Agent Technology

This paper presents a framework for dynamic work∞ow creation and execution developed as part of ARGUGRID, a collaborative project that seeks to provide a new model for programming the Grid at a semantic, knowledge-based level of abstraction through the use of argumentative agent technology. In this framework, work∞ow selection is coordinated by agent interactions based upon a dialogue game that allows agents to argue about work∞ows and their properties.

The vision of intelligent wireless web services, as discussed in this paper centres on the need to provide mobile construction workers highly specific data and services on an as-needed basis, with flexibility of use for the user. With the emergence of high speed wireless networks, such as Wi-Fi, Bluetooth and 3G, and parallel advancements in Internet based technologies such as the Semantic Web, Web Services, Agent based technologies and Context Awareness, the realisation of the vision of the intelligent wireless web has become a possibility. The paper presents a state-of-the-art review of the enabling technologies and discusses how, by exploiting the convergence and synergy between different technologies, it has become possible to deliver intelligent wireless web support to mobile construction workers.

Rapid growth and expansion of information and communication technology (ICT) have set the pace for an electronic revolution leading to adoption of e-marketplace within the small and medium enterprises (SMEs). Locally, this growth in ICT promises to further bolster the SMEs' position as the engine of growth for the Malaysia economy. However, there are various challenges and issues in setting up an e-marketplace in developing countries which appear to impede the growth of e-marketplace. In this paper, the realities of e-business adoption in Malaysian wood based products industry are discussed. This leads to the proposal of an integrated e-marketplace framework. This framework integrates different types of business mechanisms to facilitate in the trading of wood-based products in Malaysia. These mechanisms comprise of a third-party intermediary portal, mobile agent-based multi-attribute reverse auction and an e-negotiation feature that incorporates the use of the short messaging system service.

Modern multiagent technology can be applied fruitfully to supply chain or - to be more precise - to demand chain management. In current research there is not much discussed in this direction because today's business processes are often characterized more by small solutions than by integrated ones. This paper will prove that this approach offers very new and challenging possibilities

The concept embodying agent-mediated personal knowledge management (PKM) manifests a bottom-up process of organisational knowledge management (OKM) in achieving collective goals. Exploiting this concept from the perspective of crossing organisational boundaries and into the realm of social network, the concept of social intelligence is proposed. Social intelligence has been defined in many aspects, one of which is the sociability characteristics of a software agent in performing tasks over a social network. In modelling the PKM framework, intelligent agents are assigned with tasks to assist their human counterparts, where the PKM processes are enacted as a series of getting, understanding, and sharing knowledge and connecting to others for knowledge, over the social network. The critical issue is to identify and ‘locate’ knowledge experts for further enlightenment of one’s personal knowledge. Considering the advantages of social network and the congruence between PKM processes and Nonaka’s SECI model, the emergence of social intelligence is investigated in this paper by analysing the responses to a questionnaire survey on PKM processes. This paper also discusses the limitations of this research vis-à-vis the current practice in which the e-mail is predominantly used to manage personal knowledge. In resolving the issues identified, a nodal approach to agent-mediated PKM is proposed to model the emergence of social intelligence, where knowledge workers work cooperatively with software agents in a virtual workspace called a node. It then analyses the processes by characterising these nodes as intelligent social entities.

The relationship between the actors in the law making process is governed by the doctrine of separation of powers. Scholarly literature state that each of these actors is interdependent on the other and no single agency is able to exercise complete authority. The doctrine, however, can be extended to enable the three branches to act as checks and balances on each other. The study inquires into how the relationship between and amongst the actors in the legislative process covering both the legislative drafting (not covered under the doctrine of separation of powers) and the lawmaking processes can be modelled without infringing on the doctrine of separation of powers. We analyse the application of artificial intelligent approach to modelling and propose the application of agent technology in modelling this relationship.

This research investigated the effects of applying intelligent agent techniques to an online learning environment. The knowbots (or Knowledge Robots) created for the research were intelligent software agents that automated the repetitive tasks of human facilitators in a series of online workshops. The study specifically captured experimental results of using knowbots in multiple sessions of an ALN (Asynchronous Learning Network) online workshop, Getting Started Creating Online Courses. The study used experimental groups and comparison groups to examine the association between the use of knowbots and workshop completion rates. Also examined were the effects of knowbots on other factors such as facilitation time and learner satisfaction. The findings indicated that the use of knowbots was positively associated with higher learner completion rates in the workshops. In addition, knowbots implemented a learning-support tool that reminded learners about deadlines. The support knowbots wer...

TIntelligent multi agent systems have great potentials to use in different purposes and research areas. One of the important issues to apply intelligent multi agent systems in real world and virtual environment is to develop a framework that support machine learning model to reflect the whole complexity of the real world. In this paper, we proposed a framework of intelligent agent based neural network classification model to solve the problem of gap between two applicable flows of intelligent multi agent technology and learning model from real environment. We consider the new Supervised Multilayers Feed Forward Neural Network (SMFFNN) model as an intelligent classification for learning model in the framework. The framework earns the information from the respective environment and its behavior can be recognized by the weights. Therefore, the SMFFNN model that lies in the framework will give more benefits in finding the suitable information and the real weights from the environment which result for better recognition. The framework is applicable to different domains successfully and for the potential case study, the clinical organization and its domain is considered for the proposed framework

The increasing volume and diversity of information in biomedical research is demanding new approaches for data integration in this domain. Semantic Web technologies and applications can leverage the potential of biomedical information integration and discovery, facing the problem of semantic heterogeneity of biomedical information sources. In such an environment, agent technology can assist users in discovering and invoking the services available on the Internet. In this paper we present SEMMAS, an ontology-based, domain-independent framework for seamlessly integrating Intelligent Agents and Semantic Web Services. Our approach is backed with a proof-of-concept implementation where the breakthrough and efficiency of integrating disparate biomedical information sources have been tested.

This paper presents a multi-agent framework based on argumentative agent technology for the automation of the workflow selection and execution. In this framework, workflow selection is coordinated by agent interactions governed by the rules of a dialogue game whose purpose is to evaluate the workflow's properties via argumentation. Once a workflow is selected using this process, the workflow is executed by dynamically configuring workflow engines to coordinate the participating agents' workflow activities.

In this paper we present a theoretical framework describing an original method for the design of intelligent tutoring environments, building upon the notion of shared attention. This framework is defined as the Levels of Interaction (LoI) approach. It is applicable to applications where the learner/player is immersed in a 3D virtual environment, interacting and exchanging knowledge with an adaptive crowd