Artifact Detection and Correction in EEG data: A Review

Sadiya, Sari; Alhanai, Tuka; Ghassemi, Mohammad M.

doi:10.1109/ner49283.2021.9441341

Cited by 16 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most common problems with trials are behavioral errors (if correct responses will be required during the final analyses) and artifacts. Many studies use artifact correction algorithms (e.g., Haumann et al, 2016;Jung et al, 2000;Sadiya et al, 2021) to deal with the most common kinds of artifacts, such as eyeblinks. However, some types of artifacts are not easily corrected using these algorithms (e.g., movement artifacts and blinks that prevent the perception of a stimulus), so some trials will likely need to be rejected because of artifacts (Luck, 2014).…”

Section: Number Of Channels and Trials Surviving Exclusionmentioning

confidence: 99%

Managing EEG studies: How to prepare and what to do once data collection has begun

et al. 2023

View full text Add to dashboard Cite

In this paper, we provide guidance for the organization and implementation of EEG studies. This work was inspired by our experience conducting a large‐scale, multi‐site study, but many elements could be applied to any EEG project. Section 1 focuses on study activities that take place before data collection begins. Topics covered include: establishing and training study teams, considerations for task design and piloting, setting up equipment and software, development of formal protocol documents, and planning communication strategy with all study team members. Section 2 focuses on what to do once data collection has already begun. Topics covered include: (1) how to effectively monitor and maintain EEG data quality, (2) how to ensure consistent implementation of experimental protocols, and (3) how to develop rigorous preprocessing procedures that are feasible for use in a large‐scale study. Links to resources are also provided, including sample protocols, sample equipment and software tracking forms, sample code, and tutorial videos (to access resources, please visit: https://osf.io/wdrj3/).

show abstract

Section: Number Of Channels and Trials Surviving Exclusionmentioning

confidence: 99%

Managing EEG studies: How to prepare and what to do once data collection has begun

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In [21], mthe author depicted an EEG noise-reduction scheme that customs representation knowledge to perform patient-and taskspecific discovery of artifacts and correction. More specifically, their method is dependent on a given task and extracted 58 features from the signals.…”

Section: Literature Reviewmentioning

confidence: 99%

Detection Of Event-Related Potential Artifacts Of Oddball Paradigm By Unsupervised Machine Learning Algorithm

Akhter¹,

Beyette²

2022

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Electroencephalography (EEG) is one of the most common and benign methods for analyzing and identifying abnormalities in the human brain. EEG is an incessant measure of the activities of the human brain. In contrast, when the measurement of EEG is bounded by time and the EEG is synchronized to an exterior stimulus, is known as Event-Related Potential (ERP). ERP has the capability to perceive and explore the human brain's responses to specific sensitive, cognitive, or motor events in real time with high temporal resolution. Among the various techniques, the oddball paradigm is very famous in EEG studies. In an oddball paradigm experiment, brain responses to frequent and infrequent stimuli are measured. However, the success of ERP research is very much dependent on the analysis of clean data sets and unfortunately, EEG is a combination of both neural and nonneural activities which introduce significant sources of noise that are not related to the brain's response to the external stimulus. These unrelated non-EEG components are acknowledged as artifacts and due to these, the quality of the EEG may damage by decreasing SNR (signal-to-noise ratio). In addition, these artifacts may mislead the actual information in the study. Addressing this problem, the purpose of this research is to introduce a machine learning algorithm (ML) that can screen EEG/ERP data to remove data epochs that are disrupted by artifacts and thus produce a clean data set. Overall, three unsupervised ML algorithms are applied to identify noisy epochs and it is found that the DBScan method performs best with 93.43% accuracy. Finally, the success of this study will allow the ERP study to have a cleaner ERP data set in normal laboratory conditions with less complexity in the ERP studies.

show abstract

“…However, selecting the right threshold value is a challenging task. In recent years, machine learning (ML) algorithms have been incorporated to make this automatic and featurebased ocular artifact detection processes more robust and accurate [10,[19][20][21]. The use of ML algorithms removed the abovementioned problem of threshold value dependency.…”

Section: Introductionmentioning

confidence: 99%

Quantitative EEG features and machine learning classifiers for eye-blink artifact detection: A comparative study

Rashida

Habib

2023

Neuroscience Informatics

View full text Add to dashboard Cite

Artifact Detection and Correction in EEG data: A Review

Cited by 16 publications

References 13 publications

Managing EEG studies: How to prepare and what to do once data collection has begun

Managing EEG studies: How to prepare and what to do once data collection has begun

Detection Of Event-Related Potential Artifacts Of Oddball Paradigm By Unsupervised Machine Learning Algorithm

Quantitative EEG features and machine learning classifiers for eye-blink artifact detection: A comparative study

Contact Info

Product

Resources

About