Noisy EEG Data Research Articles

Improving EEG Forward Modeling Using High-Resolution Five-Layer BEM-FMM Head Models: Effect on Source Reconstruction Accuracy

Electroencephalographic (EEG) source localization is a fundamental tool for clinical diagnoses and brain-computer interfaces. We investigate the impact of model complexity on reconstruction accuracy by comparing the widely used three-layer boundary element method (BEM) as an inverse method against a five-layer BEM accelerated by the fast multipole method (BEM-FMM) and coupled with adaptive mesh refinement (AMR) as forward solver. Modern BEM-FMM with AMR can solve high-resolution multi-tissue models efficiently and accurately. We generated noiseless 256-channel EEG data from 15 subjects in the Connectome Young Adult dataset, using four anatomically relevant dipole positions, three conductivity sets, and two head segmentations; we mapped localization errors across the entire grey matter from 4,000 dipole positions. The average location error among our four selected dipoles is ∼5mm (±2mm) with an orientation error of ∼12∘ (±7∘). The average source localization error across the entire grey matter is ∼9mm (±4mm), with a tendency for smaller errors on the occipital lobe. Our findings indicate that while three-layer models are robust under noiseless conditions, substantial localization errors (10–20mm) are common. Therefore, models of five or more layers may be needed for accurate source reconstruction in critical applications involving noisy EEG data.

Multi-Resolution Wavelet Fractal Analysis and Subtask Training for Enhancing Few-Shot Noisy Brainwave Recognition.

The integration of healthcare monitoring with Internet of Things (IoT) networks radically transforms the management and monitoring of human well-being. Portable and lightweight electroencephalography (EEG) systems with fewer electrodes have improved convenience and flexibility while retaining adequate accuracy. However, challenges emerge when dealing with real-time EEG data from IoT devices due to the presence of noisy samples, which impedes improvements in brainwave detection accuracy. Moreover, high inter-subject variability and substantial variability in EEG signals present difficulties for conventional data augmentation and subtask learning techniques, leading to poor generalizability. To address these issues, we present a novel framework for enhancing EEG-based recognition through multi-resolution data analysis, capturing features at different scales using wavelet fractals. The original data can be expanded many times after continuous wavelet transform (CWT) and recombination, alleviating insufficient training samples. In the transfer stage of deep learning (DL) models, we adopt a subtask learning approach to train the recognition model to generalize efficiently. This incorporates wavelets at various scales instead of exclusively considering average prediction performance across scales and paradigms. Through extensive experiments, we demonstrate that our proposed DL-based method excels at extracting features from small-scale and noisy EEG data. This significantly improves healthcare monitoring performance by mitigating the impact of noise introduced by the external environment.

Multi-origins of pathological theta oscillation from neuron to network inferred by a combined data and model study with cubature Kalman filter

The brain rhythm is strongly associated with the brain function. Alzheimer's disease (AD) is characterized reflected by the brain rhythm switching from the alpha band (9–12 Hz) to the theta band (4–8 Hz), accompanied with the loss of brain function. However, extracting the implicating intrinsic characteristic variations of the brain network by utilizing the Electroencephalogram (EEG) information is challenging. Kaman observer, serving as an effective Bayesian technique, can provide a visualization service for probing the intrinsic characteristics underlying the pathological theta oscillations. This work first establishes an excitation-inhibitory neural network model and explores the role of the fraction of the inhibitory neurons and inhibitory synapses in the pathological theta oscillation. The results indicate that the reduced inhibitory neuronal proportion and attenuated inhibitory synaptic weight are the main neural bases of the frequency reduction of neural oscillation. Then, we further explore the intrinsic spiking characteristic by considering spike frequency adaptation (SFA) to the inhibitory neurons. The results show that the SFA reduces the firing rate of neurons, which facilitates the theta rhythm. The enhancement of SFA current by increasing the time constant of its gating variable can further decrease the theta frequency from 7 Hz to 4 Hz. Furthermore, for this high-dimensional nonlinear excitation-inhibitory neural network model, cubature Kalman filter (CKF) is employed to estimate the above potential variations from the EEG data. The observation results show that the attenuated trends of the inhibitory neuronal proportion and the decreased inhibitory SFA current result in the descending brain rhythm. Finally, the theoretical simulation is deduced by utilizing the mean field theory for simplifying high-dimensional model to verify the simulation results. The theoretical variations of inhibitory parameters and adaptation gating variable are consistent with the simulation results. In summary, we investigate the multi-origin factors related to inhibitory neuronal intrinsic characteristics from forward model simulation and inverse EEG estimation process. And we further verify the simulation and data-driven results by theoretical derivation. This work enhances the understanding of the systematic function of inhibitory intrinsic characteristics on pathological theta oscillation and provides an effective method to decode the dynamics underlying neural activities.

Deep Learning Framework for Modeling Cognitive Load From Small and Noisy EEG Data

Deep Learning Framework for Modeling Cognitive Load From Small and Noisy EEG Data

EEG alpha and theta time-frequency structure during a written mathematical task.

Since the first electroencephalogram (EEG) was obtained, there have been many possibilities to use it as a tool to access brain cognitive dynamics. Mathematical (Math) problem solving is one of the most important cortical processes, but it is still far from being well understood. EEG is an inexpensive and simple indirect measure of brain operation, but only recently has low-cost equipment (mobile EEG) allowed sophisticated analyses in non-clinical settings. The main purpose of this work is to study EEG activation during a Math task in a realistic environment, using mobile EEG. A matching pursuit (MP)-based signal analysis technique was employed, since MP properties render it a priori suitable to study induced EEG activity over long time sequences, when it is not tightly locked to a given stimulus. The study sample comprised sixty healthy volunteers. Unlike the majority of previous studies, subjects were studied in a sitting position with their eyes open. They completed a written Math task outside the EEG lab, wearing a mobile EEG device (EPOC+). Theta [4 Hz-7.5 Hz], alpha (7.5 Hz-13 Hz] and 0.5 Hz micro-bands in the [0.5 Hz-20 Hz] range were studied with a low-density stochastic MP dictionary. Over 1-min windows, ongoing EEG alpha and theta activity was decomposed into numerous MP atoms with median duration around 3s, similar to the duration of induced, time-locked activity obtained with event-related (des)synchronization (ERS/ERD) studies. Relative to Rest, there was lower right-side and posterior MP alpha atom/min during Math, whereas MP theta atom/min was significantly higher on anteriorly located electrodes, especially on the left side. MP alpha findings were particularly significant on a narrow range around 10 Hz-10.5 Hz, consistent with FFT alpha peak findings from ERS/ERD studies. With a streamlined protocol, these results replicate previous findings of EEG alpha and theta activation obtained during Math tasks with different signal analysis techniques and in different time frames. The efficient application to real-world, noisy EEG data with a low-resolution stochastic MP dictionary shows that this technique is very encouraging. These results provide support for studies of mathematical cognition with mobile EEG and matching pursuit.

Sparse Bayesian Learning for End-to-End EEG Decoding.

Decoding brain activity from non-invasive electroencephalography (EEG) is crucial for brain-computer interfaces (BCIs) and the study of brain disorders. Notably, end-to-end EEG decoding has gained widespread popularity in recent years owing to the remarkable advances in deep learning research. However, many EEG studies suffer from limited sample sizes, making it difficult for existing deep learning models to effectively generalize to highly noisy EEG data. To address this fundamental limitation, this paper proposes a novel end-to-end EEG decoding algorithm that utilizes a low-rank weight matrix to encode both spatio-temporal filters and the classifier, all optimized under a principled sparse Bayesian learning (SBL) framework. Importantly, this SBL framework also enables us to learn hyperparameters that optimally penalize the model in a Bayesian fashion. The proposed decoding algorithm is systematically benchmarked on five motor imagery BCI EEG datasets ( N=192) and an emotion recognition EEG dataset ( N=45), in comparison with several contemporary algorithms, including end-to-end deep-learning-based EEG decoding algorithms. The classification results demonstrate that our algorithm significantly outperforms the competing algorithms while yielding neurophysiologically meaningful spatio-temporal patterns. Our algorithm therefore advances the state-of-the-art by providing a novel EEG-tailored machine learning tool for decoding brain activity.Code is available at https://github.com/EEGdecoding/Code-SBLEST.

WRA-MTSI: A Robust Extended Source Imaging Algorithm Based on Multi-Trial EEG.

Reconstructing brain activities from electroencephalography (EEG) signals is crucial for studying brain functions and their abnormalities. However, since EEG signals are nonstationary and vulnerable to noise, brain activities reconstructed from single-trial EEG data are often unstable, and significant variability may occur across different EEG trials even for the same cognitive task. In an effort to leverage the shared information across the EEG data of multiple trials, this paper proposes a multi-trial EEG source imaging method based on Wasserstein regularization, termed WRA-MTSI. In WRA-MTSI, Wasserstein regularization is employed to perform multi-trial source distribution similarity learning, and the structured sparsity constraint is enforced to enable accurate estimation of the source extents, locations and time series. The resulting optimization problem is solved by a computationally efficient algorithm based on the alternating direction method of multipliers (ADMM). Both numerical simulations and real EEG data analysis demonstrate that WRA-MTSI outperforms existing single-trial ESI methods (e.g., wMNE, LORETA, SISSY, and SBL) in mitigating the influence of artifacts in EEG data. Moreover, WRA-MTSI yields superior performance compared to other state-of-the-art multi-trial ESI methods (e.g., group lasso, the dirty model, and MTW) in estimating source extents. WRA-MTSI may serve as an effective robust EEG source imaging method in the presence of multi-trial noisy EEG data.

An approach to extracting graph kernel features from functional brain networks and its applications to the analysis of the noisy EEG signals

Since electroencephalographic data (EEG) usually carries a certain amount of noise, it is important to study a method that can propose an effective noise-adaptive feature from EEG signals and can be effectively used for problem-solving. Firstly, to address the problem that the application of noisy EEG in problem-solving based on functional brain networks is significantly worse, we study the extraction of global topological features, called graph kernel features, from functional brain networks with better noise immunity, and propose a method for extracting graph kernel features from networks based on neighborhood subgraph pairwise distances. Secondly, to address the problem of huge data of graph kernel features proposed from functional brain networks, dimensionality reduction of graph kernel features based on kernel principal component analysis is proposed. Finally, to verify that the graph kernel features can not only be effectively used for problem-solving, but also have good noise immunity, the research on fatigue driving and emotion recognition based on the graph kernel feature extraction side of the functional brain network is carried out, and the corresponding fatigue driving state recognition model and emotion state recognition model is constructed. By testing the simulated EEG noisy data on the real fatigue driving dataset and the publicly available emotion recognition dataset Seed with different methods, it is verified that the graph kernel features are effective in classifying the noisy EEG data and have a good generalization ability for different noises.

Towards fully automated detection of epileptic disorders: a novel CNSVM approach with Clough-Tocher interpolation.

Epilepsy is a neurological disorder requiring specialists to scrutinize medical data at diagnosis. Diagnosis stage is both time consuming and challenging, requiring expertise in detection of epileptic seizures from multi-channel noisy EEG data. It is crucial that EEG signals be automatically classified in order to help experts detect epileptic seizures correctly. In this study, a novel hybrid deep learning and SVM technique is employed on a restructured EEG data. EEG signals were transformed into a two-dimensional image sequence. Clough-Tocher technique is employed for interpolation of the values obtained from the electrodes placed on the skull during EEG measurements in order to estimate the signal strength in the missing places over the picture. After theparameters in the deep learning architecture were optimized on the validation data, it is observed that the proposed technique's performance for classifying epilepsy moments over EEG signals demonstrated unmatched performance. This study fills a gap in the literature in terms of demonstrating a superior performance in automatic detection of epileptic episodes on a benchmark EEG data set and takes a substantial leap towards fully automated detection of epileptic disorders.

Mimicking Short-Term Memory in Shape-Reconstruction Task Using an EEG-Induced Type-2 Fuzzy Deep Brain Learning Network

The paper attempts to model short-term memory (STM) for shape-reconstruction tasks by employing a 4-stage deep brain leaning network (DBLN), where the first two stages are built with Hebbian learning and the last two stages with Type-2 Fuzzy logic. The model is trained stage-wise independently with visual stimulus of the object-geometry as the input of the first stage, EEG acquired from different cortical regions as input and output of respective intermediate stages, and recalled object-geometry as the output of the last stage. Two error feedback loops are employed to train the proposed DBLN. The inner loop adapts the weights of the STM based on a measure of error in model-predicted response with respect to the object-shape recalled by the subject. The outer loop adapts the weights of the iconic (visual) memory based on a measure of error of the model predicted response with respect to the desired object-shape. In the test phase, the DBLN model reproduces the recalled object shape from the given input object geometry. The motivation of the paper is to test the consistency in STM encoding (in terms of similarity in network weights) for repeated visual stimulation with the same geometric object. Experiments undertaken on healthy subjects, yield high similarity in network weights, whereas patients with pre-frontal lobe Amnesia yield significant discrepancy in the trained weights for any two trials with the same training object. This justifies the importance of the proposed DBLN model in automated diagnosis of patients with learning difficulty. The novelty of the paper lies in the overall design of the DBLN model with special emphasis to the last two stages of the network, built with vertical slice based type-2 fuzzy logic, to handle uncertainty in function approximation (with noisy EEG data). The proposed technique outperforms the state-of-the-art functional mapping algorithms with respect to the (pre-defined outer loop) error metric, computational complexity and runtime.

Robust detection of epileptic seizures based on L1-penalized robust regression of EEG signals

Epilepsy is the second common brain disorder affecting 70 million people worldwide. Electroencephalogram (EEG) has been widely used for the diagnosis of epileptic seizures. However, most of the existing EEG-based seizure detection methods cannot maintain robust performance in real life conditions. This is where the EEG data are corrupted with different sources of noise and artifacts. This study presents a robust seizure detection system that works efficiently under the real life conditions as well as the ideal conditions. A feature learning method based on L1-penalized robust regression is developed and applied to the EEG spectra to recognize the most prominent features pertinent to epileptic seizures. The extracted features are then fed into the random forest classifier for seizure detection. Results on a public benchmark dataset show that the performance of this seizure detection system is superior to prior work. It first achieves seizure detection rates of 100.00% sensitivity, 100.00% specificity, and 100.00% classification accuracy under the ideal conditions. The proposed method is also proven to be robust in the presence of white noise and EEG artifacts mainly those arising from muscle activities and eyes-blinking. It is found to achieve seizure detection accuracies in the range of 90.00–100.00% when applied to noisy EEG data corrupted with high noise levels. To the best of our knowledge, there exists no work in the literature that detects seizures under these conditions.

Using minimal number of electrodes for emotion detection using brain signals produced from a new elicitation technique

Emotion is an important aspect in the interaction between humans. There is a great interest for detecting emotions automatically. Current approaches for emotion detection using EEG are not practical for real-life situations because researchers ask participants to reduce any motion and facial muscle movement, reject noisy EEG data and rely on large number of electrodes. In this paper, we propose an approach that analyses highly contaminated brain signals. We then extract relevant features for the emotion detection task based on neuroscience findings. We reached an average accuracy of 51%, 53%, 58% and 61% for joy, anger, fear and sadness, respectively. We are also applying our approach on fewer number of electrodes that ranges from 4 to 25 electrodes and we reached an average classification accuracy of 33% for joy emotion, 38% for anger, 33% for fear and 37.5% for sadness using 4 or 6 electrodes only.

Identification of ERD using Fuzzy Inference Systems for Brain-Computer Interface

A Brain-Computer Interface uses measurements of scalp electric potential (electroencephalography - EEG) reflecting brain activity, to communicate with external devices. Recent developments in electronics and computer sciences have enabled applications that may help users with disabilities and also to develop new types of Human Machine Interfaces. By producing modifications in their brain potential activity, the users can perform control of different devices. In order to perform actions, this EEG signals must be processed with proper algorithms. Our approach is based on a fuzzy inference system used to produce sharp control states from noisy EEG data.

Identification of ERD using Fuzzy Inference Systems for Brain-Computer Interface

A Brain-Computer Interface uses measurements of scalp electric potential (electroencephalography - EEG) reflecting brain activity, to communicate with external devices. Recent developments in electronics and computer sciences have enabled applications that may help users with disabilities and also to develop new types of Human Machine Interfaces. By producing modifications in their brain potential activity, the users can perform control of different devices. In order to perform actions, this EEG signals must be processed with proper algorithms. Our approach is based on a fuzzy inference system used to produce sharp control states from noisy EEG data.