Visualization of Dengue Incidences using Expectation Maximization (EM) Algorithm

Nirbhay Mathur; Vijanth S. Asirvadam; Sarat C. Dass; Balvinder Singh Gill

doi:10.1109/ICIAS.2016.7824047

Visualization of Dengue Incidences using Expectation Maximization (EM) Algorithm

Nirbhay Mathur, Vijanth S. Asirvadam, Sarat C. Dass, Balvinder Singh Gill

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

The aim of this study was to use the geographical information system (GIS) to visualize the dengue incidences on a weekly basis in Selangor, Malaysia. Along with the prediction modeling on data using centroid model and distribution model based on K-means and Expectation Maximization (EM) algorithms respectively. The results show that weekly hotspot were mainly concentrated in the central part of Petaling district of Selangor. R-GIS(R software) and clustering algorithm were used for year 2014 with several weeks to develop the relation between the visualization and prediction of reported incidences. The results are validated for a small region (Petaling district of Selangor state) in Malaysia and they showed vulnerability hotspot in visualizing the dengue incidences. Thus, the proposed method is able to localize the nature of dengue incidence which can further be utilized for vector disease controlled process.

Original language	English
Title of host publication	2016 6th International Conference on Intelligent and Advanced Systems (ICIAS)
Publisher	IEEE
ISBN (Electronic)	9781509008452
DOIs	https://doi.org/10.1109/ICIAS.2016.7824047
Publication status	Published - 19 Jan 2017

Keywords

Dengue
GIS
clustering algorithm
weekly prediction
K-means
EM algorithm

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICIAS.2016.7824047

Cite this

@inproceedings{abd8d3fb433040fe86e9a39a80dfed4d,

title = "Visualization of Dengue Incidences using Expectation Maximization (EM) Algorithm",

abstract = "The aim of this study was to use the geographical information system (GIS) to visualize the dengue incidences on a weekly basis in Selangor, Malaysia. Along with the prediction modeling on data using centroid model and distribution model based on K-means and Expectation Maximization (EM) algorithms respectively. The results show that weekly hotspot were mainly concentrated in the central part of Petaling district of Selangor. R-GIS(R software) and clustering algorithm were used for year 2014 with several weeks to develop the relation between the visualization and prediction of reported incidences. The results are validated for a small region (Petaling district of Selangor state) in Malaysia and they showed vulnerability hotspot in visualizing the dengue incidences. Thus, the proposed method is able to localize the nature of dengue incidence which can further be utilized for vector disease controlled process.",

keywords = "Dengue, GIS, clustering algorithm, weekly prediction, K-means, EM algorithm",

author = "Nirbhay Mathur and Asirvadam, {Vijanth S.} and Dass, {Sarat C.} and Gill, {Balvinder Singh}",

year = "2017",

month = jan,

day = "19",

doi = "10.1109/ICIAS.2016.7824047",

language = "English",

booktitle = "2016 6th International Conference on Intelligent and Advanced Systems (ICIAS)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Visualization of Dengue Incidences using Expectation Maximization (EM) Algorithm

AU - Mathur, Nirbhay

AU - Asirvadam, Vijanth S.

AU - Dass, Sarat C.

AU - Gill, Balvinder Singh

PY - 2017/1/19

Y1 - 2017/1/19

N2 - The aim of this study was to use the geographical information system (GIS) to visualize the dengue incidences on a weekly basis in Selangor, Malaysia. Along with the prediction modeling on data using centroid model and distribution model based on K-means and Expectation Maximization (EM) algorithms respectively. The results show that weekly hotspot were mainly concentrated in the central part of Petaling district of Selangor. R-GIS(R software) and clustering algorithm were used for year 2014 with several weeks to develop the relation between the visualization and prediction of reported incidences. The results are validated for a small region (Petaling district of Selangor state) in Malaysia and they showed vulnerability hotspot in visualizing the dengue incidences. Thus, the proposed method is able to localize the nature of dengue incidence which can further be utilized for vector disease controlled process.

AB - The aim of this study was to use the geographical information system (GIS) to visualize the dengue incidences on a weekly basis in Selangor, Malaysia. Along with the prediction modeling on data using centroid model and distribution model based on K-means and Expectation Maximization (EM) algorithms respectively. The results show that weekly hotspot were mainly concentrated in the central part of Petaling district of Selangor. R-GIS(R software) and clustering algorithm were used for year 2014 with several weeks to develop the relation between the visualization and prediction of reported incidences. The results are validated for a small region (Petaling district of Selangor state) in Malaysia and they showed vulnerability hotspot in visualizing the dengue incidences. Thus, the proposed method is able to localize the nature of dengue incidence which can further be utilized for vector disease controlled process.

KW - Dengue

KW - GIS

KW - clustering algorithm

KW - weekly prediction

KW - K-means

KW - EM algorithm

U2 - 10.1109/ICIAS.2016.7824047

DO - 10.1109/ICIAS.2016.7824047

M3 - Conference contribution

BT - 2016 6th International Conference on Intelligent and Advanced Systems (ICIAS)

PB - IEEE

ER -

Visualization of Dengue Incidences using Expectation Maximization (EM) Algorithm

Abstract

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this