Improving Performance of Devanagari Script Input-Based P300 Speller Using Deep Learning

The performance of an existing Devanagari script (DS) input-based P300 speller with conventional machine learning techniques suffers from low information transfer rate (ITR). This occurs due to its required large size of display, i.e., 8 × 8 row-column (RC) paradigm which exhibits issues like crowding effect, adjacency, fatigue, task difficulty, and required large number of trials for character recognition. For P300 detection, deep learning algorithms have shown the state of art performance compared to the conventional machine learning algorithms in the recent past. Therefore, authors have been motivated to develop a deep learning architecture for DS-based P300 speller which can detect the target characters more accurately and in less number of trials. For this, two proven deep learning algorithms, stacked autoencoder (SAE) and deep convolution neural network (DCNN) have been adopted. For further bettering their performances, batch normalization and innovative double batch training is included here to achieve accelerated training and alleviate the problem of overfitting. Additionally, a leaky ReLU activation function has also been used in DCNN to overcome dying ReLU problem. The experiments have been performed on self-generated dataset of 20 Devanagari words with 79 characters acquired from 10 subjects using 16 channel actiCAP Xpress EEG recorder. The experimental results illustrated that the proposed DCNN is able to detect 88.22% correct targets in just three trials. Moreover, it also provides ITR of 20.58 bits per minutes, which is significantly higher than existing techniques.

[1]  Jasman Pardede,et al.  P300 Detection Using a Multilayer Neural Network Classifier Based on Adaptive Feature Extraction , 2013 .

[2]  U. Rajendra Acharya,et al.  Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network , 2017, Inf. Sci..

[3]  Subhojit Ghosh,et al.  Binary DE-Based Channel Selection and Weighted Ensemble of SVM Classification for Novel Brain–Computer Interface Using Devanagari Script-Based P300 Speller Paradigm , 2016, Int. J. Hum. Comput. Interact..

[4]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[5]  Tomohiro Yoshikawa,et al.  Improvement Of Performance Of Japanese P300 Speller By Using Second Display , 2015, J. Artif. Intell. Soft Comput. Res..

[6]  S M M Martens,et al.  Overlap and refractory effects in a brain–computer interface speller based on the visual P300 event-related potential , 2009, Journal of neural engineering.

[7]  Luca T. Mainardi,et al.  A genetic algorithm for automatic feature extraction in P300 detection , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[8]  J. Wolpaw,et al.  A novel P300-based brain–computer interface stimulus presentation paradigm: Moving beyond rows and columns , 2010, Clinical Neurophysiology.

[9]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Gang Peng,et al.  A Chinese Text Input Brain–Computer Interface Based on the P300 Speller , 2012, Int. J. Hum. Comput. Interact..

[11]  Wei Gao,et al.  Multi-ganglion ANN based feature learning with application to P300-BCI signal classification , 2015, Biomed. Signal Process. Control..

[12]  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.

[13]  Chunxia Zhang,et al.  Generalized extreme learning machine autoencoder and a new deep neural network , 2017, Neurocomputing.

[14]  Ramesh Maddula,et al.  Deep Recurrent Convolutional Neural Networks for Classifying P300 BCI signals , 2017, GBCIC.

[15]  M. Woldorff,et al.  Distortion of ERP averages due to overlap from temporally adjacent ERPs: analysis and correction. , 2007, Psychophysiology.

[16]  Amit Konar,et al.  A general type-2 fuzzy set induced single trial P300 detection , 2017, 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[17]  Lukáš Vařeka,et al.  Stacked Autoencoders for the P300 Component Detection , 2017, Front. Neurosci..

[18]  Subhojit Ghosh,et al.  Multi-objective binary DE algorithm for optimizing the performance of Devanagari script-based P300 speller , 2017 .

[19]  Mahmoud Hassan,et al.  An efficient P300-speller for Arabic letters , 2015, 2015 International Conference on Advances in Biomedical Engineering (ICABME).

[20]  S. G. Ponnambalam,et al.  Multi-objective genetic algorithm as channel selection method for P300 and motor imagery data set , 2015, Neurocomputing.

[21]  Hubert Cecotti,et al.  Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  M. Thulasidas,et al.  Robust classification of EEG signal for brain-computer interface , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[23]  Reza Fazel-Rezai,et al.  A comparison between a matrix-based and a region-based P300 speller paradigms for brain-computer interface , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[24]  Wei Wu,et al.  Deep learning based on Batch Normalization for P300 signal detection , 2018, Neurocomputing.

[25]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[26]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[27]  E. W. Sellers,et al.  Toward enhanced P300 speller performance , 2008, Journal of Neuroscience Methods.

[28]  E. Sellers,et al.  How many people are able to control a P300-based brain–computer interface (BCI)? , 2009, Neuroscience Letters.

[29]  Narendra D. Londhe,et al.  Deep convolutional neural network based character detection in devanagari script input based P300 speller , 2017, 2017 International Conference on Electrical, Electronics, Communication, Computer, and Optimization Techniques (ICEECCOT).

[30]  Yael Arbel,et al.  Single trial independent component analysis for P300 BCI system , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[31]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[33]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[34]  Ernesto Bribiesca,et al.  P300 Detection Based on EEG Shape Features , 2016, Comput. Math. Methods Medicine.

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

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

[37]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[38]  Nader Pouratian,et al.  A method for optimizing EEG electrode number and configuration for signal acquisition in P300 speller systems , 2015, Clinical Neurophysiology.

[39]  A. Erfanian,et al.  A mutual information based channel selection scheme for P300-based brain computer interface , 2011, 2011 5th International IEEE/EMBS Conference on Neural Engineering.

[40]  Andrew Y. Ng,et al.  Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks , 2017, ArXiv.

[41]  N. Birbaumer,et al.  BCI2000: a general-purpose brain-computer interface (BCI) system , 2004, IEEE Transactions on Biomedical Engineering.

[42]  Geoffrey E. Hinton,et al.  On rectified linear units for speech processing , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[43]  Subhojit Ghosh,et al.  A Novel Weighted Edit Distance-Based Spelling Correction Approach for Improving the Reliability of Devanagari Script-Based P300 Speller System , 2016, IEEE Access.