Wearable Brain-computer Interface Research Articles

Separable Common Spatio-Spectral Patterns for Motor Imagery BCI Systems.

Feature extraction is one of the most important steps in any brain-computer interface (BCI) system. In particular, spatio-spectral feature extraction for motor-imagery BCIs (MI-BCI) has been the focus of several works in the past decade. This paper proposes a novel method, called separable common spatio-spectral patterns (SCSSP), for extraction of discriminant spatio-spectral EEG features in MI-BCIs. Assuming a binary classification problem, SCSSP uses a heteroscedastic matrix-variate Gaussian model for the multiband EEG rhythms, and seeks the spatio-spectral features whose variance is maximized for one brain task and minimized for the other task. Therefore, SCSSP can be considered as a spatio-spectral generalization of the conventional common spatial patterns (CSP) algorithm. The experimental results on two-class and multiclass motor-imagery data from publicly available BCI Competition datasets demonstrate that the proposed computationally efficient method competes closely with filter-bank CSP (FBCSP), and can even outperform the FBCSP if enough training data are available. Furthermore, SCSSP provides us with a simple measure for ranking the discriminant power of extracted spatio-spectral features, which is not possible in FBCSP. The matrix-variate Gaussian assumption allows the SCSSP method to jointly process the EEG data in both spatial and spectral domains. As a result, compared to the similar solutions in the literature such as FBCSP, the proposed SCSSP method requires significantly lower computations. The proposed computationally efficient spatio-spectral feature extractor is particularly suitable for applications in which the computational power is limited, such as emerging wearable mobile BCI systems.

Pervasive brain monitoring and data sharing based on multi-tier distributed computing and linked data technology.

EEG-based Brain-computer interfaces (BCI) are facing basic challenges in real-world applications. The technical difficulties in developing truly wearable BCI systems that are capable of making reliable real-time prediction of users' cognitive states in dynamic real-life situations may seem almost insurmountable at times. Fortunately, recent advances in miniature sensors, wireless communication and distributed computing technologies offered promising ways to bridge these chasms. In this paper, we report an attempt to develop a pervasive on-line EEG-BCI system using state-of-art technologies including multi-tier Fog and Cloud Computing, semantic Linked Data search, and adaptive prediction/classification models. To verify our approach, we implement a pilot system by employing wireless dry-electrode EEG headsets and MEMS motion sensors as the front-end devices, Android mobile phones as the personal user interfaces, compact personal computers as the near-end Fog Servers and the computer clusters hosted by the Taiwan National Center for High-performance Computing (NCHC) as the far-end Cloud Servers. We succeeded in conducting synchronous multi-modal global data streaming in March and then running a multi-player on-line EEG-BCI game in September, 2013. We are currently working with the ARL Translational Neuroscience Branch to use our system in real-life personal stress monitoring and the UCSD Movement Disorder Center to conduct in-home Parkinson's disease patient monitoring experiments. We shall proceed to develop the necessary BCI ontology and introduce automatic semantic annotation and progressive model refinement capability to our system.

Wearable brain computer interface are we there yet?

Brain computer interfaces are still restricted to the domains of health and research, but we understand what needs to be done and are getting closer to making a commercial wearable EEG system.

Gaming control using a wearable and wireless EEG-based brain-computer interface device with novel dry foam-based sensors

A brain-computer interface (BCI) is a communication system that can help users interact with the outside environment by translating brain signals into machine commands. The use of electroencephalographic (EEG) signals has become the most common approach for a BCI because of their usability and strong reliability. Many EEG-based BCI devices have been developed with traditional wet- or micro-electro-mechanical-system (MEMS)-type EEG sensors. However, those traditional sensors have uncomfortable disadvantage and require conductive gel and skin preparation on the part of the user. Therefore, acquiring the EEG signals in a comfortable and convenient manner is an important factor that should be incorporated into a novel BCI device. In the present study, a wearable, wireless and portable EEG-based BCI device with dry foam-based EEG sensors was developed and was demonstrated using a gaming control application. The dry EEG sensors operated without conductive gel; however, they were able to provide good conductivity and were able to acquire EEG signals effectively by adapting to irregular skin surfaces and by maintaining proper skin-sensor impedance on the forehead site. We have also demonstrated a real-time cognitive stage detection application of gaming control using the proposed portable device. The results of the present study indicate that using this portable EEG-based BCI device to conveniently and effectively control the outside world provides an approach for researching rehabilitation engineering.

A cell-phone-based brain–computer interface for communication in daily life

Moving a brain–computer interface (BCI) system from a laboratory demonstration to real-life applications still poses severe challenges to the BCI community. This study aims to integrate a mobile and wireless electroencephalogram (EEG) system and a signal-processing platform based on a cell phone into a truly wearable and wireless online BCI. Its practicality and implications in a routine BCI are demonstrated through the realization and testing of a steady-state visual evoked potential (SSVEP)-based BCI. This study implemented and tested online signal processing methods in both time and frequency domains for detecting SSVEPs. The results of this study showed that the performance of the proposed cell-phone-based platform was comparable, in terms of the information transfer rate, with other BCI systems using bulky commercial EEG systems and personal computers. To the best of our knowledge, this study is the first to demonstrate a truly portable, cost-effective and miniature cell-phone-based platform for online BCIs.

Introduction to the Special Section on Biomedical Devices for Personal Health Applications

This Special Section of Frontiers of Mechanical Engineering (FME) is dedicated to the topic of Biomedical Devices for Personal Health Applications. To reflect the fast pace of development in this area of research, a number of special sessions were firstly organized in the 2010 IEEE International Conference on Robotics, Automation, and Mechatronics (RAM 2010) from 28 to 30 June 2010 in Singapore. The special session organizers, also the guest editors of this journal special section, had identified wearable sensors, wearable haptic devices, and micro ingestible capsules as the topic of interests for these sessions as these topics are also the new area of growth for the medical device industry. RAM 2010, with about 200 attendees, is the 4th edition of this event held in Singapore with its predecessors in Chengdu, China (2008), Bangkok, Thailand (2006), and Singapore (2004). The scope of RAM covers niche areas in robotics, mechatronics and automation as well as their applications. The articles published in this Special Section are rigorously selected from the papers submitted to these special sessions in RAM 2010. All of the articles presented here have gone through the process of peer review for conference publication, evaluation of the presentations during the conference, and two rounds of journal publication reviews in order to meet the publication standard of FME. We hope that through such a progressive review process, the advancement in this field can be reported in a rigorous and timely manner. This Special Section contains one feature article and eight technical papers dealing with wearable sensors, ingestible robotic capsules, wearable robotic exoskeleton, wearable brain-computer interface device, and a sensing device for cognitive study on infants. Chen et al. give an overview of the personalized medical devices and point out their future challenges. Lim et al. report the design of a novel digital miniature linear sensor that has the function of goniometer for human joint movement measurement. A virtual reality system for upper limb rehabilitation based on this novel sensor is reported by Luo et al. to demonstrate its potential for rehabilitation medicine. In the article by Lin et al., the development of a new ingestible capsule was introduced. Unlike the available commercial systems, this new capsule has active mechanism to perform therapeutic functions inside the human gastronomical tracks. Rasouli et al. report two different variations of the new capsule system for enhance treatment. The design of wearable robots, or the exoskeletons are reported by Yang et al. and Sergi et al. for upper limb and lower limb applications respectively. The link from human brain to the control of upper limbs for stroke patients is reported by Ang. This link has great future potential in rehabilitation medicine. Lastly, Campolo et al. report an interesting and novel hand-held sensing device for cognitive study of infants which are the most difficult type of human subjects for study. The Guest Editor-in-chief would like to thank the Guest Editors, Prof. S J Phee, Drs. Z. Q. Luo, and C. K. Lim,