Hierarchical structured data logging system for effective lifelog management in ubiquitous environment

The researches for collecting personal daily behaviors and providing lifelog services with them have been recently increasing. Recent advances in mobile devices and sensor technologies have motivated to collect a huge amount of personal lifelog data in real time. With the rapid growth of the need for the research, there is a coming need for the effective lifelog management system which collects time-series big lifelog data sent from sensing devices and extracts major activities through processing them. For the effective lifelog management, the lifelog data can be processed in separated computing resources depending on the size and level of data. In this paper, we propose hierarchical structured data logging to support lifelog based personal services and to reduce the processing complexity and storage cost. First, we present the architecture of personal lifelog management system. With the system we present hierarchical lifelog data logging to optimally utilize computing and storage resources. Then we describe cost analysis and performance comparison for demonstrating the efficacy of our proposed system. Finally, as an initial step for experiments in our research, we describe experimental results of recognizing physical activities and extracting lifelog data which indicate major activities from them.