Papers by Keyword: Information Fusion

Paper TitlePage

Authors: Li Jiao, Hai Zhang, Hong Wei Liu
Abstract: The purpose of data fusion is to combine and process the data of multi-sensors, thus to obtain much more exact and reliable results than that of the single sensor. An improved data fusion method for commensurate sensors is presented in this paper. It overcomes the shortcoming of the traditional consensus algorithm with two sensors, which has different confidence distance while measuring in different precision. The relation matrix is fuzzified to avoid the subjective error in determining the threshold value. The results of numerical simulation shows that the improved method can make full use of the effective information from the sensors and it can help to improve the accuracy of measurement. Even when parts of sensors are affected or fully disabled, it still can get correct diagnosing results in damage identification.
Authors: Hong Wei Quan, Long Zhang, Lin Chen
Abstract: This paper addresses the problem of the uncertainty description for multi-source information fusion. Based on the uncertainty description, an overall framework of data-driven multi-source information fusion is discussed. In this framework, the theoretical models existed in traditional algorithms are reasonably reserved or modified, experimental evidence and background theory are collaboratively worked in fusion process. Through the core data-driven engine, a loop between the traditional fusion process and performance evaluation is established, where the feedback information from evaluation can be used to adjust the fusion process.
Authors: Yan Bin Han, Geng Shi Zhang, Jin Ping Li
Abstract: In this paper, a feature extraction strategy based on multiple color information fusion was proposed. Firstly this method started with analyzing the transform formula of color space, which transform was mainly thinking about RGB color space to other color spaces. Secondly by analyzing the characteristic of every color space in describing the actual color information, the advantages and disadvantages of every color space were showed. Thirdly through above conclusion, the algorithm which extracted the target feature only using single color information was defective, and then the strategy based on multiple color information fusion was proposed. Lastly the detail fusion strategy was given, which fused the probability distributed information of multiple color into the last probability distributed information as the target feature. The feature extraction strategy in this paper is verified by the camshift algorithm. The results show that the multiple color information fusion can improve the tracking performance of moving target.
Authors: Lei Wang, Jun Lu, Xian Qing Ling
Abstract: Edge is the basic feature of the image, and is easily damaged in the image processing. This paper proposed an edge-preserving method for image filtering. The scheme can improve the capability of protecting the edge information. The proposed method firstly defined two information measures that were based on fuzzy entropy and image gradient. Then the two information measures were fused by triangle-module operator to determine the image edges. At last, we used the modified filter to eliminate noise and retain the determined edge points. The experiment results, compared with AMAWM, can achieve better effects on PSNR and AG (Average Gradient), which illustrates that more edge information may be preserved after the filtering operation.
Authors: Gang Wang, Zhong Wei Guo, Wan Quan Wen, Fei Fei An
Abstract: Aiming at improving the identification and judgment on objectives of unmanned weapon system in the battlefield, this paper puts forward a new efficient method to infuse conflict evidence orienting towards shortcomings existing in the Dempster-Shafter (D-S) evidence theory when fusing conflict evidence. This paper is to improve the D-S Evidence Theory, by firstly conducting research on the influence of a certain operational environment on the sensors precision in the unmanned weapon system, and by secondly establishing sensors weight values based on fixed basic probability assignment by exploiting AHP. The improved approach can enhance the reliability of identification result, which has been proved via simulation experiments, and it improves the performance of target recognition system to a certain extent.
Authors: Abasi
Abstract: Security situational awareness has become a hot topic in the area of network securityresearch in recent years. The existing security situational awareness methods are analyzed and compared in details, and thus a newnetwork security situational awareness model based on information fusion is proposed. This modelfuses multi-source information from a mass of logs by introducing the modified D-S evidence theory,gets the values of nodes security situational awareness by situational factors fusion using attacks threat,and vulnerability information which network nodes have and successful attacks depend on, computesthe value of network security situational awareness by nodes situation fusion using service informationof the network nodes, and draws the security-situation-graph of network. Then, it analyzes the timeseries of the computing results by ARMA model to forecast the future threat in network security.Finally an example of actual network datasets is given to validate the network security situationalawareness model and algorithm. The results show that this model and algorithm is more effective andaccurate than the existing security situational awareness methods.
Authors: Jing Zhu, Cheng Jun Zhang, Li Fang Hu, Yi Cheng Zheng
Abstract: In the belief function theory, the combination of highly conflicting evidences is a research focus,and the key lies in both the rationality and timeliness of combination method.This paper analyzes deeply the existing strategy of model modification, and putsforward a new rapid evidence synthesis method based on model modification. The average evidence ofweighted combination on mean evidence isfirstly given, then fast combination on pignistic transformation can be realized. Thus the BBM accordancewith the principle of proportion redistribution isgot. This method has the advantage of Murphy’s method, and overcomes the large calculation problems at the same time. Comparedwith other methods, the new method is more effective to solve the combinationproblem of highly conflicting evidences, and has fast convergence speed, small computationalcomplexity, and higher practical application value.
Authors: Jian Li, Ying Wang, Zhi Jie Mao
Abstract: The aim of this paper is to investigate how to use the contextual knowledge in order to improve the fusion process. The concept of multisensor information fusion model based on the Dempster-Shafer Theory is introduced. The resulting information of the architecture is combined using similar sensor subset and dissimilar sensor subset. We demonstrate the effectiveness of this approach using the uncertain and disparate information compared to primary mass assignment techniques.
Authors: Hui Zheng
Abstract: The aim of this paper is to propose a new information fusion method for the problem of multi-sensor target recognition. Multi-sensor information fusion problem contains many characteristic indexes, and thus it can be regarded as a multi-attribute decision making problem. The new fusion method is put forward based on preference selection index method. The new information fusion method is not necessary to assign relative importance between attributes, but overall preference value of attributes are calculated using concept of statistics. Thus the new method can overcome the subjective randomness of subjectively weighting method. An applied example proves that the method is both effective and exercisable.
Authors: Bo Chen, Chuan Bao Jia, Ji Cai Feng
Abstract: To solve the problem of conflict confidence in D-S evidence theory, this paper proposed a new method. First a distance function was introduced, then the supporting degree of the evidence by other evidences was calculated, and the BPAs of the evidences were modified by the supporting degree using fuzzy inference theory, and the modified evidences were fused by D-S combination rules. Experiment result showed the effectiveness of the method.
Showing 1 to 10 of 148 Paper Titles