W artykule przedstawiono procedurę rejestracji sygnałów przyspieszenia pochodzących z czujników biomedycznych Shimmer, sposób ich rozmieszczenia na ciele oraz opisano klasyfikator pozwalający na rozpoznawanie wybranych kategorii ruchu ludzkiego. W części eksperymentalnej artykułu zbadano wpływ filtracji dolnoprzepustowej sygnałów na skuteczność rozpoznawania typu aktywności ruchowej.
In many scientific fields, especially medicine, information about human activity is crucial. The analysis of acceleration data coming from the sensors mounted on human’s limbs and trunk allows automatic classification of patients’activities (e.g. sitting, walking, getting up, etc). In this paper, a neural network based motion activity classifier and the procedure for recording signals from accelerometers are described. Owing to a very fast development of microcontrollers, it is now possible to create devices which enable real-time recording and transmission of signals from accelerometers. Today’s miniaturization enables the integration of accelerometers, microcontrollers and Bluetooth transmitters into a single matchbox-size device. Research carried out by Intel resulted in highly integrated devices and software platforms designed for networks of sensors which communicate wirelessly. Small size and weight of such devices as well as low energy consumption make the montage of sensors on a human body technically possible and comfortable for patients. The research proved that the localization of sensors on a human body has a great impact on the accuracy of motion type recognition. Many experiments addressing this subject were conducted, and finally an optimal sensors configuration was chosen. A group of 16 healthy people was observed. The acceleration signals were sampled with the frequency of 51,2 Hz whereas the G force was set within the range of 0 to 4. The 64 sample windows with the 32 samples overlap were used for the analysis. For each window, a set of parameters was extracted, which allowed the classification of signals. The research showed that the motion classifier based on neural networks ensures satisfying efficiency of motion type classification. Activity recognition was performed off-line. The accuracy of detection depended on the type of activity and the way the activity was performed. It turned out that for a better network training and testing, a greater number of signals must be collected.