TMS-induced EEG Artifacts Removal Methods based on Cross-Correlation Coefficients of ICA Components

This paper presents a review on signal analysis method for feature extraction of electroencephalogram (EEG) signal. It is an important aspect in signal processing as the result obtained will be used for signal classification. A good technique for feature extraction is necessary in order to achieve robust classification of signal. Considering several techniques have been implemented for extracting features in EEG signal, we only highlight the most commonly used for schizophrenia.The techniques are Hilbert-Huang transform, Principal Component Analysis, Independent Component Analysis and Local Discriminant Bases. Despite of their drawbacks, they can be applied which depends on the aim of a research, parameters and the data collected. Nevertheless, these techniques can be modified so that the new algorithm can overcome the shortcomings of original algorithm or algorithm beforehand. The modified Local Discriminant Bases algorithm is introduced in the present paper as another powerful adaptive feature extraction technique for EEG signal which is not reported elsewhere in investigating schizophrenia.

show abstract

“…. , and A is the matrix with elements , [24]. Details on Infomax [25], [26], FastICA [26], [27] and JADE [27] can be seen here.…”

Section: Independent Component Analysismentioning

confidence: 99%

“…In other words, it decomposes the independent component from the mixtures of sources. These components can be signals from brain activities or artifacts generated by Transcranial Magnetic Stimulation (TMS) [24]. The algorithm of FastICA (fICA) is described as above as in [18], [26].…”

Section: Independent Component Analysismentioning

confidence: 99%

Feature extraction of electroencephalogram (EEG) signal - A review

Azlan

Low

2014

2014 IEEE Conference on Biomedical Engineering and Sciences (IECBES)

View full text Add to dashboard Cite

show abstract

“…Independent Component Analysis (ICA) is applicable to separate EEG data into neural activity and artifact [10]. Many methods using ICA are applied to high-density EEG data to reject components of artifact [10][11]. However, there are few of them which resolve TMS induced artifact removal problem on EEG.…”

Section: Introductionmentioning

confidence: 99%

Study of the removal of TMS induced artifacts on human EEG based on the partial cross-correlations

Lee

Yoo²

2014

Advanced Science and Technology Letters

Self Cite

View full text Add to dashboard Cite

The TMS pulse in the TMS-EEG combining study introduces artifacts in the EEG electrodes. In this study a statistical method on the removal of TMS induced EEG artifacts is presented based on partial cross-correlations. The method yields estimates of linear correlations between components obtained by Independent Component Analysis (ICA) and TMS signal that are not affected by linear correlations with other artifacts. The results showed which ICA components are related to TMS induced EEG artifacts, suggesting the efficiency and the reliability of the method developed in this study.

show abstract

Section: Introductionmentioning

confidence: 99%

TMS induced EEG artifacts analysis based on the partial cross-correlations

Lee¹,

Yoo²

2014

ces

Self Cite

View full text Add to dashboard Cite

Combining Transcranial magnetic stimulation (TMS) and Electroencephaloraphy (EEG) offered insights into neural interaction during cognition which allows the investigation on the causal role of specific brain areas in behavior and the interactive connection between the brain areas. The TMS pulse in the TMS-EEG combining study introduces artifacts in the EEG electrodes which may mask the underlying neural activity lasting about 5 through even hundreds milliseconds after the pulse. In this study a statistical method on the removal of TMS induced EEG artifacts is presented based on partial cross-correlations. The method yields estimates of linear correlations between components obtained by Independent Component Analysis (ICA) and TMS signal that are not affected by linear correlations with other artifacts. We used the EEG data obtained from four healthy subjects without any neurological disorder, who were receiving single pulse TMS-EEG and sham-EEG stimulus on the left Broca's area. ICA filters trained on the reduced version of 60 channel EEG data collected during single pulse 1426 Unjoo Lee and Woo-Kyoung Yo TMS-EEG and sham-EEG recordings. It identified the reduced number of statistically independent source channels, in which the ICA components originating from the TMS-induced artifact are classified by estimating the partial cross-correlation coefficients between ICA components of single pulse TMS-EEG and sham-EEG stimulus after ICA decomposition. The results showed which ICA components are related to TMS induced EEG artifacts, suggesting the efficiency and the reliability of the method developed in this study.

show abstract

TMS-induced EEG Artifacts Removal Methods based on Cross-Correlation Coefficients of ICA Components

Abstract: In this study a noble TMS-induced artifact removal method is developed and discussed by estimating its parameters for various aspects of data

Cited by 3 publications

References 15 publications

Feature extraction of electroencephalogram (EEG) signal - A review

Feature extraction of electroencephalogram (EEG) signal - A review

Study of the removal of TMS induced artifacts on human EEG based on the partial cross-correlations

TMS induced EEG artifacts analysis based on the partial cross-correlations

Contact Info

Product

Resources

About