Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476149Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Azuraliza Abu Bakar, Prof. Dr. | |
| dc.contributor.author | Maryam Mousavi (P53681) | |
| dc.date.accessioned | 2023-10-06T09:14:04Z | - |
| dc.date.available | 2023-10-06T09:14:04Z | - |
| dc.date.issued | 2012-05-17 | |
| dc.identifier.other | ukmvital:74621 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476149 | - |
| dc.description | Dengue outbreak is one of the critical, communicable and nature born diseases and is becoming more serious in Malaysia. It is important to be able to have early detection system that could give alarm for immediate action such as fogging the specific location. However, the available strategy and action may give long terms effects to the community since inaccurate decision making or prediction may lead to other circumstances. The need to have a system that is able to detect the outbreak in reasonable time is critical. The available dengue data has not yet been extensively explored in data mining where data are analysed in an intelligent way to discover interesting patterns that could detect the abnormalities in data. In this study, a natureinspired computing technique, Artificial Immune System (AIS) is used for dengue outbreak detection. AIS can be defined as a kind of new computational technique that is inspired by the human immune system to solve problems. To date, AIS has been applied in various areas such as pattern recognition, machine learning, optimization, classification, clustering, and anomaly detection. One of the AIS variant algorithms called the Negative selection Algorithm (NSA) has been applied in anomaly detection and fault detection problems. This study aims to employ the NSA for dengue outbreak detection problem. It consists of three main phases. First phase is the preliminary study of dengue outbreak detection problem. The collection of the task relevant data is obtained from the Faculty of Health Science, UKM. A total of 8505 reported dengue patient data are collected from Hulu Langat District from year 2003 to 2009. The second phase involves the design and implementation of the NSA for dengue outbreak detection. Final phase is the model testing and evaluation where a series of modelling are conducted and the best detection model is determined based on the detection rate and the false alarm rate. The comparative study includes the evaluation of the obtained results with the previous techniques used on the same dataset. By using the NSA, the detection rate and the false alarm rate are obtained 80.93% and 24.83% respectively. Therefore, the NSA outperforms other models in terms of high detection rate and low false alarm rate.,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 | Negative | |
| dc.subject | Algorithm | |
| dc.subject | Dengue outbreak detection | |
| dc.subject | Immunocomputers | |
| dc.title | Negative selection algorithm for dengue outbreak detection | |
| dc.type | theses | |
| dc.format.pages | 71 | |
| dc.identifier.callno | QA76.875.M647 2012 3 | |
| dc.identifier.barcode | 000456 | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_74621+Source01+Source010.PDF Restricted Access | 1.23 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.