Authors: HAMED GHAZIKHANI, MODJTABA ROUHANI
Abstract: This paper presents a new method of predicting the P300 component of an electroencephalography (EEG)signal to recognize the characters in a P300 brain-computer interface (BCI) speller accurately. This method consistsof a deep learning model and the nonlinear time-frequency features. It is believed that the combination of the deepmodel network and extracting the nonlinear features of the EEG led this research to a better prediction of the P300and, therefore, character recognition. Cohen's class distribution is used in order to extract the nonlinear features of theEEG. Evaluating all of the kernels, Butterworth found to be more informative and it produced better results. Basedon the differences observed between time-frequency responses of target and nontarget signals, specific subbands areselected to extract seven features. A deep-structured neural network, namely stacked sparse autoencoders, is appliedfor BCI character recognition. This deep network reduces the dimension of feature space by extracting unsupervisedfeatures. Then, the features are fed to a Softmax classifier. Afterward, the whole network passes a fine-tuning phase by asupervised backpropagation algorithm. For evaluating the work, Dataset II of BCI Competition III is utilized. Based onthe results, this approach would improve the accuracy in both P300 detection and character recognition. This researchresults in 82.7% and 93.5% accuracy for P300 classification and character recognition, respectively.
Keywords: Cohen's class distribution, P300, brain-computer interface (bci), stacked autoencoders, event-relatedpotential (ERP)
Full Text: PDF