Feature selection algorithms for Malaysian dengue outbreak detection model. Sains Malaysiana, 46 (2): 10. pp. 255-265. ISSN 0126-6039 (2017)
Abstract
Dengue fever is considered as one of the most common mosquito borne diseases worldwide. Dengue outbreak detection can be very useful in terms of practical efforts to overcome the rapid spread of the disease by providing the knowledge to predict the next outbreak occurrence. Many studies have been conducted to model and predict dengue outbreak using different data mining techniques. This research aimed to identify the best features that lead to better predictive accuracy of dengue outbreaks using three different feature selection algorithms; particle swarm optimization (PSO), genetic algorithm (GA) and rank search (RS). Based on the selected features, three predictive modeling techniques (J48, DTNB and Naive Bayes) were applied for dengue outbreak detection. The dataset used in this research was obtained from the Public Health Department, Seremban, Negeri Sembilan, Malaysia. The experimental results showed that the predictive accuracy was improved by applying feature selection process before the predictive modeling process. The study also showed the set of features to represent dengue outbreak detection for Malaysian health agencies
| Item Type: | Article |
|---|---|
| Keywords: | Feature selection, Dengue outbreak, Knowledge discovery from databases, Nature-based algorithms, Outbreak detection |
| Taxonomy: | By Subject > Applied Sciences > Biology By Subject > Applied Sciences > Chemistry |
| Local Content Hub: | Subjects > Applied Sciences |
| Depositing User: | Mohd Ismail Zanudin |
| Date Deposited: | 04 Mar 2021 00:00 |
| Last Modified: | 04 Mar 2021 02:51 |
| Related URLs: |
Actions (login required)
 |
View Item |