Given the considerable trend towards multi-party, peer-to-peer (P2P) communication, many are looking at the P2P computing paradigm as the means to extend the capability and scalability of Internet-based services. Current P2P frameworks are, however, largely incompatible with each other and do not address all the requirements of mobile computing. Here we propose a novel solution to peer group management which is 'autonomic', 'mobile friendly' and 'service driven'. We illustrate how our approach facilitates mobile P2P services by managing peer groups based on service semantics and resource availability. Our system allows efficient 'deep' search of user personal content stored in thin mobile terminals. Results are based on an experimental prototype and are demonstrated by a simple proof-of-concept mobile service.

We investigate the behavior knowledge space method (see Xu, L. et al., IEEE Transactions SMC,2, no.3, p.418-35, 1992) and decision templates method (see Kuncheva, L. et al., Pattern Recognition, vol.34, p.299-314, 2001) of classifier fusion in the context of face verification. The study involves six experts which are not only correlated, but also their performance levels differ by as much as a factor of three. Through extensive experiments on the XM2VTS database using the Lausanne protocol, we found that the behavior knowledge space fusion strategy achieved consistently better results than the decision templates method. Most importantly, it exhibited quasi monotonic behavior as the number of experts combined increased. This is a very important conclusion, as it means that the performance of the multimodal system is not degraded by adding experts

No abstract

No abstract

No abstract