The influence of paradigm interface guided by different visual types on MI-BCI performance

Bibliographic Data

ID21452055
AuthorsJiang Shao (0009-0001-5759-313X, China University of Mining and Technology), Yuxin Bai (0009-0004-8995-2637, China University of Mining and Technology, corresponding author), Jun Yao (0000-0003-0479-8796, China University of Mining and Technology), Ying Zhang (0000-0001-6214-2440, China University of Mining and Technology), Fangyuan Tian (0000-0001-5050-8628, Xi'an University of Science and Technology), Chengqi Xue (0000-0002-2666-1072, Southeast University)
Year2025
Volume44
Issue1
Pages120-130
Publication date2025-01-02
Open AccessNo
TypeARTICLE
VenueBehaviour and Information Technology (JOURNAL)
Journal identifiersISSN: 0144-929X • E-ISSN: 1362-3001
PublisherInforma UK Limited (PUBLISHER • GB)
DOI10.1080/0144929x.2024.2312436
OpenAlexW4391473261
LanguageEN
References cited47

Visual paradigms of Brain-Computer Interfaces (BCI) for motor imagery (MI) tasks are the basis for communication through (electroencephalogram) EEG signals. During the MI-BCI user training process, this study analyzes and summarises four different visual paradigms and compares their impact on the outcomes of MI-BCI training. Four different visual paradigms are experimentally compared through classification outcomes and subjective evaluation. EEG features were extracted via Common Spatial Patterns (CSP) and passed to a Support Vector Machine (SVM) model for their classification. The results show that all four types of visual paradigms have a significant impact on the outcomes of MI-BCI training, with Paradigm Set II having the most significant impact. This is because paradigm set II offers a paradigm interface with relatively low visual complexity on the basis of action observation, and visual guidance with more clarity and more accurate EEG classification

Brain–computer interface · Electroencephalography · Human–computer interaction · Interface (matter) · Operating system · Advanced Memory and Neural Computing · Computer Science · EEG and Brain-Computer Interfaces · Gaze Tracking and Assistive Technology · Neuroscience · Psychology

Tools

Open DOI