An extension of a fuzzy reputation agent trust model (AFRAS) in the ART testbed推荐.pdfVIP

Soft Comput (2010) 14:821–831 DOI 10.1007/s00500-009-0470-9 FOCUS An extension of a fuzzy reputation agent trust model (AFRAS) in the ART testbed Javier Carbo Æ Jose Manuel Molina-Lopez Published online: 29 July 2009 Springer-Verlag 2009 Abstract With the introduction of web services, users and the advantage of using fuzzy representation of trust and require an automated way of determining their reliability reputation. and even their matching to personal and subjective pref- erences. Therefore, trust modelling of web services, man- Keywords Trust and reputation of services aged in an autonomous way by intelligent agents, is a Autonomous agents Fuzzy sets challenging and relevant issue. Due to the dynamic and distributed nature of web services, recommendations of web services from third parties may also play an important 1 Introduction role to build and update automated trust models. In this context, the agent reputation and trust (ART) testbed has As the amount of information in the web via html pages, been used to compare trust models in three international wikis, blogs, and other documents grows, it gets more competitions. The testbed runs locally and defines an ART difficult to distinguish accurate information from inaccu- appraisal domain with a simulation engine, although the rate or untrustworthy information. A search engine query trust models may be applied to any kind of automated and usually results in outdated and/or unreliable informations remote services, such as web services. Our previous works and the user is forced to choose manually what she/he proposed an already-published trust model called AFRAS considers the most reliable source based on her/his