157 | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_85082+SOURCE1+SOURCE1.0.PDF Restricted Access | 916.67 kB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.