Detection of water-quality contamination events based on multi-sensor fusion using an extented Dempster–Shafer method

This study presents a method for detecting contamination events of sources of drinking water based on the Dempster?Shafer (D-S) evidence theory. The detection method has the purpose of protecting water supply systems against accidental and intentional contamination events. This purpose is achieved by first predicting future water-quality parameters using an autoregressive (AR) model. The AR model predicts future water-quality parameters using recent measurements of these parameters made with automated (on-line) water-quality sensors. Next, a probabilistic method assigns probabilities to the time series of residuals formed by comparing predicted water-quality parameters with threshold values. Finally, the D-S fusion method searches for anomalous probabilities of the residuals and uses the result of that search to determine whether the current water quality is normal (that is, free of pollution) or contaminated. The D-S fusion method is extended and improved in this paper by weighted averaging of water-contamination evidence and by the analysis of the persistence of anomalous probabilities of water-quality parameters. The extended D-S fusion method makes determinations that have a high probability of being correct concerning whether or not a source of drinking water has been contaminated. This paper's method for detecting water-contamination events was tested with water-quality time series from automated (on-line) water quality sensors. In addition, a small-scale, experimental, water-pipe network was tested to detect water-contamination events. The two tests demonstrated that the extended D-S fusion method achieves a low false alarm rate and high probabilities of detecting water contamination events.

[1]  Simin Nadjm-Tehrani,et al.  Anomaly Detection in Water Management Systems , 2012, Critical Infrastructure Protection.

[2]  Mark W. Koch,et al.  Distributed Sensor Fusion in Water Quality Event Detection , 2011 .

[3]  Zhuge Jian,et al.  A Network Anomaly Detector Based on the D-S Evidence Theory , 2006 .

[4]  Hyun-U Ko,et al.  Disposable chemical sensors and biosensors made on cellulose paper , 2014, Nanotechnology.

[5]  Shi Wen-kang,et al.  Combining belief functions based on distance of evidence , 2004 .

[6]  G. C. Tiao,et al.  Consistent Estimates of Autoregressive Parameters and Extended Sample Autocorrelation Function for Stationary and Nonstationary ARMA Models , 1984 .

[7]  R. Haught,et al.  Real-time contaminant detection and classification in a drinking water pipe using conventional water quality sensors: techniques and experimental results. , 2009, Journal of environmental management.

[8]  Pao Tai Lin,et al.  Mid-infrared materials and devices on a Si platform for optical sensing , 2014, Science and technology of advanced materials.

[9]  Li Fei.  Approach for constructing basic probability assignment for evidence theory in problems of ordered propositions , 2012 .

[10]  Sean Andrew McKenna,et al.  COMBINING WATER QUALITY AND OPERATIONAL DATA FOR IMPROVED EVENT DETECTION , 2011 .

[11]  Thierry Denoeux,et al.  A neural network classifier based on Dempster-Shafer theory , 2000, IEEE Trans. Syst. Man Cybern. Part A.

[12]  J. Powell,et al.  Censored regression quantiles , 1986 .

[13]  R. Clark,et al.  Modeling and testing of reactive contaminant transport in drinking water pipes: chlorine response and implications for online contaminant detection. , 2008, Water research.

[14]  Fabio Roli,et al.  Fusion of multiple classifiers for intrusion detection in computer networks , 2003, Pattern Recognit. Lett..

[15]  J. Powell,et al.  Censored regression quantiles with endogenous regressors , 2007 .

[16]  Gang Xu,et al.  Data Fusion for Traffic Incident Detector Using D-S Evidence Theory with Probabilistic SVMs , 2008, J. Comput..

[17]  Nicolas von Ahsen,et al.  Improved real-time multiplex polymerase chain reaction detection of methylenetetrahydrofolate reductase (MTHFR) 677C>T and 1298A>C polymorphisms using nearest neighbor model-based probe design. , 2007, The Journal of molecular diagnostics : JMD.

[18]  Brian L. Mark,et al.  Mobility Tracking Based on Autoregressive Models , 2011, IEEE Transactions on Mobile Computing.

[19]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[20]  M Kovač,et al.  Launching the AquaMAV: bioinspired design for aerial–aquatic robotic platforms , 2014, Bioinspiration & biomimetics.

[21]  Katherine A. Klise,et al.  Water quality change detection: multivariate algorithms , 2006, SPIE Defense + Commercial Sensing.

[22]  Rehan Sadiq,et al.  Interpreting drinking water quality in the distribution system using Dempster-Shafer theory of evidence. , 2005, Chemosphere.

[23]  Ping Wang.  The Reliable Combination Rule of Evidence in Dempster-Shafer Theory , 2008, 2008 Congress on Image and Signal Processing.

[24]  Éloi Bossé,et al.  A new distance between two bodies of evidence , 2001, Inf. Fusion.

[25]  Paul Verschure,et al.  The state of the art in biomimetics. , 2013, Bioinspiration & biomimetics.

[26]  Arthur P. Dempster,et al.  A Generalization of Bayesian Inference , 1968, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[27]  Mark Gibson,et al.  Technologies and Techniques for Early Warning Systems to Monitor and Evaluate Drinking Water Quality: A State-of-the-Art Review , 2005 .

[28]  邓勇,et al.  A new fusion approach based on distance of evidences , 2005 .

[29]  Qi Liu,et al.  Combining belief functions based on distance of evidence , 2004, Decis. Support Syst..

[30]  Li Yun.  Multi-sensor information fusion based on integration of GA-BP network and D-S evidence theory , 2011 .

[31]  Kari Sentz,et al.  Combination of Evidence in Dempster-Shafer Theory , 2002 .

[32]  Philip K. Chan,et al.  A machine learning approach to detecting attacks by identifying anomalies in network traffic , 2003 .

[33]  George J. Klir,et al.  A design condition for incorporating human judgement into monitoring systems , 1999 .

[34]  Jing Zhao,et al.  Review of graphene-based strain sensors , 2013 .

[35]  K. Klise,et al.  TESTING WATER QUALITY CHANGE DETECTION ALGORITHMS. , 2008 .

[36]  James G. Uber,et al.  Model-Based Real-Time Detection of Contamination Events , 2009 .