Classification Technique of Human Motion Context based on Wireless Sensor Network

The fusion technology of small sensor and wireless communication was followed by various application examples of the embedded system, where the social infrastructural facilities and ecological environment were wirelessly monitored. In the paper, new monitoring and classifying method of human motion context was proposed by using 2-axial MEMS accelerometer and 916 MHz short range data communication technology. During four types of subjects motion, waveform changes of the accelerometer data was acquired by wireless sensor network, then analyzed by principal component analysis (PCA) and support vector machine (SVM) method for clustering the first and second principal components. To classify the subjects motion type, supervised learning method was used for segmentation algorithm. The present study showed that the developed algorithm could classify four types correctly. Therefore, human motion context during daily life could be monitored and classified by using wireless sensor network