The routine dailyactivities that tend to be sedentary and repetitive may cause severe healthproblems. This issue has encouraged researchers to design a system to detectand record people activities in real time and thus encourage them to do morephysical exercise. By utilizing sensors embedded in a smartphone, many researchstudies have been conducted to try to recognize user activity. The most commonsensors used for this purpose are accelerometers and gyroscopes; however, wefound out that a gravity sensor has significant potential to be utilized aswell. In this paper, we propose a novel method to recognize activities usingthe combination of an accelerometer and gravity sensor. We design a simplehierarchical system with the purpose of developing a more energy efficientapplication to be implemented in smartphones. We achieved an average of 95% forthe activity recognition accuracy, and we also succeed at proving that our workis more energy efficient compared to other works.