Brain-computer interface systems – Overview, design challenges and applications

[DaNGeROuS KiLLeR]

Abstract

Brain-Computer Interfaces are systems that translate the user's intention coded by brain activity measures into a control signal without using activity of any muscles or peripheral nerves. These control signals can potentially be employed to substitute motor capabilities (e.g. brain-controlled prosthetics for amputees or patients with spinal cord injuries, brain-controlled wheel chair); to help in the restoration of such functions (e.g. as a tool for stroke rehabilitation), to enable alternative communication (e.g. virtual keyboard, speller etc.) for those who are disabled or otherwise unable to communicate, and other applications such as serious games for enhancing cognition skills.

The first part of the tutorial will provide an overview of Brain-Computer Interface (BCI), applications, methods for brain signal acquisition and their comparison, relevant Electroencephalogram (EEG) signal features for BCI and signal processing & machine learning tools for BCI. Further, we will focus on a potential BCI research topic, i.e., BCI based neurofeedback games for improving the attention and cognitive skills. Recently BCI based neurofeedback games have attained much attention in research because of its great potential for enhancing brain’s cognitive skills. Neurofeedback allows an individual to self-regulate his brain signal in response to its real-time visual or auditory feedback. We will present design of EEG-based neurofeedback games and discuss some interesting results. Some of our recent work using low cost commercially available EMOTIV EEG system (which has only fewer electrodes compared to conventionally used EEG systems) for decoding motor imagery directions, and detection of familiarity (possible applications in psychology, criminal investigation etc.) will also be discussed.

The second part of the tutorial will focus on the use of neural correlates of cognitive processes for brain-computer interfacing. In this approach the BCI instead of using surrogate, arbitrary mental tasks to control a device, will exploit onto electrophysiological responses that are naturally elicited during human-machine interaction. We will present several examples showing the feasibility of decoding correlates of error processing, anticipation and visual attention in realistic tasks. Furthermore, we will discuss how these signals can be exploited in tasks such as robot control, driving support in intelligent cars and neurorehabilitation.

 

Biographies

Vinod Prasad received his B. Tech. degree in Instrumentation and Control Engineering from University of Calicut, India in 1993 and the Master of Engineering (By Research) and Ph.D. degrees from School of Computer Engineering, Nanyang Technological University (NTU), Singapore, in 2000 and 2004 respectively. He has spent the first 5 years of his career in industry as an automation engineer at Kirloskar, Bangalore, Tata Honeywell, Pune and Shell Singapore. From September 2000 to September 2002, he was a Lecturer in Singapore Polytechnic, Singapore. He joined NTU as a Lecturer in the School of Computer Engineering in September 2002; became an Assistant Professor in December 2004, and since September 2010 he is a tenured Associate Professor in NTU. He also served as a Visiting Associate Professor in Dept. of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada, during June – July 2013.

Vinod’s research interests include digital signal processing, low power, reconfigurable circuits & systems for wireless communications, BCI and its applications in neurofeedback, neurorehabilitation, neuroprosthetics and assistive technology devices, computer arithmetic and residue number system (RNS). He has published 186 papers in refereed international journals and conferences, supervised and graduated 9 PhDs, secured research grants amounting over $2.3 million as principal investigator from various funding agencies such as Singapore Ministry of Education, Ministry of Defence, DSO National Labs, European Aeronautic Defence & Space Company (EADS), Embassy of France in Singapore, Singapore Millennium Foundation and Civil Aviation Authority of Singapore. He is a Senior Member of IEEE, Associate Editor of IEEE Transactions on Human-Machine Systems, Associate Editor of Circuits, Systems, and Signal Processing Journal (Springer), and Technical Committee Co-Chair of Brain-Machine Interface Systems of IEEE Systems, Man & Cybernetics Society. He has won the Nanyang Award for Excellence in Teaching in 2009, the highest recognition conferred by NTU to individual faculty for teaching. Website: www.ntu.edu.sg/home/asvinod

Ricardo Chavarriaga is a senior researcher at the Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland. He received an engineering degree in electronics from the Pontificia Universidad Javeriana (Cali, Colombia) in 1998, and a Ph.D. in Computational Neuroscience from the EPFL in 2005. He co-chairs the IEEE SMC technical committee in BMI systems and is in the editorial board of the journals Brain-Computer interfaces, IEEE Transactions on Human-Machine Systems and Frontiers in Neurorobotics. In the past he has organized BCI-related Tutorials at the IEEE conference on Cybernetics 2013, the IEEE/ACM Human-Robot interaction conference 2009 and the IEEE SMC conference 2014; as well as workshops at the International BCI conference 2013, and the IEEE SMC conferences in 2011 and 2014.

His research focuses on robust brain-machine interfaces and multimodal human-machine interaction. Specifically, decoding of cortical potentials that convey information about the user's cognitive processes. In particular error recognition, anticipation of [CENSORED]ure events and decision-making. Furthermore, He investigates on how the exploitation of such processes can be integrated with shared control principles and hybrid approaches for BMI control of complex devices.