Intelligent User Interface for Intelligent Multimedia Repository

초록

Recently, much efforts have been spent for efficiency of user interface since the assumption of expertized or well-traaited users is no more valid these days. Today's users of computer systems are expanded to ordinary people. furthermore, toww much network accessible information resources in the form of various media increases reapidly everyday. the primary goal of the intelligent multimedia repository(IMR) is to assist users in accessing multimedia information efficiently. primary users of the IMR are assumed to be novice users even though the system can be userd for users at different levels of expertise. users are not well-trained poeple in using computer systems. thus, the semantic gap between users and the system must be mainly reduced from the system site. the technology of the IMR, a Human computer interaction model has been devised, and the IUI for the IMR has been designed and developed. machine learning thechnologieshave been emploeyd to provide user adaption/intelligent capability to the system. the IUI of the IMR consists user interface manager, and user model . the UIM performs the function of managing intellignet user interface. the um stores the behavioral knowledge of the user. the um stores the history of query and response interactions to absorb communication erros due to semantic gaps beween the user and the imr. the um is implemented by decision tree based case-based resoning and back propagation neural networks. experimental results show the iui can improve the preformace of the imr.