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 fusion approach based on distance of evidences

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.

An Evidence Combination Method based on DBSCAN Clustering

Dempster-Shafer(D-S)evidence theory is a key technology for integrating uncertain information from multiple sources.However,the combination rules can be paradoxical when the evidence seriously conflict with each other.In the paper,we propose a novel combination algorithm based on unsupervised Density-Based Spatial Clustering of Applications with Noise(DBSCAN)density clustering.In the proposed mechanism,firstly,the original evidence sets are preprocessed by DBSCAN density clustering,and a successfully focal element similarity criteria is used to mine the potential information between the evidence,and make a correct measure of the conflict evidence.Then,two different discount factors are adopted to revise the original evidence sets,based on the result of DBSCAN density clustering.Finally,we conduct the information fusion for the revised evidence sets by D-S combination rules.Simulation results show that the proposed method can effectively solve the synthesis problem of high-conflict evidence,with better accuracy,stability and convergence speed.

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.

New conflict representation model in generalized power space

The study on alternative combination rules in Dempster- Shafer theory （DST） when evidences are in conflict has emerged again recently as an interesting topic, especially in data/information fusion applications. The earlier researches have mainly focused on investigating the alternative which would be appropriate for the conflicting situation, under the assumption that a conflict is identified. However, the current research shows that not only the combination rule but also the classical conflict coefficient in DST are not correct to determine the conflict degree between two pieces of evidences. Most existing methods of measuring conflict do not consider the open world situation, whose frame of discernment is incomplete. To solve this problem, a new conflict representa- tion model to determine the conflict degree between evidences is proposed in the generalized power space, which contains two parameters： the conflict distance and the conflict coefficient of inconsistent evidences. This paper argues that only when the con- flict measure value in the new representation model is high, it is safe to say the evidences are in conflict. Experiments illustrate the efficiency of the proposed conflict representation model.

An ECR-PCR rule for fusion of evidences defined on a non-exclusive framework of discernment

In the research of uncertain information processing,Dempster-Shafer Theory(DST)provides a framework for dealing with uncertain information,where evidence is defined on a Frame of Discernment(FOD)consisting of mutually exclusive elements.However,the requirement of exclusiveness on FOD sometimes is not satisfied,as shown in Dezert-Smarandache Theory(DSm T),a derivative of DST.In DSm T,the non-exclusiveness is expressed by propositions’intersection and the fusion of evidence is realized through a Proportional Conflict Redistribution(PCR)rule.In order to handle non-exclusive FODs,a new framework called D Number Theory(DNT)has been proposed recently,which quantifies the non-exclusive degree between propositions different from DSm T.In previous studies,an Exclusive Conflict Redistribution(ECR)rule has been designed in DNT to implement the fusion of evidence defined on a non-exclusive FOD,but there are some deficiencies in the ECR rule.In this paper,a new rule called ECR-PCR rule is proposed by combining the ECR and PCR rules to better implement the fusion of evidence defined on a nonexclusive FOD.Within the proposed rule,the definition of conflict utilizes the idea of ECR’s exclusive conflict,and the disposal of conflict is following the idea of PCR’s proportional redistribution.Properties of the ECR-PCR rule are presented.The effectiveness of the proposed new rule is verified through numerical examples and applications,in comparison with other fusion methods.

Interactive-Adaptive Combination Rule

Aiming at the invalidation of DS theory dealing with the evidence in a high conflict and reducing confidence level of DSm theory processing a low conflict,this paper proposes an interactive-adaptive combination rule. Adopting the angle similarity based on hyper-power set as the weight of generalized Dempster rule and PCR rule,the new rule adaptively processes various evidence combination issues. In this way,the rule can obtain not only the better fusion of decision making effect in a low conflict,but also the solution to the synthesis in a high conflict. Simulation analysis demonstrates the validity and applicability from this rule of combination.

基于改进证据理论的冲突证据融合方法

为解决证据理论中Dempster组合规则融合高度冲突证据效果不佳的问题,提出一种同时考虑证据重要性与可靠性的综合权重生成方法和基于加权复数基本概率分配函数的证据融合方法。以提高证据融合结果的收敛性能和诊断精度为目标,建立相应的优化证据融合模型。实验结果表明,所提方法能够有效识别并处理证据冲突,克服证据加权融合过程中剩余信度被完全抛弃的问题,获得更好的融合结果和更快的收敛速度,提高诊断精度。

基于pignistic概率距离的冲突证据合成方法

Dempster Shafer证据理论在数据融合中有着广泛的应用。但当证据之间高度冲突时,应用DS证据合成公式往往会得出错误的结果。在现有的证据合成改进方法中,均使用冲突系数k来度量证据之间冲突的程度。最新的研究表明:影响证据冲突的因素不仅仅是冲突系数k,还和证据的pignistic概率距离等因素有关。在原有的冲突系数k之上,引入pignistic概率距离,提出了一种新的冲突证据合成方法。仿真结果表明:当证据之间的冲突小时,合成结果近似于D-S证据合成公式,当证据之间的冲突较大时,这种方法在公式模型上比其他方法完善,冲突证据的合成结果更加合理。

一种新的证据组合规则

通过对证据组合问题进行深入的理论分析,提出一种新的基于局部冲突、局部分配和一致性部分进行合取规则的证据组合方法,同时利用证据的可信度来修正证据结构.在确定证据的可信度时,给出一种通用的计算模型.与很多改进的组合方法相比,该方法不仅适用于冲突情况,而且也适用于证据间比较一致的情况.数值仿真表明,所提出方法能加快收敛速度,同时降低决策风险.

证据冲突:丢弃,发现或化解?

组合可能冲突的信息是智能推理中重要的研究内容,其中,证据理论是一种典型的不确定性智能推理方法。在证据理论中,用以融合和更新证据信息的推理组合规则是其理论基石。Dempster组合规则通过合取运算来构造信息结构,得到了广泛的应用。然而,当证据冲突比较大、证据源不完全可靠或辨识框架不完备时,Dempster组合规则得到的结果并不符合常理。为此,改进组合规则和处理证据冲突,成为证据理论中一个重要的研究课题。将全面回顾和比较国内外现有的主要推理组合方法,基于不同的冲突处理机制,建立相应的理论框架,涵盖绝大多数推理方法,从理论上对证据推理方法的研究,进行一个全面的总结,并剖析各种组合方法的优缺点和相互关系,指出最新的研究趋势。

一种新的证据冲突分析方法

当证据高度冲突时,使用DS组合规则经常会得到错误的结果,因此对DS证据理论的合成方法进行改进成为人们研究的重点.但是如何去度量或确定证据之间冲突的程度却常常被人忽视.在以往的研究中均使用冲突系数k作为表征证据之间冲突的量,但是研究结果表明,k不能很好的描述证据之间的冲突.对表征证据冲突的变量进行了研究,提出了一种新的表征证据之间冲突的变量-关联系数,基于偏熵和混合熵,定义了关联系数,该系数可以定量的表示证据之间的冲突.当关联系数接近1时证据之间冲突很小,当关联系数接近0时证据之间高度冲突.算例验证了所提出的基于关联系数的冲突表示方法的有效性.

一种有效处理冲突证据的组合方法

为了有效融合高度冲突的证据 ,提出一种新的基于证据距离的组合方法 .首先引入了一个证据体距离函数 ,之后求出系统中各证据被其它证据所支持的程度 ,对支持度归一化后获得各个证据的可信度 ,并将可信度作为证据的权重 ,对系统中的证据加权平均后再利用Dempster组合规则实现信息融合 .与其它方法比较 ,该方法在系统存在伪证据 (干扰 )

基于pignistic概率距离的改进证据组合规则

针对使用传统冲突系数识别证据冲突存在的不足,采用pignistic变换后得到的概率赋值函数之间的距离,结合传统冲突量化标准,讨论了Dempster组合规则适用条件,并提出了一种改进的证据组合方法.该方法通过证据之间的pignistic概率距离表示证据之间的冲突程度,将证据间的冲突程度转化成相似程度,然后求出证据之间的支持程度,并确定权重系数,最后采用Demp-ster组合规则合成权重系数调整后的基本概率赋值.数值算例分析结果表明,改进的证据组合方法可以有效地处理证据冲突,且具有较快的收敛速度.

D-S证据理论中冲突证据的合成方法

针对高度冲突证据的合成问题,分析了D-S合成方法及其改进方法的不足,提出了一种新的改进方法。新方法仍利用D-S合成公式,但针对该公式要求参与合成的各证据需具有相同重要程度的要求,考虑到融合系统中各证据的重要程度可能不同,直接利用公式合成可能得到与实际相悖的结论,因而引入证据权的概念,给出了证据权的具体算法,通过证据权对已有的基本可信度分配函数进行修正得到了重要性相同的新的证据的基本可信度分配模型。最后通过算例比较表明新方法的合成结果更为理想。

DS证据理论冲突处理新方法

针对经典DS证据理论在处理高度冲突的证据信息时会产生有悖常理结论的情况,基于证据支持度的思想,引入了证据之间相容系数的概念,并随之引入证据可信度的概念,提出了一种新的证据权重的确定方法;最后运用DS证据理论组合规则进行数据融合。与之前其他处理方法相比,考虑到证据之间冲突与包容共存的情况,客观计算证据的权值,收敛更快,融合结论更符合事实,弥补了经典证据理论的不足,为DS证据理论的改进提供了一条新的途径。

D-S证据理论中冲突处理的新方法

针对经典D-S证据理论在处理高度冲突的证据信息时会产生有悖常理结论的问题,提出了一种新的证据合成方法。通过加性策略计算冲突焦元的支持信度,把证据中冲突焦元的支持信度作为新的基本概率分配,通过两两依次合成的方法实现多证据的合成。实验结果表明,该合成方法能够有效解决零元悖论问题,且在合成的结果的准确性、区分能力和适应性等方面优于现有典型方法。

一种基于局部冲突分配的DST组合规则

冲突证据融合是信息融合中一个非常重要但始终没有很好地解决的问题.本文从选择有效的冲突衡量参数的角度出发,分析了悖论与证据冲突的关系,给出了新的冲突衡量参数,并基于此参数提出了一种新的基于局部冲突分配策略的证据推理组合规则.大量实例表明,提出的证据推理组合规则能够解决现有的证据理论悖论问题,是一种较为通用的证据推理组合规则.

广义幂集空间中证据冲突的原因分析

经典证据理论不能有效处理高度冲突的证据,极大制约了证据理论的应用.早期的研究主要集中在修改Dempster组合规则或修改数据模型.Liu的研究又为这个方向提出了一个新的问题:如何有效表示证据之间的冲突?但是还存在问题:如何有效地判断冲突的成因?针对经典证据理论中的冲突系数无法合理度量证据之间的冲突程度,提出新的证据冲突系数表示模型,在冲突证据原因流程分析中总结出冲突的成因.最后用数值算例说明了本文所提出方法的有效性.

一种基于信息源可信度的证据组合新方法

D-S证据组合规则在处理高冲突度信息时,会得出与直觉相反的结论,进而遭到质疑,也引发了很多专家学者的研究。根据指挥员在作战中处理冲突证据的一般习惯,提出了一种基于信息源可信度的证据组合新方法。建立了信息源可信度的计算模型,给出了基于信息源可信度的按比例分配冲突度的证据组合推理规则,算例验证结果表明,新的组合推理规则在处理冲突方面的性能得到了明显改进。