Key points are not available for this paper at this time.
The primary goal of an ambulatory monitoring of motor activities (AMMA) system is to document the occurrence of random and spontaneous motor activities (e.g., sitting, lying, standing, walking, running, etc.) of the ambulatory subject in natural environmental circumstances. Much progress has been made in recording fidelity, reduction in energy requirement, fixation of the accelerometers, equipment size and weight, memory capacity and data acquisition. At present, our laboratory is interested in developing an automated off-line AMMA-signal analysis system. The system has to take care of activity (wave) detection, recognition of onsets and endpoints of the various activities (waves), and computation of a set of relevant clinical parameters (e.g., total walking time, number of times rising from a chair, etc.) from long-term recorded data. Two methods are currently being used for computerizing the off-line analysis system: using an artificial neural network and using a set of selected features extracted from the input data. The present paper is aimed at the latter method. The method was successfully applied to long-term recorded data sets of eight male amputees and three other subjects. The primary results indicate that the method is a potentially useful tool to computerize the off-line analysis system.
Kiani et al. (1997) studied this question.