Application of hybrid GLCT-PICA de-noising method in automated EEG artifact removal

Jindal, Komal; Upadhyay, Rahul; Singh, Hari Shankar

doi:10.1016/j.bspc.2020.101977

Cited by 10 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…35 In present study, Fast power ICA based artifact detection and correction method is utilized for cleaning of recorded EEG activity. 30 The preprocessing pipeline consists of three steps. In the first step, Fast-power ICA (fpICA) based Blind Source Separation (BSS) is performed to decompose artifactual EEG activity into independent sources (i.e., ICs) of artifactual/noncerebral and cerebral activities.…”

Section: Data Preprocessingmentioning

confidence: 99%

“…In the first step, Fast-power ICA (fpICA) based Blind Source Separation (BSS) is performed to decompose artifactual EEG activity into independent sources (i.e., ICs) of artifactual/noncerebral and cerebral activities. 30 After separation of EEG activity into ICs, automatic identification of artifactual ICs is carried out using the Katz-Fractal-Sparsity (KFS) criterion, in the second step. In the third step, the identified ICs are corrected using general linear chirplet transform (GLCT) based TF coefficient suppression criterion and thereafter, inverse ICA is performed on the corrected ICs to attain clean EEG activity.…”

Section: Data Preprocessingmentioning

confidence: 99%

“…In the third step, the identified ICs are corrected using general linear chirplet transform (GLCT) based TF coefficient suppression criterion and thereafter, inverse ICA is performed on the corrected ICs to attain clean EEG activity. 30,36 Figure 3 shows the schematic diagram of GLCT-fpICA based EEG artifact correction pipeline.…”

Section: Data Preprocessingmentioning

confidence: 99%

“…As the first stage of the present methodology, raw EEG activity is treated to reject severe EEG artifacts following our previously proposed hybrid GLCT-fpICA based EEG de-noising pipeline. 30 Thereafter, in order to estimate the most informative EEG electrodes "Multiclass Discriminant Analysis (MDA) based Selective Opposition Grey Wolf Optimization (SOGWO)" criterion is applied on the clean EEG activity. A detailed feature set is estimated from the selected EEG channel that includes time-domain, frequency-domain, and TF domain-based features.…”

Section: Introductionmentioning

confidence: 99%

“…In present study, a channel selection and feature optimization‐based EEG processing and classification pipeline is developed while focusing on multi‐class MI‐BCI tasks. As the first stage of the present methodology, raw EEG activity is treated to reject severe EEG artifacts following our previously proposed hybrid GLCT‐fpICA based EEG de‐noising pipeline 30 . Thereafter, in order to estimate the most informative EEG electrodes “Multi‐class Discriminant Analysis (MDA) based Selective Opposition Grey Wolf Optimization (SOGWO)” criterion is applied on the clean EEG activity.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A novel EEG channel selection and classification methodology for multi‐class motor imagery‐based BCI system design

Jindal

Upadhyay

Singh

2022

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

Multi-class MI EEG analysis is an extensively used paradigm in BCI. However, multiple EEG channels lead to redundant information extraction and would reduce the distinction among various MI tasks. Therefore, optimal channel selection from multi-channel EEG activity still remains a challenging task. In this study, to enhance the multi-class BCI system's performance, a novel channel selection, and features optimization methodology have been proposed.First, multi-channel EEG dataset is reduced to an optimum no. of channels subset using developed MDA-SOGWO based EEG channel selection criterion.After that, the discriminable feature-set is generated from time, frequency, and FAWT based time-frequency domain of EEG dataset. Then, an informative feature-set is constructed from extracted features through CCA-RFE based feature selection criterion. Finally, training and validation of selected feature-set are carried out using ELM, LDA, RF, and MLP classifiers. The proposed methodology is evaluated on multi-class MI datasets of BCI Competition IV 2a and BCI Competition III 3a, yielding classification accuracy of 85.65% and 95.15%, respectively. The classification results pose the proposed methodology as an efficient method for future BCI system design.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%

Section: Data Preprocessingmentioning

confidence: 99%

Section: Data Preprocessingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations