专业英语.docx

1、专业英语 专业英语 组员 张强 闵韩杰 马士博 杨瑞文Detection of water-quality contamination events based on multi-sensor fusion using an extented DempsterShafer method水污染事件检测质量的基于多传感器融合使用extented dempstershafer方法 基于多传感器使用Dempster理论方法检测水质污染事件AbstractThis study presents a method for detecting contamination events of sources

2、of drinking water based on the DempsterShafer (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 (

3、AR) model. The AR model predicts future water-quality parameters using recent measurements of these parameters made with automated (on-line) water-quality sensors. F Next, a probabilistic method assigns probabilities to the time series of residuals formed by comparing predicted water-quality paramet

4、ers 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 t

5、his 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 drink

6、ing water has been contaminated. This papers 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

7、 tests demonstrated that the extended D-S fusion method achieves a low false alarm rate and high probabilities of detecting water contamination events.摘要本研究提出了一种用于检测基于Dempster Shafer饮用水源污染事件的方法（D-S）证据理论。该检测方法具有保护水供应系统免受意外和故意污染事件的目的。这是第一次使用一个自回归预测未来水质参数（AR）模型的实现。AR模型预测未来水质参数，使用这些参数进行自动测量（在线）近期水质传感器。其

8、次，概率方法分配的概率与阈值比较预测水质参数形成的时间序列的残差。最后，D-S证据融合方法寻找残差异常的概率和使用的搜索结果来判断水质是正常的（即，无污染或者污染）。D-S证据融合方法改进和扩展，本文采用加权平均水污染的证据，通过对水质参数异常的概率性分析。扩展的D-S融合方法测定有很高的概率是正确的关于是否饮用水源被污染。本文的方法用于检测水污染事件进行了水质时间序列自动（在线）水质传感器。此外，一个小规模的实验，水管网检测水污染事件。两试验表明，扩展的D-S融合方法具有较低的误报率和检测水污染事件的高概率。1. IntroductionEarly warning systems (EWS)

9、 for water quality are becoming more frequently used by drinking-water purveyors and water-quality monitoring agencies. In 2005, the US Environmental Protection Agency (USEPA) defined EWS as an integrated system for monitoring, analyzing, interpreting, and communicating data, which can then be used

10、to make decisions that are protective of public health and minimize unnecessary concern and inconvenience to the public 1. Most water-quality EWS detect water contamination events based on water-quality criteria. In other words, a water contamination event is declared when real-time water quality da

11、ta are outside the expected range of allowable water-quality criteria, at which point an alert is issued. Such exceedance-criteria event detection method, however, may overlook implicit information present in the water quality measurements and may cause a high false alarm rate (FAR) and false negati

12、ve rate (FNR) 2, 3.1简介早期预警系统（EWS）水质越来越频繁使用的饮用水供应商和水质监测机构。2005，美国环境保护署（USEPA）定义为“一种监测预警系统，综合系统分析，解释，并传送数据，然后可以用来做决定，保护公众健康和减少不必要的关注和对公众造成的不便” 1 。大多数水质检测水污染事件预警系统基于水质标准。换句话说，水污染事件时宣布实时水质数据超出允许的水质量标准的预期范围，在这一点上发出警报。这种超越标准的事件检测方法，然而，可能忽略了隐性信息在测试水质现状及可能引起的高误报率（FAR）和假阴性率（FNR） 2，3 。In 2005, Hall et al 4 de

13、monstrated that changes in water-quality parameters, which potentially indicate contamination, can be detected using real- or near real-time sensors. Empirical evidence shows that water quality parameters, such as pH, conductivity, total or free chlorine and TOC (total organic carbon), are sensitive

14、 indicators of nicotine, arsenic trioxide, aldicarb and Escherichia coli contaminants. Motivated by this type of empirical evidence, a class of methods named anomaly-based water-contamination event detection has garnered increasing attention. The existing methods for anomaly detection of water-conta

15、mination events based on online measurements of water-quality parameters are mainly divided into three categories, namely, statistical, artificial intelligence and data mining methods. Statistical methods are based on time-series prediction with fixed-length moving-time window and a single water qua

16、lity parameter, which cannot track well trends present in water quality data 2, 3, 57. Artificial intelligence (AI) methods, such as artificial neural networks (ANN) and support vector machines (SVM), classify water quality data into normal and anomalous classes after supervised learning training 2,

17、 3, 8. Data-mining methods, such as K-means classification and the multivariate nearest-neighbor (MV-NN) algorithm, which combine different water-quality parameters and location information, are also used for protecting drinking water systems 2, 5, 6, 9, 10. In addition to the above three categories

18、, several researchers introduced data-fusion methods to combine various types of information, for example, operational data 11, additional station-specific features 8 and data from multiple monitoring stations 12 to improve the detection of water-contamination events. Although research on water-cont

19、amination event detection has proliferated in recent years, careful analysis of those methods reveals that many of them still have several shortcomings. Specially, they (1) have a high rate of false alarms and false negatives in practical applications due to the complexity and incompleteness of wate

20、r quality data; (2) could not realize multi-feature fusion to obtain a comprehensive evaluating result; (3) are cumbersome, computationally demanding and unsuitable for online detection; (4) need a large number of real water-quality contamination events for model training, yet the latter events are

21、rare.2005，霍尔等人 4 表明，水质参数的变化，这可能表明污染，可以使用实时或接近实时的传感器检测。经验证据表明，水质参数，如pH值，电导率，总的和游离氯和TOC（总有机碳），是尼古丁的敏感指标，三氧化二砷，涕灭威，大肠杆菌污染。出于这类证据，一类方法基于水污染事件检测已经获得了越来越多的关注异常。现有的水污染事件，基于水质参数在线测量的异常检测方法主要分为三类，即，统计，人工智能和数据挖掘的方法。统计方法是基于固定长度移动时间窗口的时间序列预测和一个单一的水质参数，不能跟踪趋势，水质数据 2，3，57 。人工智能（AI）的方法，如人工神经网络（ANN）和支持向量机（SVM），将水质数

22、据为正常和异常类，经过学习训练 2，3，8 。数据挖掘的方法，如k-均值分类和多元的最近邻（mv-nn）算法，并结合不同的水质参数和位置信息，也可用于保护饮用水系统 2，5，6，9，10 。除了以上三类，一些研究人员介绍了数据融合方法，将各种类型的信息，例如，操作数据 11 ，其他站的具体特点 8 和数据从多个监测站 12 提高水污染事件的检测。虽然对水污染事件检测的研究在近几年激增，这些方法仔细分析发现，他们中的许多人仍然有几个缺点。特别是，他们（1）在实际应用中存在较高的误报率和漏报率由于水质数据的复杂性和不完整性；（2）无法实现多特征融合得到综合评价结果；（3）繁琐，计算能力的要求，适合

23、在线检测；（4）需要大量的实际水质污染事件模型的训练，但后者的事件是罕见的。Considering the shortcomings commonly found in existing methods, this study proposes a water-contamination event detector based on an extension and improvement of the DempsterShafer (D-S) evidence theory. D-S evidence theory can be regarded as an extension of cl

24、assical probabilistic reasoning, which makes inferences from incomplete and uncertain knowledge, provided by different independent knowledge sources. A key advantage of D-S evidence theory is its ability to deal with lack of knowledge and missing information about a phenomenon of interest. In partic

25、ular, it provides explicit estimation of the imprecision and conflicts that may exist among different sources of information 14. Furthermore, D-S evidence theory is less computationally intensive than other competing methods 15. Given the referred advantages, D-S evidence theory has been widely appl

26、ied in the field of event detection, multi-sensor networks 16, pattern classification 17 and hyperspectral imagery processing 18. Sentz and Ferson 14 presented several applications of the D-S evidenced theory in detail. Among these applications one can cite network anomaly detection 13, 19, failure

27、detection 20, 21 and road traffic accident detection 22. These applications have shown that D-S evidence theory has been successful in solving detection problems where differences in some characteristics of the evidence are not enough to distinguish normal evidence or anomalous evidence 13.针对常见的现有方法

28、的不足，本文提出了一种基于扩展和Dempster谢弗改善水污染事件检测器（D-S）证据理论。D-S证据理论可以看成是古典概率推理的延伸，使得不完整、不确定知识的推论，由不同的独立的知识来源。D-S证据理论的一个关键优势是其应对一个现象感兴趣的知识和信息缺乏能力的缺失。特别是，它提供的不精确性和可能存在的冲突的不同信息源之间的显式估计 14 。此外，D-S证据理论比其他竞争方法 15 不计算密集。鉴于简称D-S证据理论的优点，已广泛应用于事件检测领域，传感器网络 16 ，模式分类的高光谱图像处理 17 和 18 。森茨和汉斯 14 提出了应用D-S证据理论进行了详细介绍。这些应用程序可以引用网络

29、异常检测 13，19 中，故障检测 20，21 和 22 道路交通事故检测。这些应用表明，D-S证据理论在证据的一些特征差异不足以区分“正常”或“异常”的证据的证据 13 解决检测问题是成功的。In this study, the improved D-S theory for the detection of water-contamination events relies on the times series of residuals of water-quality parameters predictions and the use of weighted-averaging an

30、d time-dimension information to resolve conflicts or ambiguities that arise when attempting to detect water-contamination events. Such conflicts or ambiguities are named herein evidence conflicts. Simulated and experimental water-contamination events of different severity are used to test the propos

31、ed approach for detecting water-contamination events.在这项研究中，对水污染事件的检测改进的D-S证据理论依赖于水质参数的预测和加权平均和时间维度的信息来解决冲突或歧义出现企图检测水污染事件时，使用的时间序列的残差。这样的矛盾或歧义载明证据冲突。模拟不同程度的实验水污染事件是用来测试所提出的方法用于检测水污染事件。2. Methodology2.1. D-S evidence theory2方法论2.1D-S证据理论The D-S theory of evidence is based on the classic works of Demp

32、ster 23 and Shafer 24. The D-S theory offers an alternative to the traditional probabilistic theory for the mathematical representation of uncertainty 14. The D-S theorys applications range from expert decision support systems to multi-attribute decision-making and data fusion. In this section, the main concepts underlying the D-S theory of evidence are summarized, and basic notation is introduced.D-S证据理论是基于Dempster Shafer 23 和 24 经典作品。D-S证据理论提供了一种替代传统的概率理论对不确定性 14 的数学表示。D-S证据理论的应用范围从专家决策支持系统的多属性决策和数据融合。在这一部分中，潜在的D-S证据理论的主要概念进行了总结，并介绍了基本的符号