Electromyogram (EMG) Removal by Adding Sources of EMG (ERASE)—A Novel ICA-Based Algorithm for Removing Myoelectric Artifacts From EEG

Li, Yongcheng; Wang, Po T.; Vaidya, Mukta; Flint, Robert D.; Liu, Charles Y.; Slutzky, Marc W.; An, Hongyu

doi:10.3389/fnins.2020.597941

Cited by 17 publications

(12 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the EEG signals and the electrooculogram (EOG) signals and electromyogram (EMG) signals overlap in the frequency band, only two filterings cannot completely remove the interference of the EOG and EMG. In this study, fast independent component analysis (Fast ICA) [ 29 ] was applied to remove EOG and EMG artifacts [ 30 ]. The Fast ICA algorithm is derived from the cocktail party problem.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Depression Diagnosis Method Based on the Hybrid Neural Network and Attention Mechanism

Wang

Liu

et al. 2022

Brain Sciences

View full text Add to dashboard Cite

Depression is a common but easily misdiagnosed disease when using a self-assessment scale. Electroencephalograms (EEGs) provide an important reference and objective basis for the identification and diagnosis of depression. In order to improve the accuracy of the diagnosis of depression by using mainstream algorithms, a high-performance hybrid neural network depression detection method is proposed in this paper combined with deep learning technology. Firstly, a concatenating one-dimensional convolutional neural network (1D-CNN) and gated recurrent unit (GRU) are employed to extract the local features and to determine the global features of the EEG signal. Secondly, the attention mechanism is introduced to form the hybrid neural network. The attention mechanism assigns different weights to the multi-dimensional features extracted by the network, so as to screen out more representative features, which can reduce the computational complexity of the network and save the training time of the model while ensuring high precision. Moreover, dropout is applied to accelerate network training and address the over-fitting problem. Experiments reveal that the 1D-CNN-GRU-ATTN model has more effectiveness and a better generalization ability compared with traditional algorithms. The accuracy of the proposed method in this paper reaches 99.33% in a public dataset and 97.98% in a private dataset, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Figure 2 shows the flow of EEG signal preprocessing. [29] was applied to remove EOG and EMG artifacts [30]. The Fast ICA algorithm is derived from the cocktail party problem.…”

mentioning

confidence: 99%

A Depression Diagnosis Method Based on the Hybrid Neural Network and Attention Mechanism

Wang

Liu

et al. 2022

Brain Sciences

View full text Add to dashboard Cite

show abstract

“…However, it requires additional reference signals from reference electrodes channels or additional biological monitoring equipment. Li et al [ 17 ] adopted additional channels of real EMG from neck and head muscles as input and realized the significant separation of EEG and EMG artifacts without losing the underlying EEG features. Mannan et al [ 18 ] realized the simultaneous collection of EEG and EOG signals by adding the channels of EOG electrodes and combined independent component analysis (ICA), regression, and high-order statistics to identify and eliminate artifactual activities from EEG data.…”

Section: Literaturementioning

confidence: 99%

Intelligent Method for Real-Time Portable EEG Artifact Annotation in Semiconstrained Environment Based on Computer Vision

Qian

Wang²,

Wang

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

As a convenient device for observing neural activity in the natural environment, portable EEG technology (PEEGT) has an extensive prospect in expanding neuroscience research into natural applications. However, unlike in the laboratory environment, PEEGT is usually applied in a semiconstrained environment, including management and engineering, generating much more artifacts caused by the subjects’ activities. Due to the limitations of existing artifacts annotation, the problem limits PEEGT to take advantage of portability and low-test cost, which is a crucial obstacle for the potential application of PEEGT in the natural environment. This paper proposes an intelligent method to identify two leading antecedent causes of EEG artifacts, participant’s blinks and head movements, and annotate the time segments of artifacts in real time based on computer vision (CV). Furthermore, it changes the original postprocessing mode based on artifact signal recognition to the preprocessing mode based on artifact behavior recognition by the CV method. Through a comparative experiment with three artifacts mark operators and the CV method, we verify the effectiveness of the method, which lays a foundation for accurate artifact removal in real time in the next step. It enlightens us on how to adopt computer technology to conduct large-scale neurotesting in a natural semiconstrained environment outside the laboratory without expensive laboratory equipment or high manual costs.

show abstract

“…To solve this problem, complex analytical approaches are required to detangle brain and non‐brain contributions to EEG signals. For instance, additional information from inertial motion units (Beach et al, 2021) or electromyography (Li et al, 2021) could help decompose movement‐contaminated sections of EEG recordings during sports. Furthermore, technical solutions like dual‐layer EEG set‐ups (Nordin et al, 2019) may improve signal‐to‐noise ratio by removing signal components stemming from mechanical impacts on electrodes.…”

Section: Introductionmentioning

confidence: 99%

Ecological validity in exercise neuroscience research: A systematic investigation

Chang

Büchel

Reinecke

et al. 2022

Eur J of Neuroscience

View full text Add to dashboard Cite

The contribution of cortical processes to adaptive motor behaviour is of great interest in the field of exercise neuroscience. Next to established criteria of objectivity, reliability and validity, ecological validity refers to the concerns of whether measurements and behaviour in research settings are representative of the real world. Because exercise neuroscience investigations using mobile electroencephalography are oftentimes conducted in laboratory settings under controlled environments, methodological approaches may interfere with the idea of ecological validity. This review utilizes an original ecological validity tool to assess the degree of ecological validity in current exercise neuroscience research. A systematic literature search was conducted to identify articles investigating cortical dynamics during goal-directed sports movement. To assess ecological validity, five elements (environment, stimulus, response, body and mind) were assessed on a continuum of artificiality-naturality and simplicity-complexity. Forty-seven studies were included in the present review. Results indicate lowest average ratings for the element of environment. The elements stimulus, body and mind had mediocre ratings, and the element of response had the highest overall ratings. In terms of the type of sport, studies that assessed closed-skill indoor sports had the highest ratings, whereas closed-skill outdoor sports had the lowest overall rating. Our findings identify specific elements that are lacking in ecological validity and areas of improvement in current exercise neuroscience literature. Future studies may potentially increase ecological validity by moving from reductionist, artificial environments towards complex, natural environments and incorporating realworld sport elements such as adaptive responses and competition.

show abstract

Electromyogram (EMG) Removal by Adding Sources of EMG (ERASE)—A Novel ICA-Based Algorithm for Removing Myoelectric Artifacts From EEG

Cited by 17 publications

References 82 publications

A Depression Diagnosis Method Based on the Hybrid Neural Network and Attention Mechanism

A Depression Diagnosis Method Based on the Hybrid Neural Network and Attention Mechanism

Intelligent Method for Real-Time Portable EEG Artifact Annotation in Semiconstrained Environment Based on Computer Vision

Ecological validity in exercise neuroscience research: A systematic investigation

Contact Info

Product

Resources

About