基于环境建模与仿真的P300脑机接口性能评估研究

doi:10.16182/j.issn1004731x.joss.25-0098

摘要/Abstract

摘要：

针对脑机接口(brain-computer interface，BCI)技术从实验室走向实用化过程中，真实环境因素对系统性能影响难以精准预测与评估的问题，提出基于多因素仿真实验的研究方法。构建可控仿真实验环境，对噪声、光照2类关键物理环境因素进行参数化建模，结合脑电通道数量这一系统参数，系统性探究上述因素对P300-BCI解码性能的作用规律。仿真实验结果表明：噪声对系统解码性能存在明显影响，低噪声环境下的准确率高于高噪声环境；光照因素未对系统性能产生明显作用；解码通道数量越少准确率越低，且3通道与全通道解码的性能无明显差异。该研究为非理想环境下BCI系统的性能建模提供了实证数据，也为该技术在真实场景的适应性设计与仿真验证提供了方法论参考。

关键词: P300, 脑机接口, 真实环境, 建模与仿真, 解码性能

Abstract:

In the process of brain-computer interface(BCI) technology stepping from laboratory to practical application scenarios, it is difficult to make an accurate prediction and evaluation of the effect of real environment factors on the system performance. Therefore, a research method based on a multi-factor simulation experiment was proposed. A controllable simulation experiment environment was constructed, and the parametric modeling of two key physical environmental factors, namely noise and light, was carried out. By taking the number of electroencephalogram channels as the system parameter, this paper systematically studied the influence mechanism of the aforementioned factors on the decoding performance of P300-BCI. The simulation experiment results show that noise has a significant impact on the decoding performance of the system. The accuracy is higher in a low noise environment, compared with that in a high noise environment. The light factor has no obvious effect on the system performance. As the number of decoding channels decreases, the accuracy shows a corresponding decline. In addition, no significant difference is observed in decoding performance between three channels and all channels. This study not only provides empirical data for the performance modeling of the BCI system in a non-ideal environment but also provides methodological reference for the adaptive design and simulation verification of this technology in real scenarios.

Key words: P300, brain-computer interface(BCI), real environment, modeling and simulation, decoding performance

中图分类号:

TP391.9

葛晓飞,连金岭,韩锦等 . 基于环境建模与仿真的P300脑机接口性能评估研究[J]. 系统仿真学报, 2026, 38(3): 746-757.

Ge Xiaofei,Lian Jinling,Han Jin,et al . Research on Performance Evaluation of P300 Brain-computer Interface Under Environment Modeling and Simulation[J]. Journal of System Simulation, 2026, 38(3): 746-757.

图/表 13

图 1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

表2

表 3

参考文献 30

[1]	Wolpaw J R, McFarland D J, Neat G W, et al. An EEG-based Brain-computer Interface for Cursor Control[J]. Electroencephalography and Clinical Neurophysiology, 1991, 78(3): 252-259.
[2]	Bi Luzheng, Lian Jinling, Ke Jie, et al. A Speed and Direction-based Cursor Control System with P300 and SSVEP[J]. Biomedical Signal Processing and Control, 2014, 14: 126-133.
[3]	Maarten De Vos, Kroesen Markus, Emkes Reiner, et al. P300 Speller BCI with a Mobile EEG System: Comparison to a Traditional Amplifier[J]. Journal of Neural Engineering, 2014, 11(3): 036008.
[4]	Bai Xin, Li Minglun, Qi Shouliang, et al. A Hybrid P300-SSVEP Brain-computer Interface Speller with a Frequency Enhanced Row and Column Paradigm[J]. Frontiers in Neuroscience, 2023, 17: 1133933.
[5]	Oana Andreea Rusanu. A Brain-computer Interface Application Based on P300 Evoked EEG Potentials for Enabling the Communication Between Users and Chat GPT[C] ∥ Smart Mobile Communication & Artificial Intelligence. Cham : Springer Nature Switzerland, 2024: 226-238.
[6]	Bensch Michael, Karim Ahmed A, Mellinger Jürgen, et al. Nessi: An EEG-controlled Web Browser for Severely Paralyzed Patients[J]. Computational Intelligence and Neuroscience, 2007, 2007(1): 071863.
[7]	Ganzer P D, S C 4th Colachis, Schwemmer M A, et al. Restoring the Sense of Touch Using a Sensorimotor Demultiplexing Neural Interface[J]. Cell, 2020, 181(4): 763-773.
[8]	Mathew Joel, Grace Mary Kanaga E, Bhuvaneshwari M, et al. Development of a Web Application for Audio Communication Using EEG Signals[J]. Grenze International Journal of Engineering and Technology, 2024, 10(1): 721-726.
[9]	Mercado Jose, Espinosa-Curiel Ismael, Escobedo Lizbeth, et al. Developing and Evaluating a BCI Video Game for Neurofeedback Training: The Case of Autism[J]. Multimedia Tools and Applications, 2019, 78(10): 13675-13712.
[10]	Kumar Rahul, Singla Rajesh. EEG Based Attention Score Analysis of Two Game Genre[J]. Neuro Quantology, 2022, 20(14): 866-871.
[11]	Yu Yang, Liu Yadong, Jiang Jun, et al. An Asynchronous Control Paradigm Based on Sequential Motor Imagery and Its Application in Wheelchair Navigation[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, 26(12): 2367-2375.
[12]	Prashant Kumar Tiwari, Choudhary Abhishek, Gupta Saurabh, et al. Sensitive Brain-computer Interface to Help Manoeuvre a Miniature Wheelchair Using Electroence-phalography[C] ∥ 2020 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS). Piscataway: IEEE, 2020: 1-6.
[13]	Dash D, Ferrari P, Wang Jun. Decoding Imagined and Spoken Phrases from Non-invasive Neural (MEG) Signals[J]. Frontiers in Neuroscience, 2020, 14: 290.
[14]	Amemiya Shiori, Takao Hidemasa, Abe Osamu. Resting-state fMRI: Emerging Concepts for Future Clinical Application[J]. Journal of Magnetic Resonance Imaging, 2024, 59(4): 1135-1148.
[15]	Xia Hongling, Chen Wei, Hu Die, et al. Rapid Discrimination of Quality Grade of Black Tea Based on Near-infrared Spectroscopy (NIRS), Electronic Nose (E-nose) and Data Fusion[J]. Food Chemistry, 2024, 440: 138242.
[16]	Cohen Michael X. Where Does EEG Come from and What Does It Mean?[J]. Trends in Neurosciences, 2017, 40(4): 208-218.
[17]	Jin Young Park, Min Byoung-Kyong, Jung Young-Chul, et al. Illumination Influences Working Memory: An EEG Study[J]. Neuroscience, 2013, 247: 386-394.
[18]	Min Byoung-Kyong, Jung Young-Chul, Kim Eosu, et al. Bright Illumination Reduces Parietal EEG Alpha Activity During a Sustained Attention Task[J]. Brain Research, 2013, 1538: 83-92.
[19]	Pieper Kerstin, Spang Robert P, Prietz Pablo, et al. Working with Environmental Noise and Noise-cancelation: A Workload Assessment with EEG and Subjective Measures[J]. Frontiers in Neuroscience, 2021, 15: 771533.
[20]	Tseng L H, Cheng Mingtai, Chen S T, et al. An EEG Investigation of the Impact of Noise on Attention[J]. Advanced Materials Research, 2013, 779-780: 1731-1736.
[21]	Kim Ki-Hong, Lee Hyang-Beum. The Effects of Whole Body Vibration Exercise Intervention on Electroence-phalogram Activation and Cognitive Function in Women with Senile Dementia[J]. Journal of Exercise Rehabilitation, 2018, 14(4): 586-591.
[22]	Lian Jinling, Qiao Xin, Zhao Yuwei, et al. EEG-based Target Detection Using an RSVP Paradigm Under Five Levels of Weak Hidden Conditions[J]. Brain Sciences, 2023, 13(11): 1583.
[23]	Nelken Israel. Processing of Complex Stimuli and Natural Scenes in the Auditory Cortex[J]. Current Opinion in Neurobiology, 2004, 14(4): 474-480.
[24]	Polley D B, Steinberg E E, Merzenich M M. Perceptual Learning Directs Auditory Cortical Map Reorganization Through Top-down Influences[J]. Journal of Neuroscience, 2006, 26(18): 4970-4982.
[25]	Engineer N D, Percaccio C R, Pandya P K, et al. Environmental Enrichment Improves Response Strength, Threshold, Selectivity, and Latency of Auditory Cortex Neurons[J]. Journal of Neurophysiology, 2004, 92(1): 73-82.
[26]	Lian Jinling, Bi Luzheng, Fei Weijie. A Novel Event-related Potential-based Brain-computer Interface for Continuously Controlling Dynamic Systems[J]. IEEE Access, 2019, 7: 38721-38729.
[27]	Chang C C, Lin C J. LIBSVM: A Library for Support Vector Machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 27.
[28]	Chen Xiaogang, Wang Yijun, Nakanishi M, et al. High-speed Spelling with a Noninvasive Brain-computer Interface[J]. Proceedings of the National Academy of Sciences of the United States of America, 2015, 112(44): E6058-E6067.
[29]	Corbetta M, Shulman G L. Control of Goal-directed and Stimulus-driven Attention in the Brain[J]. Nature Reviews Neuroscience, 2002, 3(3): 201-215.
[30]	Miller E K, Cohen J D. An Integrative Theory of Prefrontal Cortex Function[J]. Annual Review of Neuroscience, 2001, 24: 167-202.

通道	准确率/p值	低噪声低光照	低噪声中光照	低噪声高光照	高噪声低光照	高噪声中光照	高噪声高光照
全部通道	准确率/%	94.08±1.20	89.81±2.35	90.47±3.13	88.71±3.68	88.72±2.76	88.64±1.29
最优3通道	准确率/%	92.59±1.51	89.19±2.47	89.16±2.73	86.41±3.79	85.20±2.16	85.89±2.24
最优3通道	p值	0.058 2	0.579 8	0.290 8	0.106 6	0.048 9	0.198 6
最优2通道	准确率/%	90.10±2.47	86.36±2.64	83.41±3.27	83.53±3.44	81.87±2.74	85.50±2.03
最优2通道	p值	0.083 0	0.029 9	0.034 2	0.001 9	0.017 0	0.177 6
最优1通道	准确率/%	83.46±2.17	76.67±2.47	77.37±2.97	76.32±2.69	76.34±2.03	76.77±2.35
最优1通道	p值	0.000 1	<0.000 1	0.001 8	0.000 2	0.004 3	<0.000 1

因素	平方和	自由度	均方	F值	p值
通道	0.622 2	3	0.207 3	25.43	0
噪声	0.075 1	1	0.075 1	9.21	0.002 6
光照	0.038 8	2	0.019 4	2.38	0.094 6
通道×噪声	0.003 8	3	0.001 3	0.16	0.925 6
通道×光照	0.001 2	6	0.000 2	0.03	0.999 9
噪声×光照	0.037 2	2	0.018 6	2.28	0.104 1
通道×噪声×光照	0.014 2	6	0.002 4	0.29	0.941 0

仿真环境	低噪声低光照	低噪声中光照	低噪声高光照	高噪声低光照	高噪声中光照	高噪声高光照
LDA准确率/%	92.59±1.51	89.19±2.47	89.16±2.73	86.41±3.79	85.20±2.16	85.89±2.24
SVM准确率/%	87.88±1.58	85.64±2.12	84.19±3.08	83.30±3.08	80.73±2.32	81.85±2.18
p值	0.000 2	0.001 4	0.001 2	0.009 7	0.000 1	0.004 5
LDA信息传输率/%	15.53±0.55	14.40±0.86	14.40±0.87	13.62±1.10	12.90±0.71	13.16±0.76
SVM信息传输率/%	13.75±0.54	13.06±0.72	12.70±0.91	12.40±0.88	11.48±0.72	11.81±0.69
p值	0.000 1	0.001 0	0.001 1	0.002 4	0.000 1	0.002 8