The study demonstrates part of an ambient assisted living system developed for the remote care of the elderly. Described methods and experiments involve acceleration-based trajectories analysis that yields a feature vector to be subjected to an expert system able to create an individual patient's model by learning high-level features of her/his motion. At this stage we have implemented a footstep detector that permits each foot movement to be analyzed separately and described in terms of predefined features. By mounting the sensors at five various locations on the subjects body, we have indicated areas that feature a high sensitivity to the measurement of abnormal step incidents. Our experiments demonstrate also features able to distinguish abnormal patient motion.