eprintid: 7262
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/72/62
datestamp: 2023-11-09 16:19:04
lastmod: 2023-11-09 16:19:04
status_changed: 2023-11-09 16:08:54
type: conference_item
metadata_visibility: show
creators_name: Loshini, T.
creators_name: Asirvadam, V.S.
creators_name: Dass, S.C.
creators_name: Gill, B.S.
title: Predicting localized dengue incidences using ensemble system identification
ispublished: pub
keywords: Atmospheric humidity; Forecasting; Identification (control systems); Information science; Rain; Religious buildings, Cumulative rainfall; Dengue Incidences; Ensemble modeling; Ensemble systems; Mean temperature; Prediction accuracy; Prediction model; Predictor variables, Mean square error
note: cited By 7; Conference of International Conference on Computer, Control, Informatics and Its Applications, IC3INA 2015 ; Conference Date: 5 October 2015 Through 7 October 2015; Conference Code:118992
abstract: Neighbouring regions do have an influence on the pattern of dengue incidences for a particular site. This study presents ensemble models, where dengue incidences of a district can be estimated using a dengue prediction model of that district together with its neighbouring districts. Seven districts of Selangor are chosen in this study and an ensemble dengue incidence prediction model is built based on the respective districts and its neighbours. Dengue incidence models for each district are developed using predictor variables which include previous dengue incidences and weather variables (namely, the mean temperature, relative humidity and cumulative rainfall). These predictors are found to have specific model order lag time. To measure the efficiency of ensemble models, the formed ensemble model for each district is compared with their respective single model using the Mean Square Error (MSE) criteria. It was found that out of seven districts, five districts had better prediction accuracy based on their ensemble models. Hence, we conclude that ensemble models predict dengue incidences well. © 2015 IEEE.
date: 2016
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84963655905&doi=10.1109%2fIC3INA.2015.7377737&partnerID=40&md5=015a4e85be3d4153f892645cf5ff7fb6
id_number: 10.1109/IC3INA.2015.7377737
full_text_status: none
publication: Proceeding - 2015 International Conference on Computer, Control, Informatics and Its Applications: Emerging Trends in the Era of Internet of Things, IC3INA 2015
pagerange: 6-11
refereed: TRUE
isbn: 9781479987733
citation:   Loshini, T. and Asirvadam, V.S. and Dass, S.C. and Gill, B.S.  (2016) Predicting localized dengue incidences using ensemble system identification.  In: UNSPECIFIED.