Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476172Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Salwani Abdullah, Prof.Dr. | |
| dc.contributor.author | Alikar Najmeh (P53645) | |
| dc.date.accessioned | 2023-10-06T09:14:19Z | - |
| dc.date.available | 2023-10-06T09:14:19Z | - |
| dc.date.issued | 2013-05-08 | |
| dc.identifier.other | ukmvital:74752 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476172 | - |
| dc.description | In recent decades, one of the most important and the most prevalent cancer, excluding skin cancer among women is breast cancer, where caused 458,503 deaths in worldwide in 2008. Also, it is estimated that in the United States 209,060 cases of breast cancer will be diagnosed and 40,230 people will die from this disease in 2010. Therefore, an exact and accurate diagnosis and detection of this cancer type can develop patient health and ensure a long survival for them. The fuzzy approach produces systems that attain high classification performance with the possibility of attributing a confidence measure to the output diagnosis. In this research a model is proposed, in which a fuzzy rule-based classification system, a heuristic algorithm and a particle swarm optimization (PSO) integrated to generate a hybrid intelligent algorithm for breast cancer diagnosis. Two orthogonal and triangular fuzzy sets types are applied to represent input membership functions where are used to fuzzify the crisp values related to the features on the dataset. The PSO is used to create fuzzy if-then rules, evaluate and update them and the heuristic algorithm is applied to calculate the certainty grade of the rules, respectively. A design of experiments approach called Taguchi method is employed to tune different parameters of the proposed algorithm. Finally, the effectiveness of PSO algorithm is examined on a well-known dataset named Wisconsin Breast Cancer Dataset (WBCD) and its results are compared with some related works in the literature. These works are classified based on three training data and testing data types used to test their algorithms. The proposed model achieved accuracies of 97.4% and 99.35% for triangular fuzzy sets on 683 and 466 training data respectively, and 99.5% for orthogonal fuzzy sets on 400 training data. This shows that the proposed hybrid intelligent algorithm is an effective and accurate algorithm for breast cancer diagnosis.,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 | Breast cancer | |
| dc.subject | Swarm | |
| dc.subject | Fuzzy rule-based system | |
| dc.subject | Particles (Nuclear physics) | |
| dc.title | Breast cancer diagnosis using particle swarm optimization and fuzzy rule-based system | |
| dc.type | theses | |
| dc.format.pages | 95 | |
| dc.identifier.callno | Q337.3.A444 2013 3 | |
| dc.identifier.barcode | 000335 | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_74752+Source01+Source010.PDF Restricted Access | 1.18 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.