Activity time collection and analysis through temporal reasoning

In this research, we focused on the problem of context switching [2,4] and recording overhead [2,4,5] faced by the users while recording time log for the personal software process (PSP). Even the existing solution to these problems i.e. using sensors to automatically collect activity time, cannot record all the activities performed by the user. Our approach address these problems from different prospective by asking the user to record the activity time any time while doing that activity using speech recognition sensor. The problems that arise using our approach is that the speech sensor generated time log does not show when the activity started or ended (partial information) and also the user can forget to record the activity in speech sensor. To solve these problems, we then investigated how we can infer best information about user activity duration without asking the user to provide further information.