Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Open data mining for Taiwan's dengue epidemic.

ChienHsing Wu1, Shu-Chen Kao2, Chia-Hung Shih3

  • 1Department of Information Management, National University of Kaohsiung, 700, Kaohsiung University Rd., Nanzih District, Kaohsiung 81148, Taiwan, ROC.

Acta Tropica
|March 18, 2018
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A knowledge elicitation approach to traffic accident analysis in open data: comparing periods before and after the Covid-19 outbreak.

Heliyon·2022
Same author

Predictors for psychological distress of young burn survivors across three years: A cohort study of a burn disaster in Taiwan.

Journal of nursing scholarship : an official publication of Sigma Theta Tau International Honor Society of Nursing·2021
Same author

Functionality of Silk Cocoon (<i>Bombyx mori</i> L.) Sericin Extracts Obtained through High-Temperature Hydrothermal Method.

Materials (Basel, Switzerland)·2021
Same author

Laying Diet Supplementation with <i>Ricinus communis</i> L. leaves and Evaluation of Productive Performance and Potential Modulation of Antioxidative Status.

The journal of poultry science·2020
Same author

Assessment and determinants of global outcomes among 445 mass-casualty burn survivors: A 2-year retrospective cohort study in Taiwan.

Burns : journal of the International Society for Burn Injuries·2020
Same author

A longitudinal study on psychological reactions and resilience among young survivors of a burn disaster in Taiwan 2015-2018.

Journal of advanced nursing·2019

This study shows that open data mining effectively predicts Taiwan

Area of Science:

  • Public Health Informatics
  • Data Mining
  • Epidemiology

Background:

  • Dengue fever poses a significant public health challenge in Taiwan.
  • Utilizing open data sources for epidemiological surveillance is an emerging area of research.
  • The predictive power of various data types for disease outbreaks requires further investigation.

Purpose of the Study:

  • To quantitatively assess the applicability of data mining techniques for discovering knowledge from open data concerning Taiwan's dengue epidemic.
  • To compare the predictive performance of data mining models with and without the inclusion of Google Trends data.
  • To identify key data features contributing to the prediction of dengue outbreaks.

Main Methods:

  • A quantitative approach was employed, analyzing 70,914 dengue cases in Taiwan.
Keywords:
Data miningDengue epidemicGoogle trendOpen dataSimplicity

Related Experiment Videos

  • Data mining techniques were applied to government open data, climate data (temperature, humidity), and Google Trends data.
  • Classification power and prediction accuracy were evaluated, comparing models with and without Google Trends.

    • Main Results:

    • Location and time (month) from open data exhibited the highest classification power.
    • Climate variables (temperature and humidity) also demonstrated significant predictive value.
    • Including Google Trends data decreased both prediction accuracy (0.94 vs. 0.96) and model simplicity (0.37 vs. 0.46) compared to models using only open and climate data.

    Conclusions:

    • Open data, particularly location and temporal information, combined with climate data, is highly valuable for predicting dengue epidemics in Taiwan.
    • Data mining provides an effective tool for extracting actionable insights from public health data.
    • The inclusion of Google Trends data may not enhance, and can potentially decrease, the accuracy and simplicity of dengue outbreak prediction models.