Investigation of a wavelet-based neural network learning algorithm applied to P300 based brain-computer interface

The paper presented herein proposes an algorithm that aims at improving the classification accuracy of Brain-Computer Interface (BCI) speller. In this work, feed-forward neural network with back propagation learning is used for classification purposes. Testing of the proposed algorithm was performed through the utilization of two datasets, namely; Berlin BCI Competition III and EPFL BCI groups. Results, for the first dataset, indicated that the use of 64 electrodes with 30 hidden layers grants an accuracy of 94.9 %, while an average accuracy of 95.8% (range: 92%-100%) was obtained for the second dataset when using a 32 electrode configuration with 20 hidden layers. The obtained accuracy levels, in this study, are higher when compared with other recent classification approaches.

[1]  Yasser M. Kadah,et al.  Machine learning methodologies in P300 speller Brain-Computer Interface systems , 2009, 2009 National Radio Science Conference.

[2]  Naser Hamdi,et al.  A Comparison Study on Machine Learning Algorithms Utilized in P300-based BCI , 2013 .

[3]  Pan Wang,et al.  P300 Detection Algorithm Based on Fisher Distance , 2010 .

[4]  Rami J Oweis,et al.  An alternative respiratory sounds classification system utilizing artificial neural networks , 2015, Biomedical journal.

[5]  S. Coyle,et al.  Brain–computer interfaces: a review , 2003 .

[6]  Abbas Erfanian,et al.  An online EEG-based brain-computer interface for controlling hand grasp using an adaptive probabilistic neural network. , 2010, Medical engineering & physics.

[7]  Rami J. Oweis,et al.  ANN-based EMG classification for myoelectric control , 2014, Int. J. Medical Eng. Informatics.

[8]  Ali Motie Nasrabadi,et al.  Fusion of classic P300 detection methods' inferences in a framework of fuzzy labels , 2008, Artif. Intell. Medicine.

[9]  Thippa Reddy Gadekallu,et al.  Cuckoo Search Optimized Reduction and Fuzzy Logic Classifier for Heart Disease and Diabetes Prediction , 2017, Int. J. Fuzzy Syst. Appl..

[10]  G. Thippa Reddy,et al.  FFBAT-Optimized Rule Based Fuzzy Logic Classifier for Diabetes , 2016 .

[11]  Tarik Al-Ani,et al.  Signal Processing and Classification Approaches for Brain-Computer Interface , 2010 .

[12]  Rami J Oweis,et al.  Seizure classification in EEG signals utilizing Hilbert-Huang transform , 2011, Biomedical engineering online.

[13]  Alain Rakotomamonjy,et al.  BCI Competition III: Dataset II- Ensemble of SVMs for BCI P300 Speller , 2008, IEEE Transactions on Biomedical Engineering.

[14]  E. Donchin,et al.  A P300-based brain–computer interface: Initial tests by ALS patients , 2006, Clinical Neurophysiology.

[15]  E. Donchin,et al.  Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. , 1988, Electroencephalography and clinical neurophysiology.

[16]  Leonard J. Trejo,et al.  Feature Extraction of Event-Related Potentials Using Wavelets: An Application to Human Performance Monitoring , 1999, Brain and Language.

[17]  Rami J. Oweis,et al.  CT Image Reconstruction Approaches Applied to Time-Frequency Representation of Signals , 2003, EURASIP J. Adv. Signal Process..

[18]  Dennis J. McFarland,et al.  Brain–computer interfaces for communication and control , 2002, Clinical Neurophysiology.

[19]  Neelu Khare,et al.  An Efficient System for Heart Disease Prediction Using Hybrid OFBAT with Rule-Based Fuzzy Logic Model , 2017, J. Circuits Syst. Comput..

[20]  Mahesh S. Chavan.  Comparative Study of Chebyshev I and Chebyshev II Filter used For Noise Reduction in ECG Signal , 2008 .

[21]  Touradj Ebrahimi,et al.  An efficient P300-based brain–computer interface for disabled subjects , 2008, Journal of Neuroscience Methods.

[22]  G. Pfurtscheller,et al.  The BCI competition III: validating alternative approaches to actual BCI problems , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.