Cluster Based Regression Model on Dengue Incidence Using Dual Climate Variables

Shermon S. Mathulamuthu, Vijanth S. Asirvadam, Sarat C. Dass, Balvinder S. Gill

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Dengue fever is one of the major health related issues as reported in World Health Organization (WHO). Therefore, a study is needed on the factors that influencing dengue incidences. This paper presents the influence of dengue incidence with dual climate variable in the 3D form scatter plot. Machine learning techniques such as clustering and regression is done to compare the sum square of residual (SSE) to conclude which climate variable is giving a big impact on dengue cases. Unsupervised techniques of K-means clustering is done to group the data accordingly. Averaged silhouette width method is used to define the number of K group. Each cluster the regression model is built and SSE is shown in table. Thus through the SSE the model validity can be known.
Original languageEnglish
Title of host publication2016 IEEE Conference on Systems, Process and Control (ICSPC)
PublisherIEEE
Pages64-69
Number of pages6
ISBN (Electronic)9781509011810
DOIs
Publication statusPublished - 8 May 2017

Keywords

  • Dengue Incidences
  • Machine Learning
  • K-means Cluster
  • Averaged Silhouette width
  • Regression

Cite this

Mathulamuthu, S. S., Asirvadam, V. S., Dass, S. C., & Gill, B. S. (2017). Cluster Based Regression Model on Dengue Incidence Using Dual Climate Variables. In 2016 IEEE Conference on Systems, Process and Control (ICSPC) (pp. 64-69). IEEE. https://doi.org/10.1109/SPC.2016.7920705