%0 Journal Article
%T Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals
%A Birsel Ayrulu-Erdem
%A Billur Barshan
%J Sensors
%D 2011
%I MDPI AG
%R 10.3390/s110201721
%X We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a prototype wavelet function, selection of the wavelet type can influence the performance of wavelet-based applications significantly. We also investigate the effect of selecting different wavelet families on classification accuracy and ANN complexity and provide a comparison between them. The maximum classification accuracy of 97.7% is achieved with the Daubechies wavelet of order 16 and the reverse bi-orthogonal (RBO) wavelet of order 3.1, both with similar ANN complexity. However, the RBO 3.1 wavelet is preferable because of its lower computational complexity in the DWTdecomposition and reconstruction.
%K leg motion classification
%K inertial sensors
%K gyroscopes
%K accelerometers
%K discrete wavelet transform
%K wavelet decomposition
%K feature extraction
%K pattern recognition
%K artificial neural networks
%U http://www.mdpi.com/1424-8220/11/2/1721