We are developing a context-aware application for use in homes, which detects high-level user behavior, such as “leaving the home” and “going to bed”, and provides services according to the behavior proactively. To detect user behavior, a behavioral pattern is created by extracting frequent characteristics from the user’s behavior logs acquired from sensors online, using an extraction threshold based on the criterion of frequency. Most context-aware applications need to determine such a threshold. A conventional model determines a fixed common threshold value for all users. However, the common value is improper for some users because proper values vary among users. This paper proposes a detection method of high-level behavior with a model for determining the threshold value dynamically according to individual behavioral pattern.