Uncertain information fusion with robust adaptive neural networks-fuzzy reasoning

In practical multi-sensor information fusion systems, there exists uncertainty about the network structure, active state of sensors, and information itself （including fuzziness, randomness, incompleteness as well as roughness, etc）. Hence it requires investigating the problem of uncertain information fusion. Robust learning algorithm which adapts to complex environment and the fuzzy inference algorithm which disposes fuzzy information are explored to solve the problem. Based on the fusion technology of neural networks and fuzzy inference algorithm, a multi-sensor uncertain information fusion system is modeled. Also RANFIS learning algorithm and fusing weight synthesized inference algorithm are developed from the ANFIS algorithm according to the concept of robust neural networks. This fusion system mainly consists of RANFIS confidence estimator, fusing weight synthesized inference knowledge base and weighted fusion section. The simulation result demonstrates that the proposed fusion model and algorithm have the capability of uncertain information fusion, thus is obviously advantageous compared with the conventional Kalman weighted fusion algorithm.

On Normalization of Comprehensive Evaluation System with Complex Uncertain Information

This paper systematically proposes basic requirements on normalization of comprehensive evaluation system with complex uncertain information due to human participation. Four basic academic ideas are as follows: 1) It is necessary to normalize conditions of information acquisition. 2) The effectiveness of comprehensive evaluation depends on the correctness of information acquisition. 3) Any evaluation results can be transformed into linguistic satisfactory degrees. 4) Linguistic values can include a great deal of information. This paper mainly deals with how to select objects to be evaluated, evaluators (panelists) and the methods of information processing, how to construct criteria of evaluation, how to normalize terms of evaluation, the results of evaluation, and the procedure of evaluation.

Interval Arithmetic and Its Application to Electrical Circuits

Interval arithmetic is an elegant tool for practical work with inequalities, approximate numbers, error bounds, and more generally with certain convex and bounded sets. In this section we give a number of simple examples showing where intervals and ranges of functions over intervals arise naturally. Interval mathematics is a generalization in which interval numbers replace real numbers, interval arithmetic replaces real arithmetic, and interval analysis replaces real analysis. Interval is limited by two bounds： lower bound and upper bound. The present paper introduces some of the basic notions and techniques from interval analysis needed in the sequel for presenting various uses of interval analysis in electric circuit theory and its applications. In this article we address the representation of uncertain and imprecise information, the interval arithmetic and its application to electrical circuits.

信息化高炮武器系统能力的未确知测度综合评价

为定量地综合评价信息化高炮武器系统的作战效能,假设武器系统具有一定可用度和可信度条件下,对系统完成规定任务的能力提出了一种基于未确知理论的评价模型。结合信息化高炮武器系统的特点,应用未确知理论研究了评价其系统能力的指标体系和度量方法,建立了基于未确知测度的一种武器评价识别模型,用实例分析了测度可以量化的单因素测度函数,介绍了指标评价等级测度计算方法。该模型克服了以往用模糊评价法的不足,可定量地综合评价信息化高炮武器系统作战效能。

A novel approach for remanufacturing process planning considering uncertain and fuzzy information

Remanufacturing,as one of the optimal disposals of end-of-life products,can bring tremendous economic and ecological benefits.Remanufacturing process planning is facing an immense challenge due to uncertainties and fuzziness of recoverable products in damage conditions and remanufacturing quality requirements.Although researchers have studied the influence of uncertainties on remanufacturing process planning,very few of them comprehensively studied the interactions among damage conditions and quality requirements that involve uncertain,fuzzy information.Hence,this challenge in the context of uncertain,fuzzy information is undertaken in this paper,and a method for remanufacturing process planning is presented to maximize remanufacturing efficiency and minimize cost.In particular,the characteristics of uncertainties and fuzziness involved in the remanufacturing processes are explicitly analyzed.An optimization model is then developed to minimize remanufacturing time and cost.The solution is provided through an improved Takagi-Sugeno fuzzy neural network(T-S FNN)method.The effectiveness of the proposed approach is exemplified and elucidated by a case study.Results show that the training speed and accuracy of the improved T-S FNN method are 23.5%and 82.5%higher on average than those of the original method,respectively.

Extending the Relational Model to Deal withProbabilistic Data

According to the soundness and completeness of information in databases, the expressive form and the semantics of incomplete information are discussed in this paper. On the basis of the discussion, the current studies on incomplete data in relational databases are reviewed. In order to represent stochastic uncertainty in most general sense in the real world, probabilistic data are introduced into relational databases. An extended relational data model is presented to express and manipulate probabilistic data and the operations in relational algebra based on the extended model are defined in this paper.