The use of brain–computer interfaces (BCIs) to control intelligent devices is a current and future research direction. However, the challenges of low accuracy of real-time recognition and the need for multiple electroencephalographic channels are yet to be overcome. While a number of research teams have proposed many ways to improve offline classification accuracy, the potential problems in real-time experiments are often overlooked. In this study, we proposed a label-based channel diversion preprocessing to solve the problem of low real-time classification accuracy. The Tikhonov regularised common spatial-pattern algorithm (TRCSP) and one vs rest support vector machine (OVR-SVM) were used for feature extraction and pattern classification. High accuracy was achieved in real-time three-class classification using only three channels (average real-time accuracy of 87.46%, with a maximum of 90.33%). In addition, the stability and reliability of the system were verified through lighting control experiments in a real environment. Using the autonomy of MI and real-time feedback of light brightness, we have built a fully autonomous interactive system. The improvement in the real-time classification accuracy in this study is of great significance to the industrialisation of BCI.
De SilvaLCMorikawaCPetraIM. State of the art of smart homes. Eng Appl Artif Intell2012; 25: 1313–1321.
2.
QinLYNasirNMHuqMS, et al. Smart home control for disabled using brain computer interface. Int J Integr Eng2020; 12: 74–82.
3.
XiongMHotterRNadinD, et al. A low-cost, semi-autonomous wheelchair controlled by motor imagery and jaw muscle activation. In: 2019 IEEE international conference on systems, man and cybernetics (SMC), Bari, Italy, 6–9 October 2019, pp.2180–2185. New York: IEEE.
4.
YuYLiuYJiangJ, et al. An asynchronous control paradigm based on sequential motor imagery and its application in wheelchair navigation. IEEE Trans Neural Syst Rehabil Eng2018; 26: 2367–2375.
5.
XuBLiWLiuD, et al. Continuous hybrid BCI control for robotic arm using noninvasive electroencephalogram, computer vision, and eye tracking. Mathematics2022; 10: 618–623.
6.
BorgheaiSBMcLindenJZiskAH, et al. Enhancing communication for people in late-stage ALS using an fNIRS-based BCI system. IEEE Trans Neural Syst Rehabil Eng2020; 28: 1198–1207.
7.
PetersBBedrickSDudyS, et al. SSVEP BCI and eye tracking use by individuals with late-stage ALS and visual impairments. Front Hum Neurosci2020; 14: 595890.
8.
PawuśDPaszkielS. BCI wheelchair control using expert system classifying EEG signals based on power spectrum estimation and nervous tics detection. Appl Sci2022; 12(20): 10385.
9.
AbennaSNahidMBouyghfH, et al. EEG-based BCI: a novel improvement for EEG signals classification based on real-time preprocessing. Comput Biol Med2022; 148: 105931.
10.
JeyabalanVSamrajAKiongLC. Motor imaginary signal classification using adaptive recursive bandpass filter and adaptive autoregressive models for brain machine interface designs. Int J Bioeng Life Sci2007; 1(5): 242–249.
11.
QiuWFungKSChanFH, et al. Adaptive filtering of evoked potentials with radial-basis-function neural network prefilter. IEEE Trans Biomed Eng2002; 49(3): 225–232.
12.
IacovielloDPetraccaASpezialettiM, et al. A real-time classification algorithm for EEG-based BCI driven by self-induced emotions. Comput Methods Programs Biomed2015; 122(3): 293–303.
13.
LotzeMHalsbandU. Motor imagery. J Physiol Paris2006; 99: 386–395.
14.
PfurtschellerG. Functional brain imaging based on ERD/ERS. Vision Res2001; 41: 1257–1260.
15.
KhaziMKumarAVidyaMJ. Analysis of EEG using 10: 20 electrode system. Int J Innov Res Sci Eng Technol2012; 1: 185–191.
16.
FengQC. Design of brain–computer interface based on OpenBCI and OpenViBE. Chin J Med Phys2020; 37: 210–219.
17.
ThomasKPGuanCLauCT, et al. A new discriminative common spatial pattern method for motor imagery brain-computer interfaces. IEEE Trans Biomed Eng2009; 56: 2730–2733.
18.
WuXPZhouBYZhangL, et al. Recent progress and future development of spatial filtering technique in brain–computer interface. J Anhui Univ Sci2017; 41: 14–31.
19.
TalukdarUHazarikaSMGanJQ. Adaptation of common spatial patterns based on mental fatigue for motor-imagery BCI. Biomed Signal Process Control2020; 58: 101829.
20.
WuWChenZGaoX, et al. Probabilistic common spatial patterns for multichannel EEG analysis. IEEE Trans Pattern Anal Mach Intell2015; 37: 639–653.
21.
WeiYWuYTudorJ. A real-time wearable emotion detection headband based on EEG measurement. Sens Actuators A Phys2017; 263: 614–621.
22.
ZahidSZAqilMTufailM, et al. Online classification of multiple motor imagery tasks using filter bank based maximum-a-posteriori common spatial pattern filters. IRBM2020; 41: 141–150.
23.
PisnerDASchnyerDM. Support vector machine. In: MechelliAVieiraS (eds) Machine learning: methods and applications to brain disorders. London: Academic Press, 2020, pp.101–121.
24.
SelimSTantawiMMShedeedHA, et al. A CSP\AM-BA-SVM approach for motor imagery BCI system. IEEE Access2018; 6: 49192–49208.
25.
SilvaCRde AraújoRSAlbuquerqueG, et al. Interfacing brains to robotic devices-a VRPN communication application. In: Costa-FelixRMachadoJAlverengaA (eds) 26th Brazilian congress on biomedical engineering, IFMBE proceedings. Singapore: Springer, 2019, pp.597–603.
26.
ZhengMYangBXieY. EEG classification across sessions and across subjects through transfer learning in motor imagery-based brain-machine interface system. Med Biol Eng Comput2020; 58: 1515–1528.
27.
ChenHCheL. Design and implementation for the PWM closed-loop feedback interface circuit of a sandwich capacitive accelerometer based on ARM. Int J Mod Phys B2021; 35: 2150094.
28.
AngKKChinZYWangC, et al. Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Front Neurosci2012; 6: 39.
29.
BaziyadAGRidhaD. A study and performance analysis of three paradigms of wavelet coefficients combinations in three-class motor imagery based BCI. In: 2014 5th international conference on intelligent systems, modelling and simulation. Langkawi, Malaysia, 27–29 January 2014, pp.201–205. New York: IEEE.
30.
HasanBASGanJQ. Conditional random fields as classifiers for three-class motor-imagery brain–computer interfaces. J Neural Eng2011; 8: 025013.
31.
LiBYangBGuanC, et al. Three-class motor imagery classification based on FBCSP combined with voting mechanism. In: 2019 IEEE international conference on computational intelligence and virtual environments for measurement systems and applications (CIVEMSA), Tianjin, China, 14–16 June 2019, pp.1–4. New York: IEEE.
32.
ZhouBWuXZhangL, et al. Robust spatial filters on three-class motor imagery EEG data using independent component analysis. J Biosci Med2014; 2: 43–49.
