Brain–computer interfaces (BCIs) have been widely discussed over the past two decades as one of the solutions to improve the quality of life for disabled people. Currently, research in this particular area is growing especially as the prices for low-cost electroencephalography (EEG) devices have been falling into a level that makes them affordable for general consumers. Therefore, this thesis focuses on the developments of asynchronous motor imagery (MI) based brain-computer interfaces (BCIs) applications, signal processing and machine learning to provide some basic capabilities for consumer grade products. For the proposed MI detection technique, two channels of FC5 and FC6 according to 10-20 system over the primary motor area are used to recognize three MI tasks of tongue, left hand and right hand movements. The amplitude features of EEG signals are extracted from power spectral analysis especially in mu rhythm (8 - 12 Hz) and low beta wave (12 - 16 Hz) bands. MI features were obtained from offline analysis, and then applied to neural network (NN) with particle swarm optimization (PSO). The classification paradigm then applied to real-time BCI for humanoid robot control applications in terms of recognized MI classes of subjects. According to the experiments of 45 trials for a healthy subject, the NN with PSO-based MI recognition accuracy is 91%.

Brain–computer interfaces (BCIs) have been widely discussed over the past two decades as one of the solutions to improve the quality of life for disabled people. Currently, research in this particular area is growing especially as the prices for low-cost electroencephalography (EEG) devices have been falling into a level that makes them affordable for general consumers. Therefore, this thesis focuses on the developments of asynchronous motor imagery (MI) based brain-computer interfaces (BCIs) applications, signal processing and machine learning to provide some basic capabilities for consumer grade products. For the proposed MI detection technique, two channels of FC5 and FC6 according to 10-20 system over the primary motor area are used to recognize three MI tasks of tongue, left hand and right hand movements. The amplitude features of EEG signals are extracted from power spectral analysis especially in mu rhythm (8 - 12 Hz) and low beta wave (12 - 16 Hz) bands. MI features were obtained from offline analysis, and then applied to neural network (NN) with particle swarm optimization (PSO). The classification paradigm then applied to real-time BCI for humanoid robot control applications in terms of recognized MI classes of subjects. According to the experiments of 45 trials for a healthy subject, the NN with PSO-based MI recognition accuracy is 91%.

REFERENCES
[1]"World Report on Disability," World Health Organization, Geneva, Switzerland 2011.
[2]I. Iturrate, J. M. Antelis, A. Kubler, and J. Minguez, "A Noninvasive Brain-Actuated Wheelchair Based on a P300 Neurophysiological Protocol and Automated Navigation," IEEE Transactions on Robotics, vol. 25, pp. 614-627, 2009.
[3]B. Rebsamen, E. Burdet, G. Cuntai, Z. Haihong, T. Chee Leong, and Q. Zeng, "A Brain-Controlled Wheelchair Based on P300 and Path Guidance," IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics 2006 ( BioRob 2006), Pisa, Italy, 2006, pp. 1101-1106.
[4]A. Jackson, C. T. Moritz, J. Mavoori, T. H. Lucas, and E. E. Fetz, "The neurochip BCI: towards a neural prosthesis for upper limb function," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 14, pp. 187-190, 2006.
[5]M. Nicolis, "Walk Again Project, " picture taken from http://www.theguardian.com/technology/2014/apr/01/mind-controlled-robotic-suit-exoskeleton-world-cup-2014
[6]J. J. Vidal, "Toward Direct Brain-Computer Communication," Annual Review of Biophysics and Bioengineering, vol. 2, pp. 157-180, 1973
[7]J. R. Wolpaw, N. Birbaumer, W. J. Heetderks, D. J. McFarland, P. H. Peckham, and G. Schalk, "Brain-computer interface technology: a review of the first international meeting," IEEE Transactions on Rehabilitation Engineering, vol. 8, pp. 164-173, 2000.
[8]N. F. Luis and G. Jaime, "Brain Computer Interfaces, a Review," Sensor Journal-Brain Computer Interface, pp. 1211-1279, 2012.
[9]J. L. Collinger, B. Wodlinger, J. E. Downey, W. Wang, E. C. Tyler-Kabara, and D. J. Weber, "High-performance neuroprosthetic control by an individual with tetraplegia," The Lancet, vol. 381, pp. 557-564, 2013.
[10]P. Suppes, M. Perreau-Guimaraes, and D. Wong, "Partial Orders of Similarity Differences Invariant Between EEG-Recorded Brain and Perceptual Representations of Language," Neural Computation, vol. 21, pp. 3228-3269, 2009.
[11]H. Hasminda-Hassan, Z. H. Murat, V. Ross, Z. Mohd-Zain, and N. Buniyamin, "Enhancing learning using music to achieve a balanced brain," 3rd International Congress on Engineering Education (ICEED), Kuala Lumpur, Malaysia, 2011, pp. 66-70.
[12]H. Slagter, A. Lutz, L. Greischar, S. Nieuwenhuis, and R. Davidson, "Theta Phase Synchrony and Conscious Target Perception: Impact of Intensive Mental Training," Journal of Cognitive Neuroscience, vol. 21, pp. 1536-1549, 2009.
[13]G. Vecchiato, F. Babiloni, L. Astolfi, J. Toppi, P. Cherubino, and D. Jounging, "Enhance of theta EEG spectral activity related to the memorization of commercial advertisings in Chinese and Italian subjects," 4th International Conference on Biomedical Engineering and Informatics (BMEI), Shanghai, China, 2011, pp. 1491-1494.
[14]V. K. Varadan, S. Oh, H. Kwon, and P. Hankins, "Wireless Point-of-Care Diagnosis for Sleep Disorder With Dry Nanowire Electrodes," Journal of Nanotechnology in Engineering and Medicine, vol. 1, pp. 031012-031012, 2010.
[15]M.-J. Hoeve, B. J. v. d. Zwaag, M. v. Burik, K. Slump, and R. Jones, "Detecting Epileptic Seizure Activity in the EEG by Independent Component Analysis," 14th Workshop on Circuits, Systems and Signal Processing (ProRISC 2003), Veldhoven, Netherlands, 2003.
[16]M. Salvaris and F. Sepulveda, "Visual modifications on the P300 speller BCI paradigm," Journal of Neural Engineering, vol. 6, pp. 046011, 2009.
[17]S. Amiri, R. Fazel-Rezai, and V. Asadpour, "A Review of Hybrid Brain-Computer Interface Systems," Advances in Human-Computer Interaction, vol. 2013, pp. 8, 2013.
[18]J. R. Wolpaw, D. J. McFarland, G. W. Neat, and C. A. Forneris, "An EEG-based brain-computer interface for cursor control," Electroencephalography and Clinical Neurophysiology, vol. 78, pp. 252-259, 1991.
[19]C. J. Bell, R. P. Rao, R. Chalodhorn, and P. Shenoy, "Control of a humanoid robot by a noninvasive brain-computer interface in humans," Journal of Neural Engineering, 2008.
[20]G. Pfurtscheller and F. H. Lopes da Silva, "Event-related EEG/MEG synchronization and desynchronization: basic principles," Clinical Neurophysiology, vol. 110, pp. 1842-57, Nov 1999.
[21]G. Pfurtscheller and A. Aranibar, "Evaluation of event-related desynchronization (ERD) preceding and following voluntary self-paced movement," Electroencephalography and clinical neurophysiology, vol. 46, pp. 138-46, Feb, 1979.
[22]D. J. McFarland, L. A. Miner, T. M. Vaughan, and J. R. Wolpaw, "Mu and beta rhythm topographies during motor imagery and actual movements," Brain topography, vol. 12, pp. 177-86, Spring, 2000.
[23]A. Bashashati, M. Fatourechi, R. K. Ward, and G. E. Birch, "A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals," Journal of Neural Engineering, vol. 4, pp. R32-R57, 2007.
[24]D. J. Krusienski, G. Schalk, D. J. McFarland, and J. R. Wolpaw, "Rhythm Matched Filter for Continuous Control of a Brain-Computer Interface," IEEE Transactions on Biomedical Engineering vol. 54, pp. 273-280, 2007.
[25]P. Herman, G. Prasad, T. M. McGinnity, and D. Coyle, "Comparative Analysis of Spectral Approaches to Feature Extraction for EEG-Based Motor Imagery Classification," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 16, pp. 317-326, 2008.
[26]Evers, G., PSO Research Toolbox Documentation (20110515), M.S. thesis code documentation, 2011, < http://www.georgeevers.org/pso_research_toolbox_documentation.pdf >