Data Mining of Life Log for Developing a User model-based Service Application

Abstract

In this research, the authors aimed to mining Life logs for developing a user model-based service application. Life logs can be constructed by analyzing Motion logs, which are obtained from questionnaires, or motion data collected from sensors. And the user models, which help applications to provide appropriate service, can be constructed by mining these Life logs.To achieve the above goal, first we collect Motion logs. Although Motion logs can be easily obtained from the questionnaires, it is more complicate to extract necessary information from the raw data gathered from sensors. Therefore, we adopted the fuzzy inference and fuzzy membership functions to obtain Motion logs from the raw data of the sensors. Life logs can then be created from Motion logs. Finally, we construct different user models by mining Life logs to support applications providing appropriate service. We also introduce several related applications in this paper.Our research results show the great potential of applying user models-based approach to service applications. By adopting our approach, the services ability and scope of applications in service grid can be further enhanced and expanded.