Motion pattern and posture: Correctly assessed by calibrated accelerometers

Basic motion patterns and posture can be distinguished by multichannel acce lerometry, as recently shown. A refinement of this method appeared to be de sirable to further increase its effectiveness, especially to distinguish wa lking and climbing stairs, and body rotation during sleep. Recordings were made of 31 subjects, according to a standard protocol comprising 13 motions and postures. This recording was repeated three times with appropriate per mutation. Five uni-axial sensors and three sites of placement (sternum with three axes, right and left thigh) were selected. A hierarchical classifica tion strategy used a standard protocol (i.e., individual reference patterns ) to distinguish subtypes of moving behaviors and posture. The analysis met hod of the actometer signals reliably detected 13 different postural and ac tivity conditions (only 3.2 % misclassifications). A minimum set of sensors can be found for a given application; for example, a two-sensor configurat ion would clearly suffice to differentiate between four basic classes (sitt ing, standing, lying, moving) in ambulatory monitoring.