Soft Computing Methods for Predicting Environmental Quality: A Case Study of the Zimbabwe Sugar Processing Industry
No Thumbnail Available
Date
2013
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Sugarcane growing and processing is associated with environmental degradation and pollution. The impact that sugar processing industries have on the environment affects the ecosystem. Methods of soft computing that is fuzzy logic, neural networks, and genetic algorithms can be adopted for environmental protection, particularly in the developing countries. Soft computing techniques, particularly neural networks and fuzzy logic, have been used to predict and sometimes control air quality. This paper looks at how fuzzy logic can be adopted for predicting air quality. The common environmental impacts associated with sugarcane production are water and air pollution. This paper focuses on air pollution. The major waste streams are identified and the extent of air pollution is predicted by classifying the air quality as poor, ordinary, very good, and excellent. This paper presents a fuzzy rule base that can be used to classify the pollutants and predict the air quality based on the amount of the specific pollutant in the air. The Mamdani fuzzy inference system is used to build the rule base, with the membership functions being non-intersecting and triangular. The adoption of fuzzy logic techniques will help sugar processing industries to be aware of the impact their operations have on the environment.
Description
Keywords
Citation
Zimwara, D., Mugwagwa, L. and Nherera, K., 2013. Soft computing methods for predicting environmental quality: A case study of the Zimbabwe sugar processing industry. J. US-China Public Administration, 10(4), pp.345-357.