Abstract: Human memory very often fails. People are frequently beset with questions like “Who is that person? I think I met him/her last year.” Available memory systems cannot well support the recall of names effectively. This paper explores the memory recall enhancement problem from the perspective of memory cue extraction and associative search, and proposes a generic method to extract memory cues from heterogeneous, multimodal, physical/virtual data sources. Specifically, we can use the contact name recall in the academic community as the target application to showcase our proposed methodology. We next develop an intelligent social contact manager that supports 1) auto collection of rich contact data from a combination of various pervasive sensors and Web data sources, and 2) associative search of contacts when human memory fails. The proposed system is validated with the help of testing the performance of contact data collection techniques. An user study on contact memory recall is conducted, through which several findings about contact memorizing and recall are presented. Various Classic cognitive psychology theories are used to interpret these findings [1].

Keywords: Contact recall, memory aid, pervasive computing, social contact management, Web intelligenc.