Hand and Foot Movement of Motor Imagery Classification Using Wavelet Packet Decomposition and Multilayer Perceptron Backpropagation

Abstract

The development of bionic aids for paralyzed patients leads to the Brain-Computer Interface (BCI) implementation with various obstacles, especially in interpreting brain signals as triggers for the bionic organ. The reading of electrical signal activity in the brain in the BCI system uses electroencephalography (EEG) signal, which comes from many electrodes in the head area and is non-stationary. The measured EEG signal contains much information, including information for the hands and feet motor imagery, so a classification system is needed to separate the information to be processed, such as hand and foot movements. This research aims to develop an imagery motor classification system for the hands and feet so that signals can be classified correctly. The system design is made through several stages of the signal processing process consisting of the pre-processing stage using centering, the feature extraction stage with wavelet packet decomposition (WPD), and multilayer perceptron back-propagation (MLP-BP) as the classifier. Based on the result, this study got the highest accuracy value, about 26.8% at level three, and gain above 0.02. This small accuracy is due to the large error due to under fitting.

Fabric yarn detection based on improved fast R-CNN model

“…Finally, the warp and weft density of the woven fabric is obtained through program calculation [12][13][14][15]. Shi et al Carried out multi-layer wavelet decomposition on woven fabric image through wavelet transform, reconstructed single-layer signal and calculated average brightness value of warp and weft yarn direction image, and finally calculated warp and weft density according to periodic change of brightness signal [16,17]. Combined image processing technology with time-frequency transform theory, transformed woven image from the time domain to frequency domain through Fourier transform, selected characteristic region to filter and separate single group of warp and weft yarn images.…”