By Topic

Brain-Computer Interface (BCI), 2013 International Winter Workshop on

Date 18-20 Feb. 2013

Filter Results

Displaying Results 1 - 25 of 49
  • Tutorial on multimodal neuroimaging for brain-computer interfacing

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (247 KB) |  | HTML iconHTML  

    Multimodal techniques have seen a rising interest from the neuroscientific as well as the BCI community in recent times. In this abstract two aspects of multi-modal imaging will be reviewed. Firstly, how recordings of multiple subjects can help in finding subject-independent BCI classifiers and secondly how multi-modal neuroimaging methods, namely combined EEG and NIRS measurements can help in enhancing as well as robustifying BCI performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian common spatial patterns

    Page(s): 3
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (132 KB) |  | HTML iconHTML  

    Summary form only given. Common spatial patterns (CSP) or its probabilistic counterpart, probabilistic CSP (PCSP), is a popular discriminative feature extraction method for automatically classifying electroencephalography (EEG) brain waves. Models for CSP or PCSP are trained on a subject-by-subject basis, so inter-subject information, which might be available when brain waves are measured from multiple subjects who undergo the same mental task, is neglected. In this paper we present a brief overview of our recent work on how Bayesian multi-task learning is applied to multi-subject EEG classification, treating subjects as tasks to capture inter-subject relatedness in Bayesian treatment of PCSP. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Brain-computer interface for stroke rehabilitation with clinical studies

    Page(s): 4 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (131 KB) |  | HTML iconHTML  

    Summary form only given. Stroke is the leading cause of severe disabilities in the developed world. Each year, there are around 15 million new stroke cases worldwide. About 30% of stroke survivors need various forms of rehabilitation. Among these, upper limb weakness and loss of hand function are among the most devastating types of disabilities. Despite optimal acute medical treatment and modern rehabilitation, 45% of the patients do not achieve complete recovery of their bodily functions. In addition, 85% to 90% of stroke survivors with upper limb impairment do not regain full functional use of their upper extremities. Limitations in current physiotherapy and occupational therapy techniques include: (i) difficulties in rehabilitation for the severely paralyzed arm and hand which are often treated with passive modalities, (ii) difficulties in achieving intensive rehabilitation and high repetitions in those with moderate to severe upper extremity paralysis, (iii) problems in motivating and sustaining patient interest in repetitive exercises, (iv) therapy is often perceived to be boring due to lack of immediate biofeedback. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mobile real-time EEG imaging Bayesian inference with sparse, temporally smooth source priors

    Page(s): 6 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (235 KB) |  | HTML iconHTML  

    EEG based real-time imaging of human brain function has many potential applications including quality control, in-line experimental design, brain state decoding, and neuro-feedback. In mobile applications these possibilities are attractive as elements in systems for personal state monitoring and well-being, and in clinical settings were patients may need imaging under quasi-natural conditions. Challenges related to the ill-posed nature of the EEG imaging problem escalate in mobile real-time systems and new algorithms and the use of meta-data may be necessary to succeed. Based on recent work (Delorme et al., 2011) we hypothesize that solutions of interest are sparse. We propose a new Markovian prior for temporally sparse solutions and a direct search for sparse solutions as implemented by the so-called “variational garrote” (Kappen, 2011). We show that the new prior and inference scheme leads to improved solutions over competing sparse Bayesian schemes based on the “multiple measurement vectors” approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neuro-driving: Automatic perception technique for upcoming emergency situations

    Page(s): 8 - 9
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1315 KB) |  | HTML iconHTML  

    We propose a neuro-driving simulation framework for the detection of emergency situation under general circum-stances. Previous work on neuro-driving has been shown that neural activity related with emergency situations while driving generates a different characteristic spatio-temporal event-related potential (ERP) pattern compared to normal state [1]. In this paper, on the basis of those study, three kinds of emergency situations are designed to discriminate ERP patterns between a variety of emergencies and normal driving situation. Based on comparison analysis based on KU and BBCI dataset, it is believed that the proposed framework can be considered as a novel EEG-based automatic perception technique for upcoming emergency situations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatial projections of neural arrays: A short guide to classic and new signal analysis techniques

    Page(s): 10 - 11
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (214 KB) |  | HTML iconHTML  

    Electroencephalography and other neural recording techniques collect simultaneous data with a multitude of channels. A variety of methods have been proposed to analyze such high-dimensional data and go by various 3-letter acronyms such as PCA, ICA, LDA, SVM, CSP, DSS, CCA, CSD. What all of these methods have in common is that they integrate information by averaging across space, and the different techniques only differ in the contribution of each channel to the average. This has the potential to substantially improve signal quality. The goal of this presentation is to give an overview of existing techniques focusing on those techniques that have an easy to understand objective criterion. It should thus provide a guide on how to pick the technique that best suits a given experimental goal. The review will start with the simplest and most straightforward idea, and finish with a few more recent and novel techniques that are not yet widely known. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Divergence estimation for machine learning and signal processing

    Page(s): 12 - 13
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (254 KB) |  | HTML iconHTML  

    Approximating a divergence between two probability distributions from their samples is a fundamental challenge in the statistics, information theory, and machine learning communities, because a divergence estimator can be used for various purposes such as two-sample homogeneity testing, change-point detection, and class-balance estimation. Furthermore, an approximator of a divergence between the joint distribution and the product of marginals can be used for independence testing, which has a wide range of applications including feature selection and extraction, clustering, object matching, independent component analysis, and causality learning. In this talk, we review recent advances in direct divergence approximation that follow the general inference principle advocated by Vladimir Vapnik-one should not solve a more general problem as an intermediate step. More specifically, direct divergence approximation avoids separately estimating two probability distributions when approximating a divergence. We cover direct approximators of the Kullback-Leibler (KL) divergence, the Pearson (PE) divergence, the relative PE (rPE) divergence, and the L2-distance. Despite the overwhelming popularity of the KL divergence, we argue that the latter approximators are more useful in practice due to their computational efficiency, high numerical stability, and superior robustness against outliers. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Progress toward a high-performance neural prosthetic

    Page(s): 14 - 15
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (204 KB) |  | HTML iconHTML  

    Recent demonstrations have shown conclusively that intracortical signals recorded from paralyzed subjects will provide the substrate to restore natural hand and arm function with high- performance prosthetic devices. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decoding cognitive brain states

    Page(s): 16 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (563 KB) |  | HTML iconHTML  

    The last years have seen a rise in interest in using BCI methodology for investigating non-medical questions beyond the purpose of communication and control. This abstract first provides a short introduction to BCI challenges from a machine learning perspective. The remaining sections present selected applications of BCI discussing in particular the use of EEG in combination with BCI methods for investigating how signal quality is processed on a sensory and cognitive level. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Eeg/sonication-based brain-brain interfacing

    Page(s): 19 - 20
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (184 KB) |  | HTML iconHTML  

    EEG has been practically used to detect brain signals, which can control brain-computer interfaces (BCls) in a noninvasive way. Recently, low-intensity focused-ultrasound (LIFU) sonication has gained attention as a potent candidate for the noninvasive and spatially-accurate transcranial computer-brain interfacing (CBI). Based on the benefit of these two techniques, the convergence of both EEG-based BCI and sonication-based CBI approaches might eventually lead to the field of `brain-to-brain interface' (BBI), in which two individual brains can communicate by sending signals through functionally minimized computers. Further exploration of this new conceptual technique will be needed to realize this technology and to apply it to a wide range of our mental communication. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Japanese SRPBS for BMI research: Decoded neurofeedback as a causal tool in systems neuroscience

    Page(s): 21
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (76 KB) |  | HTML iconHTML  

    Summary form only given. Japanese MEXT started SRPBS (strategic research for promotion of brain sciences) in 2008. Field A was on BMI and I am the leader of this. I will describe achievement within this large group funding. Within ATR, we have developed next generation noninvasive decoding method as well as decoded neurofeedback method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Bayesian approach for spatio-spectral filter optimization in BCI

    Page(s): 22 - 23
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (597 KB) |  | HTML iconHTML  

    In this paper, we propose a novel Bayesian frame-work for discriminative feature extraction for motor imagery classification in an EEG-based BCI, in which the class-discriminative frequency bands and the corresponding spatial filters are optimized by means of the probabilistic and information-theoretic approaches. In our framework, the problem of simultaneous spatio-spectral filter optimization is formulated as the estimation of an unknown posterior pdf that represents the probability that a single-trial EEG of predefined mental tasks can be discriminated in a state. We demonstrate the feasibility and effectiveness of the proposed method by analyzing the results and its success on two public databases. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel P300-based BCI system for words typing

    Page(s): 24 - 25
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (452 KB) |  | HTML iconHTML  

    The conventional P300 BCI system for character spelling is typically composed of a paradigm that displays flashing characters and a classifier which identifies target characters. Typically a user has to type each character of a word at a time: this spelling process is slow and it can take several minutes to type an entire word. In this work, we propose a new word typing scheme by integrating a word suggestion mechanism via a dictionary search into the conventional P300-based speller. Our new P300-based word typing system consists of an initial character spelling paradigm, a smart dictionary unit to give suggestions of possible words, and the final word selection paradigm to select a word out of the suggestions. Our proposed methodology reduces typing time significantly and makes word typing more convenient. We have tested our system with four subjects and our results demonstrate an average words typing time of 1.66 minute, whereas the conventional took 2.9 minute for the same words. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Non-homogeneous spatial filter optimization for EEG-based brain-computer interfaces

    Page(s): 26 - 28
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (969 KB) |  | HTML iconHTML  

    Neuronal power attenuation or enhancement in specific frequency bands over the sensorimotor cortex, called Event-Related Desynchronization (ERD) or Event-Related Synchronization (ERS), respectively, is a major phenomenon in brain activities involved in imaginary movement of body parts. However, it is known that the nature of motor imagery-related electroencephalogram (EEG) signals is non-stationary and highly variable over time and frequency. In this paper, we propose a novel method of finding a discriminative time- and frequency-dependent spatial filter, which we call `non-homogeneous filter.' We adaptively select bases of spatial filters over time and frequency. By taking both temporal and spectral features of EEGs in finding a spatial filter into account it is beneficial to be able to consider non-stationarity of EEG signals. In order to consider changes of ERD/ERS patterns over the time-frequency domain, we devise a spectrally and temporally weighted classification method via statistical analysis. Our experimental results on the BCI Competition IV dataset II-a clearly presented the effectiveness of the proposed method outperforming other competing methods in the literature. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel tactile stimulation system for BCI feedback

    Page(s): 29 - 31
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (805 KB) |  | HTML iconHTML  

    When BCI based devices are operated, users are often desired to interact with environment. However, conventional visual BCI feedback disturbs continuous and smooth interactions. Therefore, a new tactile stimulation system suitable for delivering BCI feedback to user is developed. The system employs tactile illusion of movement to produce a continuous movement within six coin motors. Two protocols that convert the BCI feedback into spatiotemporal patterns of the stimulator are tested online. The results show that there are no identified artifacts in the EEG signal and no degradation of classification accuracy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A study on information transfer rate by brain-computer interface (BCI) using functional near-infrared spectroscopy (fNIRS)

    Page(s): 32 - 33
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (896 KB) |  | HTML iconHTML  

    We develop an 8-channel time domain functional near-infrared spectroscopy (fNIRS) system and measure concentration changes of hemoglobin during left/right arm lifting. Correlation-based signal improvement (CBSI) method is used to remove the effect of the head movement. We investigate the performances of the information transfer rate as a function of classification accuracy estimated by support vector machine. We achieve the information transfer rate in the range of 0.28~2.08 bits/min. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • BMFLC with neural network and DE for better event classification

    Page(s): 34 - 35
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (749 KB) |  | HTML iconHTML  

    The event-related desynchronization(ERD) is a well known phenomenon that is commonly used for classification in brain-computer interface(BCI) applications. The classification accuracy of ERD based BCI can be improved by selection of subject-specific reactive band rather than complete μ-band. After obtaining time-frequency(TF) mapping of EEG signal with a Fourier based adaptive method, differential evolution(DE) is used for the identification of the reactive band. Compared to classical band-power based method, the proposed method based on subject-specific reactive band yields better accuracy with BCI competition dataset IV. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Classifying ECoG signals prior to voluntary movement onset

    Page(s): 36 - 38
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (696 KB) |  | HTML iconHTML  

    Recently, in brain-computer interface (BCI) researches, earlier neural signals have allowed researchers to reduce the time gap between a subject's real action and the BCI response. The aims of this study were to use pre-movement signals to predict motor tasks, and to decide whether the prefrontal area, which has been recognized as generating premovement signals that reflect motor intention or preparation, generates useful pre-movement signals. Six patients with intractable epilepsy participated in this study and performed self-paced hand grasping and elbow flexion while electrocortico-graphy (ECoG) was recorded. The electrodes that showed clear power differences in a specific frequency band between two different movements were chosen at a preparatory stage (-2.0 s to 0 s). The average value of the squared power of the signal sample was extracted for the feature. A support vector machine (SVM) was used as a classifier. A total of twelve electrodes differentiating hand grasping and elbow flexion were selected. Four electrodes were placed on the prefrontal area. The average prediction rate was 74% (range, 55.4 to 99.3%) across the six subjects. The successful prediction of movement intention indicates that the prefrontal area may generate useful premovement signals and implies that our approach could produce BCI response faster than a subject's real actions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Common spatial patterns based on generalized norms

    Page(s): 39 - 42
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1013 KB) |  | HTML iconHTML  

    The Common Spatial Patterns (CSP) algorithm is commonly used to finds spatial filters for classification of electroencephalogram (EEG) signals. However, conventional CSP is sensitive to outliers and artifacts because it is based on variance using L2-norm. In this paper, we consider generalized Lp norm based CSP, called CSP-Lp, and verify whichp is optimal for CSP-Lp by maximizing the Lp norm ratio of filtered dispersion of one class to the other class. The spatial filters of CSP-Lp are obtained empirically. Simulation result on a toy example shows the robustness of CSP-Lp depending on Lp-norm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decoding three-dimensional arm movements for brain-machine interface

    Page(s): 43 - 45
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (820 KB) |  | HTML iconHTML  

    Although estimation of 3-dimensional arm movements is crucial to control prosthetic devices using brain signals, there have been few non-invasive brain-machine interface (BMI) studies estimating arm movements. Here, we aimed to estimate 3-dimensional movements using magnetoencephalography (MEG) signals. For the movement decoding, we determined 68 MEG channels on motor-related area and 4 sub-frequency bands, 0.5-8, 9-22, 25-40 and 57-97Hz, based on event-related desynchronization (ERD) and synchronization (ERS). Our results demonstrate that non-invasive signals can estimate 3-dimensional movements with considerably high performance (mean r > 0.6). We also verified that low-frequency activity plays an important role in estimating a 3-dimensional movement trajectory. These results imply that disabled people will be able to control prosthetic devices without surgery in the near future. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design of a robotic wheelchair with a motor imagery based brain-computer interface

    Page(s): 46 - 48
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1820 KB) |  | HTML iconHTML  

    This paper presents a prototype for an electro-encephalogram (EEG) based brain-actuated wheelchair system using motor imagery. To overcome some of the limitations of other previous works, such as gaze dependence and unnecessary stops, five commands (left, left-diagonal, right, right-diagonal, and forward) were decoded based on the motor imagery correlates in EEG signals. Also, the system was modularized into three components: BCI control, and network. On the basis of the conclusions, we can expect a robust brain-actuated wheelchair system, which can allow the user's intention to control the wheelchair in multi-directional movements, thereby increasing the user's authority compared with many of the alternative approaches. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection of multi-class emergency situations during simulated driving from ERP

    Page(s): 49 - 51
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2226 KB) |  | HTML iconHTML  

    We present a driving simulator study investigating whether a driver's braking intention in emergency situations can be detected under more general circumstances than previously described in the literature. Precisely, we here simulated three kinds of realistic emergency situations instead of only one as considered in Haufe et al., 2011. For each of the three situations, the analysis of electroencephalography (EEG) data reveals a different characteristic spatio-temporal event-related potential (ERP) sequence. For all stimuli, topographical maps of area under the curve (AUC) scores related to the discrimination between emergency and normal driving situations show a significant positive deflection in parietal regions about 300ms post-stimulus. Thus, it is possible to predict different emergency situations from EEG before the actual braking. A classification analysis indeed reveals that EEG-based emergency braking detection can be performance faster than electromyography- or pedal-based detection, while being as robust. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dry electrode design and performance evaluation for EEG based BCI systems

    Page(s): 52 - 53
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (751 KB) |  | HTML iconHTML  

    For the design of electroencephalography (EEG) based BCI systems, crucial issues are to acquire high fidelity EEG signals and to provide convenient installation to users. Electrodes are the key components which measure EEG signals from user's scalp. In this paper, we introduce a design of dry electrodes for BCI systems. The proposed electrodes are equipped with six spring loaded probes. They are capable of acquiring EEG signals of good enough quality without usage of conductive gels. To verify the performance of proposed electrodes, we measure contact impedance and compare them with those of conventional wet electrodes and G.tec Sahara dry electrodes. From the results, the impedance of proposed electrodes is shown to be satisfied without conductive gels. In future research, we will improve the design of proposed electrodes by adding active circuits. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • EEG asymmetry and anxiety

    Page(s): 54 - 55
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (198 KB) |  | HTML iconHTML  

    This study examined a relationship between anxiety scale score and two types of EEG asymmetry: resting state and fear-induced state. 30 adults who have no psychiatric history were participated, and their EEGs were recorded while resting and watching emotion-inducing film clips respectively. The result was obtained that there is no significant difference in resting state EEG asymmetry between high and low anxiety, but there is a meaningful difference in fear-induced frontal EEG asymmetry between two anxiety levels. The group with high anxiety level shows greater EEG asymmetry. We discussed the way how this result could be applied to anxiety treatment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Eeg-based emotion recogntion during emotionally evocative films

    Page(s): 56 - 57
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (168 KB) |  | HTML iconHTML  

    It is difficult to classify anger, fear, and surprise emotions with autonomic nervous system response patterns, because these three emotions show similar levels of valence and arousal dimensions. The purpose of this study was to classify three emotions by using EEG signals. Linear discriminant analysis (LDA) using three types of EEG characteristics showed that the mean recognition accuracy was 66.3%. These findings reveal that three emotions were successfully able to be classified based on EEG signals. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.