Water Quality Classification Using an Artificial Neural Network (ANN)

Postgraduate Symposium in Civil and Environmental Engineering 2019

生态环境科学;土木建筑工程

Sulaiman, Khadijah^1 ; Hakim Ismail, Lokman^1 ; Adib Mohammad Razi, Mohd^1 ; Shalahuddin Adnan, Mohd^1 ; Ghazali, Rozaida^2

Faculty of Civil and Environmental Engineering, University Tun Hussein Onn, Malaysia^1

Faculty of Computer Sciences and Information Technology, University Tun Hussein Onn, Malaysia^2

关键词: Biological oxygen demand;    Environmental data;    Impact on the environment;    Laboratory analysis;    Quality classification;    Root mean square errors;    Total suspended solids;    Training and testing;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/601/1/012005/pdf
DOI  :  10.1088/1757-899X/601/1/012005

来源: IOP

【 摘 要 】

Malaysia is currently a rapidly developing country to achieve a 2020 vision. However the development that has been carried out contributed to a negative impact on the environment especially on water quality. Due to the deterioration of water quality, serious management efforts on water quality has been taken. Thus, the aim of this study is to investigate a technique that can automatically classify the water quality. The technique is based on the concept of Artificial Neural Network (ANN). Since the greater part of their methodologies depend on the idea of 'pattern recognition'. Thus, it is convenient to inspect its ability in classify water quality. There are six environmental data were used in this study such as pH, total suspended solids (TSS), dissolved oxygen (DO), chemical oxygen demand (COD), biological oxygen demand (BOD), and ammonia. The data was obtained by in-site measurement and laboratory analysis. Then, the data was used as the feeder of input variables in the ANN database system. After training and testing the network of ANN, the result showed that 80.0% of accuracy classification with 0.468 of root mean square error (RMSE). This showed the encouraging results for classification.