A TrAdaBoost-based method for detecting multiple subjects’ P300 potentials_Journal of Biomedical Engineering

Authors：

XU Guizhi ^1,2 , LIN Fang ^1,2 , GONG Minghong ^1,2 ,  LI Mengfan ^1,2 , YU Hongli ^1,2

1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Electrical Engineering, Hebei University of Technology, Tianjin 300132, P.R.China;
2. Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, School of Electrical Engineering, Hebei University of Technology, Tianjin 300132, P.R.China;

Corresponding author：

LI Mengfan, Email: mfli@hebut.edu.cn

Keywords：

brain-computer interface; P300; transfer learning; TrAdaBoost; linear discriminant analysis classifier; support vector machine

DOI：

10.7507/1001-5515.201811025

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Individual differences of P300 potentials lead to that a large amount of training data must be collected to construct pattern recognition models in P300-based brain-computer interface system, which may cause subjects’ fatigue and degrade the system performance. TrAdaBoost is a method that transfers the knowledge from source area to target area, which improves learning effect in the target area. Our research purposed a TrAdaBoost-based linear discriminant analysis and a TrAdaBoost-based support vector machine to recognize the P300 potentials across multiple subjects. This method first trains two kinds of classifiers separately by using the data deriving from a small amount of data from same subject and a large amount of data from different subjects. Then it combines all the classifiers with different weights. Compared with traditional training methods that use only a small amount of data from same subject or mixed different subjects’ data to directly train, our algorithm improved the accuracies by 19.56% and 22.25% respectively, and improved the information transfer rate of 14.69 bits/min and 15.76 bits/min respectively. The results indicate that the TrAdaBoost-based method has the potential to enhance the generalization ability of brain-computer interface on the individual differences.

Citation： XU Guizhi, LIN Fang, GONG Minghong, LI Mengfan, YU Hongli. A TrAdaBoost-based method for detecting multiple subjects’ P300 potentials. Journal of Biomedical Engineering, 2019, 36(4): 531-540. doi: 10.7507/1001-5515.201811025 Copy

1.	Zhang Yu, Zhou Guoxu, Jin Jing, et al. Sparse Bayesian classification of EEG for brain-computer interface. IEEE Trans Neural Netw Learn Syst, 2016, 27(11): 2256-2267.
2.	Pfurtscheller G, Aranibar A. Event-related cortical desynchronization detected by power measurements of scalp EEG. Electroencephalogr Clin Neurophysiol, 1977, 42(6): 817-826.
3.	吴边, 苏煜, 张剑慧, 等. 基于P300电位的新型BCI中文输入虚拟键盘系统. 电子学报, 2009, 37(8): 1733-1738, 1745.
4.	马忠伟, 高上凯. 基于P300电位的脑机接口系统中参数优化问题的研究. 中国生物医学工程学报, 2009, 28(6): 851-855.
5.	马振武, 穆俊林. 2型糖尿病患者的负性情绪及其P300电位的对照研究. 中国康复医学杂志, 2004, 19(3): 218.
6.	刘聪, 徐晓东, 戴好运, 等. 基于N-back认知任务的正常脑老化事件相关电位分析. 生物医学工程学杂志, 2017, 34(6): 824-830.
7.	尚淑怡, 尤春景. 认知电位P300的应用及研究进展. 中国康复, 2008, 23(2): 133-135.
8.	范晓丽, 赵朝义, 罗虹, 等. 基于2-back任务下ERP特征的脑力疲劳客观评价研究. 生物医学工程学杂志, 2018, 35(6): 15-22.
9.	邹可, 孙元锋, 唐向东, 等. 阻塞性睡眠呼吸暂停低通气综合征患者早期认知功能损害的事件相关电位研究. 生物医学工程学杂志, 2014, 31(4): 870-874.
10.	Farwell L A, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr Clin Neurophysiol, 1988, 70(6): 510-523.
11.	Tang Jingsheng, Liu Yadong, Hu Dewen, et al. Towards BCI-actuated smart wheelchair system. Biomed Eng Online, 2018, 17: 111-132.
12.	Zhang Zhijun, Huang Yongqian, Chen Siyuan, et al. An intention-driven semi-autonomous intelligent robotic system for drinking. Front Neurorobot, 2017, 11. DOI: 10.3389/fnbot.2017.00048.
13.	王金甲, 杨成杰, 胡备. P300脑机接口控制智能小车系统的设计与实现. 生物医学工程学杂志, 2013, 30(2): 223-228.
14.	王金甲, 杨成杰. P300脑机接口控制智能家居系统研究. 生物医学工程学杂志, 2014, 31(4): 762-766.
15.	Oskoei M A, Hu Huosheng. Support vector machine-based classification scheme for myoelectric control applied to upper limb. IEEE Trans Biomed Eng, 2008, 55(8): 1956-1965.
16.	Li Wei, Li Mengfan, Zhou Huihui, et al. A dual stimuli approach combined with convolutional neural network to improve information transfer rate of event-related potential-based brain-computer interface. Int J Neural Syst, 2018, 28(10). DOI: 10.1142/S012906571850034X.
17.	Medrano P, Nyhus E, Smolen A, et al. Individual differences in EEG correlates of recognition memory due to DAT polymorphisms. Brain Behav, 2017, 7(12): e00870.
18.	Jayaram V, Alamgir M, Altun Y, et al. Transfer learning in brain-computer interfaces. IEEE Comput Intell Mag, 2016, 11(1): 20-31.
19.	Lotte F, Congedo M, Lécuyer A, et al. A review of classification algorithms for EEG-based brain-computer interfaces. J Neural Eng, 2007, 4(2): R1-R13.
20.	Shin H C, Roth H R, Gao Mingchen, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging, 2016, 35(5): 1285-1298.
21.	Yuan Zhixiang, Bao Damang, Chen Zekai, et al. Integrated transfer learning algorithm using multi-source TrAdaBoost for unbalanced samples classification// International Conference on Computing Intelligence and Information System. Nanjing: IEEE Computer Society, 2017: 188-195.
22.	胡伟, 陈炜峰, 胡凯, 等. 基于改进加权多源TrAdaBoost算法的无参考图像质量评价方法. 科学技术与工程, 2018, 18(18): 87-93.
23.	谢星宇, 张颖璐. 基于改进的 TrAdaboost 算法的学生成绩排名预测. 计算机与现代化, 2016(2): 122-126.
24.	Wei Chunshu, Lin Yuanpin, Wang Yute, et al. Selective transfer learning for EEG-based drowsiness detection// IEEE International Conference on Systems, Man, and Cybernetics. Hong Kong: IEEE, 2016: 3229-3232.
25.	马忠伟, 高上凯. 基于P300的脑-机接口: 视觉刺激强度对性能的影响. 清华大学学报: 自然科学版, 2008, 48(3): 415-418.
26.	徐桂芝, 王宁, 张天恒, 等. 虚拟现实视觉体验对事件相关电位影响的研究. 信号处理, 2018, 34(8): 952-962.
27.	Hong Bo, Guo Fei, Liu Tao, et al. N200-speller using motion-onset visual response. Clin Neurophysiol, 2009, 120(9): 1658-1666.
28.	Dai W, Yang Q, Xue G R, et al. Boosting for transfer learning// International Conference on Machine Learning. Oregon: ACM, 2007: 193-200.
29.	付荣荣, 侯培国, 李曼迪. 基于Fisher准则的单次运动想象脑电信号意图识别研究. 生物医学工程学杂志, 2018, 35(5): 774-778.
30.	Chen S, Liu J, Zhou Z H. Making FLDA applicable to face recognition with one sample per person. Pattern Recognit, 2004, 37(7): 1553-1555.
31.	Heddam S, Kisi O. Modelling daily dissolved oxygen concentration using least square support vector machine, multivariate adaptive regression splines and M5 model tree. J Hydrol, 2018, 559: 499-509.
32.	孙即祥. 现代模式识别. 第2版. 北京: 高等教育出版社, 2008.
33.	Mcfarland D J, Sarnacki W A, Wolpaw J R. Brain-computer interface (BCI) operation: optimizing information transfer rates. Biol Psychol, 2003, 63(3): 237-251.
34.	杨立才, 李金亮, 姚玉翠, 等. 基于F-score特征选择和支持向量机的P300识别算法. 生物医学工程学杂志, 2008, 25(1): 23-26, 52.
35.	郁洪强, 赵欣, 汪曣, 等. 过度使用互联网对事件相关电位N400的影响. 生物医学工程学杂志, 2008, 25(5): 1014-1020.
36.	Waytowich N R, Lawhern V J, Bohannon A W, et al. Spectral transfer learning using information geometry for a user-independent brain-computer interface. Front Neurosci, 2016, 10: 430.
37.	Adair J, Brownlee A, Daolio F, et al. Evolving training sets for improved transfer learning in brain computer interfaces// Nicosia G, Pardalos P, Giuffrida G, et al. Machine Learning, Optimization, and Big Data. Cham: Springer, 2018.
38.	Islam R, Tanaka T, Molla K I. Multiband tangent space mapping and feature selection for classification of EEG during motor imagery. J Neural Eng, 2018, 15(4). DOI: 10.1088/1741-2552/aac313.
39.	袁鹏. 跨脑信息挖掘及其在脑—机接口中的应用. 北京: 清华大学, 2015.
40.	Wang Yijun, Jung T P. A collaborative brain-computer interface for improving human performance. PLoS One, 2011, 6(5): e20422.

1. Zhang Yu, Zhou Guoxu, Jin Jing, et al. Sparse Bayesian classification of EEG for brain-computer interface. IEEE Trans Neural Netw Learn Syst, 2016, 27(11): 2256-2267.
2. Pfurtscheller G, Aranibar A. Event-related cortical desynchronization detected by power measurements of scalp EEG. Electroencephalogr Clin Neurophysiol, 1977, 42(6): 817-826.
3. 吴边, 苏煜, 张剑慧, 等. 基于P300电位的新型BCI中文输入虚拟键盘系统. 电子学报, 2009, 37(8): 1733-1738, 1745.
4. 马忠伟, 高上凯. 基于P300电位的脑机接口系统中参数优化问题的研究. 中国生物医学工程学报, 2009, 28(6): 851-855.
5. 马振武, 穆俊林. 2型糖尿病患者的负性情绪及其P300电位的对照研究. 中国康复医学杂志, 2004, 19(3): 218.
6. 刘聪, 徐晓东, 戴好运, 等. 基于N-back认知任务的正常脑老化事件相关电位分析. 生物医学工程学杂志, 2017, 34(6): 824-830.
7. 尚淑怡, 尤春景. 认知电位P300的应用及研究进展. 中国康复, 2008, 23(2): 133-135.
8. 范晓丽, 赵朝义, 罗虹, 等. 基于2-back任务下ERP特征的脑力疲劳客观评价研究. 生物医学工程学杂志, 2018, 35(6): 15-22.
9. 邹可, 孙元锋, 唐向东, 等. 阻塞性睡眠呼吸暂停低通气综合征患者早期认知功能损害的事件相关电位研究. 生物医学工程学杂志, 2014, 31(4): 870-874.
10. Farwell L A, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr Clin Neurophysiol, 1988, 70(6): 510-523.
11. Tang Jingsheng, Liu Yadong, Hu Dewen, et al. Towards BCI-actuated smart wheelchair system. Biomed Eng Online, 2018, 17: 111-132.
12. Zhang Zhijun, Huang Yongqian, Chen Siyuan, et al. An intention-driven semi-autonomous intelligent robotic system for drinking. Front Neurorobot, 2017, 11. DOI: 10.3389/fnbot.2017.00048.
13. 王金甲, 杨成杰, 胡备. P300脑机接口控制智能小车系统的设计与实现. 生物医学工程学杂志, 2013, 30(2): 223-228.
14. 王金甲, 杨成杰. P300脑机接口控制智能家居系统研究. 生物医学工程学杂志, 2014, 31(4): 762-766.
15. Oskoei M A, Hu Huosheng. Support vector machine-based classification scheme for myoelectric control applied to upper limb. IEEE Trans Biomed Eng, 2008, 55(8): 1956-1965.
16. Li Wei, Li Mengfan, Zhou Huihui, et al. A dual stimuli approach combined with convolutional neural network to improve information transfer rate of event-related potential-based brain-computer interface. Int J Neural Syst, 2018, 28(10). DOI: 10.1142/S012906571850034X.
17. Medrano P, Nyhus E, Smolen A, et al. Individual differences in EEG correlates of recognition memory due to DAT polymorphisms. Brain Behav, 2017, 7(12): e00870.
18. Jayaram V, Alamgir M, Altun Y, et al. Transfer learning in brain-computer interfaces. IEEE Comput Intell Mag, 2016, 11(1): 20-31.
19. Lotte F, Congedo M, Lécuyer A, et al. A review of classification algorithms for EEG-based brain-computer interfaces. J Neural Eng, 2007, 4(2): R1-R13.
20. Shin H C, Roth H R, Gao Mingchen, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging, 2016, 35(5): 1285-1298.
21. Yuan Zhixiang, Bao Damang, Chen Zekai, et al. Integrated transfer learning algorithm using multi-source TrAdaBoost for unbalanced samples classification// International Conference on Computing Intelligence and Information System. Nanjing: IEEE Computer Society, 2017: 188-195.
22. 胡伟, 陈炜峰, 胡凯, 等. 基于改进加权多源TrAdaBoost算法的无参考图像质量评价方法. 科学技术与工程, 2018, 18(18): 87-93.
23. 谢星宇, 张颖璐. 基于改进的 TrAdaboost 算法的学生成绩排名预测. 计算机与现代化, 2016(2): 122-126.
24. Wei Chunshu, Lin Yuanpin, Wang Yute, et al. Selective transfer learning for EEG-based drowsiness detection// IEEE International Conference on Systems, Man, and Cybernetics. Hong Kong: IEEE, 2016: 3229-3232.
25. 马忠伟, 高上凯. 基于P300的脑-机接口: 视觉刺激强度对性能的影响. 清华大学学报: 自然科学版, 2008, 48(3): 415-418.
26. 徐桂芝, 王宁, 张天恒, 等. 虚拟现实视觉体验对事件相关电位影响的研究. 信号处理, 2018, 34(8): 952-962.
27. Hong Bo, Guo Fei, Liu Tao, et al. N200-speller using motion-onset visual response. Clin Neurophysiol, 2009, 120(9): 1658-1666.
28. Dai W, Yang Q, Xue G R, et al. Boosting for transfer learning// International Conference on Machine Learning. Oregon: ACM, 2007: 193-200.
29. 付荣荣, 侯培国, 李曼迪. 基于Fisher准则的单次运动想象脑电信号意图识别研究. 生物医学工程学杂志, 2018, 35(5): 774-778.
30. Chen S, Liu J, Zhou Z H. Making FLDA applicable to face recognition with one sample per person. Pattern Recognit, 2004, 37(7): 1553-1555.
31. Heddam S, Kisi O. Modelling daily dissolved oxygen concentration using least square support vector machine, multivariate adaptive regression splines and M5 model tree. J Hydrol, 2018, 559: 499-509.
32. 孙即祥. 现代模式识别. 第2版. 北京: 高等教育出版社, 2008.
33. Mcfarland D J, Sarnacki W A, Wolpaw J R. Brain-computer interface (BCI) operation: optimizing information transfer rates. Biol Psychol, 2003, 63(3): 237-251.
34. 杨立才, 李金亮, 姚玉翠, 等. 基于F-score特征选择和支持向量机的P300识别算法. 生物医学工程学杂志, 2008, 25(1): 23-26, 52.
35. 郁洪强, 赵欣, 汪曣, 等. 过度使用互联网对事件相关电位N400的影响. 生物医学工程学杂志, 2008, 25(5): 1014-1020.
36. Waytowich N R, Lawhern V J, Bohannon A W, et al. Spectral transfer learning using information geometry for a user-independent brain-computer interface. Front Neurosci, 2016, 10: 430.
37. Adair J, Brownlee A, Daolio F, et al. Evolving training sets for improved transfer learning in brain computer interfaces// Nicosia G, Pardalos P, Giuffrida G, et al. Machine Learning, Optimization, and Big Data. Cham: Springer, 2018.
38. Islam R, Tanaka T, Molla K I. Multiband tangent space mapping and feature selection for classification of EEG during motor imagery. J Neural Eng, 2018, 15(4). DOI: 10.1088/1741-2552/aac313.
39. 袁鹏. 跨脑信息挖掘及其在脑—机接口中的应用. 北京: 清华大学, 2015.
40. Wang Yijun, Jung T P. A collaborative brain-computer interface for improving human performance. PLoS One, 2011, 6(5): e20422.

Journal of Biomedical Engineering

A TrAdaBoost-based method for detecting multiple subjects’ P300 potentials

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content