To cope with the increasing number of aging population, a type of care which can help prevent or postpone entry into institutional care is preferable. Activity recognition can be used for home-based care in order to help elderly people to remain at home as long as possible. This paper proposes a practical multi-sensor activity recognition system for home-based care utilizing on-body sensors. Seven types of sensors are investigated on their contributions toward activity classification. We collected a real data set through the experiments participated by a group of elderly people. Seven classification models are developed to explore contribution of each sensor. We conduct a comparison study of four feature selection techniques using the developed models and the collected data. The experimental results show our proposed system is superior to previous works achieving 97% accuracy. The study also demonstrates how the developed activity recognition model can be applied to promote a home-based care and enhance decision support system in health care.