A computational framework for identity based on situation. On the behavior of dempsters rule of combination and the. This paper presents a new classifier combination technique based on the dempstershafer theory of evidence. This article first introduces the basics of the dempstershafer ds theory of belief functions and shows how this framework can be used for managing uncertainties using a fraud. Dempstershafer theory dst, also known as the theory of evidence or the theory of belief functions, was introduced by shafer in 1976 1, based on dempsters previous works 24. Using dempstershafers theory of evidence to combine aspects. There is, however, a simple way of approach ing the dempstershafer theory that only requires a min. His student, glenn shafer 1976, developed method for obtaining degrees of belief for one question from subjective probabilities for a related dempstershafer theory. The evidence combination rule is the kernel of the er approach. Equipped with the ds theory knowledge, and the usage of pyds massfunction, the following sections describe the classification on the iris plant dataset using dempstershafer theory iris plant dataset. Dempstershafer theory is a mathematical theory of evidence, offers an alternative to traditional probabilistic theory for the mathematical representation of uncertainty. The dempstershafer theory of belief functions for managing uncertainties. It sho wn that application of the dempstershafer rule com bination in this case leads to ev aluation of masses.
The application of dempstershafer theory demonstrated with. Another model is the theory of evidence, or dempstershafer theory, which provides a method for combining evidences from different sources without prior. This theory offers an elegant theoretical framework for modeling uncertainty, and provides a method for combining distinct bodies of evidence collected from. The theory of belief functions, also referred to as evidence theory or dempstershafer theory dst, is a general framework for reasoning with uncertainty, with understood connections to other frameworks such as probability, possibility and imprecise probability theories. International journal of advanced network, monitoring and controls. Dempstershafer theory does not require an assumption regarding the probability of the individual constituents of the set or interval. The dempstershafer theory of evidence accumulation is one of the main tools for combining data obtained from multiple sources. Dempstershafer theory dst, also known as the theory of evidence or the theory of belief functions, was introduced by shafer in 1976 1 based on dempsters previous works 2, 3, 4. The dempstershafer ds evidence theory is based on the work of dempster during the 1960s and successfully1,2 extended by shafer3.
Dempstershafer theory of evidence is introduced, and the problem of application dst to online diagnosis for operation condition monitoring and failure detection and recognition is analyzed. Application of dempster shafer theory to assess the status. Dempstershafer theory an overview sciencedirect topics. An extended approach for dempstershafer theory ieee. Under this assumption, it is permissible to apply the.
Using dempstershafer theory in xml information retrieval. Main advantage of this framework is the explicit representation of ignorance. Future work we will consider different combination rules and applications of dempster shafer theory, look at weighting evidence, increase our set of scenarios. And evidence is, of course, the subject matter of law. Faulttolerant interval estimation fusion by dempster. Dempstershafer theory is an approach to combining evidence. Combination of evidence in dempstershafer theory electronic. The dempstershafer theory sometimes abbreviated to dst is a mathematical theory of evidence. Optimal object association in the dempstershafer framework.
The significant innovation of this framework is that it allows for the allocation of a probability mass to sets or. A new measure of conflict and hybrid combination rules in the. Generalized combination rule for evidential reasoning. Toward a dempstershafer theory of concepts sciencedirect. Any suspects exceeding the threshold value would be suspected of being guilty. The dempstershafer theory of evidence is a powerful method for combining measures of evidence from different classifiers. Sensor data fusion for contextaware computing using dempster. Combination of evidence in information retrieval there are two main reasons for why evidence combination can improve retrieval. The evidence is combined using dempsters rule of combination, and the belief committed to the relevance is obtained. Sentiment prediction based on dempstershafer theory of evidence. In bayesian statistics, how one can infer a belief distribution of the parameter for a parametric distribution fx, given a set of observations has been a classic problem. Using the dempstershafer theory of evidence to rank documents.
The dempstershafer ds theory of evidence can combine evidence with one parameter. Given two ds structures s, m 1 and s, m 2 over a set s, dempstershafer rule for combining beliefs provides a procedure to compute a new ds structure s, m 1. Dempstershafer evidence theory and study of some key. We discuss the sources of uncertainty in combining evidence in information retrievel and the. The burden of our theory is that this rule dempsters rule of combination corresponds to the pooling of evidence. Ds evidence theory is an uncertainty reasoning method and it decomposes the entire problem into several subproblems, sub evidences, and then uses the evidence combination rule to get the solution of the. The application of the theory hinges on the use of a rule for combining evidence from different sources.
Dempstershafers ds theory of evidence is a theory of uncertainty 8 that was first introduced by statistician arthur dempster 2 and extended by glenn shafer 6. A novel information fusion method based on dempstershafer. This report surveys a number of possible combination rules for dempstershafer structures and provides examples of the implementation of these rules for discrete and intervalvalued data. Combination of type iii digit recognizers using the dempster. Researcharticle exploring the combination of dempstershafer theory and neural network for predicting trust and distrust xinwang,1,2,3,4 yingwang,2,3 andhongbinsun1. Section 5 discusses the combination of situation theory and dempster shafer theory.
Situations and evidence for identity using dempstershafer theory. Particularly appealing is the mathematical theory of evidence developed by arthur dempster. In this paper a special case of combination of two bodies of evidence with nonzero conflict coefficient is considered. This paper presents an event recognition framework, based on dempstershafer theory, that combines evidence of events from lowlevel computer vision analytics. In a narrow sense, the term dempstershafer theory refers to the original conception of the theory by dempster and shafer. This theory is often described as a generalization of the bayesian theory to. Central to dempster shafer theory is the rule of combination of beliefs. Outline motivation algorithm description limitations and future work. The dempsterschafer theory of belief functions for managing.
A simple view of the dempstershafer theory of evidence. Using the dempstershafer theory of evidence to resolve. The advantage of the method is in the information fusion with the considerations of both information imprecision and uncertainty in multiinformation analysis. Pdf dempster shafer theory offers an alternative to traditional probabilistic theory for the mathematical representation of uncertainty. Weighted dempstershafer evidence combination rules implementation of equation eq. Combination of evidence a key idea in dempstershafer theory is that beliefs are elaborated by aggregating different items of evidence. This model also incorporates the uncertain nature of information retrieval and relevance feedback. Neural network combining classifier based on dempstershafer theory 5the main idea is similar to the concept of a neuron. Dempstershafer ds theory is one of the main tools for reasoning about data obtained from multiple sources, subject to uncertain information 12, 16. Oct 01, 2020 central to dempstershafer theory is the rule of combination of beliefs representing e. In section 4, we illustrate how dempstershafer combination of evidence can be used to. The basic mechanism for evidence combination is dempsters rule of combination, which can be naturally derived using the random code metaphor as follows.
Combination of evidence in dempstershafer theory core. A new technique for combining multiple classifiers using. Here we purposed a temporal weighted evidence combination method together with the procedure of application. The theory allows one to combine evidence from different sources and arrive at a degree of belief represented by a mathematical object called belief function that takes into account all the available evidence. The dempstershafer ds theory of evidence, first introduced by arthur p.
An important aspect of this theory is the combination of evidence obtained from multiple sources and the modeling of conflict between them. A simple view of the dempstershafer theory of evidence and. Combination of acoustic classifiers based on dempstershafer. In this paper, it is proposed to apply the dempstershafer theory dst or the theory of evidence to map vegetation, aquatic and mineral surfaces with a view to detecting potential areas of observation of outcrops of geological formations rocks, breastplates, regolith, etc. Dempster in the context of statistical inference, the theory was later developed by glenn. Its main difference to probability theory is that it allows the explicit representation of ignorance and the combination of evidence. The following combination rule that combines multiple mi into a single m is fundamental for most applications of the dempstershafer theory. The proposition of evidence theory provides mathematical support for the establishment of. Special issue on the dempstershafer theory of evidence. Abstract evidence theory is best suitable for the problem of red system operation is a real time, dynamic decision process, a. It is shown that application of the dempstershafer rule of combination in this case leads to an evaluation of masses of the combined bodies that is. There are three important functions in dempster shafer theory.
The evidential reasoning er approach is an extension of ds theory that can combine evidence with two parameters weights and reliabilities. Using the dempstershafer theory of evidence to resolve abox inconsistencies andriy nikolov victoria uren. This equally trusting approach can cause problems if our sensor fusion system is not properly designed. Shafer theory does not require an assumption regarding the probability of. Dempstershafer theory, uncertainty, constraint programming, eclipse prolog. Operation condition monitoring using temporal weighted.
Sensor data fusion for contextaware computing using. Evidence combination dempstershafer theory provides a method to combine the previous measures of evidence of different sources. Representation, independence, and combination of evidence. Contextdependent combination of sensor information in dempstershafer theory for bdi calderwood, s. This is a pdf file of an article that has undergone enhancements after acceptance, such as the addition of a cover. In section 4, we illustrate how dempstershafer combination of evidence can be used.
It is a popular choice for testing with classification. We study here a combination rule based on dempstershafer theory of evidence 5 which can be considered an extension of bayesian probability. The theory of evidence also handles the problem of how to. Let m 1 and m 2 be the mass functions for twoindependent bodies ofevidence. The dempstershafer theory dst is a mathematical theory of evidence.
Particularly appealing is the mathematical theory of evidence. Shortliffe the drawbacks of pure probabilistic methods and of the certainty factor model have led us in recent years to consider alternate approaches. Using dempstershafers theory of evidence to combine aspects of. A new belief entropy in dempstershafer theory based on. Pdf dempstershafer theory offers an alternative to traditional probabilistic theory for the mathematical representation of uncertainty. Pdf a simple view of the dempstershafer theory of evidence.
The iris plant dataset is another standard benchmark problem of uci datasets. Pdf combination of evidence in dempstershafer theory. An introduction and fraud risk assessment illustration. In this paper, we apply the dempstershafer ds theory of evidence 31.
Pdf sand 20020835 unlimited release printed april 2002. It sho wn that application of the dempstershafer rule com bination. The principal task of such reasoning is data fusion, or evidence accumulation. Dempster shafer theory of evidence conflict between basic probability assignments combination rules. Dempstershafer theory offers an alternative to traditional probabilistic theory for the mathematical representation of uncertainty. The significant innovation of this framework is that it allows for the allocation of a probability mass to sets or intervals as opposed to mutually exclusive singletons. Dempstershafer evidence theory and study of some key problems.
Exploring the combination of dempstershafer theory and. Pdf on the combinality of evidence in the dempstershafer. Publishers pdf, also known as version of record queens university belfast research portal. We will consider different combination rules and applications of dempstershafer theory, look at weighting evidence, and increase our set of scenarios, particularly ones with vague evidence pointing to nonsingleton sets. This is a potentially valuable tool for the evaluation of risk and reliability in engineering applications when it is not possible to obtain a precise measurement from experiments, or when knowledge is obtained. They have the property to allow a non linear separation of classes with very good generalization capacities. Anyway combination has always been considered in the framework of classical probability theory. The key contribution of this thesis is introducing the dempstershafer theory of evidence as a generalizable sensor fusion solution to overcome the typical contextsensing difficulties, wherein some of the available information items are subjective, sensor observations probability objective chance distribution is not known accurately. Dempsters combination rule provides a way to fuse different bpas.
The significant innovation of this framework is that it allows. Central to dempstershafer theory is the rule of combination of beliefs. Dempstershafer theory, evidence, data fusion, coal mining, sealed fires, air. It considers sets of propositions instead of just single propositions and assigns to each set an interval within which the degree of belief for the set must lie. Dempster shafer theory inconsistent with evaluation of probabilities. A case of combination of evidence in the dempstershafer theory. Handwritten indic script recognition based on the dempster.
Plaa is naturally referred to as the belief interval of a. If is the basic probability assignment provided by source, the combination. Combination of evidence in dempstershafer theory unt. Pdf dempstershafer theory for a querybiased combination. To develop an adequate understanding of this theory re quires considerable effort and a good background in proba bility theory. Dempstershafer theory, which can be regarded as a generalisation of probability theory, is a widely used formalism for reasoning with uncertain information. The dempstershafer theory of evidence 5,7,8 is a proven method for combining information from different sources, whose performance, however, depends very much. Contextdependent combination of sensor information in.
Dempster 1967 developed means for combining degrees of belief derived from independent items of evidence. Script recognition articles for handwritten documents are relatively limited in. Using the dempstershafer theory of evidence to resolve abox. Ds evidence theory is proposed based on the research of dempster 8. In the current versions of the dempstershafer theory, the only essential restriction on the validity of the rule of combination is that the sources of evidence must be statistically independent. This theory offers an elegant theoretical framework for modeling uncertainty, and provides a method for combining distinct bodies of evidence collected.
The dempstershafer evidence theory for image segmentation 5 2. The dempstershafer theory of evidence jean gordon and edward h. Dempstershafer theory described in glenn shafers 1976 book a mathematical theory of evidence is a generalized scheme for expressing uncertainty. Dempster shafer theory evidence tutorial telegraph. Dempstershafer theory for classification using python. They were first introduced by vapnik 9 for the text recognition task. Video event recognition by dempstershafer theory xin hong, yan huang, wenjun ma, paul miller, weiru liu and huiyu zhou 1 abstract. Among many theoretical advances, the most noticeable are the theory of linear belief functions,4 the theory of transferable beliefs,5 and the theory of hints. In fact, most of the existing approaches use simpl. We discuss the sources of uncertainty in combining evidence in. Combination of evidence in dempstershafer theory citeseerx dempstershafer theory offers an alternative to traditional probabilistic theory for the.
Combination of type iii digit recognizers using the. Combination of acoustic classifiers based on dempster. Using dempstershafers theory of evidence to combine. A case of combination of evidence in the dempstershafer.
585 981 430 681 1082 977 998 499 1292 1094 1046 1494 1251 628 1280 478 354 795 640 960 4 958 1309 959 781 1391 1398 497 1187 594