Related Experiment Video
Updated: Jun 26, 2026
06:09
P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
Published on: September 8, 2023
An Immersive P300 Brain-Computer Interface Based on 3D Morphological Stimuli and Self-Adaptive Bayesian Linear
Junhong Luo1,2, Mengnan Zhu1, Yongbo Xiao3
1School of Artificial Intelligence, Guangzhou Maritime University, Guangzhou 510725, China.
Biomimetics (Basel, Switzerland)
|June 25, 2026
Summary
This study introduces an immersive P300 brain-computer interface (BCI) using 3D-Morph stimulation and self-adaptive Bayesian linear discriminant analysis (SA-BLDA). The novel approach enhances accuracy and efficiency while reducing user workload compared to traditional 2D BCIs.
Area of Science:
- Neuroscience
- Computer Science
- Human-Computer Interaction
Background:
- Conventional P300-based brain-computer interfaces (BCIs) often use 2D visual flashing, leading to visual fatigue and reduced immersion.
- Limitations in visual immersion and user fatigue hinder the long-term usability and performance of traditional BCIs.
Purpose of the Study:
- To develop and evaluate an immersive P300-BCI framework using a novel 3D-Morph stimulation paradigm.
- To integrate the 3D-Morph paradigm with self-adaptive Bayesian linear discriminant analysis (SA-BLDA) for improved accuracy and efficiency.
- To assess the impact of the proposed framework on classification performance, interaction efficiency, and user workload.
Main Methods:
- Implemented a 3D-Morph paradigm utilizing dynamic 2D-to-3D morphological transformations in a virtual reality environment.
- Employed SA-BLDA to adapt the number of stimulation rounds based on classification confidence.
- Conducted experiments with 24 participants comparing the 3D-Morph paradigm against a conventional 2D paradigm.
Main Results:
- The 3D-Morph paradigm with SA-BLDA significantly improved offline classification accuracy (94.17%) and information transfer rate (ITR, 25.50 bits/min) compared to the 2D paradigm (87.29%, 22.75 bits/min).
- Online experiments showed higher accuracy (91.46%) and ITR (37.23 bits/min) with the 3D-Morph system, alongside reduced response time and computational processing time.
- Subjective workload assessments (NASA-TLX) indicated significantly lower user workload across all dimensions with the proposed immersive BCI framework.
Conclusions:
- The integration of 3D-Morph stimulation and SA-BLDA offers a significant advancement in P300-BCI technology.
- This immersive framework enhances classification performance, interaction efficiency, and user experience.
- The proposed system presents a feasible and practical solution for advanced BCI applications.
