Evaluating daily life quality is important in ambient intelligence applications targeted for health status monitoring. When we consider the fact that people approximately spend one-third of their lives sleeping, we need to monitor the sleep quality as well as the activities of daily living in order to be able to provide a seamless health monitoring system. In this paper, a seamless activity recognition system that makes use of multi-modal wireless sensor networks (WSNs) and mobile phones is proposed. The proposed system is then used to collect life-log and sleep behavior data from actual users. In the lights of this information, important factors affecting the sleep quality of a person is extracted.