Over the past two decades, motor imagery brain-computer interface (MI-BCI) system has been extensively developed. In this system signal processing algorithms are critical to robust operation. In BCI community, however, there is no comprehensive review of the recent development of signal processing algorithms. Through analyzing the latest papers, signal processing algorithms of pre-processing, feature extraction, feature selection, and classification components are discussed in detail. Besides, post-processing and other existing problems are mentioned. The following key issues are addressed: (1) which components are the key of signal processing; (2) which signal processing algorithms are frequently used in each component; (3) which signal processing algorithms attract more attention. This information can be used as reference and guidance for further research.
Nicolas-AlonsoL.F. and Gomez-GilJ., Brain computer interfaces, a review, Sensors12(2) (2012), 1211–1279.
2.
FatourechiM., BashashatiA., WardR.K. and BirchG.E., EMG and EOG artifacts in brain computer interface systems: A survey, Clin Neurophysiol118(3) (2007), 480–494.
3.
BashashatiA., FatourechiM., WardR.K. and BirchG.E., A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals, J Neural Eng4(2) (2007), R32–R57.
4.
HwangH.J., KimS., ChoiS. and ImC.H., EEG-based brain-computer interfaces: A thorough literature survey, Int J Hum Comput Interact29(12) (2013), 814–826.
5.
Velasco-AlvarezF., Ron-AngevinR. and Blanca-MenaM.J., Free virtual navigation using motor imagery through an asynchronous brain-computer interface, Presence Teleop Virt19(1) (2010), 71–81.
6.
ObermaierB., MullerG.R. and PfurtschellerG., “Virtual keyboard” controlled by spontaneous EEG activity, IEEE Trans Neural Syst Rehabil Eng11(4) (2003), 422–426.
7.
LeebR., PerdikisS., ToninL., BiasiucciA., TavellaM., CreaturaM., MolinaA., Al-KhodairyA., CarlsonT. and MillanJ.D., Transferring brain-computer interfaces beyond the laboratory: Successful application control for motor-disabled users, Artif Intell Med59(2) (2013), 121–132.
8.
WolpawJ.R., BirbaumerN., McFarlandD.J., PfurtschelleG. and VaughanT.M., Brain-computer interfaces for communication and control, Clin Neurophysiol113(6) (2002), 767–791.
9.
MuhlC., AllisonB., NijholtA. and ChanelG., A survey of affective brain computer interface: Principles, state-of-the-art, and challenges, Brian-computer Interfaces1(2) (2014), 66–84.
10.
van GervenM., FarquharJ., SchaeferR., VlekR., GeuzeJ., NijholtA., RamseyN., HaselagerP., VuurpijlL., GielenS. and DesainP., The brain-computer interface cycle, J Neural Eng6(4) (2009), 041001.
11.
MasonS.G., BashashatiA., FatourechiM., NavarroK.F. and BirchG.E., A comprehensive survey of brain interface technology designs, Ann Biomed Eng35(2) (2007), 137–169.
12.
PasqualottoE., FedericiS. and BelardinelliM.O., Toward functioning and usable brain-computer interfaces (BCIs): A literature review, Disabil Rehabil7(2) (2012), 89–103.
13.
HeB., BaxterB., EdelmanB.J., ClineC.C. and YeW.J.W., Noninvasive brain-computer interfaces based on sensorimotor rhythms, P IEEE103(6) (2015), 907–925.
14.
AlotaibyT., Abd El-SamieF.E., AlshebeiliS.A. and AhmadI., A review of channel selection algorithms for EEG signal processing, Eurasip J Adv Sigl Pr2015 (2015), 66.
15.
HammonP.S. and de SaV.R., Preprocessing and meta-classification for brain-computer interfaces, IEEE Trans Biomed Eng54(3) (2007), 518–525.
16.
LiuQ., ChenK., AiQ.S. and XieS.Q., Review: Recent development of signal processing algorithms for SSVEP-based brain computer interfaces, J Med Biol Eng34(4) (2014), 299–309.
17.
LotteF., CongedoM., LecuyerA., LamarcheF. and ArnaldiB., A review of classification algorithms for EEG-based brain-computer interfaces, J Neural Eng4(2) (2007), R1–R13.
18.
KrusienskiD.J., Grosse-WentrupM., GalanF., CoyleD., MillerK.J., ForneyE. and AndersonC.W., Critical issues in state-of-the-art brain-computer interface signal processing, J Neural Eng8(2) (2011), 025002.
19.
YaoL., ShuX.K., MengJ.J., ZhangD.G., ShengX.J. and ZhuX.Y., Enhanced motor imagery based brain-computer interface via unilateral wrist vibrotactile stimulation, Proceedings of the 6th IEEE/EMBS International Conference on Neural Engineering2013, pp29–32.
20.
Galdo-AlvarezS., BonillaF.M., Gonzalez-VillarlA.J. and Carrillo-de-la-PenaM.T., Functional equivalence of imagined vs. real performance of an inhibitory task: An EEG/ERP study, Front Hum Neurosci10 (2016), 467.
21.
LuJ., McFarlandD.J. and WolpawJ.R., Adaptive laplacian filtering for sensorimotor rhythm-based brain-computer interfaces, J Neural Eng10(1) (2013), 016002.
22.
McFarlandD.J., The advantages of the surface laplacian in brain-computer interface research, Int J Psychophysiol97(3) (2015), 271–276.
23.
BrandlS., FrolichL., HohneJ., MullerK.R. and SamekW., Brain-computer interfacing under distraction: An evaluation study, J Neural Eng13(5) (2016), 056012.
24.
XuR., JiangN., Mrachacz-KerstingN., DremstrupK. and FarinaD., Factors of influence on the performance of a short-latency non-invasive brain switch: Evidence in healthy individuals and implication for motor function rehabilitation, Front Neurosci9 (2016), 527.
25.
ParkW., KwonG.H., KimY.H., LeeJ.H. and KimL., EEG response varies with lesion location in patients with chronic stroke, J Neuroeng Rehabil13 (2016), 21.
26.
YaoL., ShengX.J., ZhangD.G., JiangN., FarinaD. and ZhuX.Y., A BCI system based on somatosensory attentional orientation, IEEE Trans Neural Syst Rehabil Eng25(1) (2017), 78–87.
27.
VuckovicA., HasanM.A., OsuagwuB., FraserM., AllanD.B., ConwayB.A. and NasseroleslamiB., The influence of central neuropathic pain in paraplegic patients on performance of a motor imagery based brain computer interface, Clin Neurophysiol126(11) (2015), 2170–2180.
28.
XiaoR. and DingL., EEG resolutions in detecting and decoding finger movements from spectral analysis, Front Neurosci9 (2015), 308.
29.
DuannJ.R. and ChiouJ.C., A comparison of independent event-related desynchronization responses in motor-related brain areas to movement execution, movement imagery, and movement observation, Plos One11(9) (2016), e0162546.
30.
Garcia-CossioE., SeverensM., NienhuisB., DuysensJ., DesainP., KeijsersN. and FarquharJ., Decoding sensorimotor rhythms during robotic-assisted treadmill walking for brain computer interface (BCI) applications, Plos One10(12) (2015), e0137910.
31.
SeverensM., Perusquia-HernandezM., NienhuisB., FarquharJ. and DuysensJ., Using actual and imagined walking related desynchronization features in a BCI, IEEE Trans Neural Syst Rehabil Eng23(5) (2015), 877–886.
32.
HashimotoY. and UshibaJ., EEG-based classification of imaginary left and right foot movements using beta rebound, Clin Neurophysiol124(11) (2013), 2153–2160.
33.
Lopez-LarrazE., MontesanoL., Gil-AgudoÁ. and MinguezJ., Continuous decoding of movement intention of upper limb self-initiated analytic movements from pre-movement EEG correlates, J Neuroeng Rehabil11 (2014), 153.
34.
GeronimoA., SimmonsZ. and SchiffS.J., Performance predictors of brain– computer interfaces in patients with amyotrophic lateral sclerosis, J Neural Eng13(2) (2016), 026002.
35.
ZichC., De VosM., KrancziochC. and DebenerS., Wireless EEG with individualized channel layout enables efficient motor imagery training, Clinl Neurophysiol126(4) (2015), 698–710.
DalyI., BillingerM., Laparra-HernandezJ., AloiseF., GarcíaM.L., FallerJ., SchererR. and Muller-PutzG., On the control of brain-computer interfaces by users with cerebral palsy, Clin Neurophysiol124(9) (2013), 1787–1797.
38.
BloklandY., SpyrouL., ThijssenD., EijsvogelsT., ColierW., Floor-WesterdijkM., VlekR., BruhnJ. and FarquharJ., Combined EEG-fNIRS decoding of motor attempt and imagery for brain switch control: An offline study in patients with tetraplegia, IEEE Trans Neural Syst Rehabil Eng22(2) (2014), 222–229.
39.
TangwiriyasakulC., MocioiuV., van PuttenM.J.A.M. and RuttenW.L.C., Classification of motor imagery performance in acute stroke, J Neural Eng11(3) (2014), 036001.
40.
GibsonR.M., ChennuS., OwenA.M. and CruseD., Complexity and familiarity enhance single-trial detectability of imagined movements with electroencephalography, Clin Neurophysiol125(8) (2014), 1556–1567.
41.
Muller-PutzG.R., SteyrD. and FallerJ., Adaptive hybrid brain-computer interaction: Ask a trainer for assistance!, Proceedings of the 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society2014, pp. 1493–1496.
42.
JerbicA.B., HorkiP., SoviljS., IsgumV. and CifrekM., Hilbert-huang time-frequency analysis of motor imagery EEG data for brain-computer interfaces, Proceedings of the 6th European Conference on the International Federation for Medical and Biological Engineering2015, pp. 62–65.
43.
Cantillo-NegreteJ., Gutierrez-MartinezJ., Carino-EscobarR.I., Carrillo-MoraP. and Elias-VinasD., An approach to improve the performance of subject-independent BCIs-based on motor imagery allocating subjects by gender, Biomed Eng Online13 (2014), 158.
44.
ZhangR., XuP., ChenR., LiF.L., GuoL.J., LiP.Y., ZhangT. and YaoD.Z., Predicting inter-session performance of SMR-based brain-computer interface using the spectral entropy of resting-state EEG, Brain Topogr28(5) (2015), 680–690.
45.
ZichC., DebenerS., ThoeneA.K., ChenL.C. and KrancziochC., Simultaneous EEG-fNIRS reveals how age and feedback affect motor imagery signatures, Neurobiol Aging49 (2017), 183–197.
46.
YiW.B., QiuS., QiH.Z., ZhangL.X., WanB.K. and MingD., EEG feature comparison and classification of simple and compound limb motor imagery, J Neuroeng Rehabil10 (2013), 106.
47.
Lindig-LeonC. and BougrainL., A multi-label classification method for detection of combined motor imageries, Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics2015, pp. 3128–3133.
48.
YiW.B., QiuS., WangK., QiH.Z., HeF., ZhouP., ZhangL.X. and MingD., EEG oscillatory patterns and classification of sequential compound limb motor imagery, J Neuroeng Rehabil13 (2016), 11.
49.
BamdadianA., GuanC.T., AngK.K. and XuJ.X., Towards improvement of MI-BCI performance of subjects with BCI deficiency, Proceedings of the 7th International IEEE/EMBS Conference on Neural Engineering, 2015, pp. 17–20.
50.
SchwarzA., SchererR., SteyrlD., FallerJ. and Muller-PutzG.R., A co-adaptive sensory motor rhythms brain-computer interface based on common spatial patterns and random forest, Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society2015, pp. 1049–1052.
51.
YiW.B., QiuS., WangK., QiH.Z., ZhaoX., HeF., ZhouP., YangJ.J. and MingD., Enhancing performance of a motor imagery based brain-computer interface by incorporating electrical stimulation-induced SSSEP. J Neural Eng14(2) (2017), 026002.
52.
ThomasK.P., GuanC.T., LauC.T., VinodA.P. and AngK.K., A new discriminative common spatial pattern method for motor imagery brain-computer interfaces, IEEE Trans Biomed Eng56(11) (2009), 2730–2733.
53.
ThomasK.P., GuanC.T., LauC.T., VinodA.P. and AngK.K., Adaptive tracking of discriminative frequency components in electroencephalograms for a robust brain-computer interface, J Neural Eng8(3) (2011), 036007.
54.
KamT.E., SukH.I. and LeeS.W., Non-homogeneous spatial filter optimization for electroencephalogram (EEG)-based motor imagery classification, Neurocomputing108 (2013), 58–68.
55.
LiangS., ChoiK.S., QinJ., PangW.M., WangQ. and HengP.A., Improving the discrimination of hand motor imagery via virtual reality based visual guidance, Comput Meth Prog Bio132 (2016), 63–74.
56.
LiM.A., CuiY., HaoD.M. and YangJ.F., An adaptive feature extraction method in BCI-based rehabilitation, J Intell Fuzzy Syst28(2) (2015), 525–535.
57.
TradD., Al-aniT. and JemniM., A feature extraction technique of EEG based on EMD-BP for motor imagery classification in BCI, Proceedings of the International Conference on Information and Communication Technology and Accessibility, 2015, pp. 1–6.
58.
DarvishiS., GharabaghiA., BoulayC.B., RiddingM.C., AbbottD. and BaumertM., Proprioceptive feedback facilitates motor imagery-related operant learning of sensorimotor beta-band modulation, Front Neurosci11 (2017), 60.
59.
MengM., LuS.N., ManH.T., MaY.L. and GaoY.Y., Feature extraction method of motor imagery EEG based on DTCWT sample entropy, Proceedings of the 34th Chinese Control Conference2015, pp. 3964–3968.
60.
HongJ., QinX.S., BaiJ., ZhangP.P. and ChengY., A combined feature extraction method for left-right hand motor imagery in BCI, Proceedings of the International Conference on Mechatronics and Automation2015, pp. 2621–2625.
61.
Suraj, TiwariP., GhoshS. and SinhaR.K., Classification of two class motor imagery tasks using hybrid GA-PSO based k-means clustering, Comput Intel Neurosc2015 (2015), 945729.
62.
ChungY.G., KangJ.H. and KimS.P., Correlation of fronto-central phase coupling with sensorimotor rhythm modulation, Neural Networks36 (2012), 46–50.
63.
JianW.J., ChenM.Y. and McFarlandD.J., EEG based zero-phase phase-locking value (PLV) and effects of spatial filtering during actual movement, Brain Res Bull130 (2017), 156–164.
64.
PeiX.M., ZhengC.X., XuJ., BinG.Y. and WangH.W., Multi-channel linear descriptors for event-related EEG collected in brain computer interface, J Neural Eng3(1) (2006), 52–58.
65.
LiX., ZhangH., GuanC.T., OngS.H., PanY. and AngK.K., Joint spatial-temporal filter design for analysis of motor imagery EEG, Proceedings of International Conference on Acoustics, Speech and Signal Processing2013, pp978–982.
66.
LiM.A., LiuH.N., ZhuW. and YangJ.F., Applying improved multiscale fuzzy entropy for feature extraction of MI-EEG, Appl Sci7(1) (2017), 92.
67.
HuangD.D., QianK., FeiD.Y., JiaW.C., ChenX.D. and BaiO., Electroencephalography (EEG)-based brain-computer interface (BCI): A 2-D virtual wheelchair control based on event-related desynchronization/synchronization and state control, IEEE Trans Neural Syst Rehabil Eng20(3) (2012), 379–388.
68.
IbanezJ., SerranoJ.I., del CastilloM.D., Monge-PereiraE., Molina-RuedaF., Alguacil-DiegoI. and PonsJ.L., Detection of the onset of upper-limb movements based on the combined analysis of changes in the sensorimotor rhythms and slow cortical potentials, J Neural Eng11(5) (2014), 056009.
69.
ParkW., KwonG.H., KimD.H., KimY.H., KimS.P. and KimL., Assessment of cognitive engagement in stroke patients from single-trial EEG during motor rehabilitation, IEEE Trans Neural Syst Rehabil Eng23(3) (2015), 351–362.
70.
KamrunnaharM., DiasN.S. and SchiffS.J., Toward a model-based predictive controller design in brain-computer interfaces, Ann Biomed Eng39(5) (2011), 1482–1492.
71.
ShanH.J., XuH.J., ZhuS.A. and HeB., A novel channel selection method for optimal classification in different motor imagery BCI paradigms, Biomed Eng Online14 (2015), 93.
72.
OnoT., KimuraA. and UshibaJ., Daily training with realistic visual feedback improves reproducibility of event-related desynchronisation following hand motor imagery, Clin Neurophysiol124(9) (2013), 1779–1786.
73.
ZichC., DebenerS., De VosM., FrerichsS., MaurerS. and KrancziochC., Lateralization patterns of covert but not overt movements change with age: An EEG neurofeedback study, Neuroimage116 (2015), 80–91.
74.
ReynoldsC., OsuagwuB.A. and VuckovicA., Influence of motor imagination on cortical activation during functional electrical stimulation, Clin Neurophysiol126(7) (2015), 1360–1369.
75.
MisawaT., MatsudaJ. and HirobayashiS., A singl-trial multiclass classification of various motor imagery tasks for EEG-based brain-computer interface communication, Electr Commun Jpn100(1) (2017), 18–26.
76.
AcqualagnaL., BotrelL., VidaurreC., KublerA. and BlankertzB., Large-scale assessment of a fully automatic co-adaptive motor imagery-based brain computer interface, Plos One11(2) (2016), e0148886.
77.
KitaharaK., HayashiY., KondoT. and YanoS., Sound imagery contributes to foot MI-based BCI even through it does not influence on the sensorimotor rhythms, Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference2016, pp. 1–6.
78.
SollfrankT., RamsayA., PerdikisS., WilliamsonJ., Murray-SmithR., LeebR., MillanJ.D. and KublerA., The effect of multimodal and enriched feedback on SMR-BCI performance, Clin Neurophysiol127(1) (2015), 490–498.
79.
ShinY., LeeS., LeeJ. and LeeH.N., Sparse representation-based classification scheme for motor imagery-based brain-computer interface systems, J Neural Eng9(5) (2012), 056002.
80.
HammerE.M., HalderS., BlankertzB., SannelliC., DickhausT, KleihS., MullerK.R. and KublerA., Psychological predictors of SMR-BCI performance, Biol Psychol89(1) (2012), 80–86.
81.
ZhangR., XuP., ChenR., LiF.L., GuoL.J., LiP.Y., ZhangT. and YaoD.Z., Predicting inter-session performance of SMR-based brain-computer interface using the spectral entropy of resting-state EEG, Brain Topogr28(5) (2015), 680–690.
82.
SburleaA.l., MontesanoL. and MinguezJ., Continuous detection of the self-initiated walking pre-movement state from EEG correlates without session-to-session recalibration, J Neural Eng12(3) (2015), 036007.
83.
MondiniV., MangiaA.L. and CappelloA., EEG-based BCI system using adaptive features extraction and classification procedures, Comput Intel Neurosc2016 (2016), 4562601.
84.
RousselP., NegishiA. and MitsukuraY., Presentation of an SMR-based BCI using auditory feedback based on pitch, Proceedings of the 17th International Conference on Research and Education in Mechatronics2016, pp. 174–177.
85.
IbanezJ, SerranoJ.I., del CastilloM.D., GallegoJ.A. and RoconE., Online detector of movement intention based on EEG-application in tremor patients, Biomed Signal Proces8(6) (2013), 822–829.
86.
MachadoJ. and BalbinotA., Executed movement using EEG signals through a naive bayes classifier, Micromachines5(4) (2014), 1082–1105.
87.
KusR., ValbuenaD., ZygierewiczJ., MalechkaT., GraeserA. and DurkaP., Asynchronous BCI based on motor imagery with automated calibration and neurofeedback training, IEEE Trans Neural Syst Rehabil Eng20(6) (2012), 823–835.
88.
LisiG., HamayaM., NodaT. and MorimotoJ., Dry-wireless EEG and asynchronous adaptive feature extraction towards a plug-and-play co-adaptive brain robot interface, Proceedings of the International Conference on Robotics and Automation2016, pp. 959–966.
89.
TangZ.C., SunS.Q., ZhangS.Y., ChenY.M., LiC. and ChenS., A brain-machine interface based on ERD/ERS for an upper-limb exoskeleton control, Sensors16(12) (2016), 2050.
90.
EdelmanB.J., BaxterB. and HeB., EEG source imaging enhances the decoding of complex right-hand motor imagery tasks, IEEE Trans Biomed Eng63(1) (2016), 4–14.
91.
LiuC., WangH., LuZ.G., EEG classification for multiclass motor imagery BCI, Proceedings of the 25th Chinese Control and Decision Conference2013, pp. 4450–4453.
92.
MeenaY.K., CecottiH., Wong-LinK., PrasadG., Towards increasing the number of commands in a hybrid brain-computer interface with combination of gaze and motor imagery, Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society2015, pp. 506–509.
93.
Aviles-CruzC., Villegas-CortezJ., Ferreyra-RamirezA., LopezA.Z., EEG pattern recognition: An efficient improvement combination of ERD/ERS/laterality features to create a self-paced BCI system, Proceedings of the 8th Mexican Conference on Pattern Recognition2016, pp. 231–240.
94.
SaaJ.F.D. and CetinM., Discriminative methods for classification of asynchronous imaginary motor tasks from EEG data, IEEE Trans Neural Syst Rehabil Eng21(5) (2013), 716–724.
95.
LiY., KambaraH., KoikeY. and SugiyamaM., Application of covariate shift adaptation techniques in brain-computer interfaces, IEEE Trans Biomed Eng57(6) (2010), 1318–1324.
96.
LotteF., Signal processing approaches to minimize or suppress calibration time in oscillatory activity-based brain-computer interfaces, P IEEE103(6) (2015), 871–890.
97.
AbdulghaniA.M., CassonA.J. and Rodriguez-VillegasE., Compressive sensing scalp EEG signals: Implementations and practical performance, Med Biol Eng Comput50(11) (2012), 1137–1145.
98.
Sole-CasalsJ., CaiafaC.F., ZhaoQ. and CichockiA., Brain-computer interface with corrupted EEG data: A tensor completion approach, Cogn Comput (2018). 10.1007/s12559-018-9574-9.
