Brain Computer Interface Implementation on Cognitive States

Brain–Computer Interface (BCI) is a channel of communication between a brain and a machine. It is based on the interpretation of the electrical activity of mind and can be used to direct any external action such as control of a wheelchair. This paper discusses the development of a cost effective, efficient, non-invasive and easy to use multiclass BCI. For this self-acquired Electroencephalography (EEG) signals of different cognitive actions recorded over cerebral cortexes of different people are analyzed and then classified using Linear Discriminant Analysis (LDA). These classified signals are used to control the movement of a self-developed prototype of stretcher via a microcontroller. Stretcher in the proposed model can be replaced by any other machine and that machine can be controlled directly by brain. Hence this novel model can be used to develop brain-controlled devices for normal people as well as for People with Disability (PWD).

[1]  A. Karim,et al.  Neural Internet: Web Surfing with Brain Potentials for the Completely Paralyzed , 2006, Neurorehabilitation and neural repair.

[2]  S. Sequeira,et al.  EEG-signals based control strategy for prosthetic drive systems , 2013, 2013 IEEE 3rd Portuguese Meeting in Bioengineering (ENBENG).

[3]  G. Comi,et al.  IFCN standards for digital recording of clinical EEG. International Federation of Clinical Neurophysiology. , 1998, Electroencephalography and clinical neurophysiology.

[4]  Shaikh Anowarul Fattah,et al.  Low-cost EEG based electric wheelchair with advanced control features , 2017, TENCON 2017 - 2017 IEEE Region 10 Conference.

[5]  L. F. M. Alma Rosa Méndez Gordillo,et al.  Design and construction of a brain-computer interface for applications in neuro-robotics , 2015 .

[6]  Jaime Gómez Gil,et al.  Brain Computer Interfaces, a Review , 2012, Sensors.

[7]  Mieko Ohsuga,et al.  Applicability of the “Emotiv EEG Neuroheadset” as a user-friendly input interface , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

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

[9]  M. Nuttin,et al.  A brain-actuated wheelchair: Asynchronous and non-invasive Brain–computer interfaces for continuous control of robots , 2008, Clinical Neurophysiology.

[10]  Shahnawaz Qureshi,et al.  An Empirical Study of Machine Learning Techniques for Classifying Emotional States from EEG Data , 2012 .

[11]  Mariska J. Vansteensel,et al.  The brain-computer interface researcher’s questionnaire: from research to application , 2017 .

[12]  Humera Farooq,et al.  Investigating EEG Patterns for Dual-Stimuli Induced Human Fear Emotional State , 2019, Sensors.

[13]  Gonzalo M. Rojas,et al.  Study of Resting-State Functional Connectivity Networks Using EEG Electrodes Position As Seed , 2018, Front. Neurosci..

[14]  Robert Oostenveld,et al.  The five percent electrode system for high-resolution EEG and ERP measurements , 2001, Clinical Neurophysiology.

[15]  Sim Kok Swee,et al.  Fast fourier analysis and EEG classification brainwave controlled wheelchair , 2016, 2016 2nd International Conference on Control Science and Systems Engineering (ICCSSE).

[16]  Mohammed Abo-Zahhad,et al.  A New EEG Acquisition Protocol for Biometric Identification Using Eye Blinking Signals , 2015 .