Abstract. The synergy of communication, computation and sensing capabilities in mobile systems-on-chip artifacts such as smartphones has made possible the development of wearable smart sensor systems for user activity monitoring and recognition. Assessing physical activity is useful to enhance people health as experts have evidenced a clear correlation between physical activity and overweight, obesity and metabolism-related syndromes. Due to user acceptability and the convenient nonintrusive manner for measuring data, smartphones have the advantage of taking proprioceptive motion measurements outside of a controlled environment for rather long periods of time using embedded sensors such as the accelerometer, however, activity recognition poses several challenges. Particularly, though work has been reported for accelerometer-based activity recognition using smartphones, the portability of the device to a single fixed tight position has been a major constraint to easy the interpretation of the collected data on resource-limited devices. In this chapter, a human activity hierarchical recognition system based on neural networks without the need of the smartphone to be constrained to a single fixed position is presented. Yet it is used as a representative example to show the challenges, the role and some of the main potential impacts that smartphones have and will have in mHealth. Experimental results on Android-capable smartphones on four on-body locations show that the recognition system achieves high classification rates, above 92%, for five activities including static, walking, running, and up-down stairs walking, which outperforms other proposals. The system is fully implemented in a smartphone running continuously in near real-time with reduced power consumption in a proof-of-concept client-server application for mHealth.