The evolution of AI approaches for motor imagery EEG-based BCIs Aurora Saibene120000000244058234 Silvia Corchs230000000217398110

2025-04-26 0 0 377.03KB 16 页 10玖币

侵权投诉

The evolution of AI approaches for motor

imagery EEG-based BCIs

Aurora Saibene1,2[0000−0002−4405−8234], Silvia Corchs2,3[0000−0002−1739−8110],

Mirko Caglioni1, and Francesca Gasparini1,2[0000−0002−6279−6660]

1University of Milano-Bicocca, Viale Sarca 336, 20126, Milano, Italy

aurora.saibene@unimib.it, m.caglioni2@campus.unimib.it,

francesca.gasparini@unimib.it

2NeuroMI, Milan Center for Neuroscience, Piazza dell’Ateneo Nuovo 1, 20126,

Milano, Italy

3University of Insubria, Via J. H. Dunant 3, 21100, Varese, Italy

silvia.corchs@uninsubria.it

Abstract. The Motor Imagery (MI) electroencephalography (EEG) based

Brain Computer Interfaces (BCIs) allow the direct communication be-

tween humans and machines by exploiting the neural pathways connected

to motor imagination. Therefore, these systems open the possibility of

developing applications that could span from the medical ﬁeld to the

entertainment industry. In this context, Artiﬁcial Intelligence (AI) ap-

proaches become of fundamental importance especially when wanting to

provide a correct and coherent feedback to BCI users. Moreover, publicly

available datasets in the ﬁeld of MI EEG-based BCIs have been widely

exploited to test new techniques from the AI domain. In this work, AI

approaches applied to datasets collected in diﬀerent years and with dif-

ferent devices but with coherent experimental paradigms are investigated

with the aim of providing a concise yet suﬃciently comprehensive survey

on the evolution and inﬂuence of AI techniques on MI EEG-based BCI

data.

Keywords: artiﬁcial intelligence ·brain computer interface ·electroen-

cephalography ·motor imagery

1 Introduction

Translating thoughts into commands understandable by external applications

and devices is the basic principle ruling the development of Brain Computer

Interfaces (BCIs) [32]. The most appreciated method to collect neural signals is

the electroencephalogram (EEG), having that it records data with non-invasive

surface sensors called electrodes, it is suﬃciently low-cost and with possible high

temporal and spatial resolution [7]. Moreover, the EEG signals are characterized

by rhythms, whose ﬂuctuations may be exploited to detect speciﬁc brain states

[35]. Among these brain conditions, the imagination of voluntary movements,

called Motor Imagery (MI), may be observed over the primary sensorimotor cor-

tex with amplitude variations of the µand βrhythms [39] [8]. These eﬀects can

arXiv:2210.06290v1 [eess.SP] 11 Oct 2022

2 A. Saibene et al.

be exploited to create MI EEG-based BCIs that can be used for a variety of ap-

plications spanning from rehabilitation procedures to the control of wheelchair

movements [32], and in conjunction with virtual and augmented reality [15].

Therefore, one of the main BCI life-cycle components is represented by feedback,

which beneﬁts from the evolution and improvement of Artiﬁcial Intelligence (AI)

approaches [6] in predicting the diﬀerent brain states to be translated into sys-

tem commands.

Consequently, how have the AI techniques evolved in and inﬂuenced the ﬁeld

of MI EEG-based BCIs, considering the great number of possibilities oﬀered by

these systems?

This work aims at providing a brief overview and discussion on this topic by

analysing the AI approaches that have been applied to some representative

datasets present in the domain literature.

Therefore, in Section 2 the paper ﬁrstly provides an overall view of the time-

line related to MI EEG-based BCIs and justiﬁes the choice of speciﬁc datasets,

that are described in Section 3. An overview of the AI techniques applied to these

data is provided in Section 4 and observations on the presented AI approaches

are discussed in Section 5. Finally, conclusions are drawn in Section 6.

2 Overview

The research on MI EEG-based BCIs has become particularly proliﬁc in the last

years. In fact, typing a quick query on Scopus4title, abstract and keywords of

indexed works, i.e., TITLE-ABS-KEY((mi OR motor AND imagery OR motor

AND imagination) AND (eeg OR electroencephalographic) AND based AND (bci

OR brain AND computer AND interface)), we obtain the graphic in Figure 1.

Notice that the search was conducted during September 2022.

Besides having a clear understanding of a constant increase of publications on

these topics starting from 2017 and having for now its apex in 2021, Figure 1

provides a story of the early phases of the MI EEG-based BCIs, which set the

foundation for later works.

An initial period (1996-2003) during which the BCI community began to discuss

these topics was followed by a discrete boost (2004) of the research production

probably due to the insightful work of Schalk et al. [31] and the outcome of the

BCI Competition 2003 [5].

Starting from the evident direction took by many laboratories concerning the de-

velopment of systems capable of enabling a mean of communication and control

for patients with severe motor disabilities, Schalk et al. presented the BCI20005,

which is an open-source platform that allows the management of BCI systems

and that remains active and maintained to the present day. Moreover, not only

some of the authors of [31] were involved in the BCI Competition 2003, but also

the names of the researchers of the pioneer work of 1996 [13] obtained with the

4https://www.scopus.com/

5https://www.bci2000.org/mediawiki/index.php/Main_Page

The evolution of AI approaches for motor imagery EEG-based BCIs 3

Scopus search, unsurprisingly appear. In fact, they contributed to dataset III ti-

tled Motor Imagery, which presented data acquired on the main central cortical

electrodes (C{3,4,z}) during the imagination of left or right hand movements,

with the main aim of providing a continuous feedback to the BCI users. The win-

ning strategy to the proposed problem was presented by Lemm et al. [18], who

tried to disclose motor intention by characterizing the EEG signal rhythmic ac-

tivity through complex Morlet wavelet [34] application and using a probabilistic

model to predict left or right hand MI.

Fig. 1. Number of papers per year obtained by querying Scopus on MI EEG-based

BCI related keywords (search conducted during September 2022).

Afterwards, the BCI Competitions - Berlin Brain Computer-Interface6datasets

quickly became benchmarks on which test strategies to provide more eﬃcient and

reliable BCI systems.

By adding to the ﬁrst query the string (bci AND competition AND (2003 OR ii

OR iii OR iv)), representing the BCI Competition II (or 2003), III and IV, and

limiting the results to year 2021 only, 27 papers are provided in output, of which

23 use the BCI Competition IV datasets (especially, 2a and 2b). Considering

that Figure 1 reports 97 works published in 2021 and that the screening through

Scopus is done only on the title, abstract, and keywords of the works indexed

by this search engine, the number of publications using the BCI Competition IV

dataset 2a and 2b [33] seems to be fairly high and justiﬁes a deeper analysis con-

cerning the AI techniques tested on them to better understand their evolution

during a long time span.

However, these datasets present EEG recordings acquired on a restricted

number of subjects, considering a restricted number of electrodes and experimen-

tal conditions (as detailed in Section 3). Wanting to have a general overview of

the evolution of AI approaches in MI EEG-based BCIs and noticing its increased

6https://www.bbci.de/competition/

4 A. Saibene et al.

use as a benchmark in the last 10 years, the EEG Motor Movement/Imagery

Dataset [31] [11] collected from a larger population, using a diﬀerent montage,

and considering diverse MI tasks, but using the BCI2000 system, is also consid-

ered.

Moreover, a great attention has been given to wearable technologies, espe-

cially in the last few years, since the necessity of moving the use of BCIs from

medical and laboratory environments to real-world scenarios is becoming more

pressing due to a variety of needs like developing in-home rehabilitation tools

[9], exploiting customer-grade devices [37], and providing continuous assistive

technologies [23] that patients could easily use alone without having to buy ex-

pensive equipment.

Following these principles, Peterson et al. [29] have collected the MI-OpenBCI

dataset using wearable low-cost technologies to record MI EEG-based BCI data.

Therefore, an overview of this dataset is provided to have a closer look on future

developments of these new systems and the changing role of AI when facing

them.

3 Datasets

Considering the brief overview presented in Section 2, the datasets that will be at

the center of this paper analysis are the BCI Competition IV dataset 2a (2012)

and 2b (2012) [33], the EEG Motor Movement/Imagery Dataset (2009) [31] [11],

and the MI-OpenBCI (2020) one [29]. In this section a concise description of their

characteristics is reported for completeness.

3.1 BCI Competition IV dataset 2a

The BCI Competition IV dataset 2a [33] is provided under the name Contin-

uous Multi-class Motor Imagery. In fact, it has been collected from 9 subjects

executing a cue-based BCI paradigm consisting of left/right hand, both feet and

tongue MI. Each subject participated in diﬀerent days to 2 experimental sessions

containing 6 experimental runs of 48 trials each.

Figure 2 depicts the montage consisting of 22 Ag/AgCl electrodes for scalp

recording, reference and ground electrodes placed on the left and right mastoids,

and 3 monopolar electrooculogram channels (positioned to provide reference for

artifact removal).

The signals have been acquired with 250Hz sampling rate and the dataset au-

thors provided them bandpass (0.5-100Hz) and notch (50Hz) ﬁltered. The noisy

trials were removed by manual screening of experts.

3.2 BCI Competition IV dataset 2b

The BCI Competition IV dataset 2b [33] presents the following short description:

Session-to-Session Transfer of a Motor Imagery BCI under Presence of Eye

Artifacts. In fact, the motivation driving its presence into the BCI competition

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

TheevolutionofAIapproachesformotorimageryEEG-basedBCIsAuroraSaibene1;2[0000000244058234],SilviaCorchs2;3[0000000217398110],MirkoCaglioni1,andFrancescaGasparini1;2[0000000262796660]1UniversityofMilano-Bicocca,VialeSarca336,20126,Milano,Italyaurora.saibene@unimib.it,m.caglioni2@campus.unimib.it,france...

展开>> 收起<<

The evolution of AI approaches for motor imagery EEG-based BCIs Aurora Saibene120000000244058234 Silvia Corchs230000000217398110.pdf

共16页,预览4页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

The evolution of AI approaches for motor imagery EEG-based BCIs Aurora Saibene120000000244058234 Silvia Corchs230000000217398110

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: