Automation of Environmental and Economic Systems Research Using Data Mining
- DOI
- 10.2991/aebmr.k.200729.067How to use a DOI?
- Keywords
- environmental and economic system, environment, cluster analysis, random forest, data mining, support vector method
- Abstract
The subject of the study is environmental and economic systems. The authors specified the concept of environmental and economic systems as the natural environment under the influence of human economic and social activities, including mutual influence, as well as the consequences resulting from it. The authors set a goal to develop a methodology for the study of environmental and economic systems that would adequately assess their current state and forecast changes. The approach to the study of such systems consists in the staged application of cluster analysis and data mining classification methods (random forest and support vectors method) and followed assessment of the quality of the model and choosing the best method. In presented research, the analytical procedures are automated in the R-Studio package. The analysis of the same indicators by two different methods confirmed the direct relationship between the costs and investments in environmental protection and the results of environmental protection: with the growth of investments in environmental protection, indicators of recycled water use, discharge of polluted wastewater, air emissions of pollutants were reduced.
- Copyright
- © 2020, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - A.E. Kharitonova AU - A.V. Tikhonova AU - M.V. Kagirova AU - A.M. Kozhemyakina PY - 2020 DA - 2020/07/30 TI - Automation of Environmental and Economic Systems Research Using Data Mining BT - Proceedings of the International Conference on Policies and Economics Measures for Agricultural Development (AgroDevEco 2020) PB - Atlantis Press SP - 352 EP - 360 SN - 2352-5428 UR - https://doi.org/10.2991/aebmr.k.200729.067 DO - 10.2991/aebmr.k.200729.067 ID - Kharitonova2020 ER -