دانلود رایگان مقاله انگلیسی داده کاوی باز برای اپیدمی دنگ تایوانی - الزویر 2018

Abstract

By using a quantitative approach, this study examines the applicability of data mining technique to discover knowledge from open data related to Taiwan’s dengue epidemic. We compare results when Google trend data are included or excluded. Data sources are government open data, climate data, and Google trend data. Research findings from analysis of 70,914 cases are obtained. Location and time (month) in open data show the highest classification power followed by climate variables (temperature and humidity), whereas gender and age show the lowest values. Both prediction accuracy and simplicity decrease when Google trends are considered (respectively 0.94 and 0.37, compared to 0.96 and 0.46). The article demonstrates the value of open data mining in the context of public health care.

Concluding Remarks

The article highlights the value of open data mining in the context of public health care. It has three main purposes: the utilization of data mining technique (ID3) to predict dengue epidemic, the integration of multiple open data sources, and the derivation of practical insights from an empirical qualitative survey of domain specialists and experts. Results show that the classification-oriented data mining technique can be successfully applied to Taiwan’s dengue open data. From the viewpoint of health care management, variables used to describe Taiwan’s dengue epidemic are either congenital (location, season, climate, and individual) and hence mostly uncontrollable, or acquired (Google trends) and created through relationships. We reported and ordered the predicted power of congenital variables through quantitative analyses. Moreover, there has been a gap between academic and practical perceptions. To reduce the gap, the use of discovered knowledge via an empirical survey may be advantageous to the development of dengue control strategy and policy. This requires the development of an in-depth understanding of dengue epidemic in particular and of the data modeling in general. Furthermore, climate is changing rapidly, which may greatly influence living environments. This means that the effects of location, time, and climate variables on dengue epidemics are very likely to change. Future studies should therefore keep tracking the possible impact of those on the dengue fever epidemic.