C. Zhang (1992). Cooperation Under Uncertainty in Distributed Expert Systems. Artificial Intelligence, Vol. 56, pp. 21-69.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....selfish protocol is presented. An appointment made through this protocol is a overall optimum common time slot. Third, an axiomatic framework is identified for fusing agents individual evaluations for a proposal. The framework is also applicable to solution synthesis in distributed expert systems [21, 22, 20], parallel combination operations [10] in expert systems and aggregation operations [19] in fuzzy mathematics. In addition, a meeting scheduling example is used to illustrate the proposed methodology. It is worth further developing: 1) other protocols for more complicated meeting scheduling ....

C. Zhang, `Cooperation under Uncertainty in Distributed Expert Systems ', Artificial Intelligence, 56, 21-69, (1992).

....selfish protocol is presented. An appointment made through this protocol is a overall optimum common time slot. Third, an axiomatic framework is identified for fusing agents individual evaluations for a proposal. The framework is also applicable to solution synthesis in distributed expert systems [21, 22, 20], parallel combination operations [10] in expert systems and aggregation operations [19] in fuzzy mathematics. In addition, a meeting scheduling example is used to illustrate the proposed methodology. It is worth further developing: 1) other protocols for more complicated meeting scheduling ....

C. Zhang, `Cooperation under Uncertainty in Distributed Expert Systems ', Artificial Intelligence, 56, 21-69, (1992).

....bases as information sources. So such coordination tools seem to work just at a syntactic level rather than a semantic level. Furthermore, as expert systems have been built up in many real fields over the past decade, the research on Cooperative Distributed Expert Systems (CDES) has emerged (C.Zhang ,92) M.Zhang and C.Zhang ,94) and (T.Itoh, T.Watanabe and T.Yamaguchi ,95) integrating two kinds of technology from knowledge acquisition and software agents. The work in the field of CDES focuses on the cooperation among distributed expert systems but has not yet been getting into cooperation ....

....sources. So such coordination tools seem to work just at a syntactic level rather than a semantic level. Furthermore, as expert systems have been built up in many real fields over the past decade, the research on Cooperative Distributed Expert Systems (CDES) has emerged (C.Zhang ,92) M. Zhang and C.Zhang ,94) and (T.Itoh, T.Watanabe and T.Yamaguchi ,95) integrating two kinds of technology from knowledge acquisition and software agents. The work in the field of CDES focuses on the cooperation among distributed expert systems but has not yet been getting into cooperation in real complex domains at ....

[Article contains additional citation context not shown here]

C.Zhang, (1992). Cooperation under Uncertainty in Distributed Expert Systems, Artificial Intelligence. Vol.56. pp.21-69.

....We make no claim that every agent in the system must be a BN. An agent may take other representation formalism, and integration of a hybrid system is one of the issues that demand further study. A study of integrating inexact reasoning models (other than BNs) in DAI systems is presented by Zhang [13]. Acknowledgement This work is supported by the Dean s Research Funding from Faculty of Science, University of Regina, the General NSERC Grant from University of Regina, and Research Grant OGP0155425 from NSERC. ....

C. Zhang. Cooperation under uncertainty in distributed expert systems. Artificial Intelligence, (56):21--69, 1992.

....agents is very important. In order for agents to be able to communicate, they either need to use the same knowledge representation method, or have a means of translating between the methods used by different agents. This is especially true if the various agents are capable of handling uncertainty [11]. If different agents have different means of handling uncertainty, then one agent that, say, uses possibility theory to represent its uncertainty will not be able to understand the results of another agent that employs belief functions unless the agents have a means of translating from one ....

Zhang, C. Cooperation under uncertainty in distributed expert systems, Artificial Intelligence, 56 (1992) 21--69. This article was processed using the L A T E X macro package with LLNCS style

.... assume similar representations E 374 of partial solutions (and their certainty measures) which makes combining them E 420 straightforward, although some researchers have considered challenges in crossing E 415 between representations, such as combining different uncertainty measurements E 370 [Zhang 1992]. E 42 In functionally accurate cooperation, the iterative exchange of partial results is E 425 expected to lead, eventually, to some agent having enough information to keep E 415 moving the overall problem solving forward. Given enough information E 349 exchange, therefore, the overall ....

Chenqi Zhang. Cooperation under uncertainty in distributed expert<E-415> systems. Artificial Intelligence 56:21-69, 1992.<E-219>

....Furthermore, this strategy is compared with related work. 1 Introduction Synthesis of solutions has been become one of critical issues among cooperative expert systems for more than ten years [8] Some synthesis strategies have been developed in distributed expert systems (DESs) such as [2, 7, 9]. These strategies were mainly based on the mathematical analysis of the characteristics of the inputs (multiple solutions from ESs) In recent years, we have developed some synthesis strategies [10] using neural networks. These strategies were based on a number of samples with both inputs and ....

....introduction to each module and a case base. a) Transformation module If the range of uncertainties of a proposition is not in the range [0,1] the uncertainties of the proposition are transformed from that range to the range of [0, 1] by using the heterogeneous transformation functions [7] in the transformation module. For example, if an ES uses the EMYCIN [6] model, the range of [ Gamma1; 1] should be transformed into the range of [0, 1] in the PROBABILITY model [1] b) Normalization module After transformation, the sum of uncertainties may not satisfy the requirements in ....

[Article contains additional citation context not shown here]

C. Zhang (1992). Cooperation Under Uncertainty in Distributed Expert Systems. Artificial Intelligence, Vol. 56, pp. 21-69.

....expert system PROSPECTOR [11] for determining site potential for mineral exploration. So, to achieve cooperation among these expert systems, the rst step is to transform the uncertainty of a proposition from one uncertain reasoning model to another if they use di erent uncertain reasoning models [90, 91, 93, 43, 95], then the second step is to synthesise the transformed di erent results [97, 98] In other words, the transformation among di erent uncertain reasoning models is the foundation for cooperation among these heterogeneous expert systems, and so this is a very important and very interesting problem. ....

....) 1 minfjCF (H;S1 )j;jCF (H;S2 )jg if CF (H; S 1 ) CF (H; S 2 ) 0: 1) Theorem 1 ( 1; 1) CF ) is a group. Proof. It is easy to verify that the operator CF on ( 1; 1) is closed, and satis es the associative and commutative laws. The unit element is 0 and the inverse element of x is x [90]. So, 1; 1) CF ) is a group. 2 The above group, called the certainty factor group, can be described clearly as follows: 1) set: 1; 1) 2) operator CF : 1; 1) 1; 1) 1; 1) is given by: CF (x 1 ; x 2 ) x 1 x 2 x 1 x 2 if x 1 0, x 2 0, x 1 x 2 x 1 x 2 if x 1 0, ....

[Article contains additional citation context not shown here]

C. Zhang, Cooperation under Uncertainty in Distributed Expert Systems, Arti cial Intelligence, 56, pp. 21-69, 1992.

....uncertain reasoning model, Wang [14] suggested some descriptive conditions which operations of propagation for uncertainty through an inference network should satisfy. In other words, all of them considered the generality but only suitable for a few special cases. Although the work of Zhang in [17] is more general than those mentioned previously, he is mainly concerned with parallel combinations. In fuzzy mathematics, some researchers [4, 16, 11] studied various operations of AND, OR and NOT and presented an axiom foundation for them which re ects part of the law of uncertain reasoning by ....

C. Zhang. Cooperation under uncertainty in distributed expert systems, Arti cial Intelligence 56, 21-69, 1992.

No context found.

C. Zhang, "Cooperation under uncertainty in distributed expert systems", Artificial Intelligence 56 (1992) 21-69.

....combination of random sets under a closed world assumption. Keywords : Uncertainty information, Interval structures. 1 Introduction It is discovered that there exist uncertainties in many kinds of informations, e.g. in the fields of cooperation under uncertainty in multiple agent systems [9] [11] and information indexing and retrieval [6] 8] To make decisions under uncertain information, it is crucial to choose an appropriate structure to represent uncertain information, and to operate uncertain information under the structure [10] Although probability theory is the standard ....

....approximations of the rough set model, the lower and upper bound of incidence calculus, and the belief and plausibility functions all obeyed the axioms of an interval structure. For reasoning under uncertainty, especially in the fields of cooperation under uncertainty in multiple agent systems [9] [11] and information indexing and retrieval [4] 6] Dempster Shafer theory and interval structures play important roles, because we can view them as uniforms for building the concept spaces such as synthesis spaces and term spaces. In [4] we provide a model on modeling information indexing and ....

C. Zhang, "Cooperation under uncertainty in distributed expert systems", Artificial Intelligence, vol. 56, pp. 21-69, 1992.

....but also prove that our algorithm is better than Katz and Rosenschein s algorithm both on time complexity and space complexity. Keywords: Planning, Verification, Multiple agent systems. 1 Introduction Distributed problem solving plays an important role in distributed artificial intelligence [2,10,17,19,20,21]. Now, it is fashionable to use planning as a kind of approach for distributed problem solving in multiple agent environments [4,7] Planning research in multiple agent systems has historically focussed on two distinct classes of problems. One paradigm has been that of planning for multiple ....

C. Zhang, Cooperation under uncertainty in distributed expert systems, Artificial Intelligence, 1992, 56(1): 21-69.

....utilities of hypotheses and the concept of conclusion distances which describes the degrees of difference between conclusions. Based on these concepts, we present a two level decision model. This model can select a best alternative which is the delegate of common goods. I. INTRODUCTION In [9], Zhang classifies the cooperation among expert systems (ESs) in a distributed expert system (DES) into four types: horizontal cooperation, hierarchical cooperation, recursive cooperation and hybrid cooperation. Horizontal cooperation and hierarchical cooperation are very basic kinds of ....

....alternatives (competing, the second step) Synthesis of solutions with uncertainties is considered as an appropriate method to accomplish the first step of horizontal cooperation. Up to now, there have been several methods of synthesizing uncertainties of solutions in cooperative problem solving [2,5,9,12], and the most typical method is the default method of solution synthesis offered in HECODES [9,10] However, these models are often criticized for their robustness. This drawback stems mainly from the fact that an appropriate mathematical model is not used. Another drawback of these models is ....

[Article contains additional citation context not shown here]

C. Zhang, "Cooperation under uncertainty in distributed expert systems", Artificial Intelligence, vol. 56, no. 1, 1992, pp. 21-69.

....be sure which agents have the PSA to do its tasks. Because it always assumes that other agents will help one another only when it is in their own best interests to do so, and in most cases the solutions sent by different agents for a same task are always different and even contain uncertainty [ 36 ] For task level cooperation, one common approach is to use a central coordinator (agent) which has a centralized planning. Using this approach, the central agent generates the global plan and then hands out pieces of that plan to be performed by the participating agents [ 5 ] 15 ] 26 ] ....

....5 Related work This research relates two research fields, one is the synthesis of solutions under uncertainties, another is making decisions in uncertainty worlds. Up to now, there have been several methods of synthesizing uncertainties of solutions in cooperative problem solving [ 16 ] 22 ] 36 ] 39 ] and the most typical method is the default method of solution synthesis offered in HECODES [ 36 ] However, these models are often criticized for their robustness. This drawback stems mainly from the fact that an appropriate mathematical model is not used. In order to use a robust ....

[Article contains additional citation context not shown here]

C. Zhang, Cooperation under uncertainty in distributed expert systems, Artificial Intelligence, 1992, 56(1): 21-69.

....A distributed expert system (DES) consists of expert systems (ESs) which are linked by Internet. It differs from the more general area of distributed processing because it is concerned with distributing control as well as data, and it can involve extensive cooperation between expert systems [7]. Some approaches have been done on cooperation in DESs [7] These approaches to cooperation concentrate mainly on scheduling of tasks and ESs under certainty, or in other words, the organization of ESs to cooperatively solve a problem under certainty. In [7] Zhang classifies the cooperation ....

....systems (ESs) which are linked by Internet. It differs from the more general area of distributed processing because it is concerned with distributing control as well as data, and it can involve extensive cooperation between expert systems [7] Some approaches have been done on cooperation in DESs [7]. These approaches to cooperation concentrate mainly on scheduling of tasks and ESs under certainty, or in other words, the organization of ESs to cooperatively solve a problem under certainty. In [7] Zhang classifies the cooperation among ESs in a DES into four types: horizontal cooperation, ....

[Article contains additional citation context not shown here]

C. Zhang, Cooperation under uncertainty in distributed expert systems, Artificial Intelligence, 1992, 56(1): 21-69.

....A distributed expert system (DES) consists of multiple physically separated processing nodes which have at least one expert system (ES) Some work has been done on cooperation in DES [1,4] Important approaches of cooperation include negotiation, FA C, and organizational structuring. In [8], Zhang classifies the cooperation among component ESs in a DES into four types: horizontal cooperation, hierarchical cooperation, recursive cooperation and hybrid cooperation. In this paper we are concerned only with horizontal cooperation, and we deal in particular with cooperation under ....

....England research grant and partially supported by the large grant from the Australian Research Council (A49530850) Email: fChengqi, Yuefengg neumann.une.edu.au. Phone: 61 (02) 67 73 2350 1 there have been several methods of synthesizing uncertainties of solutions in cooperative problem solving [3,8,9,10], and the most typical method is the default method of solution synthesis offered in HECODES [8,9] The default method is perhaps best understood by virtue of its simplicity. However, this model is often criticized for its robustness. This drawback stems mainly from the fact that an appropriate ....

[Article contains additional citation context not shown here]

C. Zhang, Cooperation under uncertainty in distributed expert systems, Artificial Intelligence, 1992, 56(1): 21-69.

....uncertain reasoning model, Wang [14] suggested some descriptive conditions which operations of propagation for uncertainty through an inference network should satisfy. In other words, all of them considered the generality but only suitable for a few special cases. Although the work of Zhang in [17] is more general than those mentioned previously, he is mainly concerned with parallel combinations. In fuzzy mathematics, some researchers [4, 16, 11] studied various operations of AND, OR and NOT and presented an axiom foundation for them which reflects part of the law of uncertain reasoning by ....

C. Zhang. Cooperation under uncertainty in distributed expert systems, Artificial Intelligence 56, 21--69, 1992.

....strategies is one of the critical research issues in a DES field. Several synthesis strategies have been proposed to solve belief conflicts in DESs [5] such as, uncertainty management strategy proposed by Khan in 1985, a synthesis strategy for heterogeneous DESs introduced by Zhang in 1992 [4], and an improved synthesis strategy which considers both uncertainties and authorities of ESs proposed by Liu in 1992. More recently, based on the above researches, we have also proposed a new comprehensive synthesis strategy to overcome several limitations of the above strategies and we have ....

....from the root to a leaf in an inference network G. Definition 3: A rule chain is defined as any chain from one node to another node in an inference network G if there exists a general rule chain K through this chain, i.e. a rule chain is a sequence of rules in R and a part of a general chain [4]. Definition 4: The original evidence set of proposition B is represented by EB , where EB is a unique set of leaf propositions which satisfy the condition that there is a rule chain to connect such a leaf and proposition B. The next three definitions are our formal definitions of different ....

[Article contains additional citation context not shown here]

C. Zhang, Cooperation under Uncertainty in Distributed Expert Systems. Artificial Intelligence, 56, pp. 21-69, 1992.

....be divided into two parts, conflict cases and non conflict cases. Traditional methods of solving belief conflicts in DESs are synthesis strategies which include: uncertainty management strategy developed by Khan [2] in 1985; a synthesis strategy for heterogeneous DESs introduced by Zhang in 1992 [6]; and an improved synthesis strategy which considers both uncertainties and authorities of ESs proposed by Liu in 1992 [3] In 1994, based on the above research, we also proposed a new comprehensive synthesis strategy to overcome several limitations of above strategies [7] Also in 1994, we have ....

C. Zhang (1992). Cooperation under Uncertainty in Distributed Expert Systems, Artificial Intelligence, 56, pp.21-69.

....computer system, the content of communication is often accurate. In DAI systems, most of time we can just communicate partial results or tentative hypothesis to other agents. Dealing with uncertainty is an important issue. Some researchers have to solve this problem by mathematical methods. Zhang [7] successfully used the synthesis of the solution to solve the horizontal cooperation among different expert systems in a distributed expert system (HECODES) A different expert system offers different solutions to a particular subtask. These differences are in two main ways: a) the solution are ....

....but their associated uncertainties are different. From the point of view of inexact reasoning, different solution can be thought of as being the same solution with different associated uncertainties. So the synthesis of solutions is the synthesis of uncertainties of solutions in a DES. Zhang [7] proposed a scheme of handing uncertainty in a distributed environment. The scheme can be decomposed into three steps: a) dealing with competing hypotheses; b) co operation; and (c) decision making. The special features are in this scheme: a) It is consistent for different inexact reasoning ....

C. Zhang, Cooperation Under Uncertainty in Distributed Expert Systems. Artificial Intelligence, Vol. 56, pp. 21-69, 1992.

....ESs and the authorities for each ES are considered. 3 The Heterogeneous Transformation of Uncertainties In DESs, the transformation of uncertainties of a proposition between different inexact reasoning models is one of the fundamental problems for cooperative problem solving. It has two roles [10] for heterogeneous transformation: a) If ESs in a DES use different inexact reasoning models, it is necessary to transform the uncertainties of propositions from different models to a single model when ESs cooperate. For example, if one ES uses the EMYCIN model, the range of uncertainties is in ....

C. Zhang, Cooperation Under Uncertainty in Distributed Expert Systems. Artificial Intelligence, Vol. 56, pp. 21-69, 1992.

....no exception. HECODES is used to build DESs to facilitate cooperation among ESs. Four types of cooperation are supported according to the type of relationship involved in the interdependence of ESs. They are: horizontal cooperation; tree cooperation; recursive cooperation; and hybrid cooperation [16]. Using these types of cooperation which are implemented through communication, HECODES can solve complicated problems that are too difficult for any single ES to solve. In figure 1, the communication module is separated from the knowledge base of H COMM, where H COMM is the name of the ....

C. Zhang, Cooperation under uncertainty in distributed expert systems, Artificial Intelligence, 56, pp. 21-69, 1992.

.... mean value of corresponding inputs but also the uniformity about corresponding inputs [2] 2) a synthesis strategy for heterogeneous DESs which was developed based on both transformation functions among different inexact reasoning models among heterogeneous ESs and mean values of inputs from ESs [9]; and (3) a synthesis strategy based on the factors of authorities from ESs, mean values of inputs, influence among ESs for decision making, and uniformity of inputs from ESs. All of these strategies implemented analysis methods by some mathematical theories. 9 Popular mathematical theories used ....

C. Zhang, Cooperation under Uncertainty in Distributed Expert Systems. Artificial Intelligence, Vol. 56, pp. 21-69, 1992.

No context found.

Zhang C. Cooperation under uncertainty in distributed expert systems. Artificial Intelligence, 1992, 56: 21--69.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC