Dempster-Shafer (DS) theory of evidence has been widely used in many data fusion ap- plication systems. However, how to determine basic probability assignment, which is the main and the first step in evidence theory, ...Dempster-Shafer (DS) theory of evidence has been widely used in many data fusion ap- plication systems. However, how to determine basic probability assignment, which is the main and the first step in evidence theory, is still an open issue. In this paper, a new method to obtain Basic Probability Assignment (BPA) is proposed based on the similarity measure between generalized fuzzy numbers. In the proposed method, species model can be constructed by determination of the min, average and max value to construct a fuzzy number. Then, a new Radius Of Gravity (ROG) method to determine the similarity measure between generalized fuzzy numbers is used to calculate the BPA functions of each instance. Finally, the efficiency of the proposed method is illustrated by the classi- fication of Iris data.展开更多
An improvement method for the combining rule of Dempster evidence theory is proposed. Different from Dempster theory, the reliability of evidences isn't identical; and varies with the event. By weight evidence acc...An improvement method for the combining rule of Dempster evidence theory is proposed. Different from Dempster theory, the reliability of evidences isn't identical; and varies with the event. By weight evidence according to their reliability, the effect of unreliable evidence is reduced, and then get the fusion result that is closer to the truth. An example to expand the advantage of this method is given. The example proves that this method is helpful to find a correct result.展开更多
A hierarchical peer-to-peer(P2P)model and a data fusion method for network security situation awareness system are proposed to improve the efficiency of distributed security behavior monitoring network.The single po...A hierarchical peer-to-peer(P2P)model and a data fusion method for network security situation awareness system are proposed to improve the efficiency of distributed security behavior monitoring network.The single point failure of data analysis nodes is avoided by this P2P model,in which a greedy data forwarding method based on node priority and link delay is devised to promote the efficiency of data analysis nodes.And the data fusion method based on repulsive theory-Dumpster/Shafer(PSORT-DS)is used to deal with the challenge of multi-source alarm information.This data fusion method debases the false alarm rate.Compared with improved Dumpster/Shafer(DS)theoretical method based on particle swarm optimization(PSO)and classical DS evidence theoretical method,the proposed model reduces false alarm rate by 3%and 7%,respectively,whereas their detection rate increases by 4%and 16%,respectively.展开更多
Tree trunks detection and their location information are needed to perform effective production and management in forestry and fruit farming.A novel algorithm based on data fusion with a vision camera and a 2D laser s...Tree trunks detection and their location information are needed to perform effective production and management in forestry and fruit farming.A novel algorithm based on data fusion with a vision camera and a 2D laser scanner was developed to detect tree trunks accurately.The transformation was built from a laser coordinate system to an image coordinate system,and the model of a rectangle calibration plate with two inward concave regions was established to implement data alignment between two sensors data.Then,data fusion and decision with Dempster-Shafer theory were achieved through integration of decision level after designing and determining basic probability assignments of regions of interesting(RoIs)for laser and vision data respectively.Tree trunk width was calculated by using laser data to determine basic probability assignments of RoIs of laser data.And a stripping segmentation algorithm was presented to determine basic probability assignments of RoIs of vision data,by calculating the matching level of RoIs like tree trunks.A robot platform was used to acquire data from sensors and to perform the developed tree trunk detection algorithm.Combined calibration tests were conducted to calculate a conversion matrix transforming from the laser coordinate system to the image coordinate system,and then field experiments were carried out in a real pear orchard under sunny and cloudy conditions,with trunk width measurement of 120 trees and 40 images processed by the presented stripping segmentation algorithm.Results showed the algorithm was successful to detect tree trunks and data fusion improved the ability for tree trunk detection.This algorithm could provide a new method for tree trunk detection and accurate production and management in orchards.展开更多
A new data fusion algorithm is presented. The new algorithm has two steps. First, three basic probability assignments dependent on different attribute parameters with Demspter fusion rule are processed. Using the fusi...A new data fusion algorithm is presented. The new algorithm has two steps. First, three basic probability assignments dependent on different attribute parameters with Demspter fusion rule are processed. Using the fusion results, one can calculate the evidence interval of the proposition that “the return is from target”. Then based on the magnitude of the center of the evidence interval, one can reject some false alarms, so as to cut down the number of clutters accepted by the filter gate. Second, the attribute parameter likelihood function(APLF, for short) and kinematic measurement likelihood function are used to form a joint likelihood function. A method is also proposed for calculating APLF. As for APLF, it is found and proved that there are differences between similar targets and dissimlar targets. By using the differences, one can distinguish adjacent targets more efficiently. In a word, the technique presented in this paper is an integrated adaptive data association fusion algorithm. The advantages of the algorithm are discussed and demonstrated via single and multiple targets tracking simulations. In simulation, the target maneuver, the presence of clutter and the varying of parameters are taken into consideration.展开更多
This paper describes mainly a decision-level data fusion technique for fault diagnosis for elec-tronically controlled engines. Experiments on a SANTANA AJR engine show that the data fusion method provides good engine ...This paper describes mainly a decision-level data fusion technique for fault diagnosis for elec-tronically controlled engines. Experiments on a SANTANA AJR engine show that the data fusion method provides good engine fault diagnosis. In data fusion methods, the data level fusion has small data preproc-essing loads and high accuracy, but requires commensurate sensor data and has poor operational perform-ance. The decision-level fusion based on Dempster-Shafer evidence theory can process noncommensurate data and has robust operational performance, reduces ambiguity, increases confidence, and improves sys-tem reliability, but has low fusion accuracy and high data preprocessing cost. The feature-level fusion pro-vides good compromise between the above two methods, which becomes gradually mature. In addition, ac-quiring raw data is a precondition to perform data fusion, so the system for signal acquisition and processing for an automotive engine test is also designed by the virtual instrument technology.展开更多
Based on the framework of evidence theory, data fusion aims at obtaining a single Basic Probability Assignment (BPA) function by combining several belief functions from distinct information sources. Dempster’s rule o...Based on the framework of evidence theory, data fusion aims at obtaining a single Basic Probability Assignment (BPA) function by combining several belief functions from distinct information sources. Dempster’s rule of combination is the most popular rule of combinations, but it is a poor solution for the management of the conflict between various information sources at the normalization step. Even when it faces high conflict information, the classical Dempster-Shafer’s (D-S) evidence theory can involve counter-intuitive results. This paper presents a modified averaging method to combine conflicting evidence based on the distance of evidences; and also gives the weighted average of the evidence in the system. Numerical examples showed that the proposed method can realize the modification ideas and also will provide reasonable results with good convergence efficiency.展开更多
Application of data fusion technique in intrusion detection is the trend of next- generation Intrusion Detection System (IDS). In network security, adopting security early warn- ing technique is feasible to effectivel...Application of data fusion technique in intrusion detection is the trend of next- generation Intrusion Detection System (IDS). In network security, adopting security early warn- ing technique is feasible to effectively defend against attacks and attackers. To do this, correlative information provided by IDS must be gathered and the current intrusion characteristics and sit- uation must be analyzed and estimated. This paper applies D-S evidence theory to distributed intrusion detection system for fusing information from detection centers, making clear intrusion situation, and improving the early warning capability and detection efficiency of the IDS accord- ingly.展开更多
Data with missing values,or incomplete information,brings some challenges to the development of classification,as the incompleteness may significantly affect the performance of classifiers.In this paper,we handle miss...Data with missing values,or incomplete information,brings some challenges to the development of classification,as the incompleteness may significantly affect the performance of classifiers.In this paper,we handle missing values in both training and test sets with uncertainty and imprecision reasoning by proposing a new belief combination of classifier(BCC)method based on the evidence theory.The proposed BCC method aims to improve the classification performance of incomplete data by characterizing the uncertainty and imprecision brought by incompleteness.In BCC,different attributes are regarded as independent sources,and the collection of each attribute is considered as a subset.Then,multiple classifiers are trained with each subset independently and allow each observed attribute to provide a sub-classification result for the query pattern.Finally,these sub-classification results with different weights(discounting factors)are used to provide supplementary information to jointly determine the final classes of query patterns.The weights consist of two aspects:global and local.The global weight calculated by an optimization function is employed to represent the reliability of each classifier,and the local weight obtained by mining attribute distribution characteristics is used to quantify the importance of observed attributes to the pattern classification.Abundant comparative experiments including seven methods on twelve datasets are executed,demonstrating the out-performance of BCC over all baseline methods in terms of accuracy,precision,recall,F1 measure,with pertinent computational costs.展开更多
基金Supported by National High Technology Project (863)(No. 2006AA02Z320)the National Natural Science Founda-tion of China (No.30700154, No.60874105)+1 种基金Zhejiang Natural Science Foundation (No.Y107458, RY1080422)the School Youth Found of Shanghai Jiaotong University
文摘Dempster-Shafer (DS) theory of evidence has been widely used in many data fusion ap- plication systems. However, how to determine basic probability assignment, which is the main and the first step in evidence theory, is still an open issue. In this paper, a new method to obtain Basic Probability Assignment (BPA) is proposed based on the similarity measure between generalized fuzzy numbers. In the proposed method, species model can be constructed by determination of the min, average and max value to construct a fuzzy number. Then, a new Radius Of Gravity (ROG) method to determine the similarity measure between generalized fuzzy numbers is used to calculate the BPA functions of each instance. Finally, the efficiency of the proposed method is illustrated by the classi- fication of Iris data.
文摘An improvement method for the combining rule of Dempster evidence theory is proposed. Different from Dempster theory, the reliability of evidences isn't identical; and varies with the event. By weight evidence according to their reliability, the effect of unreliable evidence is reduced, and then get the fusion result that is closer to the truth. An example to expand the advantage of this method is given. The example proves that this method is helpful to find a correct result.
基金Supported by the National Natural Science Foundation of China(61370212)the Research Fund for the Doctoral Program of Higher Education of China(20122304130002)+1 种基金the Natural Science Foundation of Heilongjiang Province(ZD 201102)the Fundamental Research Fund for the Central Universities(HEUCFZ1213,HEUCF100601)
文摘A hierarchical peer-to-peer(P2P)model and a data fusion method for network security situation awareness system are proposed to improve the efficiency of distributed security behavior monitoring network.The single point failure of data analysis nodes is avoided by this P2P model,in which a greedy data forwarding method based on node priority and link delay is devised to promote the efficiency of data analysis nodes.And the data fusion method based on repulsive theory-Dumpster/Shafer(PSORT-DS)is used to deal with the challenge of multi-source alarm information.This data fusion method debases the false alarm rate.Compared with improved Dumpster/Shafer(DS)theoretical method based on particle swarm optimization(PSO)and classical DS evidence theoretical method,the proposed model reduces false alarm rate by 3%and 7%,respectively,whereas their detection rate increases by 4%and 16%,respectively.
基金The study was supported by“Jiangsu Provincial Natural Science Foundation of China(No.BK20151436)Blue Project of Jiangsu Province”.
文摘Tree trunks detection and their location information are needed to perform effective production and management in forestry and fruit farming.A novel algorithm based on data fusion with a vision camera and a 2D laser scanner was developed to detect tree trunks accurately.The transformation was built from a laser coordinate system to an image coordinate system,and the model of a rectangle calibration plate with two inward concave regions was established to implement data alignment between two sensors data.Then,data fusion and decision with Dempster-Shafer theory were achieved through integration of decision level after designing and determining basic probability assignments of regions of interesting(RoIs)for laser and vision data respectively.Tree trunk width was calculated by using laser data to determine basic probability assignments of RoIs of laser data.And a stripping segmentation algorithm was presented to determine basic probability assignments of RoIs of vision data,by calculating the matching level of RoIs like tree trunks.A robot platform was used to acquire data from sensors and to perform the developed tree trunk detection algorithm.Combined calibration tests were conducted to calculate a conversion matrix transforming from the laser coordinate system to the image coordinate system,and then field experiments were carried out in a real pear orchard under sunny and cloudy conditions,with trunk width measurement of 120 trees and 40 images processed by the presented stripping segmentation algorithm.Results showed the algorithm was successful to detect tree trunks and data fusion improved the ability for tree trunk detection.This algorithm could provide a new method for tree trunk detection and accurate production and management in orchards.
文摘A new data fusion algorithm is presented. The new algorithm has two steps. First, three basic probability assignments dependent on different attribute parameters with Demspter fusion rule are processed. Using the fusion results, one can calculate the evidence interval of the proposition that “the return is from target”. Then based on the magnitude of the center of the evidence interval, one can reject some false alarms, so as to cut down the number of clutters accepted by the filter gate. Second, the attribute parameter likelihood function(APLF, for short) and kinematic measurement likelihood function are used to form a joint likelihood function. A method is also proposed for calculating APLF. As for APLF, it is found and proved that there are differences between similar targets and dissimlar targets. By using the differences, one can distinguish adjacent targets more efficiently. In a word, the technique presented in this paper is an integrated adaptive data association fusion algorithm. The advantages of the algorithm are discussed and demonstrated via single and multiple targets tracking simulations. In simulation, the target maneuver, the presence of clutter and the varying of parameters are taken into consideration.
基金Supported by the Trans-Century Training Programme Founda-tion for the Talents by the Ministry of Education China and Shandong Natural Science Foundation China (No.Y2002F17)
文摘This paper describes mainly a decision-level data fusion technique for fault diagnosis for elec-tronically controlled engines. Experiments on a SANTANA AJR engine show that the data fusion method provides good engine fault diagnosis. In data fusion methods, the data level fusion has small data preproc-essing loads and high accuracy, but requires commensurate sensor data and has poor operational perform-ance. The decision-level fusion based on Dempster-Shafer evidence theory can process noncommensurate data and has robust operational performance, reduces ambiguity, increases confidence, and improves sys-tem reliability, but has low fusion accuracy and high data preprocessing cost. The feature-level fusion pro-vides good compromise between the above two methods, which becomes gradually mature. In addition, ac-quiring raw data is a precondition to perform data fusion, so the system for signal acquisition and processing for an automotive engine test is also designed by the virtual instrument technology.
基金Project (No. 51476040103JW13) supported by the National DefenseKey Laboratory of Target and Environment Feature of China
文摘Based on the framework of evidence theory, data fusion aims at obtaining a single Basic Probability Assignment (BPA) function by combining several belief functions from distinct information sources. Dempster’s rule of combination is the most popular rule of combinations, but it is a poor solution for the management of the conflict between various information sources at the normalization step. Even when it faces high conflict information, the classical Dempster-Shafer’s (D-S) evidence theory can involve counter-intuitive results. This paper presents a modified averaging method to combine conflicting evidence based on the distance of evidences; and also gives the weighted average of the evidence in the system. Numerical examples showed that the proposed method can realize the modification ideas and also will provide reasonable results with good convergence efficiency.
文摘Application of data fusion technique in intrusion detection is the trend of next- generation Intrusion Detection System (IDS). In network security, adopting security early warn- ing technique is feasible to effectively defend against attacks and attackers. To do this, correlative information provided by IDS must be gathered and the current intrusion characteristics and sit- uation must be analyzed and estimated. This paper applies D-S evidence theory to distributed intrusion detection system for fusing information from detection centers, making clear intrusion situation, and improving the early warning capability and detection efficiency of the IDS accord- ingly.
基金supported in part by the Center-initiated Research Project and Research Initiation Project of Zhejiang Laboratory(113012-AL2201,113012-PI2103)the National Natural Science Foundation of China(61300167,61976120)+2 种基金the Natural Science Foundation of Jiangsu Province(BK20191445)the Natural Science Key Foundation of Jiangsu Education Department(21KJA510004)Qing Lan Project of Jiangsu Province。
文摘Data with missing values,or incomplete information,brings some challenges to the development of classification,as the incompleteness may significantly affect the performance of classifiers.In this paper,we handle missing values in both training and test sets with uncertainty and imprecision reasoning by proposing a new belief combination of classifier(BCC)method based on the evidence theory.The proposed BCC method aims to improve the classification performance of incomplete data by characterizing the uncertainty and imprecision brought by incompleteness.In BCC,different attributes are regarded as independent sources,and the collection of each attribute is considered as a subset.Then,multiple classifiers are trained with each subset independently and allow each observed attribute to provide a sub-classification result for the query pattern.Finally,these sub-classification results with different weights(discounting factors)are used to provide supplementary information to jointly determine the final classes of query patterns.The weights consist of two aspects:global and local.The global weight calculated by an optimization function is employed to represent the reliability of each classifier,and the local weight obtained by mining attribute distribution characteristics is used to quantify the importance of observed attributes to the pattern classification.Abundant comparative experiments including seven methods on twelve datasets are executed,demonstrating the out-performance of BCC over all baseline methods in terms of accuracy,precision,recall,F1 measure,with pertinent computational costs.