EEG-based hybrid QWERTY mental speller with high information transfer rate

BACKGROUND Brain-computer interface (BCI) spellers detect variations in brain waves to help subjects communicate with the world. This study introduces a P300-SSVEP hybrid BCI-based QWERTY speller. METHODS The proposed hybrid speller, combines SSVEP and P300 features using a hybrid paradigm. P300 was used as time division multiplexing index which results in the use of lesser number of assumed frequencies for SSVEP elicitation. Each flickering frequency was also assigned a unique colour, to enhance system accuracy. RESULTS On the basis of 20 subjects, an average accuracy of classification of 96.42% and a mean information transfer rate (ITR) of 131.0 bits per min. (BPM) was achieved during the free spelling trial (trial-F). COMPARISON The t test results revealed that the hybrid QWERTY speller performed significantly better (on the basis of mean classification accuracy and ITR) as compared to the traditional P300 speller) and the QWERTY SSVEP speller. Also, the amount of time taken to spell a word was significantly lesser in the case of hybrid QWERTY speller in contrast to traditional P300 speller while it was almost the same as compared to QWERTY SSVEP speller. CONCLUSION QWERTY speller outperformed the stereotypical P300 speller as well as QWERTY SSVEP speller.

[1]  Xiaorong Gao,et al.  An online multi-channel SSVEP-based brain–computer interface using a canonical correlation analysis method , 2009, Journal of neural engineering.

[2]  Zümray Dokur,et al.  A novel steady-state visually evoked potential-based brain-computer interface design: Character Plotter , 2014, Biomed. Signal Process. Control..

[3]  Brendan Z. Allison,et al.  P300 brain computer interface: current challenges and emerging trends , 2012, Front. Neuroeng..

[4]  Chang-Hwan Im,et al.  Performance Prediction for a Near-Infrared Spectroscopy-Brain-Computer Interface Using Resting-State Functional Connectivity of the Prefrontal Cortex , 2018, Int. J. Neural Syst..

[5]  Patrick Berg,et al.  Artifact Correction of the Ongoing EEG Using Spatial Filters Based on Artifact and Brain Signal Topographies , 2002, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[6]  Rajesh Singla,et al.  Towards enhanced information transfer rate: a comparative study based on classification techniques , 2020, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[7]  Yijun Wang,et al.  Implementing Over 100 Command Codes for a High-Speed Hybrid Brain-Computer Interface Using Concurrent P300 and SSVEP Features , 2020, IEEE Transactions on Biomedical Engineering.

[8]  Keum Shik Hong,et al.  Hybrid Brain–Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review , 2017, Front. Neurorobot..

[9]  Jijun Tong,et al.  Multi-phase cycle coding for SSVEP based brain-computer interfaces , 2015, Biomedical engineering online.

[10]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[11]  Andrzej Cichocki,et al.  Fully Online Multicommand Brain-Computer Interface with Visual Neurofeedback Using SSVEP Paradigm , 2007, Comput. Intell. Neurosci..

[12]  Mehmet Akbaba,et al.  A study on performance increasing in SSVEP based BCI application , 2018, Engineering Science and Technology, an International Journal.

[13]  Ian Daly,et al.  On the control of brain-computer interfaces by users with cerebral palsy , 2013, Clinical Neurophysiology.

[14]  Mohammad Pooyan,et al.  Improving the performance of the SSVEP-based BCI system using optimized singular spectrum analysis (OSSA) , 2018, Biomed. Signal Process. Control..

[15]  Jing Wang,et al.  Toward a hybrid brain-computer interface based on repetitive visual stimuli with missing events , 2016, Journal of NeuroEngineering and Rehabilitation.

[16]  L.J. Trejo,et al.  Brain-computer interfaces for 1-D and 2-D cursor control: designs using volitional control of the EEG spectrum or steady-state visual evoked potentials , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  Hao Yang,et al.  The hybrid BCI system for movement control by combining motor imagery and moving onset visual evoked potential , 2017, Journal of neural engineering.

[18]  Marc M. Van Hulle,et al.  Simultaneous Detection of P300 and Steady-State Visually Evoked Potentials for Hybrid Brain-Computer Interface , 2015, PloS one.

[19]  Chang-Hwan Im,et al.  evelopment of a hybrid mental spelling system combining SVEP-based brain – computer interface and webcam-based eye racking , 2015 .

[20]  Li-Wei Ko,et al.  Development of Single-Channel Hybrid BCI System Using Motor Imagery and SSVEP , 2017, Journal of healthcare engineering.

[21]  Andrzej Cichocki,et al.  Correlation-based channel selection and regularized feature optimization for MI-based BCI , 2019, Neural Networks.

[22]  Rajesh Singla,et al.  A novel hybrid paradigm based on steady state visually evoked potential & P300 to enhance information transfer rate , 2020, Biomed. Signal Process. Control..

[23]  Richard M. Leahy,et al.  Electromagnetic brain mapping , 2001, IEEE Signal Process. Mag..

[24]  Kwang Suk Park,et al.  Eliciting dual-frequency SSVEP using a hybrid SSVEP-P300 BCI , 2016, Journal of Neuroscience Methods.

[25]  Rui Zhang,et al.  Enhanced Motor Imagery Training Using a Hybrid BCI With Feedback , 2015, IEEE Transactions on Biomedical Engineering.

[26]  Reinhold Scherer,et al.  Steady-state visual evoked potential (SSVEP)-based communication: impact of harmonic frequency components , 2005, Journal of neural engineering.

[27]  Sourav Kundu,et al.  P300 based character recognition using convolutional neural network and support vector machine , 2020, Biomed. Signal Process. Control..

[28]  Gary H. Glover,et al.  Learned regulation of spatially localized brain activation using real-time fMRI , 2004, NeuroImage.

[29]  Andrzej Cichocki,et al.  The Study of Generic Model Set for Reducing Calibration Time in P300-Based Brain–Computer Interface , 2019, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[30]  Shangkai Gao,et al.  A practical VEP-based brain-computer interface. , 2006, IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[31]  Xiaorong Gao,et al.  A high-ITR SSVEP-based BCI speller , 2014 .

[32]  G. McCarthy,et al.  On the influence of task relevance and stimulus probability on event-related-potential components. , 1977, Electroencephalography and clinical neurophysiology.

[33]  Dewen Hu,et al.  An Asynchronous Hybrid Spelling Approach Based on EEG–EOG Signals for Chinese Character Input , 2019, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[34]  Tzyy-Ping Jung,et al.  A Brain–Computer Interface Based on Miniature-Event-Related Potentials Induced by Very Small Lateral Visual Stimuli , 2018, IEEE Transactions on Biomedical Engineering.

[35]  Xiaogang Chen,et al.  A Hybrid BCI speller based on the combination of EMG envelopes and SSVEP , 2015, Applied Informatics.

[36]  Xiaogang Chen,et al.  A Benchmark Dataset for SSVEP-Based Brain–Computer Interfaces , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[37]  Michael Erb,et al.  Deactivation of Brain Areas During Self-Regulation of Slow Cortical Potentials in Seizure Patients , 2006, Applied psychophysiology and biofeedback.

[38]  K. A. Colwell,et al.  Channel selection methods for the P300 Speller , 2014, Journal of Neuroscience Methods.

[39]  Shirley M Coyle,et al.  Brain–computer interface using a simplified functional near-infrared spectroscopy system , 2007, Journal of neural engineering.

[40]  W. Pritchard.  Psychophysiology of P300. , 1981, Psychological bulletin.

[41]  Xingyu Wang,et al.  A new hybrid BCI paradigm based on P300 and SSVEP , 2015, Journal of Neuroscience Methods.

[42]  Wei Wu,et al.  Frequency Recognition Based on Canonical Correlation Analysis for SSVEP-Based BCIs , 2006, IEEE Transactions on Biomedical Engineering.

[43]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update , 2018, Journal of neural engineering.

[44]  Chang-Hwan Im,et al.  Development of an SSVEP-based BCI spelling system adopting a QWERTY-style LED keyboard , 2012, Journal of Neuroscience Methods.

[45]  Jan Noyes,et al.  The QWERTY Keyboard: A Review , 1983, Int. J. Man Mach. Stud..

[46]  Miriam Seoane Santos,et al.  Improving the Classifier Performance in Motor Imagery Task Classification: What are the steps in the classification process that we should worry about? , 2018, Int. J. Comput. Intell. Syst..

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

[48]  Toby P. Breckon,et al.  On the Relative Contribution of Deep Convolutional Neural Networks for SSVEP-Based Bio-Signal Decoding in BCI Speller Applications , 2019, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[49]  John R. Smith,et al.  Steady-State VEP-Based Brain-Computer Interface Control in an Immersive 3D Gaming Environment , 2005, EURASIP J. Adv. Signal Process..

[50]  Jun Cheng,et al.  Driving event-related potential-based speller by localized posterior activities: An offline study. , 2019, Mathematical biosciences and engineering : MBE.

[51]  G Pfurtscheller,et al.  Toward a hybrid brain–computer interface based on imagined movement and visual attention , 2010, Journal of neural engineering.

[52]  Xingyu Wang,et al.  Towards correlation-based time window selection method for motor imagery BCIs , 2018, Neural Networks.