Brain Signal Analysis for Mind Controlled Type-Writer Using a Deep Neural Network

The prime objective of this work is to develop a notable methodology for modeling a mind controlled type writing system to cater the needs of individuals suffering from various communication related disorders using EEG signal analysis technique. First, the EEG signals are procured from twelve subjects who were involved in mental utterance of seven vowel sounds. The eLORETA analysis of the acquired signals confirms the involvement of occipital, parietal and pre-frontal lobes for this cognitive activity. The procured signals are then filtered to circumvent the effects of various artifacts and are transferred to a novel deep multilayer perceptron classifier for categorization of seven class labels. Performance analysis undertaken confirms that the proposed classifier is able to distinctly categorize the seven class levels with a very high precision level. A coding mechanism has also been proposed to represent the consonants by the concoction of two vowel sounds segregated by a space. Thus, the proposed scheme can be effectively utilized as a mind controlled type writing system to serve the basic requirements of disabled individuals. Additionally, this technique can also be used in certain military scenarios that demand non-verbal communication as a secure option and in various gaming applications that will aid in exhilarating the player's experience.

[1]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[2]  A. V. Olgac,et al.  Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks , 2011 .

[3]  Erich Schröger,et al.  Digital filter design for electrophysiological data – a practical approach , 2015, Journal of Neuroscience Methods.

[4]  Yoshua Bengio,et al.  Quadratic Features and Deep Architectures for Chunking , 2009, NAACL.

[5]  P. Comon,et al.  Ica: a potential tool for bci systems , 2008, IEEE Signal Processing Magazine.

[6]  Plamen Manoilov,et al.  EEG Eye-Blinking Artefacts Power Spectrum Analysis , 2006 .

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

[8]  Makoto Sato,et al.  Single-trial classification of vowel speech imagery using common spatial patterns , 2009, Neural Networks.

[9]  Mohsen Guizani,et al.  Deep Multi-Layer Perceptron Classifier for Behavior Analysis to Estimate Parkinson’s Disease Severity Using Smartphones , 2018, IEEE Access.

[10]  Aziah Ali,et al.  Word-Based Classification of Imagined Speech Using EEG , 2017 .

[11]  Yusuf Uzzaman Khan,et al.  EEG based classification of imagined vowel sounds , 2015, 2015 2nd International Conference on Computing for Sustainable Global Development (INDIACom).

[12]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

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

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Omar Farooq,et al.  Vowel classification using wavelet decomposition during speech imagery , 2016, 2016 3rd International Conference on Signal Processing and Integrated Networks (SPIN).

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

[17]  Quoc V. Le,et al.  Searching for Activation Functions , 2018, arXiv.

[18]  R. Pascual-Marqui,et al.  Resting-State EEG Source Localization and Functional Connectivity in Schizophrenia-Like Psychosis of Epilepsy , 2011, PloS one.

[19]  T. Koenig,et al.  Low resolution brain electromagnetic tomography (LORETA) functional imaging in acute, neuroleptic-naive, first-episode, productive schizophrenia , 1999, Psychiatry Research: Neuroimaging.

[20]  Razvan Pascanu,et al.  Understanding the exploding gradient problem , 2012, ArXiv.

[21]  A. Ludolph,et al.  Amyotrophic lateral sclerosis. , 2012, Current opinion in neurology.

[22]  R. Pascual-Marqui,et al.  Functional connectivity assessed by resting state EEG correlates with cognitive decline of Alzheimer’s disease – An eLORETA study , 2016, Clinical Neurophysiology.