ATMS Based Information Fusion Target Recognition Method

The non-monotonic problem exited in information fusion systems is solved. Through the introducing of non-monotonic reasoning method, which was realized with ATMS, into the information fusion system, it gains the ability to process insufficient information with flexibility and non-monotonic behavior. In the simulation test of our system, our system manifests its ability of dealing the insufficient and contradictory information, which partly solves the decision dilemma brought out by the insufficient information in battle situations. The information fusion target recognition system can process the information in battle situation fast and with flexibility.

Target recognition based on modified combination rule

Evidence theory is widely used in the field of target recognition. The invalidation problem of this theory when dealing with highly conflict evidences is a research hotspot. Several alternatives of the combination rule are analyzed and compared. A new combination approach is proposed. Calculate the reliabilities of evidence sources using existing evidences. Construct reliabilities judge matrixes and get the weights of each evidence source. Weight average all inputted evidences. Combine processed evidences with D-S combination rule repeatedly to identify a target. The application in multi-sensor target reeognition as well as the comparison with typical alternatives all validated that this approach can dispose highly conflict evidences efficiently and get reasonable reeognition results rapidly.

Improvement method for the combining rule of Dempster-Shaferevidence theory based on reliability

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.

EARLY WARNING MODEL OF NETWORK INTRUSION BASED ON D-S EVIDENCE THEORY

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.

DETERMINGING BPA UNDER UNCERTAINTY ENVIRONMENTS AND ITS APPLICATION IN DATA FUSION

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.

Data fusion in oil and gas detection

Data fusion, a new research domain, is the integration and extension of modem information techniques and many other subjects. The data fusion concept is introduced and the Dempster-Shafer evidence deduction is described and applied to oil and gas detection. An example of the method is shown using numerical simulation data. The processing result indicates that the data fusion method can be widely used in hydrocarbon detection.

A New Approach to Evidence Combination and Its Application to Targets Recognition in Image Sequence

The classical Dempster's combination rule is the most popular rule of combinations,but it is a poor solution for the management of the evidence conflict at the normalization step.When deal with high conflict information it can even involve counter-intuitive results.Based on evidence distance,some inherent characters of evidences are extracted,and discount method to combine conflicting evidence was proposed.The discount method can be also used to fuse image sequences to recognize targets.Examples show that the proposed method can provide reasonable results with good convergence efficiency.

A Hierarchical P2P Model and a Data Fusion Method for Network Security Situation Awareness System

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.

Multisensor Data Fusion for Automotive Engine Fault Diagnosis

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.

Trunk detection based on laser radar and vision data fusion

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.

DATA FUSION ALGORITHM BASED ON STATE AND ATTRIBUTE PARAMETER

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.

INTELLIGENT FUSION FOR AEROENGINE WEAR FAULT DIAGNOSIS

Four common oil analysis techniques, including the ferrography analysis （FA）, the spectrometric oil analysis （SOA）, the particle count analysis （PCA）, and the oil quality testing （OQT）, are used to implement the military aeroengine wear fault diagnosis during the test drive process. To improve the precision and the reliability of the diagnosis, the aeroengine wear fault fusion diagnosis method based on the neural networks （NN） and the Dempster-Shafter （D-S） evidence theory is proposed. Firstly, according to the standard value of the wear limit, original data are pre-processed into Boolean values. Secondly, sub-NNs are established to perform the single diagnosis, and their training samples are dependent on experiences from experts. After each sub-NN is trained, diagnosis results are obtained. Thirdly, the diagnosis results of each sub-NN are considered as the basic probability allocation value to faults. The improved D-S evidence theory is applied to the fusion diagnosis, and the final fusion results are obtained. Finally, the method is verified by a diagnosis example.

Belief Combination of Classifiers for Incomplete Data

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.

基于多元数据的夏季鸡舍环境质量评价及其对产蛋性能的影响

蛋鸡舍环境质量直接影响蛋鸡产蛋性能。为探究夏季蛋鸡舍环境质量及其对产蛋性能的影响,研究提出基于多元数据的分析方法,首先采集鸡舍内7类关键环境因子数据,按照热环境、光环境和气体环境分组,再根据改进D-S证据理论规则进行迭代融合,得到蛋鸡舍各检测点环境质量的综合评价结果,进而分析其对产蛋性能的影响。以夏季八层层叠式蛋鸡舍为试验鸡舍开展试验。结果显示:八层层叠式蛋鸡舍下四层的环境质量和平均产蛋率的最优位置均处于鸡舍前端;平均产蛋率最差的位置处于鸡舍中端,该位置环境质量综合评价结果为一般;上四层平均产蛋率最优位置为鸡舍中端,该位置环境质量综合评价结果为适宜;平均产蛋率最差位置和环境质量最差位置均为鸡舍后端(靠近风机端)。在试验鸡舍所有检测点中,平均产蛋率高于86%的检测点,环境质量综合评价结果大都为适宜,平均产蛋率低于86%的检测点,环境质量综合评价结果为一般或差,鸡舍内各检测点环境质量综合评价结果与平均产蛋率的变化趋势高度一致。该研究为准确评价蛋鸡舍环境质量,揭示蛋鸡舍环境质量对产蛋性能的影响提供了一种行之有效的方法。

基于证据理论的多传感器数据融合水质检测研究

针对多传感器水质监测数据融合中测量数据存在误差的现象,论文提出一种基于DS证据融合理论的多源监测数据融合算法.该算法将影响水质的氨氮含量(NH3-N)、溶解氧(DO)、pH值、电导率(CD)等多环境因子变量作为证据,并赋予可靠性折扣,计算出水质等级的质量函数,然后通过DS方法将其与其他证据结合起来,最后使用融合质量函数值的决策规则确定水质类别.实验证明这种方法适用于具有多源监测数据的水质类别预测,可以从不确定性传感器数据中评估水质,并提高评估性能.

D-S证据理论在空中目标识别中的应用现状与展望

D-S证据理论作为一种多源信息融合工具,在空中目标识别领域中得到了广泛应用。对D-S证据理论进行了概述;简要梳理了D-S证据理论在空中目标识别领域中的发展脉络,并提出应用中需要解决的三类关键问题;围绕上述问题,重点对该领域中的BPA获取、证据冲突度量、证据融合的应用现状进行综述;最后,基于空域控制视角,对D-S证据理论在该领域中的应用进行了展望。研究可为空中目标识别领域的理论发展和工程应用提供参考。

多传感器融合的火灾监测机器人设计

针对目前火灾报警系统不能应用在城市中非密闭空间的问题,提出一种适用于非密闭空间的多传感器融合的火灾监测机器人。该机器人采用履带式结构适应多地形移动,根据城市内非密闭下空间火势初期主要特征参数确定采集模块的搭建;利用D-S证据理论对多传感器火灾数据进行融合检测,以降低单个传感器的误报率,来提高对非密闭空间火灾事故的精确判定,并对火灾进行现场警报与远程回传。实验表明,与单一传感器判断相比,引入D-S证据理论的火灾监测机器人的火灾检测不确定性下降,检测精度得到了提高。

基于D-S证据理论的农作物气候品质预测方法研究:以晚熟杂交柑橘春见为例

【目的】基于多源气象数据构建果实品质(糖含量等级)预测模型,为科学评价果实气候品质及深入挖掘农产品气候资源提供科学依据。【方法】以晚熟柑橘春见果实为研究对象,利用多源数据融合技术、人工神经网络(BP神经网络、RBF神经网络和Elman神经网络)和D-S证据理论,包括气象数据质量控制、特征选取、特征级融合、决策级融合4个步骤,构建基于多源气象数据的果实品质(糖含量等级)预测模型。【结果】春见果实品质预测模型采用BP神经网络预测结果总体准确率为87.50%,平均绝对误差(MAE)为0.150,均方根误差(RMSE)为0.447;RBF神经网络预测结果总体准确率为85.00%,MAE为0.175,RMSE为0.474;Elman神经网络预测结果总体准确率为87.50%,MAE为0.150,RMSE为0.447;D-S证据理论决策融合总体预测准确率达95.20%,分别较BP神经网络、RBF神经网络和Elman神经网络提升7.7百分点、10.2百分点和7.7百分点,MAE和RMSE分别为0.040和0.214,均明显降低。【结论】D-S证据理论决策融合后的果实品质预测准确率相比单一神经网络预测更高、误差更小。

隧道环境内无人驾驶车辆目标决策两级信息融合感知策略

基于隧道内的特殊行驶环境和无人驾驶感知需求,选择合适的传感器及硬件搭建试验车辆,构建了毫米波雷达与摄像头多传感器融合的感知系统;基于YOLOv4目标级信息融合算法和改进D-S证据理论决策级信息融合算法,提出了一种“目标决策”两级信息融合策略;最后,在城市道路隧道环境内开展了感知信息两级融合验证试验,试验结果表明:相比单一的摄像头或毫米波雷达感知效果,基于摄像头与毫米波雷达传感器感知ROI区域关联实现的目标级融合结果可以提高9.51%的识别准确率,弥补了单一传感器在隧道环境内感知技术的不足;基于目标级融合感知结果,利用改进后的D-S证据理论算法再进行决策级融合,相比于单一的目标级融合结果,误检率降低了3.61%,显著提高了检测精度。采取多传感器感知信息目标决策两级融合策略能够满足隧道特殊环境内无人驾驶车辆可靠感知需求,为推动无人驾驶技术落地应用提供了理论与技术支撑。

融合多源数据的桥梁技术状况指标评定方法

为可靠地评定桥梁技术状况,针对桥梁技术状况评定过程的模糊性和不确定性特点,提出一种融合多源数据的桥梁技术状况指标评定方法。该方法首先通过云模型分别将桥梁技术状况指标的检测值和监测值转化为指标各等级的隶属度,并用隶属度构造改进Dempster-Shafer证据理论的基本信任分配函数,再结合证据冲突/一致度和信息熵确定综合权重系数,对基本信任分配函数进行修正,然后采用Dempster合成规则融合得到综合基本信任分配函数,最后依据最大隶属度原则得到指标的标度,实现桥梁技术状况的可靠评定。采用该方法和《公路桥梁技术状况评定标准》(JTG/T H21—2011,现行评定方法)分别评定某座斜拉桥的索力指标,结果表明,与现行评定方法相比,该方法的评定结果对应的养护对策与实际养护对策更相符,该方法有效、可行。