EEG Artifact Removal Strategies for BCI Applications: A Survey

THOTTTEMPUDI PARDHU1, NAGESH DEEVI1

Department of Electronics & Communications Engineering

BVRIT HYDERABAD College of Engineering For Women

Plot No:8-5/4, Rajiv Gandhi Nagar Colony, Nizampet Road, Bachupally, Hyderabad-500090,

Telangana, INDIA

Abstract: This paper aims to provide a comprehensive examination of the Brain-Computer Interface and

the more scientific discoveries that have resulted from it. The ultimate goal of this review is to provide

extensive research in BCI systems while also focusing on artifact removal techniques or methods that have

recently been used in BCI and important aspects of BCIs. In its pre-processing, artifact removal

methodologies were critical. Furthermore, the review emphasizes the applicability, practical challenges,

and outcomes associated with BCI advancements. This has the potential to accelerate future progress in this

field. This critical evaluation examines the current state of BCI technology as well as recent advancements.

It also identifies various BCI technology application areas. This detailed study shows that, while progress

is being made, significant challenges remain for user advancement A comparison of EEG artifact removal

methods in BCI was done, and their usefulness in real-world EEG-BCI applications was talked about. Some

directions and suggestions for future research in this area were also made based on the results of the review

and the existing artifact removal methods.

Keywords: EEG: Electro Encephalo Gram; BCI: Brain-Computer Interface; ECG:

Electrocardiogram;EMG: ElectroMyoGram;EOG: ElectroOculogram

Received: October 17, 2022. Revised: April 26, 2023. Accepted: June 7, 2023. Published: July 7, 2023.

1. Introduction

Recent advances in biomedical engineering,

medicine, and information technology have

enabled the development of

electroencephalography-based Brain-Computer

Interfaces that do not require invasive brain

surgery [1,2]. Disproportion in these frequencies

is used to diagnose certain disorders and diseases

[3,4], and numerous studies of EEG signals have

shown that certain signal bands are strongly

associated with particular activities. Table 1

shows the various brain wave patterns and

activities.

The term "Brain-Computer Interface" (also

"Brain-Machine Interface," "Human Computer

Interface," or "Neural Interface") refers to the

integration of hardware and software to facilitate

communication between a biological object and a

computer. The fields of neuroscience, signal

processing, and clinical research all intersect with

AI and ML in BCI studies, making them an

interdisciplinary field in and of themselves.

Table.1. Different brain rhythms and their brain

activities

Frequency band

Frequency

Brain states

Best recorded at

Gamma (γ)

>40Hz

Concentration

Parietal Lobe,active

frontal lobe

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

Beta (β)

14–40Hz

Awakening,conscious

and rational

contemplation.

Parietal Lobe,Frontal

Lobe

Alpha (α)

9–14Hz

Comfortable,idle,not

concentrating on

anything

Occipital Lobe,Frontal

Lobe

Theta (θ)

4–8 Hz

Dreaming or sleeping

and meditation

-------

Delta (δ)

0.3–4 Hz

Sleep,the most

profound relaxation and

restorative, healing

sleep

-----

The BCI system's operation necessitates the use

of three modules:

1.signal capturing

2. processing of signals

3. application interface & applications

2. Signal Capturing Block

The electrophysiological signals used by the BCI

are captured by the Signal Capturing Module.

The brain is the source of these signals [7]. Both

invasive and non-invasive methods have been

developed for BCI research, but invasive

methods like electrocardiograms (ECoG) and

single-neuron recordings have proven more

effective [7,8]. Comparison of signal quality with

other non-invasive brain imaging techniques,

including magnetoencephalography, positron

emission tomography, functional magnetic

resonance imaging, near-infrared spectroscopy,

and fMRI [8]. The acquired signals are amplified

to increase their strength before transmission.

Before any computer application, they must be

encoded.

3. Processing Of Signals Block

3.1 Signal Pre-Processing

As illustrated in Figure 2, preprocessing of EEG

signals is an essential first step in any brain-

computer interface-based application. The signal

is cleaned up by subtracting out artifacts like

ECG, EOG, and EMG measurements, filtering

out noise, and resampling it to meet detector input

specifications.

Brain

signal

Pre-

processi

Feature

extracti

Application

s (robotic

arm, wheel

chair,drone

control,web

cursor

control etc)

Classi

ficatio

Application

interface

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

Fig.2.Signal preprocessing steps in BCI system

Pre-processing is often done to increase

the recorded data's signal to noise ratio

before processing. Artifacts in the EEG

signal can be eliminated by filtering out

the electrical activity produced by head

and eye muscle contractions. In order to

remove artifacts from an EEG recording,

a preprocessing of the signal is required.

When properly implemented, BCI

systems can Accurate categorization

relies heavily on the EEG signal being

properly preprocessed. The EEG signal

can be cleaned up and made ready for

analysis by doing some preliminary

processing. BSS, which stands for "blind

source separation," is a popular pre-

processing method [9].Artifacts are

frequently observed in many forms of

EEG signals, as shown in Table 2.

Table.2.Different artifacts arised during signal

acquisition of EEG signal processing

S.No

Artifacts

Generated By The

Source

Frequency

Voltage

Level

Shape

/Structure

Ocular Artifacts

(EOG)

Eye

0.3 -3HZ

80-100mv

Delta waves

EMG

Jaw movements

4-6hz

0-10mv

Theta waves

ECG

Heart or cardiac

movement

0-150hz

1-10mv

Beta and

gamma waves

50/60 HZ

artifacts(power

line artifacts)

Power line attached

50/60 hz

high

Beta and

gamma waves

Sweat artifacts

sweat

0.25-0.5 hz

300 micro

volts

Delta waves

Electrode pop

Electrodes attached to

scalp

0-30hz

20 mv

Shape

appeared

different from

actual EEG

signal

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

Physical

movement

artifacts(motion

artifacts)

Body movements,head

movement,jaw

movement etc…

Very low

high

Shape

appeared

different from

actual EEG

signal

Electronic

gadgets artifacts

Mobile,laptop,personal

computer etc..

Very low

high

Shape

appeared

different from

actual EEG

signal

4. Literature Survey

The below table.3 compare the latest artifacts

removal techniques in various parameters such as

type of artifacts that can able to eliminate in EEG

signal processing which is mainly related to BCI

applications ,novelty in the algorithm or method

that chosen to mitigate artifacts ,the data that can

operated on which the proposed method can best

suited (real &simulated ) so that we can estimate

practical implementation, and also here discussed

the challenges or limitations faced to practical

viability and commented or given remarks about

each and every system of implementation. The

above table contain different artifacts removal

techniques EOG, ECG, EMG, Physical

movement artifacts(motion artifacts) etc but

mainly focused on ocular or Eye Blink (EB)

artifacts because the EB artifacts are main cause

of error or distortion in EEG signal pre-

processing.

Table 3. Comparison of various artifacts removal

techniques

Author

Type of

artifact

Method

Algorithm

used

Novelty

Data

Challenges/

limitations

Comment

Çınar,

Salim(2021

)[22]

Only

Eye

blink

(EOG)

Independe

Compone

Analysis

(ICA),

Kurtosis,

K-means,

Modified

Z-Score

(MZS) and

Adaptive

Noise

Canceller

(ANC).

The

classical

Least

Mean

Squares

(LMS) and

Normalize

d LMS

(NLMS)

algorithms

The

proposed

system does

require an

external

electrode

for

measuring

EOG

Signals

Real

&simula

ted

It is only

applicable

to this

method is

that ocular

artifacts and

other

artifacts

present it is

not efficient

method and

When

conducting

the

subtraction

process, the

disadvantag

e is the

relevant

EEG

signals can

be erased.

The

proposed

method

has high

performan

ce in both

datasets &

comfortab

measurem

ent for

patients

during

more time

EEG

recordings

Cao,

Jiuwen.et al.

(2021) [24]

Only

Eye

Gaussian

mixture

cascaded

hybrid

thresholdin

No false

positives

were found

Real and

simulate

increased

likelihood

In terms

precision

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

blink

(EOG

model

(GMM)

g method

and the

GMM

algorithm

in the

detection of

eye blink

artifacts

using the

suggested

approach.

of missing

artifacts

caused by

eye blinks

when

employing

a high

threshold.

and F1

score, the

proposed

approach

is more

reliable.

Egambaram

Ashvaany.et

al. [26]

Only

Eye

blink

(EOG

FastEMD-

CCA and

FastCCA

It is

proposed

to use a

combinatio

n of

modified

Empirical

Mode

Decomposi

tion and

Canonical

Correlation

Analysis to

perform

unsupervis

ed eye

blink

artifact

detection

(eADA).

More than

97%

Removal

Accuracy

and an

average of

10-13ms

removal

speed

simulate

The

artifact-free

EEG

samples

showed

negligible

variation.

Eyeblink

artifacts

can be

effectivel

y removed

online

with

minimal

neural

distortion.

Borowicz,

Adam. [27]

Only

Eye

blink

(EOG

independe

componen

t analysis

(ICA) and

principles

regression

analysis

multichann

el Wiener

filter

(MWF)

and a small

subset of

the frontal

electrodes

When

compared

to the ICA

approach,

the

suggested

algorithm is

straightfor

ward. Real-

time

systems can

benefit

more from

it, and that

seems to be

a crucial

factor in

BCI

research

and

Real and

simulate

utilizing

cutting-

edge

multichann

el linear

filters,

enhanced

off-line

implementa

tion, and

expanding

the

suggested

method's

applicabilit

y to

additional

types of

biomedical

data.

When

compared

to the

state-of-

the-art

method,

the new

methodol

ogy is

suitable to

real-time

systems.

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

developme

nt.

Zhou,

Weidong,

and Jean

Gotman

[28]

Only

Eye

blink

(EOG

ICA

method

Independe

Componen

t Analysis

(ICA)

combining

the EEG di

pole model

The ICA

algorithm

uses few

computatio

nal

resources.

Without

requiring

access to a

database of

reference

artifacts, it

can

separate the

EEG from

the noise.

Real and

simulate

The

frequency

distribution

s of slow

waves and

visual

artifacts are

very

similar.

This

method

was

validated

for its

ability to

automatic

ally filter

out EEG

aberration

attributabl

e to the

eyes.

. Sreeja, S.

R., et al [29]

Mainly

Eye

blink

(EOG)

& also

used for

other

artifacts

remova

morpholo

gical

componen

t analysis

(MCA)

and K-

SVD

MCA and

K-SVD are

two

sparsity-

based

approaches

that can be

used to

eliminate

artifacts.

The

suggested

sparsity-

based

approaches

can

eliminate

EB artifacts

in an EEG

signal

without the

use of any

specialized

equipment

additional

channels

for the

EOG.

Real and

simulate

One major

drawback is

that it

necessitates

the use of

extraocular

channels in

order to

capture

ocular

artifacts.

It is

applicable

to the

eliminatio

n of other

artifacts in

raw EEG

data as

well.

He, Ping, G.

Wilson, and

C. Russell

[30]

ocular

artifacts

adaptive

filtering

recursive

least

squares

algorithm

The non-

stationary

component

of EOG

signals is

monitored

using this

technique.

real

The

approach

does not

scale up to

situations

with four or

reference

inputs.

automatic

ally adjust

to a new

environm

ent

without

sacrificing

performan

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

. Chintala,

Sridhar, and

Jaisingh

Thangaraj[3

ocular

artifacts

Robust

Variable

Forgetting

Factor

(RVFF)

and

Recursive

Least

Square

(RLS)

RVFF-

RLS based

algorithm

The non-

stationary

EOG

signals are

followed

and

estimated

by the

algorithm,

and then the

subtraction

approach is

used to

acquire

clean EEG

data.

Real and

simulate

Non-

stationary

conditions

are

detrimental

to tracking

performanc

The

proposed

method

exhibits

the lowest

possible

mean

square

error in a

time-

varying

condition.

Yadav,

Anchal, and

Mahipal

Singh

Choudhry.

[33]

ocular

artifacts

EEMD &

SCICA

Kurtosis

and

mMSE

Ensemble

Empirical

Mode

Decomposi

tion

(EEMD)

and Spatial

Constraint

Independe

Componen

t Analysis

(SCICA)

To counter

act EMD's

mode

mixing and

aliasing,

EEMD is

employed.

Real

EEMD's

amplitude-

reduction

problem

Better

constraint

s on ICA

and

wavelet

augmente

independe

componen

t analysis

can boost

performan

ce even

further.

Gajbhiye,

Pranjali,

Rajesh

Kumar

Tripathy

[34]

ocular

artifacts

the FBSE-

EWT

based

rhythm

separation

technique

. The

Fourier-

Bessel

series

expansion

based

empirical

wavelet

transform

(FBSEEW

The

approach

can remove

ocular

artifact

from an

EEG

recording

without the

use of a

reference

signal.

Real

The

blending of

modes as

various

rhythmic

EEG data

appears

Compared

to existing

methods,

the

proposed

approach

improves

performan

ce while

requiring

fewer

resources.

When

compared

to other

methods,

alpha

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

wave's

MAE in

PSD value

was 0.029

average.

Islam, Md

Kafiul,

Parviz

Ghorbanzad

eh, and

Amir

Rastegarnia.

[35]

All type

artifacts

remova

l( ECG,

EOG,

EMG,

etc.)

Entropy,

kurtosis,

skewness,

periodic

waveform

index

stationary

wavelet

transform

based

artifact

removal

The

outcomes

demonstrat

e that the

suggested

reduction of

artifacts

significantl

y increases

BCI output.

Real &

simulate

The

proposed

method still

requires

work in

terms of its

discriminati

on abilities

and its

capacity to

eliminate

artifacts.

The

proposed

approach

utilizes

four

statistical

technique

s to plot

the

improbabi

lity of

various

artifacts.

Lee,

Young-Eun,

No-Sang

Kwak, and

Seong-

Whan Lee

[36]

Movem

ent

artifacts

ICA with

online

learning

constrained

independen

component

analysis

with online

learning

(cIOL)

Examining

the impact

of noise

reduction in

the

temporal

and

frequency

domains

through a

quantitative

evaluation

of artifact

removal

approaches

utilizing

two BCI

paradigms

(ERP and

SSVEP).

Real &

simulate

Timeframes

for using

the

approach

are

constrained

by the

occurrence

of gait

events. Ano

ther issue is

that there

isn't a single

adequate

template to

represent

artifacts'

wide

variety.

Develope

d a rough

estimate

of the

movement

artifacts

using the

EEG data.

Finally,

artifact-

free EEG

signals

were

recovered

using

weights

that were

updated

using

online

learning.

Song,

YoungJae,

and

Francisco

Sepulveda

[37]

EMG

artifacts

ICA, PCA,

and BSS-

CCA

EMG-CCh

Reduce

ambiguity

and

enhance

discriminati

simulate

Methodolo

gical

Constraints

excessive

amount of

Finally,

the

proposed

strategy

improved

class

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

on between

classes.

class-

dependent

EMG can

persist even

in a channel

with

reduced

CRC during

resting

conditions.

separation

(when

compared

to prior

methods)

using both

training

and test

data. The

data set

developed

for the

BCI

competiti

on is used

in a wide

variety of

applicatio

ns. This

strategy

can be

used

independe

ntly or in

tandem

with other

approache

s of

managing

artifacts.

According to the data in the table above,

the most common techniques used to clean up

EEG signals include Blind Source Separation

(BSS), Principal Component Analysis (PCA),

Canonical Correlation Analysis (CCA), Discrete

Wavelet Transform (DWT), Stationary Wavelet

Transform (SWT), Empirical Mode

Decomposition (EMD), Ensemble Empirical

Mode Decomposition (EEMD), Wavelet

Transform, and Adaptive Filtering. The

performance parameters, including the

correlation co-efficient, Mean Square Error,

Power Spectral Density, Signal-to-Noise Ratio,

and Execution Speed and Complexity, are all

improved when the preprocessing stage is

enhanced.

The above table details a discussion of advanced

artifact removal techniques for the examples

given, including those by nar, Salim(2021), who

discussed and implemented a new algorithm, the

classical Least Mean Squares (LMS) algorithm,

and the Normalized LMS algorithm (using

Independent Component Analysis, Kurtosis, K-

means, a modified Z-score, and an adaptive noise

canceler) for removing eye blink artifacts from

both real and simulated data. The system has the

limitation of only being able to deal with ocular

artifacts, making it a less-than-efficient method;

the subtraction process can result in the loss of

important EEG signals; and in another paper by

Borowicz and Adam, they discussed independent

component analysis (ICA) and regression

analysis principles and implemented them using

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

a multichannel Wiener filter; and in this study,

they used a subset of frontal electrodes to detect

ICA. It also works great with real-time systems,

which is apparently crucial for BCI

research. Additionally, a novel concept was

implemented by Zhou, Weidong, and Jean

Gotman using Independent Component Analysis

in combination with the EEG dipole model, with

a primary focus on ocular artifact elimination.

This technique was found to be effective in

automatically eradicating ocular artifacts from

the EEG. Song, YoungJae, and Francisco

Sepulveda also implemented the system using

ICA, in addition to PCA, and BSS-CCA to

remove EMG artifacts by a novel technique

called EMG-cch and best suited for use along

with the other techniques the data only

implemented on simulation results.

Genetic algorithm (GA), a technique proposed by

Trigui, Omar, et al., decreases the RMSE

between unprocessed and processed EEG data.

Using only simulated data and a small number of

channels, the proposed approach nevertheless

achieves satisfactory results.

Each and every eye blink artifact was correctly

identified by the proposed method by Cao,

Jiuwen.etal, with zero false positives.

The method developed by Egambaram,

Ashvaany, et al. CFast EMD-CCA and Fast

CCA introduced a method for detecting eye

blink artifacts without human supervision by

combining a variant of Empirical Mode

Decomposition with Canonical Correlation

Analysis. Artifact-free EEG segments showed

hardly any distortion, with an accuracy of more

than 97% and a removal speed of 10-13 ms, on

average. Artifacts caused by an eyeblink can be

corrected online with minimal neural distortion.

To eliminate EB artifacts from the EEG signal,

Sreeja, S. R., et al. suggested a method known as

K-SVD with morphological component analysis.

Both of these methods are sparsity-based

methodologies that work on both real and

simulated data without the need for channel

information, parameter tweaking (such as

thresholding), or additional hardware/EEG

channels.

Adaptive filtering for ocular artifacts

using recursive least squares was given by He,

Ping, G. Wilson, and C. Russell. When applied to

real-world data, this method follows the dynamic

components of EOG signals. It cannot be

generalized to situations involving three or more

reference inputs, but it can be automatically

adapted to a new setting without compromising

its efficacy.

Using the Robust Variable Forgetting Factor

(RVFF) and Recursive Least Square (RLS),

Chintala, Sridhar, and Jaisingh Thangaraj solved

the problem of ocular artifacts. This method

estimates and follows non-stationary EOG

signals so that pure EEG signals can be extracted

from both real and simulated data. In unstable

conditions, tracking accuracy decreases. The

proposed method achieves the smallest mean

square error in a dynamic environment.

Yadav, Anchal, and Mahipal Singh Choudhry

compute Kurtosis and mean squared error

(mSSE) using Ensemble Empirical Mode

Decomposition (EEMD) and Spatial Constraint

Independent Component Analysis (SCICA).

EEMD is also used to overcome the mode mixing

and aliasing problem of EMD, which is typically

performed on Real data. Improving the

constraints used in ICA and wavelet-enhanced

independent component analysis can further

boost performance. In order to get rid of ocular

artifacts, Gajbhiye, Pranjali, and Rajesh Kumar

Tripathy presented a rhythm separation technique

based on FBSE-EWT. Ocular artifacts can be

removed from an EEG signal using the Fourier-

Bessel series expansion based empirical wavelet

transform (FBSEEWT) method, which has been

extensively validated for real-valued data and

does not require a reference signal. When many

modes of EEG rhythm information appear, this

phenomenon is referred to as "mode mixing." The

suggested method outperforms state-of-the-art

alternatives, with a mean absolute error (MAE) in

peak signal-to-noise ratio (PSR) of only 0.029 for

rhythm.

Using entropy, kurtosis, skewness, and the

stationary wavelet transform, Islam, Md. Kafiul,

Parviz Ghorbanzadeh, and Amir Rastegarnia

proposed a method for eliminating artifacts

across all modalities. When evaluated with real

and simulated data, the results reveal that the

proposed artefact removal significantly improves

BCI output. The proposed technique still needs

better discrimination capacity and has weak

ability to eliminate genuine artefacts. The

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

suggested method for mapping artificial

probability uses four statistical parameters.

5. Conclusion

The work is mostly considered in the

preprocessing step of the overall BCI systems.

The goal of the pre-processing stage in a BCI

applications is to decrease artifacts in the EEG

signal generated by the numerous sources. Based

on the findings in the available literature, this

report summarized the key techniques, Some of

the techniques uses exclusively used for

removing artifacts which is related to eye blink

(EOG)artifacts, ECG ,EMG and all other

movement related artifacts here by go through the

different research articles basically uses different

algorithams separately or combinely that reveals

the output without artifacts in EEG signal

processing which combined with BCI related

applications either it may be cursor

movement,wheel chair movement,video

gaming,bio medical etc. Some methods, such as

adaptive filtering, Morphological Component

Analysis (MCA) and K-SVD and Entropy,

kurtosis, skewness, periodic waveform index,

remove artifacts with high precision,which works

on both real and simulated data or either of the

one , however methods with high computational

cost may not be suited for online applications. As

a result, there is no best option for removing all

forms of artifacts. So, one of the future goals of

effective artifact attenuation is to provide an

application-specific methodology with improved

time and precision, efficiency.

References

[1]. Kübler, A. (2020). The history of BCI: From a

vision for the future to real support for

personhood in people with locked-in syndrome.

Neuroethics, 13(2), 163-180.

[2]. Kawala-Janik, A. Efficiency Evaluation of

External Environments Control Using Bio-

Signals. Ph.D. Thesis, University of Greenwich,

London, UK, 2013.

[3]. Ebersole, J.S.; Pedley, T.A. Current Practice of

Clinical Electroencephalography; Lippincott

Williams & Wilkins: Philadelphia, PA, USA,

2003

[4]. Millett, D. Hans Berger: From psychic energy to

the EEG. Perspect. Biol. Med. 2001, 44, 522–

542. [CrossRef] Priyanka A. Abhang, Bharti W.

Gawali, Suresh C. Mehrotra,

[5]. Chapter 2 - Technological Basics of EEG

Recording and Operation of Apparatus,Editor(s):

Priyanka A. Abhang, Bharti W. Gawali, Suresh

C. Mehrotra,Introduction to EEG- and Speech-

Based Emotion Recognition,Academic

Press,2016

[6]. Aggarwal, Swati, and Nupur Chugh. "Signal

processing techniques for motor imagery brain

computer interface: A review." Array 1 (2019):

100003.

[7]. Donoghue JP. Connecting cortex to machines:

recent advances in brain interfaces. Nat Neurosci

2002;5:1085.

[8]. Serruya Mijail D, et al. Brain-machine interface:

instant neural control of a movement signal.

Nature 2002;416:141.

[9]. Cichocki, Andrzej, et al. "EEG filtering based on

blind source separation (BSS) for early detection

of Alzheimer's disease." Clinical

Neurophysiology 116.3 (2005): 729-737.

[10]. Al-Fahoum, Amjed S., and Ausilah A.

Al-Fraihat. "Methods of EEG signal features

extraction using linear analysis in frequency and

time-frequency domains." International

Scholarly Research Notices 2014 (2014).

[11]. Osalusi, Bamidele, Amole Abraham, and

David Aborisade. "EEG Classification in Brain

Computer Interface (BCI): A Pragmatic

Appraisal." American Journal of Biomedical

Engineering 8.1 (2018): 1-11.

[12]. Mridha, M. F., et al. "Brain-computer

interface: Advancement and challenges." Sensors

21.17 (2021): 5746.

[13]. Phan A H and Cichocki A 2010 Tensor

decompositions for feature extraction and

classification of high dimensional datasets

Nonlinear Theory Appl. 1 37–68

[14]. Washizawa Y, Higashi H, Rutkowski T,

Tanaka T and Cichocki A 2010 Tensor based

simultaneous feature extraction and sample

weighting for EEG classification Int. Conf. on

Neural Information Processing, ICONIP 2010:

Neural Information Processing. Models and

Applications (Berlin: Springer) pp 26–33

[15]. Onishi A, Phan A, Matsuoka K and

Cichocki A 2012 Tensor classification for P300-

based brain computer interface IEEE Int. Conf.

on Acoustics, Speech and Signal Processing

(IEEE) pp 581–4

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

[16]. Zhang Y, Zhou G, Jin J, Wang X and

Cichocki A 2014 Frequency recognition in

SSVEP-based BCI using multiset canonical

correlation analysis Int. J. Neural Syst. 24

1450013

[17]. Zhang Y, Zhou G, Jin J, Wang X and

Cichocki A 2015 Optimizing spatial patterns with

sparse filter bands for motor-imagery based

brain–computer interface J. Neurosci. Methods

255 85–91

[18]. Zhang, Y. U., Zhou, G., Jin, J., Wang, X.,

& Cichocki, A. (2014). Frequency recognition in

SSVEP-based BCI using multiset canonical

correlation analysis. International journal of

neural systems, 24(04), 1450013.

[19]. Zhang, Y., Zhou, G., Jin, J., Wang, X., &

Cichocki, A. (2015). Optimizing spatial patterns

with sparse filter bands for motor-imagery based

brain–computer interface. Journal of

neuroscience methods, 255, 85-91.

[20]. Zhang, Y., Zhou, G., Jin, J., Zhang, Y.,

Wang, X., & Cichocki, A. (2017). Sparse

Bayesian multiway canonical correlation analysis

for EEG pattern recognition. Neurocomputing,

225, 103-110.

[21]. Zhang Y, Zhou G, Zhao Q, Onishi A, Jin

J, Wang Xand Cichocki A 2011 Multiway

canonical correlationanalysis for frequency

components recognition in SSVEP-based BCIs

Neural Information Processing(Berlin: Springer)

[22]. Çınar, Salim. "Design of an automatic

hybrid system for removal of eye-blink artifacts

from EEG recordings." Biomedical Signal

Processing and Control 67 (2021): 102543.

[23]. Trigui, Omar, et al. "Removal of eye

blink artifacts from EEG signal using

morphological modeling and orthogonal

projection." Signal, Image and Video Processing

16.1 (2022): 19-27.

[24]. Cao, Jiuwen, et al. "Unsupervised eye

blink artifact detection from EEG with Gaussian

mixture model." IEEE Journal of Biomedical and

Health Informatics 25.8 (2021): 2895-2905.

[25]. Wang, Jianhui, et al. "Eye blink artifact

detection with novel optimized multi-

dimensional electroencephalogram features."

IEEE Transactions on Neural Systems and

Rehabilitation Engineering 29 (2021): 1494-

1503.

[26]. Egambaram, Ashvaany, et al. "Online

detection and removal of eye blink artifacts from

electroencephalogram." Biomedical Signal

Processing and Control 69 (2021): 102887.

[27]. Borowicz, Adam. "Using a multichannel

Wiener filter to remove eye-blink artifacts from

EEG data." Biomedical Signal Processing and

Control 45 (2018): 246-255.

[28]. Zhou, Weidong, and Jean Gotman.

"Automatic removal of eye movement artifacts

from the EEG using ICA and the dipole model."

Progress in Natural Science 19.9 (2009): 1165-

1170.

[29]. Sreeja, S. R., et al. "Removal of eye blink

artifacts from EEG signals using sparsity." IEEE

journal of biomedical and health informatics 22.5

(2017): 1362-1372.

[30]. He, Ping, G. Wilson, and C. Russell.

"Removal of ocular artifacts from electro-

encephalogram by adaptive filtering." Medical

and biological engineering and computing 42.3

(2004): 407-412.

[31]. Joyce, Carrie A., Irina F. Gorodnitsky,

and Marta Kutas. "Automatic removal of eye

movement and blink artifacts from EEG data

using blind component separation."

Psychophysiology 41.2 (2004): 313-325.

[32]. Chintala, Sridhar, and Jaisingh

Thangaraj. "Ocular artifact elimination from eeg

signals using rvff-rls adaptive algorithm." 2020

National Conference on Communications (NCC).

IEEE, 2020.

[33]. Yadav, Anchal, and Mahipal Singh

Choudhry. "A new approach for ocular artifact

removal from EEG signal using EEMD and

SCICA." Cogent Engineering 7.1 (2020):

1835146.

[34]. Gajbhiye, Pranjali, Rajesh Kumar

Tripathy, and Ram Bilas Pachori. "Elimination of

ocular artifacts from single channel EEG signals

using FBSE-EWT based rhythms." IEEE Sensors

Journal 20.7 (2019): 3687-3696.

[35]. Islam, Md Kafiul, Parviz Ghorbanzadeh,

and Amir Rastegarnia. "Probability mapping

based artifact detection and removal from single-

channel EEG signals for brain–computer

interface applications." Journal of Neuroscience

Methods 360 (2021): 109249.

[36]. Lee, Young-Eun, No-Sang Kwak, and

Seong-Whan Lee. "A real-time movement

artifact removal method for ambulatory brain-

computer interfaces." IEEE Transactions on

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

Neural Systems and Rehabilitation Engineering

28.12 (2020): 2660-2670.

[37]. Song, Y., & Sepulveda, F. (2018). A

novel technique for selecting EMG-contaminated

EEG channels in self-paced brain–computer

Interface task onset. IEEE Transactions on neural

systems and rehabilitation engineering, 26(7),

1353-1362.

[38]. Krauledat, Matthias, et al. "Robustifying

EEG data analysis by removing outliers." Chaos

and Complexity Letters 2.3 (2007): 259-274. J.

Clerk Maxwell, A Treatise on Electricity and

Magnetism, 3rd ed., vol. 2. Oxford: Clarendon,

1892, pp.68–73.

[39]. Gouy-Pailler, Cédric, et al. "Iterative

subspace decomposition for ocular artifact

removal from EEG recordings." International

Conference on Independent Component Analysis

and Signal Separation. Springer, Berlin,

Heidelberg, 2009. K. Elissa, “Title of paper if

known,” unpublished.

[40]. Croft, Rodney J., et al. "EOG correction:

a comparison of four methods."

Psychophysiology 42.1 (2005): 16-24. Y.

Yorozu, M. Hirano, K. Oka, and Y. Tagawa,

“Electron spectroscopy studies on magneto-

optical media and plastic substrate interface,”

IEEE Transl. J. Magn. Japan, vol. 2, pp. 740–741,

August 1987 [Digests 9th Annual Conf.

Magnetics Japan, p. 301, 1982].

[41]. M. Young, The Technical Writer’s

Handbook. Mill Valley, CA: University Science,

1989.

[42]. Jiang, Aimin, et al. "Efficient CSP

algorithm with spatio-temporal filtering for

motor imagery classification." IEEE Transactions

on Neural Systems and Rehabilitation

Engineering 28.4 (2020): 1006-1016.

[43]. Isa, NE Md, et al. "Motor imagery

classification in Brain computer interface (BCI)

based on EEG signal by using machine learning

technique." Bulletin of Electrical Engineering

and Informatics 8.1 (2019): 269-275.

[44]. Ang, Kai Keng, et al. "Filter bank

common spatial pattern (FBCSP) in brain-

computer interface." 2008 IEEE international

joint conference on neural networks (IEEE world

congress on computational intelligence). IEEE,

2008.

[45]. amoser, Herbert, Johannes Muller-

Gerking, and Gert Pfurtscheller. "Optimal spatial

filtering of single trial EEG during imagined hand

movement." IEEE transactions on rehabilitation

engineering 8.4 (2000): 441-446.

[46]. Oh, Seung-Hyeon, Yu-Ri Lee, and

Hyoung-Nam Kim. "A novel EEG feature

extraction method using Hjorth parameter."

International Journal of Electronics and Electrical

Engineering 2.2 (2014): 106-110.

[47]. Übeyli, Elif Derya, and İnan Güler.

"Features extracted by eigenvector methods for

detecting variability of EEG signals." Pattern

Recognition Letters 28.5 (2007): 592-603.

[48]. Stancin, Igor, Mario Cifrek, and Alan

Jovic. "A review of EEG signal features and their

application in driver drowsiness detection

systems." Sensors 21.11 (2021): 3786.

[49]. Stam, CJ van, and E. C. W. Van Straaten.

"The organization of physiological brain

networks." Clinical neurophysiology 123.6

(2012): 1067-1087.

[50]. Übeyli, Elif Derya. "Analysis of EEG

signals by implementing eigenvector

methods/recurrent neural networks." Digital

Signal Processing 19.1 (2009): 134-143.

[51]. Gaur, Pramod, et al. "A sliding window

common spatial pattern for enhancing motor

imagery classification in EEG-BCI." IEEE

Transactions on Instrumentation and

Measurement 70 (2021): 1-9.

[52]. Bose, Rohit, et al. "Performance analysis

of left and right lower limb movement

classification from EEG." 2016 3rd International

Conference on Signal Processing and Integrated

Networks (SPIN). IEEE, 2016.

[53]. Raschka, Sebastian, David Julian, and

John Hearty. Python: deeper insights into

machine learning. Packt Publishing Ltd, 2016.

[54]. Isa, NE Md, et al. "Motor imagery

classification in Brain computer interface (BCI)

based on EEG signal by using machine learning

technique." Bulletin of Electrical Engineering

and Informatics 8.1 (2019): 269-275.

[55]. Rish, Irina. "An empirical study of the

naive Bayes classifier." IJCAI 2001 workshop on

empirical methods in artificial intelligence. Vol.

3. No. 22. 2001.

[56]. Leung, K. Ming. "Naive bayesian

classifier." Polytechnic University Department of

Computer Science/Finance and Risk Engineering

2007 (2007): 123-156.

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

[57]. Berrar, Daniel. "Cross-Validation."

(2019): 542-545.

[58]. Ang, Kai Keng, et al. "Filter bank

common spatial pattern algorithm on BCI

competition IV datasets 2a and 2b." Frontiers in

neuroscience 6 (2012): 39.

[59]. Shenoy, H. Vikram, A. Prasad Vinod,

and Cuntai Guan. "Shrinkage estimator based

regularization for EEG motor imagery

classification." 2015 10th International

Conference on Information, Communications

and Signal Processing (ICICS). IEEE, 2015.

[60]. Lupu, R. G., Ungureanu, F., & Cimpanu,

C. (2019, May). Brain-computer interface:

Challenges and research perspectives. In 2019

22nd International Conference on Control

Systems and Computer Science (CSCS) (pp. 387-

394). IEEE.

[61]. Fouad, M. M., Amin, K. M., El-Bendary,

N., & Hassanien, A. E. (2015). Brain computer

interface: a review. Brain-computer interfaces, 3-

30.

[62]. Urigüen, J. A., & Garcia-Zapirain, B.

(2015). EEG artifact removal—state-of-the-art

and guidelines. Journal of neural engineering,

12(3), 031001.

[63]. Islam, M. K., Rastegarnia, A., & Yang,

Z. (2016). Methods for artifact detection and

removal from scalp EEG: A review.

Neurophysiologie Clinique/Clinical

Neurophysiology, 46(4-5), 287-305.

[64]. Mumtaz, W., Rasheed, S., & Irfan, A.

(2021). Review of challenges associated with the

EEG artifact removal methods. Biomedical

Signal Processing and Control, 68, 102741.

[65]. Radüntz, T., Scouten, J., Hochmuth, O.,

& Meffert, B. (2015). EEG artifact elimination by

extraction of ICA-component features using

image processing algorithms. Journal of

neuroscience methods, 243, 84-93.

[66]. Radüntz, T., Scouten, J., Hochmuth, O.,

& Meffert, B. (2017). Automated EEG artifact

elimination by applying machine learning

algorithms to ICA-based features. Journal of

neural engineering, 14(4), 046004.

[67]. Roy, V., Shukla, P. K., Gupta, A. K.,

Goel, V., Shukla, P. K., & Shukla, S. (2021).

Taxonomy on EEG artifacts removal methods,

issues, and healthcare applications. Journal of

Organizational and End User Computing

(JOEUC), 33(1), 19-46.

[68]. Mannan, M. M. N., Kamran, M. A., &

Jeong, M. Y. (2018). Identification and removal

of physiological artifacts from

electroencephalogram signals: A review. Ieee

Access, 6, 30630-30652.

[69]. Gevins, A. S., Yeager, C. L., Zeitlin, G.

M., Ancoli, S., & Dedon, M. F. (1977). On-line

computer rejection of EEG artifact.

Electroencephalography and clinical

Neurophysiology, 42(2), 267-274.

[70]. Park, H. J., Jeong, D. U., & Park, K. S.

(2002). Automated detection and elimination of

periodic ECG artifacts in EEG using the energy

interval histogram method. IEEE transactions on

Biomedical Engineering, 49(12), 1526-1533.

[71]. Nolan, H., Whelan, R., & Reilly, R. B.

(2010). FASTER: fully automated statistical

thresholding for EEG artifact rejection. Journal of

neuroscience methods, 192(1), 152-162.

[72]. Tatum, W. O., Dworetzky, B. A., &

Schomer, D. L. (2011). Artifact and recording

concepts in EEG. Journal of clinical

neurophysiology, 28(3), 252-263.

[73]. Jung, C. Y., & Saikiran, S. S. (2016). A

review on EEG artifacts and its different removal

technique. Asia-pacific Journal of Convergent

Research Interchange, 2(4), 43-60.

[74]. Jiang, X., Bian, G. B., & Tian, Z. (2019).

Removal of artifacts from EEG signals: a review.

Sensors, 19(5), 987.

[75]. Roháľová, M., Sykacek, P., Koskaand,

M., & Dorffner, G. (2001). Detection of the EEG

Artifacts by the Means of the (Extended) Kalman

Filter. Meas. Sci. Rev, 1(1), 59-62.

[76]. Blum, S., Jacobsen, N. S., Bleichner, M.

G., & Debener, S. (2019). A Riemannian

modification of artifact subspace reconstruction

for EEG artifact handling. Frontiers in human

neuroscience, 13, 141.

[77]. Shao, S. Y., Shen, K. Q., Ong, C. J., &

Wilder-Smith, E. P. (2008). Automatic EEG

artifact removal: a weighted support vector

machine approach with error correction. IEEE

Transactions on Biomedical Engineering, 56(2),

336-344.

[78]. Nejedly, P., Cimbalnik, J., Klimes, P.,

Plesinger, F., Halamek, J., Kremen, V., ... &

Jurak, P. (2019). Intracerebral EEG artifact

identification using convolutional neural

networks. Neuroinformatics, 17(2), 225-234.

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

[79]. Somers, B., Francart, T., & Bertrand, A.

(2018). A generic EEG artifact removal

algorithm based on the multi-channel Wiener

filter. Journal of neural engineering, 15(3),

036007.

[80]. Saba-Sadiya, S., Chantland, E., Alhanai,

T., Liu, T., & Ghassemi, M. M. (2021).

Unsupervised EEG artifact detection and

correction. Frontiers in digital health, 2, 608920.

[81]. Islam, M. K., Rastegarnia, A., & Yang,

Z. (2016). Methods for artifact detection and

removal from scalp EEG: A review.

Neurophysiologie Clinique/Clinical

Neurophysiology, 46(4-5), 287-305.

[82]. Abreu, R., Leal, A., & Figueiredo, P.

(2018). EEG-informed fMRI: a review of data

analysis methods. Frontiers in human

neuroscience, 12, 29.

[83]. Varone, G., Hussain, Z., Sheikh, Z.,

Howard, A., Boulila, W., Mahmud, M., ... &

Hussain, A. (2021). Real-time artifacts reduction

during TMS-EEG co-registration: a

comprehensive review on technologies and

procedures. Sensors, 21(2), 637.

[84]. Jung, T. P., Humphries, C., Lee, T. W.,

Makeig, S., McKeown, M. J., Iragui, V., &

Sejnowski, T. J. (1998, September). Removing

electroencephalographic artifacts: comparison

between ICA and PCA. In Neural Networks for

Signal Processing VIII. Proceedings of the 1998

IEEE Signal Processing Society Workshop (Cat.

No. 98TH8378) (pp. 63-72). IEEE.

[85]. Anderer, P., Roberts, S., Schlögl, A.,

Gruber, G., Klösch, G., Herrmann, W., ... &

Saletu, B. (1999). Artifact processing in

computerized analysis of sleep EEG–a review.

Neuropsychobiology, 40(3), 150-157.

[86]. Chen, X., Xu, X., Liu, A., Lee, S., Chen,

X., Zhang, X., ... & Wang, Z. J. (2019). Removal

of muscle artifacts from the EEG: a review and

recommendations. IEEE Sensors Journal, 19(14),

5353-5368.

[87]. Cao, K., Guo, Y., & Su, S. W. (2015,

December). A review of motion related EEG

artifact removal techniques. In 2015 9th

International Conference on Sensing Technology

(ICST) (pp. 600-604). IEEE.

[88]. Klekowicz, H., Malinowska, U.,

Piotrowska, A. J., Wołyńczyk-Gmaj, D.,

Niemcewicz, S., & Durka, P. J. (2009). On the

robust parametric detection of EEG artifacts in

polysomnographic recordings. Neuroinformatics,

7(2), 147-160.

[89]. Minguillon, J., Lopez-Gordo, M. A., &

Pelayo, F. (2017). Trends in EEG-BCI for daily-

life: Requirements for artifact removal.

Biomedical Signal Processing and Control, 31,

407-418.

[90]. Sadiya, S., Alhanai, T., & Ghassemi, M.

M. (2021, May). Artifact detection and correction

in eeg data: A review. In 2021 10th International

IEEE/EMBS Conference on Neural Engineering

(NER) (pp. 495-498). IEEE.

[91]. Craik, A., He, Y., & Contreras-Vidal, J.

L. (2019). Deep learning for

electroencephalogram (EEG) classification tasks:

a review. Journal of neural engineering, 16(3),

031001.

[92]. Haumann, N. T., Parkkonen, L.,

Kliuchko, M., Vuust, P., & Brattico, E. (2016).

Comparing the performance of popular

MEG/EEG artifact correction methods in an

evoked-response study. Computational

Intelligence and Neuroscience, 2016.

[93]. Sazgar, M., & Young, M. G. (2019).

EEG artifacts. In Absolute epilepsy and EEG

rotation review (pp. 149-162). Springer, Cham.

[94]. Jung, T. P., Makeig, S., Humphries, C.,

Lee, T. W., Mckeown, M. J., Iragui, V., &

Sejnowski, T. J. (2000). Removing

electroencephalographic artifacts by blind source

separation. Psychophysiology, 37(2), 163-178.

[95]. Kaya, I. (2019). A brief summary of EEG

artifact handling. Brain-Computer Interface.

[96]. Taherisadr, M., Dehzangi, O., & Parsaei,

H. (2017). Single channel EEG artifact

identification using two-dimensional multi-

resolution analysis. Sensors, 17(12), 2895.

[97]. Jafarifarmand, A., & Badamchizadeh, M.

A. (2019). EEG artifacts handling in a real

practical brain–computer interface controlled

vehicle. IEEE Transactions on Neural Systems

and Rehabilitation Engineering, 27(6), 1200-

1208.

[98]. Gorjan, D., Gramann, K., De Pauw, K.,

& Marusic, U. (2022). Removal of movement-

induced EEG artifacts: current state of the art and

guidelines. Journal of neural engineering.

[99]. Hartmann, M. M., Schindler, K.,

Gebbink, T. A., Gritsch, G., & Kluge, T. (2014).

PureEEG: Automatic EEG artifact removal for

epilepsy monitoring. Neurophysiologie

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023

Clinique/Clinical Neurophysiology, 44(5), 479-

490.

[100]. Muthukumaraswamy, S. D. (2013).

High-frequency brain activity and muscle

artifacts in MEG/EEG: a review and

recommendations. Frontiers in human

neuroscience, 7, 138.

[101]. Kang, G., Jin, S. H., Kim, D. K., & Kang,

S. W. (2018). T59. EEG artifacts removal using

machine learning algorithms and independent

component analysis. Clinical Neurophysiology,

129, e24.

Contribution of Individual Authors to the

Creation of a Scientific Article (Ghostwriting

Policy)

The authors equally contributed in the present

research, at all stages from the formulation of the

problem to the final findings and solution.

Sources of Funding for Research Presented in a

Scientific Article or Scientific Article Itself

No funding was received for conducting this study.

Conflict of Interest

The authors have no conflicts of interest to declare

that are relevant to the content of this article.

Creative Commons Attribution License 4.0

(Attribution 4.0 International, CC BY 4.0)

This article is published under the terms of the

Creative Commons Attribution License 4.0

https://creativecommons.org/licenses/by/4.0/deed.en

_US

International Journal of Electrical Engineering and Computer Science

DOI: 10.37394/232027.2023.5.8

Thotttempudi Pardhu, Nagesh Deevi

E-ISSN: 2769-2507

Volume 5, 2023