The Application of Clustering Technique to Water Quality of Surabaya River
Abstract
Surabaya river is the source of the raw water used people in Surabaya to satisfy their daily needs. Surabaya river flow starts from Mlirip (Mojokerto) as upstream past the Sidoarjo, Gresik, and until the downstream that is Jagir Wonokromo (Surabaya). The background research studies because the water surface in Surabaya decreased perceived water quality is constantly increasing as a result most of the liquid industrial waste discharged from human activities into the channel that empties in Surabaya either directly or indirectly. Water pollutant components Surabaya river is known biological oxygen demand known as BOD, chemical oxygen demand known as COD, total suspend solid known as TSS, and dissolved oxygen known as DO. Even for biological oxygen demand components at some point status monitor heavy polluted with concentrations exceeding waterquality class sub-cleanness. K-means is one of a method for clustering objects based on their characteristics. Object of study in this research is a point source the disposal of industrial wastewater empties in Surabaya river in 2013. The first step of this research study is the normalization of water quality data biological oxygen demand, chemical oxygen demand, total suspend solid and dissolved oxygen in Surabaya river. The results of this step is the concentration of data which are in the range of 0 and 1. Concentrations were normalized value applied to K-means resulting in a model that desceibes the shape of the distibution of pollutants proximity region gruop. From the result obtained K-means suitability of water quality of each region along the Surabaya river is formed of similarity and attribute similarity. Davies Bouldin Index  is an internal evaluation scheme, for cluster validation of K-means. From the results of the cluster validation, Davies Bouldin Index values obtained for 53.742. DBI value obtained is minimal DBI to the number of 672 iterations. This paper not only theoretically situation, the water quality of Surabaya river by clustering technique, but also get a conclusion of pollutant with five cluster becomes the best value Davies Bouldin Index.
Keywords
References
Ay, M., Kisi, O. (2012). Modeling of dissolved oxygen concentration using different neural network techniques in Foundation Creek, El Paso County, Colorado, USA. J. Environ. Eng. 138 (6), 654–662.
Davies, David L.; Bouldin, Donald W. (1979). "A Cluster Separation Measure". IEEE Transactions on Pattern Analysis and Machine Intelligence. PAMI-1 (2): 224–227.
Hartigan, J.A., Wong, M.A., 1979. Algorithm AS 136, A K-means clustering algorithm.J. Roy. Statist. Soc., Ser. C (Applied Statistics) 28 (1), 100–108.
Irawan, M.I., Syaharuddin, Daryono B.U., Alvida M.R. (2013), Intelligent Irrigation Water Requirement System Based on Artificial Neural Networks and Profit Optimization for Planning Time Decision Making of Crops in Lombok Island. Journal of Theoretical and Applied Information Technology 31st December 2013. Vol. 58 No. 3
Jie, L., Peng, Y., Wensheng, L., Agudamu, L., 2014. Comprehensive Assessment Grade of Air Pollutants based on Human Health Risk and ANN Method. Procedia Eng., 2014 International Symposium on Safety Science and Technology 84, 715–720. doi:10.1016/j.proeng.2014.10.483
Li, Y., Wu, H., 2012. A Clustering Method Based on K-Means Algorithm. Phys. Procedia, International Conference on Solid State Devices and Materials Science, April 1-2, 2012, Macao 25, 1104–1109. doi:10.1016/j.phpro.2012.03.206
Milligan, G.W., Cooper, M.C., 1985. An examination of procedures for determining the number of clusters in a data set. Psychometrika 50, 159–179.
Nurul, E. H., Karnaningroem, N., 2012. The implementation of hydrodynamic model in water treatment to estimate turbidity removal. International Kournal of Environmental Science and Research Vol.2, No.1, 2012, pp.129-133
Rahmawati, S.F., M. Isa Irawan, Nieke Karnaningroem, (2014a), Application of Kohonen Self Organizing Maps for Clustering Quality of Water Surabaya river. Working Paper. Faculty of Mathematics and Natural Science, Universitas Negeri Semarang, 8 November.
Rahmawati, S.F., M. Isa Irawan, Nieke Karnaningroem (2014b), Distribution of Pollutant in Surabaya River Using Kohonen Neural Network. Working Paper. Faculty of Environmental, Institut Teknologi Sepuluh Nopember Surabaya, 3 December.
Rousseeuw, P.J., 1987. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Comput. Appl. Math. 20, 53–65.
Singh, K.P., Basant, A., Malik, A., Jain, G., 2009. Artiï¬cial neural network modeling the river water quality – a case study. Ecol. Model. 220, 888–895
Su, M.R., Yang, Z.F., Chen, B., 2012. Ecosystem health assessment of urban clusters: Method and application. Procedia Environ. Sci., 18th Biennial ISEM Conference on Ecological Modelling for Global Change and Coupled Human and Natural System 13, 1134–1142.
Surabaya, 2014. . Wikipedia Free Encycl.
Zeleňáková, M., Čarnogurská, M., Gargar, I., 2012. Prediction of Pollutant Concentration in Laborec River Station, Slovak Republic. Procedia Eng., CHISA 2012 42, 1474–1483. doi:10.1016/j.proeng.2012.07.540
Zhao, Y., Xia, X.H., Yang, Z.F., Wang, F., 2012. Assessment of water quality in Baiyangdian Lake using multivariate statistical techniques. Procedia Environ. Sci., 18th Biennial ISEM Conference on Ecological Modelling for Global Change and Coupled Human and Natural System 13, 1213–1226. doi:10.1016/j.proenv.2012.01.115
Zirnea, S., Lazar, I., Foudjo, B.U.S., Vasilache, T., Lazar, G., 2013. Cluster Analysis Based of Geochemical Properties of Phosphogypsum Dump Located Near Bacau City in Romania. APCBEE Procedia, 4th International Conference on Environmental Science and Development- ICESD 2013 5, 317–322. doi:10.1016/j.apcbee.2013.05.054
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.