Dynamic Mapping and Visualizing Dengue Incidences in Malaysia Using Machine Learning Techniques

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

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

For the last many years, dengue has been reported to be one of the main causes of death in Malaysia. For more than 40 years, Malaysia is suffering from this endemic problem. The mortality and morbidity are reported for the dengue cases in a higher number of conformed cases in Malaysia. As per statistics, 136,992 cases were reported from 2008 to 2012, the highest in the record. As per the report from the Ministry of Health (MOH) of Malaysia, 77% of cases are reported from the urban area and 23% from the rural area. Since much research have been carried out in history, many researchers had concluded their novel research work, but still dengue cases are not controlled. Hence, this research suggests a novel way to visualize dengue cases and the occurrence of cases. This research uses machine learning technology combined with (geographical information system) GIS to predict dengue cases in Malaysia. The area of research is limited to the Selangor state of Malaysia as this is the most vulnerable area for dengue cases. This research focuses on unsupervised learning techniques to predict the density of cases. K-mean, KNN, and Expectation-Maximization (EM) algorithms are used to cluster the cases and visualize the pattern of dengue spread. In conclusion, all these information are mapped on dynamic mapping which will give the exact coordinates where dengue can occur. Based on this location, the fogging team can be informed and can target a specific area.

Original languageEnglish
Title of host publicationAdvanced Deep Learning for Engineers and Scientists
PublisherSpringer
Pages195-226
Number of pages32
ISBN (Electronic)9783030665197
ISBN (Print)9783030665180
DOIs
Publication statusPublished - 2021

Publication series

NameEAI/Springer Innovations in Communication and Computing
ISSN (Print)2522-8595
ISSN (Electronic)2522-8609

Keywords

  • Data prediction
  • Data visualization
  • Dengue incidences
  • EM
  • Geo-spatial mapping
  • k-means
  • KNN
  • Modeling

ASJC Scopus subject areas

  • Information Systems
  • Health Informatics
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Dynamic Mapping and Visualizing Dengue Incidences in Malaysia Using Machine Learning Techniques'. Together they form a unique fingerprint.

Cite this