An empirical survey of electroencephalography-based brain-computer interfaces

Abstract

ObjectivesThe Electroencephalogram (EEG) signal is modified using the Motor Imagery (MI) and it is utilized for patients with high motor impairments. Hence, the direct relationship between the computer and brain is termed as an EEG-based brain-computer interface (BCI). The objective of this survey is to presents an analysis of the existing distinct BCIs based on EEG.MethodsThis survey provides a detailed review of more than 60 research papers presenting the BCI-based EEG, like motor imagery-based techniques, spatial filtering-based techniques, Steady-State Visual Evoked Potential (SSVEP)-based techniques, machine learning-based techniques, Event-Related Potential (ERP)-based techniques, and online EEG-based techniques. Subsequently, the research gaps and issues of several EEG-based BCI systems are adopted to help the researchers for better future scope.ResultsAn elaborative analyses as well as discussion have been provided by concerning the parameters, like evaluation metrics, year of publication, accuracy, implementation tool, and utilized datasets obtained by various techniques.ConclusionsThis survey paper exposes research topics on BCI-based EEG, which helps the researchers and scholars, who are interested in this domain.

A Comprehensive Review of Endogenous EEG-Based BCIs for Dynamic Device Control

“…Finally, the papers in our review were selected using a systematic approach that facilitated a comprehensive survey of the literature and reduced human bias in the selection of papers. The reviews of Hekmatmanesh et al [ 7 ], Wang et al [ 8 ], Wankhade et al [ 9 ], and Abiri et al [ 10 ] did not mention the use of this kind of systematic approach, which lent added value to our review paper.…”

“… Wang, 2021 [ 8 ]: Review of BCI-controlled wheelchair systems, including electrode type, modality, and synchronicity. Wankhade, 2020 [ 9 ]: Focus on different EEG-based BCI paradigms, both exogenous and endogenous, and the signal-processing techniques used with them, as well as a brief discussion of online systems. Abiri, 2019 [ 10 ]: In-depth discussion of different EEG paradigms, including exogenous paradigms, with some discussion of signal-processing and classification techniques.…”

“…Wankhade, 2020 [ 9 ]: Focus on different EEG-based BCI paradigms, both exogenous and endogenous, and the signal-processing techniques used with them, as well as a brief discussion of online systems.…”

“…In the review paper by Wankhade et al [ 9 ], the section discussing online BCIs was limited to three papers published in 2019, 2014, and 2010. The paper also had no in-depth discussion of methods of external device control.…”

“…Table 2 shows the details of mixed-paradigm systems. Three of these systems merged traditional MI with other paradigms to attempt to overcome the relatively poor classification accuracy of MI systems when compared to exogenous systems such as SSVEP [ 9 ].…”