Document Type : Original/Review Paper

Authors

1 Computer Engineering Department, Yazd University, Yazd, Iran.

2 Computer Engineering Department, Yazd University, Yazd, Iran

10.22044/jadm.2021.10672.2202

Abstract

Due to their structure and usage condition, water meters face degradation, breaking, freezing, and leakage problems. There are various studies intended to determine the appropriate time to replace degraded ones. Earlier studies have used several features, such as user meteorological parameters, usage conditions, water network pressure, and structure of meters to detect failed water meters. This article proposes a recommendation framework that uses registered water consumption values as input data and provides meter replacement recommendations. This framework takes time series of registered consumption values and preprocesses them in two rounds to extract effective features. Then, multiple un-/semi-supervised outlier detection methods are applied to the processed data and assigns outlier/normal labels to them. At the final stage, a hypergraph-based ensemble method receives the labels and combines them to discover the suitable label. Due to the unavailability of ground truth labeled data for meter replacement, we compare our method with respect to its FPR and two internal metrics: Dunn index and Davies-Bouldin Index. Results of our comparative experiments show that the proposed framework detects more compact clusters with smaller variance.

Keywords

[1] H. Alegre et al., Performance Indicators for Water Supply Services-Second Edition, 2nd Edition, Vol. 12. IWA Publishing, 2013.
[2] A.O. Lambert, “International Report: Water losses management and techniques,” Water Supply, Vol. 2, No. 4, pp. 1–20, Sep. 2002.
[3] F. Arregui, F. Gavara, J. Soriano, and L. Pastor-Jabaloyes, “Performance Analysis of Ageing Single-Jet Water meters for Measuring Residential Water Consumption,” Water, vol. 10, No. 5, p. 612, May 2018.
[4] V. Puleo, C.M. Fontanazza, V. Notaro, M. De Marchis, G. La Loggia, and G. Freni, “Definition of Water meter Substitution Plans based on a Composite Indicator,” Procedia Eng., Vol. 70, pp. 1369–1377, Jan. 2014.
[5] L.E. Orr, V.A. Enna, and M.C. Miller, “Analysis of a Water-meter Replacement Program,” J. Am. Water Work. Assoc., Vol. 69, No. 2, pp. 68–71, Feb. 1977.
[6] D.M. Stoker, S.L. Barfuss, and M.C. Johnson, “Flow measurement accuracies of in-service residential water meters,” J. Am. Water Works Assoc., Vol. 104, No. 12, pp. E637–E642, Dec. 2012.
[7] M.R. Clinciu and R. Clinciu, “Determining the predictive reliability of the water meters using the failure rate estimation. Case study-single jet cold water meter,” IOP Conf. Ser. Mater. Sci. Eng., Vol. 399, p. 012008, Sep. 2018.
[8] F.J. Arregui, E.J. Cabrera, R. Cobacho, and J. García-Serra, “Key factors affecting water meter accuracy,” in Proceedings of the IWA Leakage Conference, Halifax, 2005, pp. 1–10.
[9] F.J. Arregui, M. Balaguer, J. Soriano, and J. García-Serra, “Quantifying measuring errors of new residential water meters considering different customer consumption patterns,” Urban Water J., Vol. 13, No. 5, pp. 463–475, Jul. 2016.
[10] C.M. Fontanazza, G. Freni, G. La Loggia, V. Notaro, and V. Puleo, “A composite indicator for water meter replacement in an urban distribution network,” Urban Water J., Vol. 9, No. 6, pp. 419–428, Dec. 2012.
 
 
 
 
 
[11] F. Yazdandoost and A. Izadi, “An asset management approach to optimize water meter replacement,” Environ. Model. Softw., Vol. 104, pp. 270–281, Jun. 2018.
[12] M. A. Cardoso, M.S. Silva, S.T. Coelho, M.C. Almeida, and D.I.C. Covas, “Urban water infrastructure asset management–a structured approach in four water utilities,” Water Sci. Technol., Vol. 66, No. 12, pp. 2702–2711, Dec. 2012.
[13] C.M. Fontanazza, V. Notaro, V. Puleo, and G. Freni, “The apparent losses due to metering errors: a proactive approach to predict losses and schedule maintenance,” Urban Water J., Vol. 12, No. 3, pp. 229–239, Apr. 2015.
[14] R.P. Weller, S.L. Barfuss, and M.C. Johnson, “The effect of surge flows on residential water meters,” AWWA Water Sci., Vol. 1, No. 1, p. e1117, Jan. 2019.
[15] M.N. Kanyama, C. Nyirenda, and N. Clement-Temaneh, “Anomaly Detection in Smart Water metering Networks,” in The 5th International Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII2017), Beijing, 2017, pp. 1–10.
[16] T. Andrysiak, Ł. Saganowski, and P. Kiedrowski, “Anomaly Detection in Smart Metering Infrastructure with the use of Time Series Analysis,” J. Sensors, Vol. 2017, pp. 1–15, 2017.
[17] A. Moahloli, A. Marnewick, and J. Pretorius, “Domestic water meter optimal replacement period to minimize water revenue loss,” Water SA, Vol. 45, No. 2 April, Apr. 2019.
[18] E. Vonk, D.G. Cirkel, and M. Blokker, “Estimating peak daily water demand under different climate change and vacation scenarios,” Water (Switzerland), Vol. 11, No. 9, p. 1874, Sep. 2019.
[19] M. Ebrahim Banihabib and P. Mousavi-Mirkalaei, “Extended linear and non-linear auto-regressive models for forecasting the urban water consumption of a fast-growing city in an arid region,” Sustain. Cities Soc., Vol. 48, p. 101585, Jul. 2019.
[20] N. Rasifaghihi, S.S. Li, and F. Haghighat, “Forecast of urban water consumption under the impact of climate change,” Sustain. Cities Soc., Vol. 52, p. 101848, Jan. 2020.
[21] G.-F. Fan, S. Qing, H. Wang, W.-C. Hong, and H.-J. Li, “Support Vector Regression Model based on Empirical Mode Decomposition and Auto Regression for Electric Load Forecasting,” Energies, Vol. 6, Nno. 4, pp. 1887–1901, Apr. 2013.
[22] Y. Chen, W.-C. Hong, W. Shen, and N. Huang, “Electric Load Forecasting based on a Least Squares Support Vector Machine with Fuzzy Time Series and Global Harmony Search Algorithm,” Energies, Vol. 9, No. 2, p. 70, Jan. 2016.
 
[23] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers Inc., 3rd Ed., San Francisco, CA, 2011.
[24] Y. Li, M. Dong, and Y. Ma, “Feature selection for clustering with constraints using Jensen-Shannon divergence,” in Proceedings of the 19th International Conference on Pattern Recognition, Tampa, Fl. Dec. 2008, pp. 1–4.
[25] R. Guzmán-Martínez and R. Alaiz-Rodríguez, “Feature Selection Stability Assessment based on the Jensen-Shannon Divergence,” Springer, Berlin, Heidelberg, 2011, pp. 597–612.
[26] F. Bagattini, I. Karlsson, J. Rebane, and P. Papapetrou, “A classification framework for exploiting sparse multi-variate temporal features with application to adverse drug event detection in medical records,” BMC Med. Inform. Decis. Mak., Vol. 19, No. 1, p. 7, 2019.
[27] J. Lin, E. Keogh, L. Wei, and S. Lonardi, “Experiencing SAX: a Novel Symbolic Representation of Time Series,” Data Min. Knowl. Discov., Vol. 15, No. 2, pp. 107–144, 2007.
[28] J. Lin, E. Keogh, S. Lonardi, and B. Chiu, “A symbolic representation of time series, with implications for streaming algorithms,” in Proceedings of the 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery, San Diego, CA, 2003, p. 2-11.
[29] C. Leys, C. Ley, O. Klein, P. Bernard, and L. Licata, “Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median,” J. Exp. Soc. Psychol., Vol. 49, No. 4, pp. 764–766, Jul. 2013.
[30] M. Goldstein and S. Uchida, “A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data,” PLoS One, Vol. 11, No. 4, p. e0152173, Apr. 2016.
[31] T. Pevný, “Loda: Lightweight on-line detector of anomalies,” Mach. Learn., vol. 102, No. 2, pp. 275–304, Feb. 2016.
[32] Y. Zhao, Z. Nasrullah, M.K. Hryniewicki, and Z. Li, “LSCP: Locally Selective Combination in Parallel Outlier Ensembles,” in Proceedings of the 2019 SIAM International Conference on Data Mining, Philadelphia, PA, 2019, pp. 585–593.
[33] F. Kaveh-Yazdy, X. Kong, J. Li, F. Li, and F. Xia, “Customer Rating Prediction using Hypergraph Kernel based Classification,” in The 2013 International Conference on Active Media Technology (AMT’13), Maebashi, Japan, 2013, pp. 187–192.
[34] K. Yu, L. Ji, and X. Zhang, “Kernel Nearest-Neighbor Algorithm,” Neural Process. Lett., Vol. 15, pp. 147–156, 2002.
[35] A. Nowak-Brzezińska and C. Horyń, “Outliers in rules-the comparison of LOF, COF, and KMEANS algorithms.,” Procedia Comput. Sci., Vol. 176, pp. 1420–1429, 2020.
[36] L. Casini, G. Delnevo, M. Roccetti, N. Zagni, and G. Cappiello, “Deep Water: Predicting Water Meter Failures Through a Human-Machine Intelligence Collaboration,” in Proceedings of the Human Interaction and Emerging Technologies, T. Ahram, R. Taiar, S. Colson, and A. Choplin, Eds. Cham, Switzerland: Springer International Publishing, 2020, pp. 688–694.
[37] A. Eftekhar, W. Juffali, J. El-Imad, T.G. Constandinou, and C. Toumazou, “Ngram-Derived Pattern Recognition for the Detection and Prediction of Epileptic Seizures,” PLoS One, Vol. 9, No. 6, p. e96235, Jun. 2014.
[38] R. Hernández-García, J. Ramos-Cózar, N. Guil, E. García-Reyes, and H. Sahli, “Improving Bag-of-Visual-Words model using visual n-grams for human action classification,” Expert Syst. Appl., Vol. 92, pp. 182–191, Feb. 2018.
[39] J. Violos, K. Tserpes, I. Varlamis, and T. Varvarigou, “Text Classification using the N-Gram Graph Representation Model over High Frequency Data Streams,” Front. Appl. Math. Stat., Vol. 4, p. 41, Sep. 2018.
[40] E. Kermany, H. Mazzawi, D. Baras, Y. Naveh, and H. Michaelis, “Analysis of Advanced Meter Infrastructure Data of Water Consumption in Apartment Buildings,” in Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, 2013, pp. 1159–1167.
[41] M. Mohammadi and M. Sarmad, “Outlier Detection for Support Vector Machine using Minimum Covariance Determinant Estimator,” J. AI Data Min., Vol. 7, No. 2, pp. 299–309, 2019.