脑电信号处理和机器学习算法

开发了基于独立分量分析的数据处理方法，用于增强脑-机接口中脑电的信噪比、选择优化电极位置、去处背景噪声等。开发了基于典型相关分析的在线脑-机接口，验证了典型相关分析在稳态视觉诱发电位脑-机接口中的有效性。开发了基于滤波器组分析和典型相关分析的稳态视觉诱发电位检测算法，提高了稳态视觉诱发电位谐波成分的利用率，显著提高了系统性能。开发了基于脑电训练数据和典型相关分析的视觉诱发电位检测算法，显著提高了信号检测的正确率，缩短了检测时间，在高通讯速率脑-机接口的实现中起关键作用。针对脑电非平稳的特性，开发了多种适用于脑-机接口的迁移学习方法，包括了不同大脑状态间的迁移、同一被试不同时间的迁移、以及不同被试之间的迁移。

The EEG signal processing and machine learning algorithms:

A data processing method based on independent component analysis is developed to enhance the EEG signal to noise ratio, select and optimize electrode position, and discard background noise in brain computer interface.  An on-line BCI system based on canonical correlation analysis is developed to validate its efficiency in SSVEP.  A SSVEP detection algorithm based on filter group analysis and its canonical correlation analysis is developed to increase SSVEP harmonic component utilization and significantly improve the system performance.  A SSVEP detection algorithm based on EEG training data and its canonical correlation analysis is developed to improve the accuracy of signal detection, shorten detection time, and play a key role in the realization of high speed BCI communication.  For the non-stationary characteristics of EEG, a variety of transfer learning method of BCI are designed, including migration between different brain states, different time migration for the same subject, and migration between different subjects.

相关文章：

[1] Wang Y, Zhang Z, Gao X, Gao S, Lead selection for SSVEP-based brain-computer interface, Conf. Proc. IEEE Eng. Med. Biol. Soc., 6: 4507-4510, 2004.

[2] Bin G, Gao X, Yan Z, Hong B, Gao S, An online multi-channel SSVEP-based brain-computer interface using a canonical correlation analysis method, J. Neural Eng., 6(4): 046002, 2009.

[3] Chen X, Wang Y, Gao S, Jung TP, Gao X, Filter bank canonical correlation analysis for implementing a high-speed SSVEP-based brain-computer interface, J. Neural Eng., 12(4): 046008, 2015.

[4] Chen X, Wang Y, Nakanishi M, Gao X, Jung TP, Gao S, High-speed spelling with a noninvasive brain-computer interface, Proc. Natl. Acad. Sci. USA., 112(44):E6058-E6067, 2015.

[5] Yuan P, Chen X, Wang Y, Gao X, Gao S, Enhancing performances of SSVEP-based brain-computer interfaces via exploiting inter-subject information, J. Neural Eng., 12(4): 046006, 2015.