Modelling of chemical oxygen demand by using ANNs, ANFIS and k-means clustering techniques

AY M., Kisi O.

JOURNAL OF HYDROLOGY, vol.511, pp.279-289, 2014 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 511
  • Publication Date: 2014
  • Doi Number: 10.1016/j.jhydrol.2014.01.054
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.279-289
  • Keywords: Adaptive neuro-fuzzy inference system, Artificial neural networks, Chemical oxygen demand, K-means clustering, Multi-linear regression, ARTIFICIAL NEURAL-NETWORKS, WATER-QUALITY, DISSOLVED-OXYGEN, PREDICTION, RIVER, CONTAMINATION, CLASSIFICATION, INTELLIGENCE, GROUNDWATER, PERFORMANCE
  • Yozgat Bozok University Affiliated: Yes


This paper proposes integration of k-means clustering and multi-layer perceptron (k-means-MLP) methods in modelling chemical oxygen demand (COD) concentration. This proposed method was tested by using daily measured water suspended solids, pH, temperature, discharge and COD concentration data of upstream of the municipal wastewater treatment plant system in Adapazari province of Turkey. Performance of the k-means-MLP method was compared with multi-linear regression, multi-layer perceptron, radial-based neural network, generalized regression neural network, and two different adaptive neuro-fuzzy inference system techniques (subtractive clustering and grid partition). Root mean square error, mean absolute error, mean absolute relative error and determination coefficient statistics were employed for the evaluation accuracy of each model. It was found that the k-means-MLP performed better than the other techniques in estimating COD. Moreover, the k-means clustering combined with the MLP could be used as a tool in modelling daily COD concentration. (C) 2014 Elsevier B.V. All rights reserved.