EEG-based Brain-machine Interface Research Articles

EEG-Based brain-machine interface for categorizing cognitive sentimental emotions

The development of brain-machine interfaces (BMIs) has revolutionized the study of neuroscience by making it possible for the brain to communicate directly with outside objects. In this study, EEG brainwave data is used to categorize emotional experiences using both individual and group methods. We employ a four-electrode resolution (TP9, AF7, AF8, and TP10) commercial MUSE EEG headband. Film clips with clear emotional content elicit both good and negative emotions. For one minute per session, neutral resting data is also obtained without external stimuli. To do this, we use machine learning algorithms to decode and interpret participant EEG data as they perform activities that evoke a range of emotional reactions. Relevant characteristics are collected from the EEG signals using intensive data preprocessing, feature extraction, and selection approaches to identify the underlying patterns of cognitive sentimental feelings. Following that, the development and assessment of classification models, such as Gradient Artificial Neural Networks (G-ANN), use the retrieved features as input. In conclusion, this study presents an EEG-based BMI system for categorizing cognitive sentimental emotions. The proposed G-ANN achieves a high accuracy of 98.59%, demonstrating superior performance compared to existing methodologies.

An EEG database for the cognitive assessment of motor imagery during walking with a lower-limb exoskeleton

One important point in the development of a brain-machine Interface (BMI) commanding an exoskeleton is the assessment of the cognitive engagement of the subject during the motor imagery tasks conducted. However, there are not many databases that provide electroencephalography (EEG) data during the use of a lower-limb exoskeleton. The current paper presents a database designed with an experimental protocol aiming to assess not only motor imagery during the control of the device, but also the attention to gait on flat and inclined surfaces. The research was conducted as an EUROBENCH subproject in the facilities sited in Hospital Los Madroños, Brunete (Madrid). The data validation reaches accuracies over 70% in the assessment of motor imagery and attention to gait, which marks the present database as a valuable resource for researches interested on developing and testing new EEG-based BMIs.

Empirical comparison of deep learning methods for EEG decoding.

Electroencephalography (EEG) is a technique that can be used in non-invasive brain-machine interface (BMI) systems to register brain electrical activity. The EEG signals are non-linear and non-stationary, making the decoding procedure a complex task. Deep learning techniques have been successfully applied in several research fields, often improving the results compared with traditional approaches. Therefore, it is believed that these techniques can also improve the process of decoding brain signals in BMI systems. In this work, we present the implementation of two deep learning-based decoders and we compared the results with other state of art deep learning methods. The first decoder uses long short-term memory (LSTM) recurrent neural network and the second, entitled EEGNet-LSTM, combines a well-known neural decoder based on convolutional neural networks, called EEGNet, with some LSTM layers. The decoders have been tested using data set 2a from BCI Competition IV, and the results showed that the EEGNet-LSTM decoder has been approximately 23% better than the competition-winning decoder. A Wilcoxon t-test showed a significant difference between the two decoders (Z = 2.524, p = 0.012). The LSTM-based decoder has been approximately 9% higher than the best decoder from the same competition. However, there was no significant difference (Z = 1.540, p = 0.123). In order to verify the replication of the EEGNet-LSTM decoder on another data, we performed a test with PhysioNet's Physiobank EEG Motor Movement/Imagery dataset. The EEGNet-LSTM presented a higher performance (0.85 accuracy) than the EEGNet (0.82 accuracy). The results of this work can be important for the development of new research, as well as EEG-based BMI systems, which can benefit from the high precision of neural decoders.

EEG in Neurorehabilitation: A Bibliometric Analysis and Content Review.

There is increasing interest in the role of EEG in neurorehabilitation. We primarily aimed to identify the knowledge base through highly influential studies. Our secondary aims were to imprint the relevant thematic hotspots, research trends, and social networks within the scientific community. We performed an electronic search in Scopus, looking for studies reporting on rehabilitation in patients with neurological disabilities. We used the most influential papers to outline the knowledge base and carried out a word co-occurrence analysis to identify the research hotspots. We also used depicted collaboration networks between universities, authors, and countries after analyzing the cocitations. The results were presented in summary tables, plots, and maps. Finally, a content review based on the top-20 most cited articles completed our study. Our current bibliometric study was based on 874 records from 420 sources. There was vivid research interest in EEG use for neurorehabilitation, with an annual growth rate as high as 14.3%. The most influential paper was the study titled "Brain-computer interfaces, a review" by L.F. Nicolas-Alfonso and J. Gomez-Gill, with 997 citations, followed by "Brain-computer interfaces in neurological rehabilitation" by J. Daly and J.R. Wolpaw (708 citations). The US, Italy, and Germany were among the most productive countries. The research hotspots shifted with time from the use of functional magnetic imaging to EEG-based brain-machine interface, motor imagery, and deep learning. EEG constitutes the most significant input in brain-computer interfaces (BCIs) and can be successfully used in the neurorehabilitation of patients with stroke symptoms, amyotrophic lateral sclerosis, and traumatic brain and spinal injuries. EEG-based BCI facilitates the training, communication, and control of wheelchair and exoskeletons. However, research is limited to specific scientific groups from developed countries. Evidence is expected to change with the broader availability of BCI and improvement in EEG-filtering algorithms.

Sub-100 $\mu$W Multispectral Riemannian Classification for EEG-Based Brain–Machine Interfaces

Motor imagery (MI) brain-machine interfaces (BMIs) enable us to control machines by merely thinking of performing a motor action. Practical use cases require a wearable solution where the classification of the brain signals is done locally near the sensor using machine learning models embedded on energy-efficient microcontroller units (MCUs), for assured privacy, user comfort, and long-term usage. In this work, we provide practical insights on the accuracy-cost trade-off for embedded BMI solutions. Our multispectral Riemannian classifier reaches 75.1% accuracy on a 4-class MI task. The accuracy is further improved by tuning different types of classifiers to each subject, achieving 76.4%. We further scale down the model by quantizing it to mixed-precision representations with a minimal accuracy loss of 1% and 1.4%, respectively, which is still up to 4.1% more accurate than the state-of-the-art embedded convolutional neural network. We implement the model on a low-power MCU within an energy budget of merely 198 μJ and taking only 16.9 ms per classification. Classifying samples continuously, overlapping the 3.5 s samples by 50% to avoid missing user inputs allows for operation at just 85 μW. Compared to related works in embedded MI-BMIs, our solution sets the new state-of-the-art in terms of accuracy-energy trade-off for near-sensor classification.

Development of a Hardware Circuit for Real-Time Acquisition of Brain Activity Using NI myDAQ

Electroencephalography (EEG) is the recording of electrical activity of the brain. The 10–20 system is the standard electrode location method used to acquire EEG data, which uses 21 electrodes to record the electrical activity of the brain. Patient preparation and correct electrode placement are important to obtain reliable outputs. The current 10–20 system consumes greater time for patient preparation and also causes discomfort due to a higher number of electrodes being used or wearing an uncomfortable cap. This paper focuses on reducing the number of electrodes, thus reducing patient discomfort as well as preparation time. Advancement in the field of hardware and software processing has led to the utilization of brain waves for communication between human and the computer. This work deals with EEG-based Brain–Machine Interface (BMI) intended for designing a portable single-channel EEG signal acquisition system. EEG signal was acquired using the data acquisition module [National Instruments (NI) myDAQ] and the signal was viewed in the NI Laboratory Virtual Instrument Engineering Workbench (LabVIEW) environment. It was observed that the peak-to-peak amplitude of alpha, beta and theta waves changes in accordance with the activity the subjects performed. Thus, the developed instrument was tested on 10 different subjects to acquire the alpha, beta and theta waves by performing different activities. From the results, it can be concluded that the developed system can be used for studying a person’s brain waves (alpha, beta and theta) based on the activity performed by the subject with a limited number of electrodes.

Brain-actuated gait trainer with visual and proprioceptive feedback

Objective. Brain-machine interfaces (BMIs) have been proposed in closed-loop applications for neuromodulation and neurorehabilitation. This study describes the impact of different feedback modalities on the performance of an EEG-based BMI that decodes motor imagery (MI) of leg flexion and extension. Approach. We executed experiments in a lower-limb gait trainer (the legoPress) where nine able-bodied subjects participated in three consecutive sessions based on a crossover design. A random forest classifier was trained from the offline session and tested online with visual and proprioceptive feedback, respectively. Post-hoc classification was conducted to assess the impact of feedback modalities and learning effect (an improvement over time) on the simulated trial-based performance. Finally, we performed feature analysis to investigate the discriminant power and brain pattern modulations across the subjects. Main results. (i) For real-time classification, the average accuracy was % and % for the two online sessions. The results were significantly higher than chance level, demonstrating the feasibility to distinguish between MI of leg extension and flexion. (ii) For post-hoc classification, the performance with proprioceptive feedback (%) was significantly better than with visual feedback (%), while there was no significant learning effect. (iii) We reported individual discriminate features and brain patterns associated to each feedback modality, which exhibited differences between the two modalities although no general conclusion can be drawn. Significance. The study reported a closed-loop brain-controlled gait trainer, as a proof of concept for neurorehabilitation devices. We reported the feasibility of decoding lower-limb movement in an intuitive and natural way. As far as we know, this is the first online study discussing the role of feedback modalities in lower-limb MI decoding. Our results suggest that proprioceptive feedback has an advantage over visual feedback, which could be used to improve robot-assisted strategies for motor training and functional recovery.

Cortical and subcortical mechanisms of brain‐machine interfaces

Technical advances in the field of Brain-Machine Interfaces (BMIs) enable users to control a variety of external devices such as robotic arms, wheelchairs, virtual entities and communication systems through the decoding of brain signals in real time. Most BMI systems sample activity from restricted brain regions, typically the motor and premotor cortex, with limited spatial resolution. Despite the growing number of applications, the cortical and subcortical systems involved in BMI control are currently unknown at the whole-brain level. Here, we provide a comprehensive and detailed report of the areas active during on-line BMI control. We recorded functional magnetic resonance imaging (fMRI) data while participants controlled an EEG-based BMI inside the scanner. We identified the regions activated during BMI control and how they overlap with those involved in motor imagery (without any BMI control). In addition, we investigated which regions reflect the subjective sense of controlling a BMI, the sense of agency for BMI-actions. Our data revealed an extended cortical-subcortical network involved in operating a motor-imagery BMI. This includes not only sensorimotor regions but also the posterior parietal cortex, the insula and the lateral occipital cortex. Interestingly, the basal ganglia and the anterior cingulate cortex were involved in the subjective sense of controlling the BMI. These results inform basic neuroscience by showing that the mechanisms of BMI control extend beyond sensorimotor cortices. This knowledge may be useful for the development of BMIs that offer a more natural and embodied feeling of control for the user. Hum Brain Mapp 38:2971-2989, 2017. © 2017 Wiley Periodicals, Inc.

Combining a hybrid robotic system with a bain-machine interface for the rehabilitation of reaching movements: A case study with a stroke patient.

Reaching and grasping are two of the most affected functions after stroke. Hybrid rehabilitation systems combining Functional Electrical Stimulation with Robotic devices have been proposed in the literature to improve rehabilitation outcomes. In this work, we present the combined use of a hybrid robotic system with an EEG-based Brain-Machine Interface to detect the user's movement intentions to trigger the assistance. The platform has been tested in a single session with a stroke patient. The results show how the patient could successfully interact with the BMI and command the assistance of the hybrid system with low latencies. Also, the Feedback Error Learning controller implemented in this system could adjust the required FES intensity to perform the task.

頭皮脳波を用いたブレイン-マシン・インターフェイスの研究開発

頭皮脳波を用いたブレイン-マシン・インターフェイスの研究開発

Design and Optimization of an EEG-Based Brain Machine Interface (BMI) to an Upper-Limb Exoskeleton for Stroke Survivors.

This study demonstrates the feasibility of detecting motor intent from brain activity of chronic stroke patients using an asynchronous electroencephalography (EEG)-based brain machine interface (BMI). Intent was inferred from movement related cortical potentials (MRCPs) measured over an optimized set of EEG electrodes. Successful intent detection triggered the motion of an upper-limb exoskeleton (MAHI Exo-II), to guide movement and to encourage active user participation by providing instantaneous sensory feedback. Several BMI design features were optimized to increase system performance in the presence of single-trial variability of MRCPs in the injured brain: (1) an adaptive time window was used for extracting features during BMI calibration; (2) training data from two consecutive days were pooled for BMI calibration to increase robustness to handle the day-to-day variations typical of EEG, and (3) BMI predictions were gated by residual electromyography (EMG) activity from the impaired arm, to reduce the number of false positives. This patient-specific BMI calibration approach can accommodate a broad spectrum of stroke patients with diverse motor capabilities. Following BMI optimization on day 3, testing of the closed-loop BMI-MAHI exoskeleton, on 4th and 5th days of the study, showed consistent BMI performance with overall mean true positive rate (TPR) = 62.7 ± 21.4% on day 4 and 67.1 ± 14.6% on day 5. The overall false positive rate (FPR) across subjects was 27.74 ± 37.46% on day 4 and 27.5 ± 35.64% on day 5; however for two subjects who had residual motor function and could benefit from the EMG-gated BMI, the mean FPR was quite low (< 10%). On average, motor intent was detected −367 ± 328 ms before movement onset during closed-loop operation. These findings provide evidence that closed-loop EEG-based BMI for stroke patients can be designed and optimized to perform well across multiple days without system recalibration.

Multisession, noninvasive closed-loop neuroprosthetic control of grasping by upper limb amputees.

Upper limb amputation results in a severe reduction in the quality of life of affected individuals due to their inability to easily perform activities of daily living. Brain-machine interfaces (BMIs) that translate grasping intent from the brain's neural activity into prosthetic control may increase the level of natural control currently available in myoelectric prostheses. Current BMI techniques demonstrate accurate arm position and single degree-of-freedom grasp control but are invasive and require daily recalibration. In this study we tested if transradial amputees (A1 and A2) could control grasp preshaping in a prosthetic device using a noninvasive electroencephalography (EEG)-based closed-loop BMI system. Participants attempted to grasp presented objects by controlling two grasping synergies, in 12 sessions performed over 5 weeks. Prior to closed-loop control, the first six sessions included a decoder calibration phase using action observation by the participants; thereafter, the decoder was fixed to examine neuroprosthetic performance in the absence of decoder recalibration. Ability of participants to control the prosthetic was measured by the success rate of grasping; ie, the percentage of trials within a session in which presented objects were successfully grasped. Participant A1 maintained a steady success rate (63±3%) across sessions (significantly above chance [41±5%] for 11 sessions). Participant A2, who was under the influence of pharmacological treatment for depression, hormone imbalance, pain management (for phantom pain as well as shoulder joint inflammation), and drug dependence, achieved a success rate of 32±2% across sessions (significantly above chance [27±5%] in only two sessions). EEG signal quality was stable across sessions, but the decoders created during the first six sessions showed variation, indicating EEG features relevant to decoding at a smaller timescale (100ms) may not be stable. Overall, our results show that (a) an EEG-based BMI for grasping is a feasible strategy for further investigation of prosthetic control by amputees, and (b) factors that may affect brain activity such as medication need further examination to improve accuracy and stability of BMI performance.

What limits the performance of current invasive brain machine interfaces?

The concept of a brain-machine interface (BMI) or a computer-brain interface is simple: BMI creates a communication pathway for a direct control by brain of an external device. In reality BMIs are very complex devices and only recently the increase in computing power of microprocessors enabled a boom in BMI research that continues almost unabated to this date, the high point being the insertion of electrode arrays into the brains of 5 human patients in a clinical trial run by Cyberkinetics with few other clinical tests still in progress. Meanwhile several EEG-based BMI devices (non-invasive BMIs) were launched commercially. Modern electronics and dry electrode technology made possible to drive the cost of some of these devices below few hundred dollars. However, the initial excitement of the direct control by brain waves of a computer or other equipment is dampened by large efforts required for learning, high error rates and slow response speed. All these problems are directly related to low information transfer rates typical for such EEG-based BMIs. In invasive BMIs employing multiple electrodes inserted into the brain one may expect much higher information transfer rates than in EEG-based BMIs because, in theory, each electrode provides an independent information channel. However, although invasive BMIs require more expensive equipment and have ethical problems related to the need to insert electrodes in the live brain, such financial and ethical costs are often not offset by a dramatic improvement in the information transfer rate. Thus the main topic of this review is why in invasive BMIs an apparently much larger information content obtained with multiple extracellular electrodes does not translate into much higher rates of information transfer? This paper explores possible answers to this question by concluding that more research on what movement parameters are encoded by neurons in motor cortex is needed before we can enjoy the next generation BMIs.

脳波BMI技術の実用化と新たな課題～多様な感情表現を可能にするアバターの表情制御を目指して～

脳波BMI技術の実用化と新たな課題～多様な感情表現を可能にするアバターの表情制御を目指して～

Decoding Intra-Limb and Inter-Limb Kinematics During Treadmill Walking From Scalp Electroencephalographic (EEG) Signals

Brain-machine interface (BMI) research has largely been focused on the upper limb. Although restoration of gait function has been a long-standing focus of rehabilitation research, surprisingly very little has been done to decode the cortical neural networks involved in the guidance and control of bipedal locomotion. A notable exception is the work by Nicolelis' group at Duke University that decoded gait kinematics from chronic recordings from ensembles of neurons in primary sensorimotor areas in rhesus monkeys. Recently, we showed that gait kinematics from the ankle, knee, and hip joints during human treadmill walking can be inferred from the electroencephalogram (EEG) with decoding accuracies comparable to those using intracortical recordings. Here we show that both intra- and inter-limb kinematics from human treadmill walking can be achieved with high accuracy from as few as 12 electrodes using scalp EEG. Interestingly, forward and backward predictors from EEG signals lagging or leading the kinematics, respectively, showed different spatial distributions suggesting distinct neural networks for feedforward and feedback control of gait. Of interest is that average decoding accuracy across subjects and decoding modes was ~0.68±0.08, supporting the feasibility of EEG-based BMI systems for restoration of walking in patients with paralysis.

A Review of fMRI as a Tool for Enhancing Eeg-Based Brain-Machine Interfaces

Human-robot interaction has been going stronger and stronger, up to find a notorious level on brain-machines interfaces. This assistive technology offers a great hope for patients suffering severe neuromuscular disorders. Starting from the current limitations hindering its extensive application outside the research laboratories, this paper reviews findings and prospects on functional magnetic resonance imaging showing how fMRI can help to overcome those limitations, while playing a key role on improving the development of brain-machine interfaces based on electroencephalography. The different types of derived benefits for this interfaces, as well as the different kinds of impact on their components, are presented under a field classification that reveals the distinctive roles that fMRI can play on the present context. The review concludes that fMRI provides complementary knowledge of immediate application, and that a greater profit could be obtained from the own EEG signal by integrating both neuroimaging modalities.

EEG-based Brain–Machine Interface induces neurorehabilitative recovery of paretic hand in patients with chronic stroke

EEG-based Brain–Machine Interface induces neurorehabilitative recovery of paretic hand in patients with chronic stroke