A NEED-AWARING MULTI-AGENT APPROACH FOR AD HOC NEED IDENTIFICATION AND GROUP FORMATION IN NOMADIC COMMUNITY COMPUTING

Abstract

Researchers have proposed community computing for facilitating both group formation and group decision making. However, legacy community computing systems do not support group needs identification for ad hoc group formation, which is a key feature of ubiquitous decision support systems and services. In this article, we describe a multi-agent-based methodology that both enables nomadic community computing and supports ad hoc needs identification and group formation. Our approach uses needs awareness through a Rescorla-Wagner model of association theories and need reasoning by rough set theory. With a focus on supporting decision making within a relatively small-sized group of multiple individuals in a community, the methodology addresses the following three characteristics: (1) ad hoc group formation; (2) context-aware group needs identification; and (3) implementation of mobile devices working indoors and outdoors. We develop a prototype system, NAMA-US, to show the feasibility of the ideas proposed in this article.

KEYWORDS:

• ad hoc need identification
• association theory
• community computing
• need awareness
• rough set theory

This research is supported by the Ubiquitous Computing and Network (UCN) Project, Knowledge and Economy Frontier R&D Program of the Ministry of Knowledge Economy (MKE) in Korea as a result of UCN's subproject UCN 10C2-T2-11T.