| Summary: | Dengue is a global public health burden affecting over 120 countries. As Malaysia has made significant progress in dengue monitoring, there are still challenges hindering effective preventative interventions and dengue management. One major obstacle is rapid urbanization, which has led to an increase in vector-borne diseases like dengue fever in cities and it is predicted that urbanization will lead to the emergence of new vector-borne diseases, particularly those spread by Aedes mosquitoes. Overall, Malaysia's efforts to reduce dengue spread have had some success, but there are significant drawbacks that limit their efficacy. To overcome these limitations, the government must implement comprehensive and consistent measures involving sustained efforts, multi-faceted strategies, and strong collaboration between relevant agencies. By doing so, effective dengue vector control can be achieved, reducing the burden of dengue fever on the population. The k-Nearest Neighbour (kNN) algorithm is a simple and effective non-parametric classification method widely used in various applications such as classification, regression analysis, statistical estimation, and pattern recognition of dengue spread. The accuracy of the kNN algorithm is influenced by the presence or absence of irrelevant features and the proportional weight assigned to each feature for classification and with high accuracy and lower error ratio in classifying certain datasets. In this dengue-related problems, kNN is used to classify the study areas based on its severity level in order to help the relevant bodies in optimizing its limited resources. The accurate classification of the severity of dengue at each district, is able to provide guideline to the authorised body for more proper resource allocation. © 2024 IEEE.
|
|---|