Dengue Incidence Prediction Using Model Variables with Registered Case Feedback
This study discussed building of localized dengue incidence prediction models for districts of Selangor. System identification with Linear Least Square estimation method is used to build a number of model orders with varied lag-time and the most accurate
- PDF / 264,248 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 70 Downloads / 211 Views
Abstract This study discussed building of localized dengue incidence prediction models for districts of Selangor. System identification with Linear Least Square estimation method is used to build a number of model orders with varied lag-time and the most accurate model is selected for each district. Model accuracy is measured using Mean Square Error (MSE) value, with smaller MSE value, represents better accuracy. The flow of study is started with identification of significant weather variables. It was found that all three weather variables namely mean temperature, relative humidity and rainfall are significant predictors. Further inclusion of dengue incidences feedback data into the model was found to enhance the model accuracy. Model accuracy is further tested by comparing between single and ensemble model of few districts. Ensemble model is built using dengue prediction model of its district together with its neighbouring districts, and was found to be better predictor in two out three districts. Therefore, it was concluded that ensemble models predict better in some cases, and single models are better in other cases, depending on rate of human movement between neighbouring districts.
⋅
⋅
Keywords System identification Linear least square Dengue Model order of lag-time Single model Ensemble model
⋅
⋅
⋅
MSE
⋅
L. Thiruchelvam (✉) ⋅ V.S. Asirvadam ⋅ S.C. Dass ⋅ H. Daud Center for Intelligent Signal & Imaging Research (CISIR), Universiti Teknologi PETRONAS, 32610 Bander Seri Iskandar, Perak, Malaysia e-mail: [email protected]; [email protected] B.S. Gill Disease Control Division, Ministry of Health, Putrajaya, Malaysia © Springer Science+Business Media Singapore 2017 H. Ibrahim et al. (eds.), 9th International Conference on Robotic, Vision, Signal Processing and Power Applications, Lecture Notes in Electrical Engineering 398, DOI 10.1007/978-981-10-1721-6_18
163
164
L. Thiruchelvam et al.
1 Introduction Dengue disease, transmitted by Aedes mosquitoes, has been increasing in Malaysia recently, especially in the state of Selangor [1]. Control against the vector population is the only way to curb this disease, as vaccination is still under study, and therefore dengue prediction models are important. Most of dengue incidences prediction models used weather variables of mean temperature, relative humidity and rainfall as predictors [2–5]. Previous studies are aligned in discussing temperature as a significant predictor of dengue incidences [3, 4]. However, relative humidity and rainfall were found to be significant predictors in some studies, and not in other studies. For example, study by Parker [6] in Nigeria, found low relative humidity condition triggered dengue occurrences. However, findings from most of other studies found high relative humidity as a good condition for higher dengue transmission [2–4]. The same mixed role was found in rainfall variable. Studies by Parker [6] found large amount of rainfall triggered increase in dengue incidences. However, study by Nakhapakorn and Tripathi [7] found
Data Loading...
