Narrow Results

The work reported in this paper is motivated towards validating an alternative approach for fault tolerance over traditional methods like checkpointing that constrain efficacious fault tolerance. Can agent intelligence be used to achieve fault tolerant parallel computing systems? If so, "What agent capabilities are required for fault tolerance?", "What parallel computational tasks can benefit from such agent capabilities?" and "How can agent capabilities be implemented for fault tolerance?" need to be addressed. Cognitive capabilities essential for achieving fault tolerance through agents are considered. Parallel reduction algorithms are identified as a class of algorithms that can benefit from cognitive agent capabilities. The Message Passing Interface is utilized for implementing an intelligent agent based approach. Preliminary results obtained from the experiments validate the feasibility of an agent based approach for achieving fault tolerance in parallel computing systems.

Mutual-belief is one important premise to ensure that cooperation among multiple agents goes smoothly. However, mutual-belief among agents is also always taken for granted. In this paper, we adapt a method based on the position-exchange principle (PEP) to reason about mutual-belief among agents. By reasoning about mutual-belief among agents, we can judge whether cooperation among agents can go on rationally or not.

However, if there are malicious agents involved in cooperation, the profit of honesty agents will be injured. To make cooperation useful, agents should be able to reason about cheating behaviors of malicious agents during cooperation. We extend the standard pi-calculus to specify the expectations of agents and define a group of criteria for anti-cheating that agents can use to establish true mutual-belief.

This paper proposes an Agent Inference Model (AIM) for constructing intelligent software agents. AIM has the ability of representing various types of fuzzy concepts, temporal concepts, and dynamic causal relationships between concepts. It also has the ability of handling feedback and analyzing inference patterns over different causal impact models. Based on AIM, a new type of intelligent agent, Dynamic Inference Agent (DIA) is presented. A dynamic inference agent has the ability to model, infer and make decisions on behalf of human beings. It uses numeric representations and computation instead of symbolic representation and logic deduction to represent knowledge and to carry out the inferences respectively. Thus the construction of DIA is simplified and the implementation code is compact. The application of DIA to various areas, especially for electronic commerce over the Internet is exemplified.

In this paper, a high-efficiency knowledge management system, HDIA_KMS, based on habitual domains and intelligent agents is proposed. The design concept of the system is to use an agent community to deal with the activities of knowledge management effectively, that is, knowledge sharing, knowledge classification, knowledge creation, and knowledge recovery. The features of this system are: collecting the surfing habits of each user and finding hidden patterns of departments to recommend articles by data mining; classifying the knowledge articles in accordance with departments and therefore rapidly finding out suitable documents for users; providing personal service through personal profiles; creating new knowledge documents by discussing among users; accepting and reclassifying improperly classified articles found by users; taking the abilities of collaboration, independence and automation of agents to help users use and improve the effects of HDIA_KMS. The PASSI methodology is adopted to analyze and design the system, and agents protocols follow the FIPA specifications.

In this paper an interactive recommending agent is proposed which helps an e-learner to enhance the quality of learning experience resulting in efficient achievement of learning objectives. The agent achieves this with the help of a fuzzy rule base working on a variety of learning materials and recommending the appropriate learning path through them. In a learner-centric environment the learning behaviour of a learner may vary to a great extent due to the characteristics of the learner and his environment. Students are often misled while choosing the appropriate path of web learning tools owing to non-availability of a human teacher/guide. By the response of a learner to different positive and negative motivation factors the proposed system employs a fuzzy machine that is fed with realization parameters e.g. Satisfied, Depressed etc. The fuzzy machine working on the paradigm of fuzzy inference system processes these realization parameters with the help of a fuzzy rule base to produce the crisp measures of the learner’s cognitive states in terms of Belief, Behaviour and Attitude. On the basis of these defuzzified crisp diagnostic parameters the proposed system will enhanced the quality of learning experience of an e-learner. To ensure this the system will provide more detailed discussion on the subject matter along with some additional learning tools. Learners often get confused to select the proper tools among various. Therefore the proposed system will also suggest most popular path among those learners with the same understanding. This recommendation comes from the analysis of data mining result. The system was tested with a wide variety of school-level students. The response obtained indicates that it is able to enhance the quality of learning experience through its recommendation.

Real and virtual organizations are conducted by preferences, goals, and policies. Since virtual organizations have a two-level structure the preferences of these different levels are a source of conflicting interests. Also, management policies itself are subject to change, especially in a virtual setting. Therefore, agility has superior value, causing the need to develop business information and planning systems that may be adapted easily. Both mentioned aspects of business planning software, namely, ease adaptation on one side and the integration of individual preferences and goals on the other are treated in the paper. An architectural design is proposed that meets the needs of virtual organizations as far as any conflicts can be solved on an individual basis. This concept is further elaborated. Negotiating agents that obey the preferences of their principals are considered as a means to search for compromise solutions. An extensive example derived from hospital management illustrates the concept.

Considering both the high complexity of urban traffic flow systems and the bounded rationality of travelers, providing traffic information to all travelers is an effective method to induce each individual to make a more rational route-choice decision. Within Advanced Traveler Information System (ATIS) working environment, temporal and spatial evolution processes of traffic flow in urban road networks are closely related to strategies of providing traffic information and contents of information. In view of the day-to-day route-choice situations, this study constructs original updating models of the cognitive travel time of travelers under four conditions, including not providing any route travel time, only providing the most rapid route travel time, only providing the most congested route travel time, and providing all the routes travel times. The disaggregate route-choice approach is adopted for simulation to reveal the relationship between the evolution process of network traffic flow and the strategy of providing traffic information. The simulation shows that providing traffic information to all travelers cannot improve the operational efficiency of road networks. It is noteworthy that an inappropriate information feedback strategy would lead to intense variation in various routes traffic flow. Compared with incomplete information feedback strategies, it is inefficient and superfluous to provide complete traffic information to all travelers.

This paper presents an adaptive approach to address a kind of adaptive learning for intelligent agent. We propose a knowledge processing cycle for intelligent agent to mimic the human's learning process. In this process we regard two important parts. We apply the assimilation process to learn the new information and the accommodation process when the new information has some conflict with agent's proper known. We use the JADE (Java Agent DEvelopment Framework) as our agent platform, and explain our approach through pursuit-evasion game.

This paper focuses in an application combining three apparently separated research areas: virtual environments, intelligent agents and museum web pages. It consists in a virtual visit to a museum guided by an intelligent agent.

The agent must respond in real time to user's requests, providing different layers of data, making difference between users by using different Knowledge-Bases. The agent not only has some autonomy during the visit but also permits the user to make his own choices. The environment is created allowing an immersion, so the user could feel himself inside the museum's structure. This kind of application works as a complementary experience, because the user is being introduced to the expositions in the museum, convincing him to make a future real visit.