BCI provides calibrated prediction intervals for time series forecasts.
problem Calibration of prediction intervals for time series forecasts.
method BCI wraps around any time series forecasting models and optimizes interval lengths using dynamic programming.
result BCI achieves long-term coverage under arbitrary distribution shifts and temporal dependence.
ASTL uses unlabeled data to improve BCI calibration.
problem Offline BCI calibration requires subject-specific data.
method Active semi-supervised transfer learning integrating active learning, semi-supervised learning, and transfer learning.
result ASTL consistently outperforms existing methods.
This paper improves MI-based BCIs by applying transfer learning across all components.
problem Reducing calibration effort for new subjects in MI-based BCIs.
method Proposes TL in spatial filtering, feature engineering, and classification blocks, and adds data alignment.
result Integrating data alignment and sophisticated TL significantly improves classification performance and reduces calibration effort.
Brain signal variability in the measurements obtained from different subjects during different sessions significantly deteriorates the accuracy of most brain-computer interface (BCI) systems. Moreover these variabilities, also known as inter-subject or inter-session variabilities, require lengthy calibration sessions b…
Objective: Using traditional approaches, a Brain-Computer Interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g.~by transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch …
This paper presents a new classification methods for Event Related Potentials (ERP) based on an Information geometry framework. Through a new estimation of covariance matrices, this work extend the use of Riemannian geometry, which was previously limited to SMR-based BCI, to the problem of classification of ERPs. As co…
Proposes a new framework for EEG-based BCIs without adversarial learning.
problem High intra- and inter-subject variabilities in EEG data.
method Mutual information-driven deep learning approach to learn class-relevant and subject-invariant feature representations.
result Effective in learning class-relevant and subject-invariant feature representations without adversarial learning.
Tensor completion improves EEG-based BCI performance with missing data.
problem Improving classification accuracy in BCI systems with noisy EEG data.
method Tensor decomposition models to infer missing entries in multidimensional EEG datasets.
result Tensor completion algorithms enhance BCI classification accuracy with missing data.
A new method improves SSVEP BCI to recognize responses in sub-second time with high accuracy.
problem Achieving high accuracy in SSVEP BCI with short response times.
method CSTA (Combining Spatial-Filtering and Temporal Alignment) method.
result CSTA achieves maximum mean accuracy of 97.43% in sub-second response time.
Paper attacks CNNs in EEG BCIs with adversarial examples.
problem Vulnerability of CNN classifiers in EEG-based BCIs.
method UFGSM to attack three popular CNN classifiers in BCIs.
result Demonstrates effectiveness of adversarial attacks on CNNs in BCIs.
Compact-CNN outperforms traditional methods in SSVEP classification.
problem Decoding SSVEPs without domain-specific knowledge.
method Compact convolutional neural network (Compact-CNN) for automatic feature extraction.
result Across subject mean accuracy of 80% (chance 8.3%) using Compact-CNN.
VR game data for P300 BCI with raccoon vs demon stimuli.
problem Developing confidence metrics for P300 BCI.
method Multiclass labeled P300 dataset in VR game context.
result Estimation of model's confidence in stimulus predictions.
Optimizes SSVEP-based BCI performance by automating threshold selection.
problem Improving classification accuracy of SSVEP-based brain-computer interfaces.
method Formalizes ITR maximization, derives a general formula, and automates threshold selection.
result Achieved ITR of 62 bit/min, outperforming previous methods by a factor of 2.
Brain computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct ch…
Bayesian model improves BCI performance for ALS users.
problem Classifying EEG signals for P300 BCIs with low SNR and complex correlations.
method GLASS model with Gaussian Latent channel and Sparse time-varying effects.
result GLASS substantially improves BCI performance in ALS users.
Novel approach to estimate P300 BCI efficiency using SNR.
problem Improving the accuracy of P300 BCI for severely disabled people.
method Introduced a novel approach considering P300 SNR for estimating efficiency, using a Gaussian noise model.
result P300 SNR significantly correlates with spelling accuracy, improving BCI efficiency.
Based on the cumulated experience over the past 25 years in the field of Brain-Computer Interface (BCI) we can now envision a new generation of BCI. Such BCIs will not require training; instead they will be smartly initialized using remote massive databases and will adapt to the user fast and effectively in the first m…
Before the operation of a motor imagery based brain-computer interface (BCI) adopting machine learning techniques, a cumbersome training procedure is unavoidable. The development of a practical BCI posed the challenge of classifying single-trial EEG with a small training set. In this letter, we addressed this problem b…
A novel deep learning method for real-time EEG signal compression.
problem Efficient processing of noisy EEG signals in real-time BCI systems.
method Deep convolutional autoencoders integrated with ROS-Neuro framework.
result Minimal jitter and preservation of original information in compressed EEG signals.
This research improves EEG-based MI-BCI systems to be more resilient to emotional arousal.
problem Lack of robustness in EEG-based MI-BCI systems due to emotional arousal.
method Subjects were exposed to VR environments to induce high and low arousal states. Machine learning models were trained on proxy subjects instead of arousal states. MI models were trained for each subject.
result MI-BCI systems are made more resilient to emotional perturbations.
Enhances EEG-based BCIs by adapting to non-stationary data shifts.
problem Non-stationary nature of EEG signals and covariate shifts.
method Covariate shift estimation and unsupervised adaptive ensemble learning.
result Significantly enhances BCI performance in MI classifications.
Brain-computer interfaces (BCIs) have been gaining momentum in making human-computer interaction more natural, especially for people with neuro-muscular disabilities. Among the existing solutions the systems relying on electroencephalograms (EEG) occupy the most prominent place due to their non-invasiveness. However, t…
Novel Bayesian model improves EEG-based BCI character selection.
problem Accurately identifying target-related responses in EEG-based BCIs.
method Probit-link Split-and-merge Gaussian Process (P-SMGP) prior for feature selection.
result Reduces computational complexity and provides interpretable statistical interpretations.
Novel BCI system classifies imagined speech with high accuracy.
problem Classifying imagined speech from brain signals.
method Hierarchical deep learning with CNN and autoencoder.
result Achieved 83.42% average accuracy across six phonological tasks.
GA optimizes EEG feature selection for BCI systems, improving classification accuracy.
problem Finding optimal EEG features for accurate classification in BCI systems.
method Genetic Algorithm (GA) for feature selection and classifier optimization.
result Katz fractal feature with LDA yields highest fitness value.
Optimal transport on SPD matrices improves domain adaptation for BCI.
problem Improving domain adaptation between two domains using SPD matrices.
method Modelled domain difference as diffeomorphism, used polar factorization theorem for optimal transport, applied weighted Riemannian mean.
result Demonstrated state-of-the-art performance on BCI data sets.
Paper proposes a new approach to improve EEG-based BCIs.
problem Improving learning performance for new subjects with minimal data.
method Aligns EEG trials in Euclidean space to make them more similar.
result Outperforms state-of-the-art approaches in offline and online experiments.
BCI system improves word selection efficiency using sequential best-arm identification.
problem Conventional non-adaptive BCI paradigms lead to a lengthy learning process.
method Casted as sequence of best-arm identification tasks in multi-armed bandits, using pre-trained LLMs and STTS algorithm.
result Substantial empirical improvement in word selection efficiency demonstrated.
Study evaluates features and classifiers for brain-computer interface tasks.
problem Improving accuracy in brain-computer interface communication.
method Examined six classical features and twelve classifiers across nine datasets.
result Energy in α and η bands, and Bayesian classifier with Gaussian assumption, outperform other methods.
EBMAL improves regression for driver drowsiness estimation from EEG.
problem Optimally selecting EEG samples for offline regression models.
method Enhanced batch-mode active learning (EBMAL) for regression.
result EBMAL achieves better regression performance for driver drowsiness estimation.
Proposes a deep multi-scale neural network for EEG signal representation learning.
problem Capturing multi-frequency properties in EEG signals for better brain-computer interface.
method A novel deep multi-scale neural network that discovers feature representations in multiple frequency/time ranges and extracts spatial relationships.
result Improved performance in various active/passive BCI datasets compared to state-of-the-art methods.
Deep learning system classifies phonological categories from EEG data.
problem Speech-related BCI for people with speaking disabilities.
method Hierarchical deep learning approach using CNN, LSTM, and autoencoder.
result Average accuracy of 77.9% across five binary classification tasks.
Developing a Brain-Computer Interface~(BCI) for seizure prediction can help epileptic patients have a better quality of life. However, there are many difficulties and challenges in developing such a system as a real-life support for patients. Because of the nonstationary nature of EEG signals, normal and seizure patter…
Framework evaluates deep learning EEG architectures on 100 datasets.
problem Evaluating different deep learning architectures for EEG signal decoding.
method Large-scale evaluation framework with 100 EEG datasets and multiple decoders.
result Comparison of three CNN architectures on different EEG tasks.
Deep Q-learning analyzes EEG for drowsiness during driving tests.
problem Estimating drowsiness during driving to improve safety.
method Adapting Q-learning to EEG data for drowsiness estimation.
result Trained model accurately tracks mind state variations in EEG data.
Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Despite its efficiency, a potential problem is that using pre-constructed sine-cosine waves as the required reference signals in…
A simple CNN architecture outperforms complex ones in P300 detection.
problem Efficiently detecting P300 component from EEG signals.
method Used a simple CNN architecture with a single depthwise separable 1D convolutional layer followed by a fully connected Sigmoid neuron.
result A single depthwise separable 1D convolutional layer with four filters achieved competitive performance.
Study uses LCRN to detect driver distraction from EEG signals.
problem Improving road safety by detecting driver distraction.
method Used a Long-term Recurrent Convolutional Network (LCRN) for EEG-based driver distraction detection.
result LCRN model outperformed state-of-the-art TSC models in detecting driver distraction.
Transfer learning improves EEG signal classification with less data.
problem Limited data for EEG signal classification.
method Transfer learning applied to deep learning models for EEG analysis.
result Outperformed top results in BCI competition IV by 33%.
A brain computer interface (BCI) is a system which provides direct communication between the mind of a person and the outside world by using only brain activity (EEG). The event-related potential (ERP)-based BCI problem consists of a binary pattern recognition. Linear discriminant analysis (LDA) is widely used to solve…
This paper presents a study in task-oriented approach to stroke rehabilitation by controlling a haptic device via near-infrared spectroscopy-based brain-computer interface (BCI). The task is to command the haptic device to move in opposing directions of leftward and rightward movement. Our study consists of data acquis…
Overcomplete representations and dictionary learning algorithms kept attracting a growing interest in the machine learning community. This paper addresses the emerging problem of comparing multivariate overcomplete representations. Despite a recurrent need to rely on a distance for learning or assessing multivariate ov…
Generative adversarial networks improve brain-computer interface performance with limited data.
problem Limited training samples in brain-computer interfaces.
method Conditional Deep Convolutional Generative Adversarial Networks (cDCGAN) for data augmentation.
result Generated artificial EEG data improves classification accuracy in brain-computer interface tasks.
We propose a generative model of a group EEG analysis, based on appropriate kernel assumptions on EEG data. We derive the variational inference update rule using various approximation techniques. The proposed model outperforms the current state-of-the-art algorithms in terms of common pattern extraction. The validity o…
A novel Bayesian model for inferring causal relations between two variables from observational data.
problem Inferring causal relations between two variables without intervention.
method Bayesian Causal Inference (BCI) using a generative Bayesian hierarchical model with Poisson lognormal distribution and Fourier diagonal Field covariance operators.
result BCI performs reliably with synthetic and real-world data, comparable to state-of-the-art algorithms.
DyEnsemble improves BCI accuracy by adapting to nonstationary neural signals.
problem Nonstationary neural signals in BCI cause decoding errors.
method Dynamic ensemble modeling that learns and combines diverse models online.
result DyEnsemble outperforms Kalman filters, especially with noisy signals.
Compensating changes between a subjects' training and testing session in Brain Computer Interfacing (BCI) is challenging but of great importance for a robust BCI operation. We show that such changes are very similar between subjects, thus can be reliably estimated using data from other users and utilized to construct a…
This paper compares traditional and new CSP methods for EEG classification in BCIs.
problem Improving signal-to-noise ratio in EEG signals for better BCI performance.
method Spatial filtering using traditional and new CSP methods with regularization.
result The traditional CSP method generally gives better results in binary classification.