The Effect of Muscle Artifact Reduction Methods on Few-channel SSVEPs during Head Movements.

Brain-computer interfaces (BCIs) with steady-state visual evoked potentials (SSVEPs) caused by flickering stimuli have caught attention as communication tools between human brains and external machines through a head-mounted display (HMD). When applying SSVEP-based BCIs to real-life environments, the head must be moved to watch the stimuli displayed in an HMD, which generates muscular artifacts and significantly reduces BCI performance. In this study, we examined four-class SSVEP identification accuracies by using four artifact reduction methods in the situation of moving the head for both simulation and real datasets. In the simulation dataset, we found that artifact subspace reconstruction (ASR) and multi-scale dictionary learning (MSDL) showed better results especially at low signal-to-noise ratio. In the real dataset, we observed that reducing muscular artifacts resulted in performance degradation for independent component analysis-based methods, while ASR and MSDL showed relatively limited degradation and in some cases improved performance. Our future work is to improve ASR and MSDL for high performance with real data and to apply them to an online SSVEP-based BCI where the user moves his/her head.

Sequential Learning on sEMGs in Short- and Long-term Situations via Self-training Semi-supervised Support Vector Machine.

The purpose of this study it to assess the effect of sequential learning of self-training support vector machine (ST-S3VM) on short- and long-term surface electromyogram (sEMG) datasets. A machine learning-based supervised classi-fier is enabling stable, complex, and high-performance motion control. Unlabeled sEMG measurements are easy by the devel-opment of wearable sensing technology. Thus, semi-supervised learning methods are attracted attention to utilize unlabeled sEMG data for supervised classifier with a small amount of labeled data. To evaluate robustness of ST-S3VM in realistic conditions, two public datasets which respectively contain a short- and long-term dataset were used. We compared the performance of ST-S3VM with four-kinds of SVM classifiers. In both short- and long-term situations, ST combined classifiers (ST-SVM and ST-S3VM) showed higher performances than the methods without ST (SVM and S3VM). In some cases, ST-S3VM had the best performance, but in other cases, ST-SVM had better performance than ST-S3VM. In order to make better use of unlabeled data, we will develop ST-S3VM to reduce the impact of harmful unlabeled data.

Time-domain Mixup Source Data Augmentation of sEMGs for Motion Recognition towards Efficient Style Transfer Mapping.

Motion recognition based on surface electromyogram (sEMG) recorded from the forearm is attracting attention for its applicability because it easily integrates with wearable devices and has a high signal-to-noise ratio. Inter-subject variability and inadequate data availability are common problems encountered in classifiers. Transfer learning (TL) techniques can reduce the inter-subject variability; however, when the amount of data recorded from each source subject is small, the TL-combined classifier is prone to overfitting problems. In this study, we tested the accuracy of motion recognition with and without TL when the source dataset was increased up to 10 times with a time-domain data augmentation method called mixup. The performance was evaluated using an 8-class sEMG dataset containing wearable sensing data from 25 subjects. We found that mixup improved the performance of TL-combined classifiers (support vector machine and 4-layered fully connected feedforward neural network). In future work, we plan to investigate the relationship between the amount of data and sEMG-based motion recognition by comparing multiple sEMG datasets and multiple data augmentation methods.

Analysis and Usage: Subject-to-subject Linear Domain Adaptation in sEMG Classification.

Before the operation of a biosignal-based application, long-duration calibration is required to adjust the pre-trained classifier to a new user data (target data). For reducing such time-consuming step, linear domain adaptation (DA) transfer learning approaches, which transfer pooled data (source data) related to the target data, are highlighted. In the last decade, they have been applied to surface electromyogram (sEMG) data with the implicit assumption that sEMG data are linear. However, sEMGs typically have non-linear characteristics, and due to the discrepancy between the assumption and actual characteristics, linear DA approaches would cause a negative transfer. This study investigated how the correlation between the source and target data affects an 8-class forearm movement classification after applying linear DA approaches. As a result, we found significant positive correlations between the classification accuracy and the source-target correlation. Additionally, the source-target correlation depended on the motion class. Therefore, our results suggest that we should choose a non-linear DA approach when the source-target correlation among subjects or motion classes is low.

Motor Imagery Classification of Finger Motions Using Multiclass CSP.

Electroencephalogram (EEG) data during motor imagery tasks regarding small-scale physical dynamics such as finger motions have low discriminability because capturing the spatial difference of the motions is difficult. We assumed that more discriminative features can be captured if spatial filters maximize the independence of each class data. This study constructed spatial filters named multiclass common spatial pattern (CSP), which maximize an approximation of mutual in-formation of extracted components and class labels, and applied them to a five-class motor-imagery dataset containing finger motion tasks. By applying multiclass CSP, the classification accuracies were improved (Mean SD: 40.6 ± 10.1%) compared with classical CSP (21.8 ± 2.5%) and no spatial filtering case (38.7±10.0%). In addition, we visualized learned spatial filters to assess the trend of discriminative features of finger motions. For these results, it was clear that multiclass CSP captured task-specific spatial maps for each finger motion and outperformed multiclass motor-imagery classification performance about 2% even when the tasks are small-scale physical dynamics.

Independent Low-Rank Matrix Analysis-Based Automatic Artifact Reduction Technique Applied to Three BCI Paradigms.

Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) can potentially enable people to non-invasively and directly communicate with others using brain activities. Artifacts generated from body activities (e.g., eyeblinks and teeth clenches) often contaminate EEGs and make EEG-based classification/identification hard. Although independent component analysis (ICA) is the gold-standard technique for attenuating the effects of such contamination, the estimated independent components are still mixed with artifactual and neuronal information because ICA relies only on the independence assumption. The same problem occurs when using independent vector analysis (IVA), an extended ICA method. To solve this problem, we designed an independent low-rank matrix analysis (ILRMA)-based automatic artifact reduction technique that clearly models sources from observations under the independence assumption and a low-rank nature in the frequency domain. For automatic artifact reduction, we combined the signal separation technique with an independent component classifier for EEGs named ICLabel. To assess the comparative efficiency of the proposed method, the discriminabilities of artifact-reduced EEGs using ICA, IVA, and ILRMA were determined using an open-access EEG dataset named OpenBMI, which contains EEG data obtained through three BCI paradigms [motor-imagery (MI), event-related potential (ERP), and steady-state visual evoked potential (SSVEP)]. BCI performances were obtained using these three paradigms after applying artifact reduction techniques, and the results suggested that our proposed method has the potential to achieve higher discriminability than ICA and IVA for BCIs. In addition, artifact reduction using the ILRMA approach clearly improved (by over 70%) the averaged BCI performances using artifact-reduced data sufficiently for most needs of the BCI community. The extension of ICA families to supervised separation that leaves the discriminative ability would further improve the usability of BCIs for real-life environments in which artifacts frequently contaminate EEGs.

Robustness analysis of decoding SSVEPs in humans with head movements using a moving visual flicker.

OBJECTIVE: The emergence of mobile electroencephalogram (EEG) platforms have expanded the use cases of brain-computer interfaces (BCIs) from laboratory-oriented experiments to our daily life. In challenging situations where humans' natural behaviors such as head movements are unrestrained, various artifacts could deteriorate the performance of BCI applications. This paper explored the effect of muscular artifacts generated by participants' head movements on the signal characteristics and classification performance of steady-state visual evoked potentials (SSVEPs). APPROACH: A moving visual flicker was employed to induce not only SSVEPs but also horizontal and vertical head movements at controlled speeds, leading to acquiring EEG signals with intensity-manipulated muscular artifacts. To properly induce neck muscular activities, a laser light was attached to participants' heads to give visual feedback; the laser light indicates the direction of the head independently from eye movements. The visual stimulus was also modulated by four distinct frequencies (10, 11, 12, and 13 Hz). The amplitude and signal-to-noise ratio (SNR) were estimated to quantify the effects of head movements on the signal characteristics of the elicited SSVEPs. The frequency identification accuracy was also estimated by using well-established decoding algorithms including calibration-free and fully-calibrated approaches. MAIN RESULTS: The amplitude and SNR of SSVEPs tended to deteriorate when the participants moved their heads, and this tendency was significantly stronger in the vertical head movements than in the horizontal movements. The frequency identification accuracy also deteriorated in proportion to the speed of head movements. Importantly, the accuracy was significantly higher than its chance-level regardless of the level of artifact contamination and algorithms. SIGNIFICANCE: The results suggested the feasibility of decoding SSVEPs in humans freely moving their head directions, facilitating the real-world applications of mobile BCIs.

Analysis of Prefrontal Single-Channel EEG Data for Portable Auditory ERP-Based Brain-Computer Interfaces.

An electroencephalogram (EEG)-based brain-computer interface (BCI) is a tool to non-invasively control computers by translating the electrical activity of the brain. This technology has the potential to provide patients who have severe generalized myopathy, such as those suffering from amyotrophic lateral sclerosis (ALS), with the ability to communicate. Recently, auditory oddball paradigms have been developed to implement more practical event-related potential (ERP)-based BCIs because they can operate without ocular activities. These paradigms generally make use of clinical (over 16-channel) EEG devices and natural sound stimuli to maintain the user's motivation during the BCI operation; however, most ALS patients who have taken part in auditory ERP-based BCIs tend to complain about the following factors: (i) total device cost and (ii) setup time. The development of a portable auditory ERP-based BCI could overcome considerable obstacles that prevent the use of this technology in communication in everyday life. To address this issue, we analyzed prefrontal single-channel EEG data acquired from a consumer-grade single-channel EEG device using a natural sound-based auditory oddball paradigm. In our experiments, EEG data was gathered from nine healthy subjects and one ALS patient. The performance of auditory ERP-based BCI was quantified under an offline condition and two online conditions. The offline analysis indicated that our paradigm maintained a high level of detection accuracy (%) and ITR (bits/min) across all subjects through a cross-validation procedure (for five commands: 70.0 ± 16.1 and 1.29 ± 0.93, for four commands: 73.8 ± 14.2 and 1.16 ± 0.78, for three commands: 78.7 ± 11.8 and 0.95 ± 0.61, and for two commands: 85.7 ± 8.6 and 0.63 ± 0.38). Furthermore, the first online analysis demonstrated that our paradigm also achieved high performance for new data in an online data acquisition stream (for three commands: 80.0 ± 19.4 and 1.16 ± 0.83). The second online analysis measured online performances on the different day of offline and first online analyses on a different day (for three commands: 62.5 ± 14.3 and 0.43 ± 0.36). These results indicate that prefrontal single-channel EEGs have the potential to contribute to the development of a user-friendly portable auditory ERP-based BCI.

Transfer Learning Over Time and Position in Wearable Myoelectric Control Systems.

Wearable sensors for upper limbs enable the use of myoelectric control systems in real environments. An important issue in the practical use of myoelectric control is how to deal with the variations of electromyograms (EMGs); the distribution of EMGs changes over days and device (electrode) positions. The amount of training data is usually limited, as the data are collected at the beginning of the system use. To compensate for the difference of EMGs over time and device placement with limited-amount training data, transfer learning can be employed. However, it was unclear how transfer learning improve the motion recognition accuracy over long-term use with varying device positions. In this paper, we evaluated transfer learning algorithms on one-month long data with three different device positions. We found that transfer learning was able to compensate for the variations over long period and also over different electrode placements, suggesting the practical efficacy of transfer learning. But there were some cases when transfer learning did not recover the original accuracy, in particular when electrodes were placed at "out-of-muscle" positions. These findings would motivate further investigations into the design of myoelectric control systems, e.g., denser electrode configurations or lifetime-long recordings.

Semi-simulation Experiments for Quantifying the Performance of SSVEP-based BCI after Reducing Artifacts from Trapezius Muscles.

Muscular artifacts often contaminate electroencephalograms (EEGs) and deteriorate the performance of brain-computer interfaces (BCIs). Although many artifact reduction techniques are available, most of the studies have focused on their reduction ability (i.e. reconstruction errors), and it has been missing to evaluate their effect on the performance of BCIs. This study aims at evaluating the performance of a state-of-the-art muscular artifact reduction technique on a scenario of a steady-state visual evoked potentials (SSVEPs)based BCI. The performance was evaluated based on a semisimulation setting using a benchmark dataset of SSVEPs artificially contaminated by muscular artifacts acquired from the trapezius. Our results showed that combining the artifact reduction method and the classification algorithm based on the task-related component analysis gained improved classification accuracy. Interestingly, the artifact reduction setting minimizing the reconstruction errors, i.e. elaborately recovering the true EEG waveforms, was inconsistent to the one maximizing the classification performance. The results suggest that artifact reduction methods should be tuned so as to tomaximize performance of BCIs.

Exploring optimal myoelectric feature indices for forearm control strategy using robust principal component analysis.

Forearm movements realize various functions needed in daily life. For reproduction of the motion sequences, active myoelectric devices have been developed. Usually, feature indices are extracted from observed signals in control strategy; however, the optimal combination of indices is still unclear. This paper introduces sparsity-inducing penalty term in principal component analysis (PCA) to explore optimal myoelectric feature indices. An electromyographic database including seven forearm movements from 30 subjects was used for performance comparison. Linear classifier with sparse features showed best performance (7.86±3.82% error rate) that was significantly better than linear classifier with all features because of recovering low rank matrix in original data. Furthermore, the sparse features had a large contribution of underlying data structure with less number of principal components than PCA. Root-mean-square, time-domain features, autoregressive coefficients, and Histogram purported to be important in projected feature space; therefore, the feature indices are important to myoelectric strategies.

Eye blink artifact rejection in single-channel electroencephalographic signals by complete ensemble empirical mode decomposition and independent component analysis.

To study an eye blink artifact rejection scheme from single-channel electroencephalographic (EEG) signals has been now a major challenge in the field of EEG signal processing. High removal performance is still needed to more strictly investigate pattern of EEG features. This paper proposes a new eye blink artifact rejection scheme from single-channel EEG signals by combining complete ensemble empirical mode decomposition (CEEMD) and independent component analysis (ICA). We compare the separation performance of our proposed scheme with existing schemes (wavelet-ICA, EMD-ICA, and EEMD-ICA) though real-life data by using signal-to-noise ratio. As a result, CEEMD-ICA showed high performance (11.86 dB) than all other schemes (10.78, 10.59, and 11.30 dB) in the ability of eye blink artifact removal.