Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/463224Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Prof.Dr. Fazel Famili | |
| dc.contributor.author | Shahram Sabzevari | |
| dc.date.accessioned | 2023-09-25T09:19:13Z | - |
| dc.date.available | 2023-09-25T09:19:13Z | - |
| dc.date.issued | 2012-01-27 | |
| dc.identifier.other | ukmvital:13327 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/463224 | - |
| dc.description | The rapid development of DNA rrncroarray technology provides biologists an opportunity to measure a large number of gene expression data in a single experiment. The data generated suffer from high dimensions and small sample sizes, which causes problems for lots of classifiers. Selecting high discriminative gene from microarray data not only can improve the performance of classification and reduce the computational complexity, but it can also reduce the medical diagnose cost by eliminating a large number of irrelevant and redundant genes. A wrapper method based on clonal selection based algorithm and naive Bayes classifier is utilized to tackle the problem. The naive Bayes classifier is chosen due to its speed, simplicity and performance. The proposed approach is tested on five standard datasets taken from the Kent Ridge Bio-medical Data Repository. The goals of this study are manifold. As a first goal, in order to investigate the efficiency of clonal selection based algorithm for solving the gene selection problem, a modified version of CLONALG algorithm is applied to the problem in hand. Furthermore, a recently proposed clonal selection based algorithm known as i-CSA is modified and applied to the problem. The algorithms applied here reveal their potential to tackle the gene selection problem on microarray data efficiently based on the results comparison with the state-of-the-art. Moreover, the aging operator employed in the i-CSA algorithm leads to better results by increasing the exploration ability of the algorithm. The second goal is to illustrate the benefits of Pareto-Based multi-objective algorithm for solving the gene selection problem. Therefore, a multi-objective version of modified i- CSA, termed as MOiCSA is proposed and applied to the same problem. The experimental results illustrate the benefits of Pareto-based multi-objective approach by finding higher-quality gene subsets, which are missed by single-objective version of the algorithm.,Information Technology | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Science and Technology / Fakulti Sains dan Teknologi | |
| dc.rights | UKM | |
| dc.subject | Gene | |
| dc.subject | Microarray Data | |
| dc.subject | Algorithm | |
| dc.subject | Genetic algorithms | |
| dc.title | Optimising Gene Selection On Microarray Data By Multi-Objective Clonal Selection Algorithm | |
| dc.type | theses | |
| dc.format.pages | 101 | |
| dc.identifier.callno | QA402.5.S234 2012 tesis | |
| dc.identifier.barcode | 001942 | |
| Appears in Collections: | Faculty of Science and Technology / Fakulti Sains dan Teknologi | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_13327+SOURCE1+SOURCE1.0.PDF Restricted Access | 2.51 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.