Personal search system based on android using lifelog and machine learning

Lifelog is the foundation on which lifelong services and healthcare services are implemented in a smart home system. It also plays a major role in the sub-processes of the system because it acquires information about the home’s residents for home automation and entertainment. Providing personalized services to individuals by acquiring and managing this personal lifelog information has great advantages in terms of service satisfaction and effectiveness. In this paper, we implemented a personal search system based on android that collected and stored an individual’s lifelog based on nine smart phone sensors and used it to derive new meaningful information about the user. The activity recognition module for classifying the user’s behavior, the naive Bayesian method, showed an accuracy of 88.23% and the area under the ROC curve value of 0.941. We designed and implemented density-based spatial clustering method in the module for extracting the point of interest and the participants filled out a satisfaction questionnaire to evaluate the search system. The proposed system efficiently uses a large amount of lifelog data and automates the process of extracting meaningful information, associating it according to the user’s intention.