Eye Blink Artifacts Research Articles

Eye-blink artifact removal from single channel EEG with k-means and SSA

In recent years, the usage of portable electroencephalogram (EEG) devices are becoming popular for both clinical and non-clinical applications. In order to provide more comfort to the subject and measure the EEG signals for several hours, these devices usually consists of fewer EEG channels or even with a single EEG channel. However, electrooculogram (EOG) signal, also known as eye-blink artifact, produced by involuntary movement of eyelids, always contaminate the EEG signals. Very few techniques are available to remove these artifacts from single channel EEG and most of these techniques modify the uncontaminated regions of the EEG signal. In this paper, we developed a new framework that combines unsupervised machine learning algorithm (k-means) and singular spectrum analysis (SSA) technique to remove eye blink artifact without modifying actual EEG signal. The novelty of the work lies in the extraction of the eye-blink artifact based on the time-domain features of the EEG signal and the unsupervised machine learning algorithm. The extracted eye-blink artifact is further processed by the SSA method and finally subtracted from the contaminated single channel EEG signal to obtain the corrected EEG signal. Results with synthetic and real EEG signals demonstrate the superiority of the proposed method over the existing methods. Moreover, the frequency based measures [the power spectrum ratio (Gamma ) and the mean absolute error (MAE)] also show that the proposed method does not modify the uncontaminated regions of the EEG signal while removing the eye-blink artifact.

A Flexible Multichannel EEG Artifact Identification Processor using Depthwise-Separable Convolutional Neural Networks

This article presents an energy-efficient and flexible multichannel Electroencephalogram (EEG) artifact identification network and its hardware using depthwise and separable convolutional neural networks. EEG signals are recordings of the brain activities. EEG recordings that are not originated from cerebral activities are termed artifacts . Our proposed model does not need expert knowledge for feature extraction or pre-processing of EEG data and has a very efficient architecture implementable on mobile devices. The proposed network can be reconfigured for any number of EEG channel and artifact classes. Experiments were done with the proposed model with the goal of maximizing the identification accuracy while minimizing the weight parameters and required number of operations. Our proposed network achieves 93.14% classification accuracy using an EEG dataset collected by 64-channel BioSemi ActiveTwo headsets, averaged across 17 patients and 10 artifact classes. Our hardware architecture is fully parameterized with number of input channels, filters, depth, and data bit-width. The number of processing engines (PE) in the proposed hardware can vary between 1 to 16, providing different latency, throughput, power, and energy efficiency measurements. We implement our custom hardware architecture on Xilinx FPGA (Artix-7), which on average consumes 1.4 to 4.7 mJ dynamic energy with different PE configurations. Energy consumption is further reduced by 16.7× implementing on application-specified integrated circuit at the post layout level in 65-nm CMOS technology. Our FPGA implementation is 1.7 × to 5.15 × higher in energy efficiency than some previous works. Moreover, our Application-Specified Integrated Circuit implementation is also 8.47 × to 25.79 × higher in energy efficiency compared to previous works. We also demonstrated that the proposed network is reconfigurable to detect artifacts from another EEG dataset collected in our lab by a 14-channel Emotiv EPOC+ headset and achieved 93.5% accuracy for eye blink artifact detection.

Design of an automatic hybrid system for removal of eye-blink artifacts from EEG recordings

Electroencephalography (EEG) signals are frequently used in several areas, such as diagnosis of diseases and BCI applications. It is important to remove noise sources for applications using EEG. This paper introduces a hybrid system to automatically remove eye-blink artifacts from the EEG by combining several methods, such as Independent Component Analysis (ICA), Kurtosis, K-means, Modified Z-Score (MZS) and Adaptive Noise Canceller (ANC). In the proposed method, all EEG recordings are first decomposed, and then the components related to the eye-blink artifacts are detected using Kurtosis and K-means. The MZS is used to detect regions of only eye-blink artifacts in the independent component. The classical Least Mean Squares (LMS) and Normalized LMS (NLMS) algorithms are used in the proposed ANC system. To comprehensively test the performance of the proposed method, simulated and real-world EEG datasets are used. The proposed system is compared with ANC systems having different reference inputs, Zeroing-ICA, and OD-ICA. In the simulated EEG dataset, the obtained overall RE, CC, SAR, SNR, Sensitivity, Specificity, and Area Under Curve (AUC) values are 0.1505, 0.9875, 1.3863, 2.7708, 100%, 93.8%, and 0.9380, respectively. In the real-world dataset, the obtained overall RE, CC, SAR, and SNR values are 0.0252, 0.9916, 2.8439, and 5.6944, respectively. The results suggest that the proposed method exhibits better performance concerning the given criteria. The proposed system does not require an external electrode for measuring eye-blink artifacts. This distinct advantage provided ensures a comfortable measurement for patients during long-term EEG recordings.

Unsupervised Eye Blink Artifact Detection From EEG With Gaussian Mixture Model.

Eye blink is one of the most common artifacts in electroencephalogram (EEG) and significantly affects the performance of the EEG related applications, such as epilepsy recognition, spike detection, encephalitis diagnosis, etc. To achieve an accurate and efficient eye blink detection, a novel unsupervised learning algorithm based on a hybrid thresholding followed with a Gaussian mixture model (GMM) is presented in this paper. The EEG signal is priliminarily screened by a cascaded thresholding method built on the distributions of signal amplitude, amplitude displacement, as well as the cross channel correlation. Then, the channel correlation of the two frontal electrodes (FP1, FP2), the fractal dimension, and the mean of amplitude difference between FP1 and FP2, are extracted to characterize the filtered EEGs. The GMM trained on these features is applied for the eye blink detection. The performance of the proposed algorithm is studied on two EEG datasets collected by the Temple University Hospital (TUH) and the Children's Hospital, Zhejiang University School of Medicine (CHZU), where the datasets are recorded from epilepsy and encephalitis patients, and contain a lot of eye blink artifacts. Experimental results show that the proposed algorithm can achieve the highest detection precision and F1 score over the state-of-the-art methods.

Automatic Eyeblink Artifact Removal From EEG Signal Using Wavelet Transform With Heuristically Optimized Threshold.

This paper proposes an automatic eyeblink artifacts removal method from corrupted-EEG signals using discrete wavelet transform (DWT) and meta-heuristically optimized threshold. The novel idea of thresholding approximation-coefficients (ACs) instead of detail-coefficients (DCs) of DWT of EEG in a backward manner is proposed for the first time for the removal of eyeblink artifacts. EEG is very sensitive and easily gets affected by eyeblink artifacts. First, the eyeblink corrupted EEG signals are identified using support vector machine (SVM) as a classifier. Then the corrupted EEG signal is decomposed using DWT up to the sixth level. Both the mother wavelet and the level of decomposition are selected using appropriate techniques. Then the ACs are thresholded in backward manner using the optimum threshold values followed by inverse DWT operation to reconstruct the original EEG signal. The AC at level 6 is thresholded and is used in IDWT with DC to get back the AC at level 5. Likewise, the backward thresholding of the ACs followed by IDWT is continued till the artifact free EEG signal is reconstructed at level 1. The optimum values of the thresholds of the ACs at different levels are optimized using two meta-heuristic algorithms, particle swarm optimization (PSO) and grey wolf optimization (GWO) for comparison. The results reveal that the proposed methodology is superior to the recently reported methods in terms of average correlation coefficient (CC) which states that the proposed method is better in terms of the quality of reconstruction in addition to being fully automatic.

VME-DWT: An Efficient Algorithm for Detection and Elimination of Eye Blink From Short Segments of Single EEG Channel.

Recent advances in development of low-cost single-channel electroencephalography (EEG) headbands have opened new possibilities for applications in health monitoring and brain-computer interface (BCI) systems. These recorded EEG signals, however, are often contaminated by eye blink artifacts that can yield the fallacious interpretation of the brain activity. This paper proposes an efficient algorithm, VME-DWT, to remove eye blinks in a short segment of the single EEG channel. The proposed algorithm: (a) locates eye blink intervals using Variational Mode Extraction (VME) and (b) filters only contaminated EEG interval using an automatic Discrete Wavelet Transform (DWT) algorithm. The performance of VME-DWT is compared with an automatic Variational Mode Decomposition (AVMD) and a DWT-based algorithms, proposed for suppressing eye blinks in a short segment of the single EEG channel. The VME-DWT detects and filters 95% of the eye blinks from the contaminated EEG signals with SNR ranging from -8 to +3 dB. The VME-DWT shows superiority to the AVMD and DWT with the higher mean value of correlation coefficient (0.92 vs. 0.83, 0.58) and lower mean value of RRMSE (0.42 vs. 0.59, 0.87). The VME-DWT can be a suitable algorithm for removal of eye blinks in low-cost single-channel EEG systems as it is: (a) computationally-efficient, the contaminated EEG signal is filtered in millisecond time resolution, (b) automatic, no human intervention is required, (c) low-invasive, EEG intervals without contamination remained unaltered, and (d) low-complexity, without need to the artifact reference.

Eye Blink Artifact Detection With Novel Optimized Multi-Dimensional Electroencephalogram Features.

Accurate eye blink artifact detection is essential for electroencephalogram (EEG) analysis and auxiliary analysis of nervous system diseases, especially in the presence of the frontal epileptiform discharges. In this paper, we develop a novel eye blink artifact detection algorithm based on optimally selected multi-dimensional EEG features. Specific efforts have been paid to filtering the frontal epileptiform discharges, where an unsupervised learning exploiting the EEG signal physiological characteristics and smooth nonlinear energy operator (SNEO) based on the K-means clustering has been firstly proposed. Multiple statistical EEG features derived from the frontal electrodes and other electrodes are then extracted to characterize eye blink artifacts. Discriminative feature selection scheme based on the variance filtering and Relief algorithms has been respectively studied, and the average correlation coefficient (ACC) is applied for feature optimization evaluation. The eye blink artifact detection is finally achieved based on the support vector machine (SVM) trained on the optimized EEG features. The effectiveness of the proposed algorithm is demonstrated by experiments carried out on the EEG database of 11 subjects recorded from the Children's Hospital, Zhejiang University School of Medicine (CHZU). Comparisons to several state-of-the-art (SOTA) eye blink artifact detection methods are also presented.

Automated blink artefact removal from EEG using variational mode decomposition and singular spectrum analysis

Blink artefacts are the major source of noise while acquiring electroencephalogram (EEG) data for analysis. To design an efficient method for blink artefact removal is essential for conducting any sort of analysis using EEG. In this paper, a novel automated eye blink artefact removal method based on variational mode decomposition (VMD) and singular spectrum analysis (SSA) is presented. The noisy EEG signals are first separated into uncorrelated components using canonical correlation analysis (CCA) and then variational mode decomposition is performed for multiresolution analysis. The decomposed components (modes) are assessed through their singular values for finding the distribution of noise using singular spectrum analysis. Phase space reconstruction (PSR) is also used to differentiate the clean modes and noisy modes. The applicability of the proposed approach is examined through statistical measures like signal to noise ratio (SNR), correlation coefficient and root mean square error (RMSE). The results indicate the efficacy of the approach in artefact removal without manual intervention as compared to the state-of-the-art technologies. The proposed method automatically identified and removed the noisy fraction of signal, yielding the requisite neural information without any manual intervention.

Novel eye‐blink artefact detection algorithm from raw EEG signals using FCN‐based semantic segmentation method

Electroencephalography (EEG) signal artefacts cause some problems in processing and analysis of EEG signals. There are several options in the literature to identify artefacts in signal areas. However, high accuracy level in artefact detection was not achieved with these methods. New methods are needed to increase the level of accuracy. Semantic segmentation algorithms, which are widely used in image processing, were used for the first time in this study to detect eye-blink artefacts in EEG signals. In the proposed method, EEG recordings obtained from four channels were divided into 10-s segments. These segments were converted into images in 256 × 256 resolution and were labelled as eye-blink, not-blink and background. The algorithm was trained with these labelled images. The trained algorithm was tested with images containing 1630 eye-blink and not-blink signal segments obtained from single-channel and multi-channel EEG signals. Classification accuracy of the algorithm was 94.4%. The proposed method successfully detected eye-blink artefacts in simultaneous multi-channel signal images.

Automatic EEG eyeblink artefact identification and removal technique using independent component analysis in combination with support vector machines and denoising autoencoder

This study proposes a novel combination of independent component analysis (ICA) in conjunction with support vector machine (SVM) and denoising autoencoder (DA), for the first time, for removal of eyeblink artefacts from the corrupted electroencephalography (EEG). At first the eyeblink corrupted EEG signals are decomposed into independent components (ICs) using ICA, the corrupted-ICs are then identified using SVM as a classifier. From the corrupted-ICs, the artefacted segment is identified with a second SVM classifier and corrected by the pre-trained DA. Finally, inverse-ICA operation is applied on the remaining ICs and the corrected ICs to obtain the artefact-free EEG signal. The proposed methodology modifies only the portion corrupted with artefacts, and does not alter the uncorrupted part, thereby preserving the neural information in the original EEG. The proposed methodology was implemented to remove eyeblinks from the EEG data collected from the publicly available EEGLab data set. The results reveal that the proposed methodology is superior to the other recently reported methods in terms of the mutual information and average correlation coefficient. Further, the proposed method is automatic and does not require any intervention of the operator, whereas the other methods require intervention of the user.

Electroencephalogram for epileptic seizure detection using stacked bidirectional LSTM_GAP neural network

Epilepsy seizure classification has been an ongoing research from decades. Auto seizure detection methods are developed by many researchers. Year by year new methods and new approaches are introduced by researchers to improve the performance of these automatic detection methods. Electroencephalogram (EEG) is the most widely used tool for detecting seizure as it has high resolution which makes it more feasible for analysis. In this paper we are introducing an approach based on stacked bidirectional long short term memory with global average pooling (LSTM_GAP) neural network for detecting epileptic seizure events. We use open access EEG dataset available in Bonn University Germany for the experiment. The model is evaluated based on three performance metrics, specificity, sensitivity and accuracy. It resulted with outstanding performance with 100% accuracy, sensitivity and specificity in detecting epileptic seizure events which is the highest accuracy among all the techniques available in state-of-the art literature. Another advantage of LSTM_GAP model lies in its robustness in noise. In real, the EEG recorded in hospital laboratories consists of artefacts generated from eye blink and muscle activities of the patients. When our model will be put to practical use by the neurologists, the EEG recordings consisting of artefacts will be given as input to the model for detecting seizure events. Hence we need to develop a model which is robust against noise and which can provide good results even when the EEG data consisting artefacts is given as input. Hence we extended our experiment to check the performance of the LSTM_GAP model by adding eye blink artefacts and muscle artefacts to the input EEG data. The model was able to give superior results even after adding artefacts. We were able to achieve 97.67% sensitivity, 98.83% specificity and 97.65% accuracy. Thus LSTM_GAP model gives superior results for the EEG with and without noise compared to other methods in the literature.

Extraction of Nystagmus Patterns from Eye-Tracker Data with Convolutional Sparse Coding.

The analysis of the Nystagmus waveforms from eye-tracking records is crucial for the clinical interpretation of this pathological movement. A major issue to automatize this analysis is the presence of natural eye movements and eye blink artefacts that are mixed with the signal of interest. We propose a method based on Convolutional Dictionary Learning that is able to automatically highlight the Nystagmus waveforms, separating the natural motion from the pathological movements. We show on simulated signals that our method can indeed improve the pattern recovery rate and provide clinical examples to illustrate how this algorithm performs.

High-resolution wide-field OCT angiography with a self-navigation method to correct microsaccades and blinks.

In this study, we demonstrate a novel self-navigated motion correction method that suppresses eye motion and blinking artifacts on wide-field optical coherence tomographic angiography (OCTA) without requiring any hardware modification. Highly efficient GPU-based, real-time OCTA image acquisition and processing software was developed to detect eye motion artifacts. The algorithm includes an instantaneous motion index that evaluates the strength of motion artifact on en face OCTA images. Areas with suprathreshold motion and eye blinking artifacts are automatically rescanned in real-time. Both healthy eyes and eyes with diabetic retinopathy were imaged, and the self-navigated motion correction performance was demonstrated.

Removal of eye-blink artifacts from EEG signal

Electroencephalography (EEG) is well known method of recording electrical brain activity with electrodes placed along the scalp. One of the challenging tasks in this field is the removal of electrical signals that are not related to brain activity.In this paper, an algorithm for the removal of the EEG signals corresponding to the eye blink artifacts is presented. The presented algorithm is based on ADJUST artifact removing tool, which uses independent component analysis (ICA) for signal decomposition. For every signal component returned by the ICA algorithm, temporal-spatial features are calculated, upon which every independent component is classified as artifact or non-artifact, and removed accordingly.

Power Aware Hessian Multi-set Canonical Correlations Based Algorithm for Wireless Eeg Sensor Networks

The miniaturized Electroencephalography (EEG) modules monitors the EEG signals over a smaller area, however, thus modules suffer from poor spatial coverage. The wireless EEG sensor network (WESN) provides an improved spatial coverage with multiple EEG modules, which communicated through a shorter distances. Further, the miniaturized EEG modules tend to create a high energy cost in wireless communication. This paper aims to remove the eye blink artifacts from the WESN EEG channels. The exploitation of correlation among the signals from various EEG modules is taken into consideration for resolving the problem of artifact removal in stringent bandwidth constraints. In this paper, Hessian multi-set canonical correlations based algorithm is used that computes optimal linear combination of the EEG signal between the local EEG channels and other modules. This correlation makes the EEG signal to be correlated at a maximum rate. The use of Hessian multi-set canonical correlations to remove the eye blink artifacts in a distributed realization reduces the transmission cost in the network. The proposed method has been validated against the real and synthetic EEG datasets, collected from the WESN shortest distance communication. The removal of redundant data from the wireless nodes, the algorithm attains an improved performance to remove the eye blink artifact with reduced power consumption in the wireless networks.

Improved energy efficient design in software defined wireless electroencephalography sensor networks (WESN) using distributed architecture to remove artifact

Software Defined Networking (SDN) has focused enormous attractiveness in changing conventional network by means of offering flexible and dynamic network management. It has drawn important concentration of the researchers from together academia and industries. Mainly, integrating SDN in Wireless Body Area Network (WBAN) applications specifies capable results in terms of handling with the issues like traffic management, security, energy efficiency etc. Recent improvements in miniaturization and energy efficient physiological sensor designs in SDN based Wireless Body Area Networks (WBANs) paved the way for health monitoring systems for collection and processing the real-time physiological data. The collection of signals from different sensor allows reliable diagnosis in heterogeneous than in homogeneous WBANs. Inspired by the evolutions of heterogeneous WBANs, a study on Wireless Electroencephalography Sensor Networks (WESNs) is carried out under distributed signal processing. The distributed WESNs are designed under two different hierarchy i.e. Hierarchical Fully-Connected Topology (HFCT) and Ad-Hoc Nearest-Neighbor Topology (ANNT) to improve the energy-efficiency using distributed Multi-channel Weighted Weiner Filter design (MW2F). Here, each module transmits linear combination of local channels with other modules. The power efficiency is improved in MW2F signal processing algorithm by avoiding centralization of EEG data. A case study is carried out to test the reduced energy consumption after the removal of eye blink artifacts and it is tested with centralized counterparts. The MW2F is evaluated in both topologies against centralized environments and significant reduction of eye blink artifacts improves the energy efficiency in HFCT than other topologies.

A Robust System for Detection of Artifacts from EEG Brain Recordings

Epilepsy is a chronic disorder and has the propensity of two or more brain. Analysis of EEG is the primary method for the diagnosis of epilepsy. Contamination of eye movement and blink artifacts presence in EEG data becomes more complicated to the doctors during the diagnosis period. Earlier detection of these artifacts gives a significant advantage of refining the Epilepsy identification process. In this regard, a robust subspace detection method is applied to detect the target signal in noise with possible interference-artifacts, then a dimensionality reduction model, with the combination of fast Independent and Robust Principal Component Analysis (FICA and rPCA) is implemented for identification of artifacts from EEG brain recordings. To perform this the proposed detection method uses synthetic data and artifact contaminated data. The extracted target subspace signal is considered as the input for rPCA and FICA. The ROC analysis is developed as a standard methodology to quantify the detectors' ability to correctly distinguish the target of interest (artifacts) from the background noise in the system.

Low Complexity Automatic Stationary Wavelet Transform for Elimination of Eye Blinks from EEG.

The electroencephalogram signal (EEG) often suffers from various artifacts and noises that have physiological and non-physiological origins. Among these artifacts, eye blink, due to its amplitude is considered to have the most influence on EEG analysis. In this paper, a low complexity approach based on Stationary Wavelet Transform (SWT) and skewness is proposed to remove eye blink artifacts from EEG signals. The proposed method is compared against Automatic Wavelet Independent Components Analysis (AWICA) and Enhanced AWICA. Normalized Root Mean Square Error (NRMSE), Peak Signal-to-Noise Ratio (PSNR), and correlation coefficient () between filtered and pure EEG signals are utilized to quantify artifact removal performance. The proposed approach shows smaller NRMSE, larger PSNR, and larger correlation coefficient values compared to the other methods. Furthermore, the speed of execution of the proposed method is considerably faster than other methods, which makes it more suitable for real-time processing.

FastEMD–CCA algorithm for unsupervised and fast removal of eyeblink artifacts from electroencephalogram

Online detection and removal of eye blink (EB) artifacts from electroencephalogram (EEG) would be very useful in medical diagnosis and brain computer interface (BCI). In this work, approaches that combine unsupervised eyeblink artifact detection with empirical mode decomposition (EMD), and canonical correlation analysis (CCA), are proposed to automatically identify eyeblink artifacts and remove them in an online manner. First eyeblink artifact regions are automatically identified and an eyeblink artifact template is extracted via EMD, which incorporates an alternate interpolation technique, the Akima spline interpolation. The removal of eyeblink artifact components relies on the elimination of EEG canonical components obtained through CCA, based on cross correlation with the extracted eyeblink artifact template. The proposed algorithm is evaluated and analyzed with respect to its ability in removing eyeblink artifacts and retaining neural information of the EEG signals. Analysis proved that the proposed algorithm, FastEMD–CCA, is efficacious in eyeblink artifact removal with an average accuracy, sensitivity, specificity and error rate of 97.9%, 97.65%, 99.22% and 2.1% respectively. The algorithm is able to clean and remove eyeblink artifacts from a 14-channel EEG of length 1 s, at an average time of 63 ms. This makes it a feasible solution for applications requiring online removal of eyeblink artifacts.

Detection of Human Brain Activities in a Normal Human being

Detection of artifacts produced in EEG data by eye blinks is a very common problem in EEG research. In this paper we address the detection of eye blink artifacts in a motor imagery (MI) EEG data. Artifacts are nothing but some kind of disturbances present in the brain signal whose origin is not the brain itself. Detection of unwanted artifacts plays a crucial role to acquire artifact free and clean brain EEG signals to analyze and detect brain activities. There are generally two ways of generation of artifacts. From a recorded signal most common and important artifacts in the form of eye blinks are recognized and encapsulated. In this paper a new software tool named BRAINSTORM is introduced for the detection of eye blink artifacts.