In decision-making problems under risk, one of the main tasks is to evaluate the probabilities of the occurrence of such random events that affect the outcomes of alternative decisions. In some specific situations, du...
详细信息
ISBN:
(数字)9798350399851
ISBN:
(纸本)9798350399851
In decision-making problems under risk, one of the main tasks is to evaluate the probabilities of the occurrence of such random events that affect the outcomes of alternative decisions. In some specific situations, due to the lack of initial information, it is difficult or even impossible to perform such evaluation. In this article we present an alternative approach to choosing decisions under uncertainty. This approach is based on the possibility theory, which is at the intersection of various developed theories of uncertainty: the theory of fuzzy sets, the theory of evidence and the theory of probabilities. Evaluating the possibilities of relevant events is a simpler task than evaluating the probabilities of these events. The article presents the conceptual foundations of the possibility theory. The use of this theory for decision making is demonstrated with a simple illustrative example.
The Dempster-Shafer theory of evidential reasoning has been proposed as a generalization of Bayesian probabilistic analysis suitable for classification and identification problems. Discriminatory information is given ...
详细信息
Health prognosis for equipment is considered as a key process of the condition-based maintenance strategy. However, in many cases, due to the performance and working environment of the sensor, working condition of equ...
详细信息
Health prognosis for equipment is considered as a key process of the condition-based maintenance strategy. However, in many cases, due to the performance and working environment of the sensor, working condition of equipment, and monitoring error, the monitored data can unavoidably exist uncertain data information, for example noisy data and noisy data. The accurate health state of equipment is difficult to be obtained. To address it, this paper presents a joint optimization model for equipment health prognosis by combining Dempster-Shafer evidence theory (DS) with Markov chain model (MCM). First, based on Markov model, DS is used to develop the state recognition framework of equipment. Then, the uncertain data is allowed to be handled in the form of interval number, and the basic probability assignments (BPA) can be generated based on the distance and similarity among interval numbers. BPA is transformed into the probability distribution of basic health states by Pignistic probability conversion in order for increasing the reliability. Finally, a case study is used to show the effectiveness and rationality of the proposed model. The results show that the proposed model has an efficient ability in dealing with uncertain data information, and can effectively solve the problem of equipment health prognosis with partially observed information.
Distributed classification using multimodal sensors is a problem of very high practical importance. Most of the existing distributed classification systems are designed under the assumptions that prior class probabili...
详细信息
ISBN:
(纸本)9780982443859
Distributed classification using multimodal sensors is a problem of very high practical importance. Most of the existing distributed classification systems are designed under the assumptions that prior class probabilities, and/or observation models are known. In this paper, we design a distributed classification system without requiring any prior model information. Specifically, at each local sensor, multiple binary support vector machine (SVM) based classifiers are used and each classifier is trained to distinguish one class from the rest. At the fusion center, the Dempster-Shafer theory is adopted to effectively combine the evidence from all SVMs with appropriately defined basic probability assignments. The final decision is made by selecting the class with the highest belief. Theoretical performance prediction methods are proposed for the designed classification system. Through experiments on a synthetic dataset and the benchmark 1999 KDD intrusion detection dataset, we demonstrate the effectiveness of the evaluation method and the superiority of the proposed framework over the conventional Bayesian cost based fusion rule in this context.
暂无评论