A comparative study: Prediction of constructed treatment wetland performance with k-nearest neighbors and neural networks

K-nearest neighbors (KNN), support vector machine (SVM) and self-organizing map (SOM) were applied to predict five-day @ 20˚C N- Allylthiourea biochemical oxygen demand (BOD) and suspended solids (SS), and to assess novel alternative methods of analyzing water quality performance indicators for constructed treatment wetlands. Concerning the accuracy of prediction, SOM showed a better performance compared to both KNN and SVM. Moreover, SOM had the potential to visualize the relationship between complex biochemical variables. However, optimizing the SOM requires more time in comparison to KNN and SVM because of its trial and error process in searching for the optimal map. The results suggest that BOD and SS can be efficiently estimated by applying machine learning tools with input variables such as redox potential and conductivity, which can be monitored in real time. Their performances are encouraging and support the potential for future use of these models as management tools for the day-to-day process control.

[1]  Heinrich Werner,et al.  New neural network types estimating the accuracy of response for ecological modelling , 2001 .

[2]  Yoon-Seok Timothy Hong,et al.  Analysis of a municipal wastewater treatment plant using a neural network-based pattern analysis. , 2003, Water research.

[3]  Jay H. Lee,et al.  Support vector machines for learning to identify the critical positions of a protein. , 2005, Journal of theoretical biology.

[4]  Young-Seuk Park,et al.  Water quality assessment using diatom assemblages and advanced modelling techniques , 2004 .

[5]  Krist V. Gernaey,et al.  Activated sludge wastewater treatment plant modelling and simulation: state of the art , 2004, Environ. Model. Softw..

[6]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[7]  Gail A. Carpenter,et al.  ARTMAP-IC and medical diagnosis: Instance counting and inconsistent cases , 1998, Neural Networks.

[8]  Holger R. Maier,et al.  Use of artificial neural networks for predicting optimal alum doses and treated water quality parameters , 2004, Environ. Model. Softw..

[9]  A. G. Frenich,et al.  Application of the Kohonen neural network in coastal water management: methodological development for the assessment and prediction of water quality. , 2001, Water research.

[10]  Wei-Zhen Lu,et al.  Potential assessment of the "support vector machine" method in forecasting ambient air pollutant trends. , 2005, Chemosphere.

[11]  John Iovine.  Understanding Neural Networks , 1998 .

[12]  Miklas Scholz.  Case study: design, operation, maintenance and water quality management of sustainable storm water ponds for roof runoff. , 2004, Bioresource technology.

[13]  Monique Polit,et al.  Prediction of parameters characterizing the state of a pollution removal biologic process , 2005, Eng. Appl. Artif. Intell..

[14]  Maged M. Hamed,et al.  Prediction of wastewater treatment plant performance using artificial neural networks , 2004, Environ. Model. Softw..

[15]  Shang-Lien Lo,et al.  Diagnosing reservoir water quality using self-organizing maps and fuzzy theory. , 2002, Water research.

[16]  R. Céréghino,et al.  Spatial analysis of stream invertebrates distribution in the Adour-Garonne drainage basin (France), using Kohonen self organizing maps , 2001 .

[17]  Esa Alhoniemi,et al.  Self-organizing map in Matlab: the SOM Toolbox , 1999 .

[18]  Francis Eng Hock Tay,et al.  Support vector machine with adaptive parameters in financial time series forecasting , 2003, IEEE Trans. Neural Networks.

[19]  H Prade,et al.  An introduction to fuzzy systems. , 1998, Clinica chimica acta; international journal of clinical chemistry.

[20]  Jan Broeze,et al.  Generalised and instance-specific modelling for biological systems , 1999, Environ. Model. Softw..

[21]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[22]  Miklas Scholz,et al.  Wetland Systems to Control Urban Runoff , 2006 .

[23]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[24]  Gérard Lacroix,et al.  Assessment of self-organizing maps to analyze sole-carbon source utilization profiles. , 2005, Journal of microbiological methods.

[25]  Miklas Scholz,et al.  Treatment of gully pot effluent containing nickel and copper with constructed wetlands in a cold climate , 2004 .

[26]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[27]  David E. Booth,et al.  A comparison of supervised and unsupervised neural networks in predicting bankruptcy of Korean firms , 2005, Expert Syst. Appl..

[29]  Miklas Scholz,et al.  Mature Experimental Constructed Wetlands Treating Urban Water Receiving High Metal Loads , 2002, Biotechnology progress.

[30]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[31]  Lluís A. Belanche Muñoz,et al.  Prediction of the bulking phenomenon in wastewater treatment plants , 2000, Artif. Intell. Eng..

[32]  Zhide Hu,et al.  Prediction of electrophoretic mobility of substituted aromatic acids in different aqueous–alcoholic solvents by capillary zone electrophoresis based on support vector machine , 2004 .

[33]  Miklas Scholz,et al.  Performance predictions of mature experimental constructed wetlands which treat urban water receiving high loads of lead and copper. , 2003, Water research.

[34]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[35]  Abhijit Mukherjee,et al.  Self-organizing neural network for identification of natural modes , 1998 .

[36]  Miklas Scholz,et al.  Neural Network Simulation of the Chemical Oxygen Demand Reduction in a Biological Activated‐Carbon Filter , 2002 .

[37]  Kai Chen,et al.  Using support vector classification for SAR of fentanyl derivatives , 2005, Acta Pharmacologica Sinica.

[38]  Heikki Mannila,et al.  Principles of Data Mining , 2001, Undergraduate Topics in Computer Science.

[39]  M. D. Luque de Castro,et al.  Use of chemometrics and mid infrared spectroscopy for the selection of extraction alternatives to reference analytical methods for total fat isolation , 2004 .

[40]  Ping-Feng Pai,et al.  Support Vector Machines with Simulated Annealing Algorithms in Electricity Load Forecasting , 2005 .

[41]  Seref Naci Engin,et al.  Determination of the relationship between sewage odour and BOD by neural networks , 2005, Environ. Model. Softw..

[42]  Iván Machón González,et al.  Self-organizing map and clustering for wastewater treatment monitoring , 2004, Eng. Appl. Artif. Intell..