无线传感器网络中传感数据估计方法研究
|
摘要
近年来，随着传感技术、无线通信技术和计算技术的发展，无线传感器网络（WirelessSensor Networks，WSN）成为感知、控制技术的发展趋势和研究热点，并受到国内外军事、工业界、学术界的强烈关注。众多学者从基础理论和应用技术角度对无线传感器网络进行了深入的研究，并取得了丰富的研究成果。同时无线传感器网络也广泛应用于军事、工业、农业、环境监测、智能交通和智能家居等诸多领域。在这些众多应用系统中，由于无线传感器节点的计算能力、存储容量、通信能力、能量等资源受限、噪声干扰和周围环境的不良影响，在传输过程中传感数据缺失或者丢失现象时有发生，甚至在某些特殊环境中，这种现象十分严重，给各种传感数据应用处理方法提出了严峻挑战。数据估计方法可以有效解决传感数据的缺失问题。此外，传感数据的估计还为无线传感器网络中的查询、聚集、节能传输、预警等应用处理方法提供强有力的支持。因此传感数据的估计对于无线传感器网络应用系统显得尤为重要。
虽然国内外学者对传感数据的估计问题开展了大量的研究工作，取得了一定的研究成果。但仍存在着一些关键问题没有解决。例如没有充分利用传感数据特性、估计方法计算复杂度高、估计精度低，以及没有考虑不确定性传感数据估计问题和传感数据流的数据模型动态变化等问题。鉴于此，本文针对这些问题开展了专项的研究工作，取得的研究成果主要包括以下几个方面：
（1）针对目前传感数据估计方法由于没有充分考虑传感数据的特性而导致具有较高计算复杂度的问题，提出了基于相关分析的传感数据估计框架。并针对目前基于支持向量回归(Support Vector Regression, SVR)的传感数据估计方法存在计算复杂度高的问题，提出了基于相关分析的最小二乘支持向量回归（Correlation Analysis-based LeastSquare Support Vector Regression，CALS-SVR）估计方法。该方法根据传感数据具有近似周期性、冗余性和时间相关的特性，通过对传感数据进行相关分析，提取与当前要估计传感数据最相关的传感数据变量，并结合最小二乘支持向量回归（Least Square SupportVector Regression，LS-SVR）估计方法对传感数据进行估计，从而大大提高估计的效率。实验表明，相对于目前提出的基于支持向量机（Support Vector Regression，SVR）和LS-SVR等传感数据估计方法，所提出的CALS-SVR具有较高的估计效率，同时具有较高的估计精度。
（2）针对目前传感数据估计方法存在的计算复杂度高、估计精度低的问题，同时考虑在无线传感器节点上实现传感数据估计问题，提出基于相关分析的多元线性回归（Correlation Analysis-based Multiple Linear Regression, CA-MLR）传感数据估计方法。该方法通过挖掘传感数据的特性，对传感数据做相关分析，然后与计算复杂度低的多元回归估计方法有机结合，从而大大提高传感数据估计方法的估计效率。实验表明，该方法具有较高的估计精度和估计效率，非常适合在无线传感器节点上实现传感数据估计。
（3）针对无线传感网络应用系统中，局部区域不确定性传感数据的处理问题，提出基于多变量主元分析（Multiple variate Principle Component Analysis，MVPCA）的不确定性传感数据处理框架。并针对区域不确定性传感数据的估计问题，提出了基于多变量主元分析的不确定性传感数据估计方法。该方法采用多变量主元分析的预处理方法提取不确定性数据的本质特征，从而减小传感数据的不确定性，然后再对传感数据进行估计，从而解决不确定性区域传感数据的估计问题。实验表明，本文所提方法能够有效对区域不确定性传感数据进行估计。
（4）针对动态传感数据流的估计方法存在着估计模型更新不及时、估计精度低的问题，提出基于卡尔曼滤波的传感数据流估计方法KF-CAMLR（Kalman Filter-CorrelationAnalysis-based Multiple Linear Regression）。该方法采用卡尔曼滤波器动态调整滤波器中的系统状态变量，同时调整传感数据估计方法中模型的参数，解决了对传感数据流中数据模型的实时跟踪的问题，从而得到较高精度的估计结果。实验结果表明，相对于同类其他方法，该估计方法具有较及时的模型更新能力、更高的估计精度和估计效率，能有效地对传感数据流的动态传感数据进行估计。
最后，本文对目前仍存在的问题和今后的研究方向提出了进一步的研究计划。
Recently, with the rapid development of sensor technology, wireless communication andcomputer techniques, the Wireless Sensor Networks (WSN) have become the evolution trendand hot research spot in sensor and control field. Great attention has been paid by the military,industry and academe field all over the world. Many researchers gave abundant findings aboutwireless sensor from both fundamental theory and application. At the same time, WSN isbeing widely applied in many fields like military, industry, agriculture, environmentmonitoring, smart traffic, smart home etc. Among these wireless sensor networks applicationsystems, the resource of low-cost wireless sensor node is constrained, i.e., capacity ofcomputing, storage, wireless communication distance and energy is very limited, and also thewireless sensor nodes are easily affected by noise, interference and surrounding environment.So during the wireless transmission, the sensor data missing often occurs, and this phenomenais worse in some special environments. This problem has become a big challenge for dataprocessing methods. And the sensor data estimation is effective way to solve this problem.Also it is a powerful tool to support data inquiry, data aggregating, energy-savingtransmission and early warning mechanism.
For the estimation of missing sensor data in wireless sensor networks, many researchershome and abroad have been doing a lot of research works and getting certian research results.But there still exist some important problems needed to be resolved. For example, thecharacteristics of the sensor data are not fully investigated and made use to estimate thesensor data, which lead to high computing complexity; The estimation accuracy is very lowwith high complexity; The estimation problem of the uncertain sensor data in a local field isnot considered; The dynamic data module of sensor data stream is not fully considered. Forthese problems, special research works are done in this paper, and the research results aregotten as follow:
(1) For the problem of most of sensor data estimation methods did not consider thecharacteristics of sensor data, whichi lead to high computational complexity, we propose acorrelation analysis-based estimation framework of sensor data. For the problem of highcomputational complexirity of SVR (Support Vector Regression)–based estimation method, based on the framework, we propose correlation analysis-based LS-SVR (Least SquareSupport Vector Regression) sensor data estimation method called CALS-SVR (CorrelationAnalysis-based LS-SVR). In this method, we consider the characteristics of the sensor data ofwireless sensor networks, and extract the most correlated sensor variable to be used as theinput of modeling and estimation. And also we adopt the LS-SVR with low computationalcomplexity to estimate the sensor data. So the estimation efficiency can be improved largely.The experiments results show that the proposed CALS-SVR has better estimation efficiencyand higher estimation accuracy compared to present sensor estimation method based SVR andLS-SVR.
(2) For the problem of high computational complexity and low estimation accuracy inexisting sensor estimation method, and also considering the implementation problem ofsensor data estimation method on the wireless sensor node of WSN. We propose thecorrelation analysis-based multiple linear regression sensor data estimation method calledCA-MLR (Correlation Analysis-based Multiple Linear Regression). In this method, weexplore the characteristics of sensor data of wireless sensor networks, and take correlationanalysis on them. And then combine with multiple regression, which has low computationalcomplexity. So the estimation efficiency can be improved largely. The experiments resultsshow that the proposed method has better estimation efficiency and accuracy, so it is verysuitable for applying on the wireless sensor node.
(3) For the problem of uncertain sensor data processing, we propose an uncertain sensordata processing framework based on MVPCA (Multiple variable Principle ComponentAnalysis). And for the problem of uncertain sensor data estimation, we propose an uncertaindata estimation method based the framework. In this method, we use the MVPCA to extractthe intrinsic feature of the uncertain sensor data. in this way, most of the uncertainty can beeliminated. Then we adopt the multiple regression based on correlation analysis to estimationthe sensor data. So the uncertain sensor data can be estimated. The experiments results showthat the proposed method can estimate the uncertain sensor data efficiently with highefficiency.
(4) For the problem of estimation mode updated not in time and big estimation error ofdynamic stream sensor data, we propose a sensor data stream estimation method, which iscalled KF-CAMLR (Kalman Filter-Correlation Analysis-based Multiple Linear Regression). In this method, the Kalman Filter is combined with multiple regression to estimate dynamicsensor data stream. The Kalman filter adjusts its working states according the estimation error,and at the same time adjusts the model parameters of the multiple regression, so theestimation model adjusts efficiently according to data model in the sensor stream. Theestimation accuracy can be improved largely. The experiments results show that the proposedsensor data stream estimation method based on Kalman can estimate dynamic sensor data insensor data stream efficiently with high estimation accuracy.
Finally， the existing problems are alalyzed and research plan for future work aredescribed.
虽然国内外学者对传感数据的估计问题开展了大量的研究工作，取得了一定的研究成果。但仍存在着一些关键问题没有解决。例如没有充分利用传感数据特性、估计方法计算复杂度高、估计精度低，以及没有考虑不确定性传感数据估计问题和传感数据流的数据模型动态变化等问题。鉴于此，本文针对这些问题开展了专项的研究工作，取得的研究成果主要包括以下几个方面：
（1）针对目前传感数据估计方法由于没有充分考虑传感数据的特性而导致具有较高计算复杂度的问题，提出了基于相关分析的传感数据估计框架。并针对目前基于支持向量回归(Support Vector Regression, SVR)的传感数据估计方法存在计算复杂度高的问题，提出了基于相关分析的最小二乘支持向量回归（Correlation Analysis-based LeastSquare Support Vector Regression，CALS-SVR）估计方法。该方法根据传感数据具有近似周期性、冗余性和时间相关的特性，通过对传感数据进行相关分析，提取与当前要估计传感数据最相关的传感数据变量，并结合最小二乘支持向量回归（Least Square SupportVector Regression，LS-SVR）估计方法对传感数据进行估计，从而大大提高估计的效率。实验表明，相对于目前提出的基于支持向量机（Support Vector Regression，SVR）和LS-SVR等传感数据估计方法，所提出的CALS-SVR具有较高的估计效率，同时具有较高的估计精度。
（2）针对目前传感数据估计方法存在的计算复杂度高、估计精度低的问题，同时考虑在无线传感器节点上实现传感数据估计问题，提出基于相关分析的多元线性回归（Correlation Analysis-based Multiple Linear Regression, CA-MLR）传感数据估计方法。该方法通过挖掘传感数据的特性，对传感数据做相关分析，然后与计算复杂度低的多元回归估计方法有机结合，从而大大提高传感数据估计方法的估计效率。实验表明，该方法具有较高的估计精度和估计效率，非常适合在无线传感器节点上实现传感数据估计。
（3）针对无线传感网络应用系统中，局部区域不确定性传感数据的处理问题，提出基于多变量主元分析（Multiple variate Principle Component Analysis，MVPCA）的不确定性传感数据处理框架。并针对区域不确定性传感数据的估计问题，提出了基于多变量主元分析的不确定性传感数据估计方法。该方法采用多变量主元分析的预处理方法提取不确定性数据的本质特征，从而减小传感数据的不确定性，然后再对传感数据进行估计，从而解决不确定性区域传感数据的估计问题。实验表明，本文所提方法能够有效对区域不确定性传感数据进行估计。
（4）针对动态传感数据流的估计方法存在着估计模型更新不及时、估计精度低的问题，提出基于卡尔曼滤波的传感数据流估计方法KF-CAMLR（Kalman Filter-CorrelationAnalysis-based Multiple Linear Regression）。该方法采用卡尔曼滤波器动态调整滤波器中的系统状态变量，同时调整传感数据估计方法中模型的参数，解决了对传感数据流中数据模型的实时跟踪的问题，从而得到较高精度的估计结果。实验结果表明，相对于同类其他方法，该估计方法具有较及时的模型更新能力、更高的估计精度和估计效率，能有效地对传感数据流的动态传感数据进行估计。
最后，本文对目前仍存在的问题和今后的研究方向提出了进一步的研究计划。
Recently, with the rapid development of sensor technology, wireless communication andcomputer techniques, the Wireless Sensor Networks (WSN) have become the evolution trendand hot research spot in sensor and control field. Great attention has been paid by the military,industry and academe field all over the world. Many researchers gave abundant findings aboutwireless sensor from both fundamental theory and application. At the same time, WSN isbeing widely applied in many fields like military, industry, agriculture, environmentmonitoring, smart traffic, smart home etc. Among these wireless sensor networks applicationsystems, the resource of low-cost wireless sensor node is constrained, i.e., capacity ofcomputing, storage, wireless communication distance and energy is very limited, and also thewireless sensor nodes are easily affected by noise, interference and surrounding environment.So during the wireless transmission, the sensor data missing often occurs, and this phenomenais worse in some special environments. This problem has become a big challenge for dataprocessing methods. And the sensor data estimation is effective way to solve this problem.Also it is a powerful tool to support data inquiry, data aggregating, energy-savingtransmission and early warning mechanism.
For the estimation of missing sensor data in wireless sensor networks, many researchershome and abroad have been doing a lot of research works and getting certian research results.But there still exist some important problems needed to be resolved. For example, thecharacteristics of the sensor data are not fully investigated and made use to estimate thesensor data, which lead to high computing complexity; The estimation accuracy is very lowwith high complexity; The estimation problem of the uncertain sensor data in a local field isnot considered; The dynamic data module of sensor data stream is not fully considered. Forthese problems, special research works are done in this paper, and the research results aregotten as follow:
(1) For the problem of most of sensor data estimation methods did not consider thecharacteristics of sensor data, whichi lead to high computational complexity, we propose acorrelation analysis-based estimation framework of sensor data. For the problem of highcomputational complexirity of SVR (Support Vector Regression)–based estimation method, based on the framework, we propose correlation analysis-based LS-SVR (Least SquareSupport Vector Regression) sensor data estimation method called CALS-SVR (CorrelationAnalysis-based LS-SVR). In this method, we consider the characteristics of the sensor data ofwireless sensor networks, and extract the most correlated sensor variable to be used as theinput of modeling and estimation. And also we adopt the LS-SVR with low computationalcomplexity to estimate the sensor data. So the estimation efficiency can be improved largely.The experiments results show that the proposed CALS-SVR has better estimation efficiencyand higher estimation accuracy compared to present sensor estimation method based SVR andLS-SVR.
(2) For the problem of high computational complexity and low estimation accuracy inexisting sensor estimation method, and also considering the implementation problem ofsensor data estimation method on the wireless sensor node of WSN. We propose thecorrelation analysis-based multiple linear regression sensor data estimation method calledCA-MLR (Correlation Analysis-based Multiple Linear Regression). In this method, weexplore the characteristics of sensor data of wireless sensor networks, and take correlationanalysis on them. And then combine with multiple regression, which has low computationalcomplexity. So the estimation efficiency can be improved largely. The experiments resultsshow that the proposed method has better estimation efficiency and accuracy, so it is verysuitable for applying on the wireless sensor node.
(3) For the problem of uncertain sensor data processing, we propose an uncertain sensordata processing framework based on MVPCA (Multiple variable Principle ComponentAnalysis). And for the problem of uncertain sensor data estimation, we propose an uncertaindata estimation method based the framework. In this method, we use the MVPCA to extractthe intrinsic feature of the uncertain sensor data. in this way, most of the uncertainty can beeliminated. Then we adopt the multiple regression based on correlation analysis to estimationthe sensor data. So the uncertain sensor data can be estimated. The experiments results showthat the proposed method can estimate the uncertain sensor data efficiently with highefficiency.
(4) For the problem of estimation mode updated not in time and big estimation error ofdynamic stream sensor data, we propose a sensor data stream estimation method, which iscalled KF-CAMLR (Kalman Filter-Correlation Analysis-based Multiple Linear Regression). In this method, the Kalman Filter is combined with multiple regression to estimate dynamicsensor data stream. The Kalman filter adjusts its working states according the estimation error,and at the same time adjusts the model parameters of the multiple regression, so theestimation model adjusts efficiently according to data model in the sensor stream. Theestimation accuracy can be improved largely. The experiments results show that the proposedsensor data stream estimation method based on Kalman can estimate dynamic sensor data insensor data stream efficiently with high estimation accuracy.
Finally， the existing problems are alalyzed and research plan for future work aredescribed.
引文
[1]李建中,高宏.无线传感器网络的研究进展[J].计算机研究与发展.2008:1-2页.
[2] J. Yick, B. Mukherjee, D. Ghosal. Wireless sensor network survey. Computer Networks[J].2008:2292-2330。
[3]孙利民,李建中,陈渝等.无线传感器网络[M].北京:清华大学出版社，2005:7-8页,135-140页.
[4]彭明盛，http://www.ibm.com/smarterplanet/cn/zh/[OL].，2009.
[5] http://wx.xinhuanet.com/2009-09/03/content_17588124.htm[OL].2009.
[6] Mihail Halatchev, Le Gruenwald, Estimating Missing Values in Related Sensor DataStreams[C], Proceedings of the11th International Conference on Management of Data.Hyderabad, India,2005:83-94P.
[7]余向阳.无线传感器网络研究综述[J].单片机与嵌入式系统应用.2008:8-11页.
[8]任丰原,黄海宁,林闯.无线传感器网络[J].软件学报.2003,14（7）:1282-1291页.
[9] Priyantha N B, Chakraborty A, Balakrishnan H. The Cricket Location-SupportSystem[C]. In: Proceedings of6thACM International Conference on Mobile Computingand Networking（ACM MOBICOM）, Boston, MA, USA. ACM Press.2000:32-43P.
[10]杨军,张德运,张云翼,王毅.基于分簇的无线传感器网络数据汇聚传送协议[J].软件学报，2010,21（5）:1127-1137页
[11] O. Gnawali, R. Fonseca, K. Jamieson, D. Moss, and P. Levis. Collection tree protocol
[C], in Proceedings of the7th ACM Conference on Embedded Networked SensorSystems.ACM,2009,1-14P.
[12] S. Papadimitriou, J. Sun, and C. Faloutsos： Streaming Pattern Discovery in MultipleTime-Series[C],31st VLDB,2005.
[13] L. Gruenwald, H. Chook, and M. Aboukhamis. Using data mining to estimate missingsensor data[C]. In ICDMW,2007:291-305P.
[14] Le Gruenwald, Md. Shiblee Sadik, Rahul Sahul Shukla, et al. DEMS: a data miningbased technique to handle missing data in mobile sensor network applications[C], DMSN2010,September13,2010, Singapore:26-32P.
[15] H. Chok and L. Gruenwald. An online spatial-temporal association rule miningframework for analyzing and estimating sensor data[C]. In IDEAS,2009:475-486P.
[16]潘立强，李建中，骆吉洲，传感器网络中一种基于多元回归模型的缺失值估计算法[J]，计算机学报，2010,Vol.33,No.1:1-11页.
[17] Jaisheel Mistry, Eulufhelo Nelwamondo, Tshlidzi Marwala. Estimating Missing Data andDetermining the Confidence of the Estimate Data[C].2008Seventh internationalconference on machine learning and applications,2008:752-755P.
[18]邹长忠，无线传感器网络中基于SVR的节点数据预测算法[J]，计算机应用.30（1）：127-136页.
[19] Yan Xiaozhen,Xie Hong, Wang Tong,et al. A Data Predicting Method based on LS-SVRIn Wireless Sensor Network[C],2010sencond international conference on wirelessnetworks and information systems (WNIS2010):73-76P.
[20] Can, Basaran, Sebnem Baydere, Giancarlo. Rearch integration: Platform survey criticalevaluation of platform commonly used in embedded wisents research [J]. Embedded WiseNts,2006, research document,1-109P.
[21] Madden S.英特尔－伯克利研究实验室数据[OL].[2006-08-08]. http://berkeley.Intel-research. Net/lab data.
[22] Tolle G. Sonoma红木监测数据[OL].[2006-08-08].http://www.cs.berkeley.edu/～get/sonoma,2005.
[23]韩敏.混沌时间序列预测理论与方法[M].北京:中国水利水电出版社,2007:155-185页.
[24]吕金虎，陆君安，陈士乐.混沌时间序列分析及其应用[M].武汉:武汉大学出版社，2002.
[25] Federico Palacios-González. TVCAR Models for Forecasting. Neurocomputing.2007,(70):2379-2391P.
[26]王海燕,卢山.非线性时间序列分析及其应用[M].北京:科学出版社,2006:2-21页.
[27] Box G E P, Jenkins J. Time Series Analysis: Forecasting and Control [M]. SanFrancisco,Holden-Day,1976.
[28]范剑青,姚琦伟.非线性时间序列—建模、预报及应用[M].北京:高等教育出版社,2005.
[29] Winters P R. Forecasting Sales by Exponentially Weighted Moving Averages [J]. JournalManagement Science,1960,(6):324-342P.
[30] Box G E P, Jenkins J. Time Series Analysis: Forecasting and Control [M]. SanFrancisco,Holden-Day,1976.
[31] Martin C. Nonlinear Prediction of Chaotic Time Series [J]. Physica D: NonlinearPhenomena,1989,35(3):335-356P.
[32] Tong H, Lim K S.Threshold Auto-regression Limit Cycles and Cyclical Data [J]. Journalof Royal Statistical Society, Series B,1980(42):245-292P.
[33] Bollerslev T. Generalised Autoregressive Conditional Heteroscedasticity [J]. Journal ofEconometrics,1986,(31):307-327P.
[34] Martin C. Nonlinear Prediction of Chaotic Time Series [J]. Physica D: NonlinearPhenomena,1989,35(3):335-356P.
[35] Irie B, Miyake, S. Capabilities of Three-layed Perceptrons[C]. In Proceedings of theIEEE Internation Conference on Neural Networks,1988:323-329P.
[36] Hu M J C. Application of the Adaline System to Weather Forecasting [D]. Master thesis,Standford Electronic Laboratories,1964.
[37] Werbos P J. Beyond Regression: New Tools for Prediction and Analysis in theBehavioral Science [D]. PH.D. Thesis, Harvard University,1974.
[38] Park Y R, Munay T J, Chen C. Predicting Sun Spots Using a Layed Perceptron NeuralNetwork [J]. IEEE Transactions on Neural Networks,1996(2):501-505P.
[39] Peiming Xin, Hong Zhao. Time Series Forecasting Using Multilayer Neural NetworkConstructed By a Monte-Carlo Based Algorithm [C].1st IEEE Symposium on WebSociety, Lanzhou, China,2009:264-267P.
[40] Vapnik V., Golowich S. and Smola A. Support vector method for function approximation,regression estimation, and signal processing [C]. In: Advances in Neural Informationprocessing Systems9, Cambridge, MA, MIT press,1997:281-287P.
[41] Weston J., Extensions to the support vector method [M], Phd. Thesis, Royal HollowayUniversity of London,1999.
[42] Zhang Xue-Gong. Using class-center vectors to build support vector machines[C].NNSP’99,1999.
[43] Jianqing Fan, Qiwei Yao. Nonlinear Time Series: Nonparametric and parametric methods[J]. Springer-Verlag, New York,2003:12-123P.
[44] Osuna E., Freund R., Girosi F., Training support vector machines: An application to factdetection [C]. In: Proceedings of CVPR’97, New York, NY, IEEE,1997:130-136P.
[45] Yang. Y, Expert network: Effective and efficient learning from human decisions in textcategorization and retrieval [C]. In Proceedings of the Seventeenth International ACMSIGIR Conference on Research and Development in Information Retrieval,1994:13-22P.
[46] Vladimir N. Vapnik. Statistical Learning Theory [M].许建华,张学工译.北京:电子工业出版社,2004:35-60页.
[47]邓乃扬,田英杰.数据挖掘中的新方法:支持向量机[M].科学出版社,2004:255-259页.
[48] Lee Y, Mangasarian O L. RSVM: Reduced support vector machines[C]. In Proceedingsof the First SIAM Intemational Conference on Data Mining,2001.
[49] Kuan-Ming Lin,Chih-Jen Lin. A study on reduced support vector machines [J]. IEEETransactions on Neural Networks,14(6),2003:1449-1459P.
[50] Suykens J, Vandewalle J. Least square support vector machine classifiers [J]. NeuralProcessing Letters,9(3),1999:293-300P.
[51] Suykens J, Branbanter J D, Lukas L.Weighted least squares support vector machines:robustness and spare approximation [J]. Neuro computing,48(l),2002:85-105P.
[52] Cool, A. L. A review of methods for dealing with missing data; Annual Meeting of theSouthwest Educational Research Association [M], Dallas, TX.2000.
[53] Iannacchione, V. G. Weighted sequential hot deck imputation macros [M]. Proceedings ofthe SAS Users Group International Conference;1982.
[54] Jiang, N., Gruenwald, L.: CFI-Stream: Mining Closed Frequent Itemsets in Data Streams
[C]. In: ACM SIGKDD international conference on knowledge discovery and datamining (2006).
[55] G. McLachlan and K. Thriyambakam; the EM Algorithm and Extensions [M]. JohnWiley&Sons;1997.
[56] Allison, P. D. Missing data [D]. Thousand Oaks, CA: Sage;2002.
[57] Little, R. J. A., Rubin, D. B. Statistical analysis with missing data [M]. John Wiley andSons.1987.
[58] D.Rubin. Multiple Imputations for Nonresponce in Surveys [M]. John Wiley&Sons;1987.
[59] J. Shafer; Model-Based Imputations of Census Short-Form Items; Annual ResearchConference [M], Washington, DC: Bureau of the Census,1995.
[60] Gelman, J. Carlin, H. Stern, and D. Rubin; Bayesian Data Analysis [M].Chapman&Hall;1995.
[61] S. Madden, M. Franklin, J. Hellerstein, and W. Hong.Tinydb: An acquisitional queryprocessing system for sensor networks [J]. Transactions on Database Systems,2005.
[62] S. Papadimitriou, J. Sun, and C. Faloutsos： Streaming Pattern Discovery in MultipleTime-Series[C],31st VLDB,2005.
[63] Nan Jiang.A data imputation model in sensor databases[C]. HPCC2007:86-96P.
[64] Yingshu Li, Chunyu Ai, Wiwek P.Deshmukh, YiweiWu. Data estimation in sensornetworks using physical and statistical[C], proceedings of the28th IEEE InternationalConference on Distributed Computing Systems (ICDCS2008), Beijing, China,2008:538-545P.
[65]潘立强，李建中.传感器网络中一种基于时-空相关性的缺失值估计算法[J].计算机研究与发展.2009, Vol.46(12):2101-2110页.
[66] N. Vijayakumar and B. Plale. Missing event prediction in sensor data streams usingkalman filters[C]. Knowledge Discovery from Sensor Data, Eds. Taylor and Francis,2009.
[67] Nan Jiang, Zhiqiang Chen. Post mining of non-redundant association rules for sensordata estimation[C].20102nd international conference on education technology andcomputer (ICETC2010),2010:102-106P.
[68] Yan xiaozhen,Xie Hong, Wang Tong, A Multiple Linear Regression Data PredictingMethod Using Correlation Analysis for Wireless Sensor Networks [J]. Journal ofComputational Information Systems (JCIS),2011,7(11):4105-4112P.
[69] Jaisheel Mistry, Eulufhelo Nelwamondo, Tshlidzi Marwala. Estimating Missing Data andDetermining the Confidence of the Estimate Data [C].2008Seventh internationalconference on machine learning and applications,2008:752-755P.
[70] Yuan Yuan Li, Lynne E.Parker, A spatial-temporal imputation technique for classificationwith missing data in a wireless sensor network [C]. International Conference onIntelligent Robots and Systems, Nice, France, Sept,22-26,2008:3272-3279P.
[71] Biljana Mileva-Boshkoska, Mile Stankovski. Prediction of missing data for ozoneconcentrations using support vector machines and radial basis neural networks [J].Informatical31(2007):425-430P.
[72] Yan Xiaozhen,Xie Hong, Wang Tong,et al. A Data Predicting Method based on LS-SVRin Wireless Sensor Network [C].2010sencond international conference on wirelessnetworks and information systems (WNIS2010):73-76P.
[73] L. Gruenwald, H. Chook, and M. Aboukhamis. Using data mining to estimate missingsensor data [C]. In Proceedings of ICDMW,2007.
[74] H. Chok and L. Gruenwald. An online spatio-temporal association rule miningframework for analyzing and estimating sensor data [C]. In IDEAS,2009
[75] Le Gruenwald, Md. Shiblee Sadik, Rahul Shukla, et al. DEMS: A data mining basedtechnique to handle missing data in mobile sensor network applications [C]. ACMDMSN2010,26-32P.
[76] Nan Jiang, Zhiqiang Chen. Post mining of non-redundant association rules for sensordata estimation [C].20102nd international conference on education technology andcomputer (ICETC2010),2010:102-106P.
[77] Le Gruenwald, Hanqing Yang, Md.Shiblee Sadik, et al.Using data mining to handlemissing data in multi-hop sensor network applications [C]. MobiDE2010, June6,2010,Indian apolis, Iindiana, USA,2010:9-16P.
[78] Qin, Yongsong; Zhu, Xiaofeng; Zhang, Jilian; Zhang, Shichao Source:2006IEEEInternational Conference on Industrial Informatics, INDIN'06,1081-1086P.
[79] Yuan Yuan Li, Lynne E.Parker, A spatial-temporal imputation technique for classificationwith missing data in a wireless sensor network [C]. International Conference onIntelligent Robots and Systems, Nice, France, Sept,22-26,2008:3272-3279P.
[80] Vadim V. Ayuyev, Joseph Jupin, Philip W. Harris, et al. Dynamic Clustering-basedEstimation on Missing Value in Mixed Type Data [C]. Data Warehousing and KnowledgeDiscovery-11th International Conference (DaWaK2009),2009:366-377P.
[81] Deshpande, A.,&Guestrin C.,&Madden, S.Using probabilistic models for datamanagement in acquisitional environments [C]. The Conference on Innovative DataSystems Research,2005.
[82] Zhang H, Moura J M F, Krogh B H. Estimation in sensor networks: A graph approach [C],Proceedings of the4th international Symposium on Information Processing in SensorNetworks. Los Angeles, California,2005:203-209P.
[83] Louis Atallah, Ahmed Elsaify, Benny Lo, Nicholas S.Hopkinson,et al. Gaussian processprediction for cross channel consensus in body sensor networks[C].the5th internationalsummer school and symposium on medical devices and biosensors,2008:165-168P.
[84] E. Elnahrawy, Research directions in sensor data streams: Solutions and challenges [J],Rutgers University, Tech. Rep. DCIS-TR-527,2003.
[85] G. McLachlan and K. Thriyambakam; the EM Algorithm and Extensions [J]. John Wiley&Sons;1997.
[86] O. Troyanskaya, M. Cantor, G. Sherlock, P. Brown, T.Hastie, R. Tibshirani, D. Botstein,and R. Altman. MissingValue Estimation Methods for DNA Microarrays [C].Bioinformatics,17,520-525P,2001.
[87] L. Gruenwald, H. Chok, and M. Aboukhamis. Mining to Estimate Missing Sensor Data
[C]. Conference on Data Mining Workshops, Oct.2007.
[88] Mihail Halatchev, Le Gruenwald. Estimating Missing Values in Related Sensor DataStreams [C]. In the proceeding of Conf. on Management of Data (2005).
[89] Jiang N, Gruenwald L. Estimating missing data in data streams, Proceedings of the12thInternational Conference on Database Systems for Advanced Applications [C]. BangkokThailand,2007:981-987P.
[90] W. Zhao and Y. Liang, A Systematic Probabilistic Approach for Estimation in DenseWireless Sensor Networks [C]. In IEEE Wireless Communications&NetworkingConference,2008
[91] Y. Li and L. Parker, A spatial-temporal imputation technique for classification withmissing data in a wireless sensor network [C]. In IEEE/RSJ International Conference onIntelligent Robots and Systems,2008. IROS2008,2008,3272–3279P.
[92] O. Gnawali, R. Fonseca, K. Jamieson, D. Moss, and P. Levis, Collection tree protocol [C].In Proceedings of the7th ACM Conference on Embedded Networked SensorSystems.ACM,2009,1–14P.
[93] N. Vijayakumar and B. Plale. Sensor Data Streams Using Kalman Filters [M]. bookchapter in Knowledge Discovery from Sensor Data, Taylor and Francis/CRC Press,2009
[94] Jong Chern Lin, C.J. Bleakley. Robust Data Collectiong and Lifetime Improvement inWireless Sensor Networks through Data Imputation [C].2010Fifth internationalconference on systems and networks communication,2010:64-69P.
[95] Guiyi Wei, Yun Ling, Binfeng Guo, et al. Prediction-based data aggregation in wirelesssensor networks: Combining grey model and Kalman filter[C]. ComputerCommunications,34(2011):793-802P.
[96] M. Takruri, S. Rajasegaral, S. Challa, et al. Spatio-temporal modelling-based drift-awarewireless sensor networks [J]. LET Wirel. Sens. Syst.2011,1(2):110-122P.
[97]纪文武.农业综合环境无线传感器网络监测系统[OL]，http://211.137.252.55:8080/agr/，2010.
[98] Vapnik V N. The nature of statistical learning theory [M]. New York: Springer,1995.
[99]袁亚湘，孙文瑜.最优化理论与方法[M].北京：科学出版社，第一版，2005,404-417.
[100]王传安.基于信息熵SVM的ICMP隐蔽通道检测研究[M].江苏大学硕士论文,2009-11-01.
[101] Scholkopf B, Smola A. Learning with Kernels [M]. MIT Press, Cambridge,MA.2002.
[102] Suykens J A K, Van Gestel T, De Brabanter J, De Moor B, Vandewalle J. Leastsquares support vector machines [M], Singapore: World scientific Publishing Co., Pte,Ltd,2002.
[103]计量经济学基础[M]，南开大学译，2007，天津：南开大学出版社.
[104]王黎明，陈颖，杨楠.应用回归分析[M],上海，复旦大学出版社，2008.
[105] Ryo Sugihara, Andrew A. Chien, Accuracy-aware data modeling in sensornetworks[C], SenSys2005, proceedings of the3rd international conference on Embeddednetworked sensor systems, New York, NY, USA.
[106] D. Papadias, Y. Tao, P. Kalnis, and J. Zhang, Indexing spatio-temporal datawarehouses [M].2002.
[107] Niki Trigoni, Yong Yao, Alan Demers, Johannes Gehrke, and Rajmohan Rajaraman.Multi-query Optimization for Sensor Networks [J]. Acta Electronica Sinica;2008-04.
[108] He T, B M, Stankovic J A, Abdelzather T F.AIDI: Adaptive application independentdata aggreation in wireless sensor networks [J]. ACM Transactions on EmbeddedComputing system，2004,3(2):426-457P.
[109] Green T J, Tannen V. Models for imcomplete and probabilistic information[J]. IEEEData Engineering Bulletin,2006,29(1):17-24P.
[110] R. Cheng and S. Prabhakar. Managing uncertainty in sensor databases[C]. InSIGMOD Record issue on Sensor Technology, December2003.
[111] Ljosa V, Singh A K. APLA: Indexing Arbitrary Probability Distributions [C]. InProceedings of the23rd IEEE International Conference on Data Engineering. Istanbul,2007:946-955P.
[112] R. Cheng, Y. Xia, S. Prabhakar, R. Shah, and J. Vitter. Efficient indexing methods forprobabilistic threshold queries over uncertain data [C]. In Proc. VLDB,2004.
[113] Pei J, Hua M, Tao Y F, Lin X M. Query answering techniques on uncertian andprobabilistic data: Tutorial summary[C]. Proceedings of the2008ACM SIGMODInternational Conference on Management of Data. Vancouver,2008:1357-1364P.
[114] Hua Ming, Pei Jian, Zhang Wenjie, Lin Xuemin. Ranking queries on uncertain data:A probabistic threshold approach[C]. Proceedings of the2008ACM SIGMODInternational Conference on Management of Data. Vancouver,2008:673-686P.
[115]何丽娟，周鸣争，陶皖,江自兵.无线传感器网络中不确定数据的估计算法[J].计算机工程与应用，2011,47(28):100-102页.
[116] Hyun Lee Jae Sung Choi Ramez Elmasri.Sensor Data Fusion using DSm Theory forActivity Recognition under Uncertainty in Home-based Care[C]. In proceeding ofInternational conference on advanced information netwrorking and applications2009:517-524P.
[117]任秀丽，田洋.传感器网络中基于预处理证据理论的数据融合[J].计算机应用，2011,31(7)：1992-1994页.
[118] Yang Zhang, Nirvana Meratnia, Paul Havinga. Outlier detection techniques forwireless sensor networks: A survey[J]. IEEE COMMUNICATIONS SURVEYS&TUTORIALS, vol12(2),2010:1-12P.
[119] Wang Cheng, Menenti M, Li Zhaoliang. Modified principal component analysis（MPCA）for feature selection of hyper-spectral imagery [J]. IEEE International,2003,(6):3781-3783P.
[120] Mina Aminghafari, Nathalie Cheze, Jean-Michel Poggi, Multivariate denoising usingwavelets and principal component analysis [J]. In Computational Statistics&DataAnalysis,2006(50):2381-2398P.
[121] Morlet D,Peyrin F,Desseigne P,Touboul P, Rubel P. Time-scale analysis ofhigh-resolution signal-averaged surface ECG using wavelet transformation[J].Computersin Cardiology,1992:393-396P.
[122]潘立登,李大宇,马俊英.软测量技术原理与应用[M].北京,中国电力出版社,2009.
[123]胡友强，数据驱动的多元统计故障诊断及应用[D]，重庆大学博士论文.2010，7：23-27页.
[124]于秀林，任雪松.多元统计分析[M].北京：中国统计出版社，1999.
[125]潘玉松.基于主元分析的传感器故障检测与诊断[D].华北电力大学博士论文.华北电力大学.2005.
[126]苏永振.航空材料结构低速冲击健康监测研究[D].南京航空航天大学.博士论文.2010，5：93-96页.
[127]陈安龙.多数据流处理的关键技术研究[D].四川大学博士论文.2006,6:13-14页.
[128] E. Elnahrawy, Research directions in sensor data streams: Solutions and challenges[J], Rutgers University, Tech. Rep. DCIS-TR-527, May2003.
[129]Kalman, R. E.1960.A New Approach to Linear Filtering and Prediction Problems[J],Transaction of the ASME-Journal of Basic Engineering, pp.35-45（March1960）.
[130]周忠海.基于激光干涉原理的海洋灾害预警关键技术研究[M].中国海洋大学博士论文,2009-06-05
[131]孟庆春.移动机器人目标动态跟踪策略研究[M].大连海事大学硕士论文2008-06-01.
[132]Welch G., Bishop G., An introduction to the Kalman [J]. Department of ComputerScience Unniversity of North Carolina at Chapel Hill,2004:1-16P.
[133]Maybeck, Peter S. Stochastic Models, Estimation [M], and Control, Volume1,Academic Press, Inc.1979.
[134]Julier S J, Uhlman J K, Durrant-Whyten H F. A general method for approximatingnonlinear transformations of probability distributions [EB/OL].http://www.robots.ox.ac.uk/~siju/work/publication/Unscented.zip,09/27/1997.
[135]Julier S J, Uhlman J K, Durrant-Whyten H F. A new approach for the nonlineartransformation of means and convarious[C]. In filters and estimations.IEEE Trans onAutomatic Control,2000,45(3):477-482P.
[2] J. Yick, B. Mukherjee, D. Ghosal. Wireless sensor network survey. Computer Networks[J].2008:2292-2330。
[3]孙利民,李建中,陈渝等.无线传感器网络[M].北京:清华大学出版社，2005:7-8页,135-140页.
[4]彭明盛，http://www.ibm.com/smarterplanet/cn/zh/[OL].，2009.
[5] http://wx.xinhuanet.com/2009-09/03/content_17588124.htm[OL].2009.
[6] Mihail Halatchev, Le Gruenwald, Estimating Missing Values in Related Sensor DataStreams[C], Proceedings of the11th International Conference on Management of Data.Hyderabad, India,2005:83-94P.
[7]余向阳.无线传感器网络研究综述[J].单片机与嵌入式系统应用.2008:8-11页.
[8]任丰原,黄海宁,林闯.无线传感器网络[J].软件学报.2003,14（7）:1282-1291页.
[9] Priyantha N B, Chakraborty A, Balakrishnan H. The Cricket Location-SupportSystem[C]. In: Proceedings of6thACM International Conference on Mobile Computingand Networking（ACM MOBICOM）, Boston, MA, USA. ACM Press.2000:32-43P.
[10]杨军,张德运,张云翼,王毅.基于分簇的无线传感器网络数据汇聚传送协议[J].软件学报，2010,21（5）:1127-1137页
[11] O. Gnawali, R. Fonseca, K. Jamieson, D. Moss, and P. Levis. Collection tree protocol
[C], in Proceedings of the7th ACM Conference on Embedded Networked SensorSystems.ACM,2009,1-14P.
[12] S. Papadimitriou, J. Sun, and C. Faloutsos： Streaming Pattern Discovery in MultipleTime-Series[C],31st VLDB,2005.
[13] L. Gruenwald, H. Chook, and M. Aboukhamis. Using data mining to estimate missingsensor data[C]. In ICDMW,2007:291-305P.
[14] Le Gruenwald, Md. Shiblee Sadik, Rahul Sahul Shukla, et al. DEMS: a data miningbased technique to handle missing data in mobile sensor network applications[C], DMSN2010,September13,2010, Singapore:26-32P.
[15] H. Chok and L. Gruenwald. An online spatial-temporal association rule miningframework for analyzing and estimating sensor data[C]. In IDEAS,2009:475-486P.
[16]潘立强，李建中，骆吉洲，传感器网络中一种基于多元回归模型的缺失值估计算法[J]，计算机学报，2010,Vol.33,No.1:1-11页.
[17] Jaisheel Mistry, Eulufhelo Nelwamondo, Tshlidzi Marwala. Estimating Missing Data andDetermining the Confidence of the Estimate Data[C].2008Seventh internationalconference on machine learning and applications,2008:752-755P.
[18]邹长忠，无线传感器网络中基于SVR的节点数据预测算法[J]，计算机应用.30（1）：127-136页.
[19] Yan Xiaozhen,Xie Hong, Wang Tong,et al. A Data Predicting Method based on LS-SVRIn Wireless Sensor Network[C],2010sencond international conference on wirelessnetworks and information systems (WNIS2010):73-76P.
[20] Can, Basaran, Sebnem Baydere, Giancarlo. Rearch integration: Platform survey criticalevaluation of platform commonly used in embedded wisents research [J]. Embedded WiseNts,2006, research document,1-109P.
[21] Madden S.英特尔－伯克利研究实验室数据[OL].[2006-08-08]. http://berkeley.Intel-research. Net/lab data.
[22] Tolle G. Sonoma红木监测数据[OL].[2006-08-08].http://www.cs.berkeley.edu/～get/sonoma,2005.
[23]韩敏.混沌时间序列预测理论与方法[M].北京:中国水利水电出版社,2007:155-185页.
[24]吕金虎，陆君安，陈士乐.混沌时间序列分析及其应用[M].武汉:武汉大学出版社，2002.
[25] Federico Palacios-González. TVCAR Models for Forecasting. Neurocomputing.2007,(70):2379-2391P.
[26]王海燕,卢山.非线性时间序列分析及其应用[M].北京:科学出版社,2006:2-21页.
[27] Box G E P, Jenkins J. Time Series Analysis: Forecasting and Control [M]. SanFrancisco,Holden-Day,1976.
[28]范剑青,姚琦伟.非线性时间序列—建模、预报及应用[M].北京:高等教育出版社,2005.
[29] Winters P R. Forecasting Sales by Exponentially Weighted Moving Averages [J]. JournalManagement Science,1960,(6):324-342P.
[30] Box G E P, Jenkins J. Time Series Analysis: Forecasting and Control [M]. SanFrancisco,Holden-Day,1976.
[31] Martin C. Nonlinear Prediction of Chaotic Time Series [J]. Physica D: NonlinearPhenomena,1989,35(3):335-356P.
[32] Tong H, Lim K S.Threshold Auto-regression Limit Cycles and Cyclical Data [J]. Journalof Royal Statistical Society, Series B,1980(42):245-292P.
[33] Bollerslev T. Generalised Autoregressive Conditional Heteroscedasticity [J]. Journal ofEconometrics,1986,(31):307-327P.
[34] Martin C. Nonlinear Prediction of Chaotic Time Series [J]. Physica D: NonlinearPhenomena,1989,35(3):335-356P.
[35] Irie B, Miyake, S. Capabilities of Three-layed Perceptrons[C]. In Proceedings of theIEEE Internation Conference on Neural Networks,1988:323-329P.
[36] Hu M J C. Application of the Adaline System to Weather Forecasting [D]. Master thesis,Standford Electronic Laboratories,1964.
[37] Werbos P J. Beyond Regression: New Tools for Prediction and Analysis in theBehavioral Science [D]. PH.D. Thesis, Harvard University,1974.
[38] Park Y R, Munay T J, Chen C. Predicting Sun Spots Using a Layed Perceptron NeuralNetwork [J]. IEEE Transactions on Neural Networks,1996(2):501-505P.
[39] Peiming Xin, Hong Zhao. Time Series Forecasting Using Multilayer Neural NetworkConstructed By a Monte-Carlo Based Algorithm [C].1st IEEE Symposium on WebSociety, Lanzhou, China,2009:264-267P.
[40] Vapnik V., Golowich S. and Smola A. Support vector method for function approximation,regression estimation, and signal processing [C]. In: Advances in Neural Informationprocessing Systems9, Cambridge, MA, MIT press,1997:281-287P.
[41] Weston J., Extensions to the support vector method [M], Phd. Thesis, Royal HollowayUniversity of London,1999.
[42] Zhang Xue-Gong. Using class-center vectors to build support vector machines[C].NNSP’99,1999.
[43] Jianqing Fan, Qiwei Yao. Nonlinear Time Series: Nonparametric and parametric methods[J]. Springer-Verlag, New York,2003:12-123P.
[44] Osuna E., Freund R., Girosi F., Training support vector machines: An application to factdetection [C]. In: Proceedings of CVPR’97, New York, NY, IEEE,1997:130-136P.
[45] Yang. Y, Expert network: Effective and efficient learning from human decisions in textcategorization and retrieval [C]. In Proceedings of the Seventeenth International ACMSIGIR Conference on Research and Development in Information Retrieval,1994:13-22P.
[46] Vladimir N. Vapnik. Statistical Learning Theory [M].许建华,张学工译.北京:电子工业出版社,2004:35-60页.
[47]邓乃扬,田英杰.数据挖掘中的新方法:支持向量机[M].科学出版社,2004:255-259页.
[48] Lee Y, Mangasarian O L. RSVM: Reduced support vector machines[C]. In Proceedingsof the First SIAM Intemational Conference on Data Mining,2001.
[49] Kuan-Ming Lin,Chih-Jen Lin. A study on reduced support vector machines [J]. IEEETransactions on Neural Networks,14(6),2003:1449-1459P.
[50] Suykens J, Vandewalle J. Least square support vector machine classifiers [J]. NeuralProcessing Letters,9(3),1999:293-300P.
[51] Suykens J, Branbanter J D, Lukas L.Weighted least squares support vector machines:robustness and spare approximation [J]. Neuro computing,48(l),2002:85-105P.
[52] Cool, A. L. A review of methods for dealing with missing data; Annual Meeting of theSouthwest Educational Research Association [M], Dallas, TX.2000.
[53] Iannacchione, V. G. Weighted sequential hot deck imputation macros [M]. Proceedings ofthe SAS Users Group International Conference;1982.
[54] Jiang, N., Gruenwald, L.: CFI-Stream: Mining Closed Frequent Itemsets in Data Streams
[C]. In: ACM SIGKDD international conference on knowledge discovery and datamining (2006).
[55] G. McLachlan and K. Thriyambakam; the EM Algorithm and Extensions [M]. JohnWiley&Sons;1997.
[56] Allison, P. D. Missing data [D]. Thousand Oaks, CA: Sage;2002.
[57] Little, R. J. A., Rubin, D. B. Statistical analysis with missing data [M]. John Wiley andSons.1987.
[58] D.Rubin. Multiple Imputations for Nonresponce in Surveys [M]. John Wiley&Sons;1987.
[59] J. Shafer; Model-Based Imputations of Census Short-Form Items; Annual ResearchConference [M], Washington, DC: Bureau of the Census,1995.
[60] Gelman, J. Carlin, H. Stern, and D. Rubin; Bayesian Data Analysis [M].Chapman&Hall;1995.
[61] S. Madden, M. Franklin, J. Hellerstein, and W. Hong.Tinydb: An acquisitional queryprocessing system for sensor networks [J]. Transactions on Database Systems,2005.
[62] S. Papadimitriou, J. Sun, and C. Faloutsos： Streaming Pattern Discovery in MultipleTime-Series[C],31st VLDB,2005.
[63] Nan Jiang.A data imputation model in sensor databases[C]. HPCC2007:86-96P.
[64] Yingshu Li, Chunyu Ai, Wiwek P.Deshmukh, YiweiWu. Data estimation in sensornetworks using physical and statistical[C], proceedings of the28th IEEE InternationalConference on Distributed Computing Systems (ICDCS2008), Beijing, China,2008:538-545P.
[65]潘立强，李建中.传感器网络中一种基于时-空相关性的缺失值估计算法[J].计算机研究与发展.2009, Vol.46(12):2101-2110页.
[66] N. Vijayakumar and B. Plale. Missing event prediction in sensor data streams usingkalman filters[C]. Knowledge Discovery from Sensor Data, Eds. Taylor and Francis,2009.
[67] Nan Jiang, Zhiqiang Chen. Post mining of non-redundant association rules for sensordata estimation[C].20102nd international conference on education technology andcomputer (ICETC2010),2010:102-106P.
[68] Yan xiaozhen,Xie Hong, Wang Tong, A Multiple Linear Regression Data PredictingMethod Using Correlation Analysis for Wireless Sensor Networks [J]. Journal ofComputational Information Systems (JCIS),2011,7(11):4105-4112P.
[69] Jaisheel Mistry, Eulufhelo Nelwamondo, Tshlidzi Marwala. Estimating Missing Data andDetermining the Confidence of the Estimate Data [C].2008Seventh internationalconference on machine learning and applications,2008:752-755P.
[70] Yuan Yuan Li, Lynne E.Parker, A spatial-temporal imputation technique for classificationwith missing data in a wireless sensor network [C]. International Conference onIntelligent Robots and Systems, Nice, France, Sept,22-26,2008:3272-3279P.
[71] Biljana Mileva-Boshkoska, Mile Stankovski. Prediction of missing data for ozoneconcentrations using support vector machines and radial basis neural networks [J].Informatical31(2007):425-430P.
[72] Yan Xiaozhen,Xie Hong, Wang Tong,et al. A Data Predicting Method based on LS-SVRin Wireless Sensor Network [C].2010sencond international conference on wirelessnetworks and information systems (WNIS2010):73-76P.
[73] L. Gruenwald, H. Chook, and M. Aboukhamis. Using data mining to estimate missingsensor data [C]. In Proceedings of ICDMW,2007.
[74] H. Chok and L. Gruenwald. An online spatio-temporal association rule miningframework for analyzing and estimating sensor data [C]. In IDEAS,2009
[75] Le Gruenwald, Md. Shiblee Sadik, Rahul Shukla, et al. DEMS: A data mining basedtechnique to handle missing data in mobile sensor network applications [C]. ACMDMSN2010,26-32P.
[76] Nan Jiang, Zhiqiang Chen. Post mining of non-redundant association rules for sensordata estimation [C].20102nd international conference on education technology andcomputer (ICETC2010),2010:102-106P.
[77] Le Gruenwald, Hanqing Yang, Md.Shiblee Sadik, et al.Using data mining to handlemissing data in multi-hop sensor network applications [C]. MobiDE2010, June6,2010,Indian apolis, Iindiana, USA,2010:9-16P.
[78] Qin, Yongsong; Zhu, Xiaofeng; Zhang, Jilian; Zhang, Shichao Source:2006IEEEInternational Conference on Industrial Informatics, INDIN'06,1081-1086P.
[79] Yuan Yuan Li, Lynne E.Parker, A spatial-temporal imputation technique for classificationwith missing data in a wireless sensor network [C]. International Conference onIntelligent Robots and Systems, Nice, France, Sept,22-26,2008:3272-3279P.
[80] Vadim V. Ayuyev, Joseph Jupin, Philip W. Harris, et al. Dynamic Clustering-basedEstimation on Missing Value in Mixed Type Data [C]. Data Warehousing and KnowledgeDiscovery-11th International Conference (DaWaK2009),2009:366-377P.
[81] Deshpande, A.,&Guestrin C.,&Madden, S.Using probabilistic models for datamanagement in acquisitional environments [C]. The Conference on Innovative DataSystems Research,2005.
[82] Zhang H, Moura J M F, Krogh B H. Estimation in sensor networks: A graph approach [C],Proceedings of the4th international Symposium on Information Processing in SensorNetworks. Los Angeles, California,2005:203-209P.
[83] Louis Atallah, Ahmed Elsaify, Benny Lo, Nicholas S.Hopkinson,et al. Gaussian processprediction for cross channel consensus in body sensor networks[C].the5th internationalsummer school and symposium on medical devices and biosensors,2008:165-168P.
[84] E. Elnahrawy, Research directions in sensor data streams: Solutions and challenges [J],Rutgers University, Tech. Rep. DCIS-TR-527,2003.
[85] G. McLachlan and K. Thriyambakam; the EM Algorithm and Extensions [J]. John Wiley&Sons;1997.
[86] O. Troyanskaya, M. Cantor, G. Sherlock, P. Brown, T.Hastie, R. Tibshirani, D. Botstein,and R. Altman. MissingValue Estimation Methods for DNA Microarrays [C].Bioinformatics,17,520-525P,2001.
[87] L. Gruenwald, H. Chok, and M. Aboukhamis. Mining to Estimate Missing Sensor Data
[C]. Conference on Data Mining Workshops, Oct.2007.
[88] Mihail Halatchev, Le Gruenwald. Estimating Missing Values in Related Sensor DataStreams [C]. In the proceeding of Conf. on Management of Data (2005).
[89] Jiang N, Gruenwald L. Estimating missing data in data streams, Proceedings of the12thInternational Conference on Database Systems for Advanced Applications [C]. BangkokThailand,2007:981-987P.
[90] W. Zhao and Y. Liang, A Systematic Probabilistic Approach for Estimation in DenseWireless Sensor Networks [C]. In IEEE Wireless Communications&NetworkingConference,2008
[91] Y. Li and L. Parker, A spatial-temporal imputation technique for classification withmissing data in a wireless sensor network [C]. In IEEE/RSJ International Conference onIntelligent Robots and Systems,2008. IROS2008,2008,3272–3279P.
[92] O. Gnawali, R. Fonseca, K. Jamieson, D. Moss, and P. Levis, Collection tree protocol [C].In Proceedings of the7th ACM Conference on Embedded Networked SensorSystems.ACM,2009,1–14P.
[93] N. Vijayakumar and B. Plale. Sensor Data Streams Using Kalman Filters [M]. bookchapter in Knowledge Discovery from Sensor Data, Taylor and Francis/CRC Press,2009
[94] Jong Chern Lin, C.J. Bleakley. Robust Data Collectiong and Lifetime Improvement inWireless Sensor Networks through Data Imputation [C].2010Fifth internationalconference on systems and networks communication,2010:64-69P.
[95] Guiyi Wei, Yun Ling, Binfeng Guo, et al. Prediction-based data aggregation in wirelesssensor networks: Combining grey model and Kalman filter[C]. ComputerCommunications,34(2011):793-802P.
[96] M. Takruri, S. Rajasegaral, S. Challa, et al. Spatio-temporal modelling-based drift-awarewireless sensor networks [J]. LET Wirel. Sens. Syst.2011,1(2):110-122P.
[97]纪文武.农业综合环境无线传感器网络监测系统[OL]，http://211.137.252.55:8080/agr/，2010.
[98] Vapnik V N. The nature of statistical learning theory [M]. New York: Springer,1995.
[99]袁亚湘，孙文瑜.最优化理论与方法[M].北京：科学出版社，第一版，2005,404-417.
[100]王传安.基于信息熵SVM的ICMP隐蔽通道检测研究[M].江苏大学硕士论文,2009-11-01.
[101] Scholkopf B, Smola A. Learning with Kernels [M]. MIT Press, Cambridge,MA.2002.
[102] Suykens J A K, Van Gestel T, De Brabanter J, De Moor B, Vandewalle J. Leastsquares support vector machines [M], Singapore: World scientific Publishing Co., Pte,Ltd,2002.
[103]计量经济学基础[M]，南开大学译，2007，天津：南开大学出版社.
[104]王黎明，陈颖，杨楠.应用回归分析[M],上海，复旦大学出版社，2008.
[105] Ryo Sugihara, Andrew A. Chien, Accuracy-aware data modeling in sensornetworks[C], SenSys2005, proceedings of the3rd international conference on Embeddednetworked sensor systems, New York, NY, USA.
[106] D. Papadias, Y. Tao, P. Kalnis, and J. Zhang, Indexing spatio-temporal datawarehouses [M].2002.
[107] Niki Trigoni, Yong Yao, Alan Demers, Johannes Gehrke, and Rajmohan Rajaraman.Multi-query Optimization for Sensor Networks [J]. Acta Electronica Sinica;2008-04.
[108] He T, B M, Stankovic J A, Abdelzather T F.AIDI: Adaptive application independentdata aggreation in wireless sensor networks [J]. ACM Transactions on EmbeddedComputing system，2004,3(2):426-457P.
[109] Green T J, Tannen V. Models for imcomplete and probabilistic information[J]. IEEEData Engineering Bulletin,2006,29(1):17-24P.
[110] R. Cheng and S. Prabhakar. Managing uncertainty in sensor databases[C]. InSIGMOD Record issue on Sensor Technology, December2003.
[111] Ljosa V, Singh A K. APLA: Indexing Arbitrary Probability Distributions [C]. InProceedings of the23rd IEEE International Conference on Data Engineering. Istanbul,2007:946-955P.
[112] R. Cheng, Y. Xia, S. Prabhakar, R. Shah, and J. Vitter. Efficient indexing methods forprobabilistic threshold queries over uncertain data [C]. In Proc. VLDB,2004.
[113] Pei J, Hua M, Tao Y F, Lin X M. Query answering techniques on uncertian andprobabilistic data: Tutorial summary[C]. Proceedings of the2008ACM SIGMODInternational Conference on Management of Data. Vancouver,2008:1357-1364P.
[114] Hua Ming, Pei Jian, Zhang Wenjie, Lin Xuemin. Ranking queries on uncertain data:A probabistic threshold approach[C]. Proceedings of the2008ACM SIGMODInternational Conference on Management of Data. Vancouver,2008:673-686P.
[115]何丽娟，周鸣争，陶皖,江自兵.无线传感器网络中不确定数据的估计算法[J].计算机工程与应用，2011,47(28):100-102页.
[116] Hyun Lee Jae Sung Choi Ramez Elmasri.Sensor Data Fusion using DSm Theory forActivity Recognition under Uncertainty in Home-based Care[C]. In proceeding ofInternational conference on advanced information netwrorking and applications2009:517-524P.
[117]任秀丽，田洋.传感器网络中基于预处理证据理论的数据融合[J].计算机应用，2011,31(7)：1992-1994页.
[118] Yang Zhang, Nirvana Meratnia, Paul Havinga. Outlier detection techniques forwireless sensor networks: A survey[J]. IEEE COMMUNICATIONS SURVEYS&TUTORIALS, vol12(2),2010:1-12P.
[119] Wang Cheng, Menenti M, Li Zhaoliang. Modified principal component analysis（MPCA）for feature selection of hyper-spectral imagery [J]. IEEE International,2003,(6):3781-3783P.
[120] Mina Aminghafari, Nathalie Cheze, Jean-Michel Poggi, Multivariate denoising usingwavelets and principal component analysis [J]. In Computational Statistics&DataAnalysis,2006(50):2381-2398P.
[121] Morlet D,Peyrin F,Desseigne P,Touboul P, Rubel P. Time-scale analysis ofhigh-resolution signal-averaged surface ECG using wavelet transformation[J].Computersin Cardiology,1992:393-396P.
[122]潘立登,李大宇,马俊英.软测量技术原理与应用[M].北京,中国电力出版社,2009.
[123]胡友强，数据驱动的多元统计故障诊断及应用[D]，重庆大学博士论文.2010，7：23-27页.
[124]于秀林，任雪松.多元统计分析[M].北京：中国统计出版社，1999.
[125]潘玉松.基于主元分析的传感器故障检测与诊断[D].华北电力大学博士论文.华北电力大学.2005.
[126]苏永振.航空材料结构低速冲击健康监测研究[D].南京航空航天大学.博士论文.2010，5：93-96页.
[127]陈安龙.多数据流处理的关键技术研究[D].四川大学博士论文.2006,6:13-14页.
[128] E. Elnahrawy, Research directions in sensor data streams: Solutions and challenges[J], Rutgers University, Tech. Rep. DCIS-TR-527, May2003.
[129]Kalman, R. E.1960.A New Approach to Linear Filtering and Prediction Problems[J],Transaction of the ASME-Journal of Basic Engineering, pp.35-45（March1960）.
[130]周忠海.基于激光干涉原理的海洋灾害预警关键技术研究[M].中国海洋大学博士论文,2009-06-05
[131]孟庆春.移动机器人目标动态跟踪策略研究[M].大连海事大学硕士论文2008-06-01.
[132]Welch G., Bishop G., An introduction to the Kalman [J]. Department of ComputerScience Unniversity of North Carolina at Chapel Hill,2004:1-16P.
[133]Maybeck, Peter S. Stochastic Models, Estimation [M], and Control, Volume1,Academic Press, Inc.1979.
[134]Julier S J, Uhlman J K, Durrant-Whyten H F. A general method for approximatingnonlinear transformations of probability distributions [EB/OL].http://www.robots.ox.ac.uk/~siju/work/publication/Unscented.zip,09/27/1997.
[135]Julier S J, Uhlman J K, Durrant-Whyten H F. A new approach for the nonlineartransformation of means and convarious[C]. In filters and estimations.IEEE Trans onAutomatic Control,2000,45(3):477-482P.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |