Search results

In the vision of pervasive computing, numerous heterogeneous devices, various information services, and users performing daily activities are physically co‐located in a environment. How can we coordinate the services and devices to assist a particular user in receiving a particular service so as to maximize the user’s satisfaction? To solve this human‐centered coordination issue, we propose an agent‐based service coordination framework for pervasive computing. It is called location‐aware middle agent framework. The middle agent takes account of the user location in cognitive way (based on location‐ontology), and determines best‐matched services for the user. Based on this coordination framework, we have developed a multi‐agent architecture for pervasive computing, called CONSORTS (Coordination System of Real‐world Transaction Services). In this paper, we first outline some requirements of the human‐centered service coordination in pervasive computing. Secondly, we describe location‐aware middle agent framework to fill the requirements. Lastly, we outline CONSORTS, an prototype of location‐aware middle agent framework, and two applications of CONSORTS, location‐aware information assistance services in a museum and wireless‐LAN based location systems on FIPA agent Networks.

The purpose of this paper is to evaluate participants' contributions to the development of discussion and knowledge creation as organizational knowledge management, and thereby help them better develop the discussion.

To evaluate participants' contributions more accurately, a method which analyzes discussion structures by Discourse Semantic Authoring was employed, which represents discussion structures explicitly in terms of discourse and dialogue relations.

The method successfully evaluates participants based on the content of their comments rather than their number. More fine‐grain semantic structure should be considered in order to improve the accuracy of this evaluation.

This paper presents a first attempt to analyze discussion structures to evaluate participants' contributions.