A decentralized parallel one-pass deconvolution algorithm for multisensor systems with multiplicative noises is proposed. Comparing with the conventional deconvolution algorithm, it avoids the computational overload a...A decentralized parallel one-pass deconvolution algorithm for multisensor systems with multiplicative noises is proposed. Comparing with the conventional deconvolution algorithm, it avoids the computational overload and the high storage requirement. The algorithm is optimal in the sense of linear minimum-variance. The simulation results illustrate the validity of the proposed algorithm.展开更多
The purpose of data fusion is to produce an improved model or estimate of a system from a set of independent data sources. Various multisensor data fusion approaches exist, in which Kalman filtering is important. In t...The purpose of data fusion is to produce an improved model or estimate of a system from a set of independent data sources. Various multisensor data fusion approaches exist, in which Kalman filtering is important. In this paper, a fusion algorithm based on multisensor systems is discussed and a distributed multisensor data fusion algorithm based on Kalman filtering presented. The algorithm has been implemented on cluster-based high performance computers. Experimental results show that the method produces precise estimation in considerably reduced execution time.展开更多
In this study,a multisensor system consisting of 23 potentiometric sensors was applied for long-term online measurements in outlet flow of the water treatment plant.Within 1 month of continuous measurements,the data s...In this study,a multisensor system consisting of 23 potentiometric sensors was applied for long-term online measurements in outlet flow of the water treatment plant.Within 1 month of continuous measurements,the data set of more than 295,000 observations was acquired.The processing of this dataset with conventional chemometric tools was cumbersome and not very informative.Topological data analysis(TDA)was recently suggested in chemometric literature to deal with large spectroscopic datasets.In this research,we explore the opportunities of TDA with respect to multisensor data with only 23 variables.It is shown that TDA allows for convenient data visualization,studying the evolution of water quality during the measurements and tracking the periodical structure in the data related to the water quality depending on the time of the day and the day of the week.TDA appears to be a valuable tool for multisensor data exploration.展开更多
基金This work was supported by the Science&Technology Research Key Projects of Ministry of Education of China.
文摘A decentralized parallel one-pass deconvolution algorithm for multisensor systems with multiplicative noises is proposed. Comparing with the conventional deconvolution algorithm, it avoids the computational overload and the high storage requirement. The algorithm is optimal in the sense of linear minimum-variance. The simulation results illustrate the validity of the proposed algorithm.
文摘The purpose of data fusion is to produce an improved model or estimate of a system from a set of independent data sources. Various multisensor data fusion approaches exist, in which Kalman filtering is important. In this paper, a fusion algorithm based on multisensor systems is discussed and a distributed multisensor data fusion algorithm based on Kalman filtering presented. The algorithm has been implemented on cluster-based high performance computers. Experimental results show that the method produces precise estimation in considerably reduced execution time.
基金The authors are grateful to O.Lominoga and Zh.Lyadova from SUE“Vodokanal of St.Petersburg”for their valuable help in organizing the experiments.DK acknowledges financial support from RFBR project#17-33-50101.EL and AL acknowledge partial financial support from the Government of Russian Federation,Grant 08-08.VB thanks the Russian Ministry of Education and Science for support of this work within the framework of the basic part of the state task on the theme:“Adaptive technologies of analytical control based on optical sensors”(Project No.4.7001.2017/BP).
文摘In this study,a multisensor system consisting of 23 potentiometric sensors was applied for long-term online measurements in outlet flow of the water treatment plant.Within 1 month of continuous measurements,the data set of more than 295,000 observations was acquired.The processing of this dataset with conventional chemometric tools was cumbersome and not very informative.Topological data analysis(TDA)was recently suggested in chemometric literature to deal with large spectroscopic datasets.In this research,we explore the opportunities of TDA with respect to multisensor data with only 23 variables.It is shown that TDA allows for convenient data visualization,studying the evolution of water quality during the measurements and tracking the periodical structure in the data related to the water quality depending on the time of the day and the day of the week.TDA appears to be a valuable tool for multisensor data exploration.
