Using Data Mining Techniques to Identify Enterprises with High Water Pollution Potential

機構典藏 > College of Business and Management > Graduate Institute & Department of Business Administration > Proceeding > Item 987654321/118372

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/118372

Title:	Using Data Mining Techniques to Identify Enterprises with High Water Pollution Potential
Authors:	Lo, H.C.;Huang, Y.Y.;Hu, L.S.
Keywords:	Industrial Waste Pollution;Logistic Regression;Neural Network
Date:	2019-10
Issue Date:	2020-03-21 12:11:07 (UTC+8)
Abstract:	To stop environmental pollution caused by improper wastewater discharges, the related enterprises are required to regularly report the water monitoring data via Internet. To make sure the data submitted are in good quality, the inspectors are arranged to carry out the checkup on site either through random samplings or the appeals and reports from the public. Those enterprises violating the regulations thus make improvements as per the inspection results. However, in view of the limited manpower, the environmental control institutions will not be able to detect all the violators immediately if simply random samplings are applied. It is, therefore, an important issue to effectively and at the primal time to single out the enterprises with high water pollution potential. Using scientific data analysis, this paper aims to identify these targeting enterprises and construct a pollution warning model. Current report data on the Internet will be employed for statistic and data mining analysis, such as logistic regression and neural network. Meanwhile, comparisons will also be made concerning the validities of these warning models, hoping to better choose the appropriate one. The study findings can be used as basis for environmental control institutions while establishing pollution warning web portals so that the enforcement authorities can keep good track of the potential targets in advance and thus enhance the accuracy of the inspection.
Appears in Collections:	[Graduate Institute & Department of Business Administration] Proceeding

Files in This Item:

File	Size	Format
index.html	0Kb	HTML	92	View/Open

Loading...