8 May 2019 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Motor imagery electroencephalography (EEG) decoding is an essential part in brain-computer interfaces (BCIs) which help motor-disabled patients to communicate with the outside world by external devices. Recently, deep learning algorithms using decomposed spectrums of EEG as inputs may omitted important spatial dependencies and different temporal scale information, thus generated the poor decoding performance. In this paper, we propose an end-to-end EEG decoding framework, which employs raw multi-channel EEG as inputs, to boost decoding accuracy by the channel-projection mixed-scale convolutional neural network (CP-MixedNet) aided by amplitudeperturbation data augmentation. Specifically, the first block in CP-MixedNet is designed to learn primary spatial and temporal representations from EEG signals. The mixed-scale convolutional block is then used to capture mixed-scale temporal information, which effectively reduces the number of training parameters when expanding reception fields of the network. Finally, based on the features extracted in previous blocks, the classification block is constructed to classify EEG tasks. Experiments are implemented on two public EEG datasets (BCI competition IV 2a and High gamma dataset) to validate the effectiveness of the proposed approach comparing to the state-of-the-art methods. The competitive results demonstrate that our proposed method is a promising solution to improve the decoding performance of motor imagery BCIs.
27 March 2019 in IEEE Transactions on Biomedical Engineering
This study proposes a new parametric time-frequency conditional Granger causality (TF-CGC) method for high-precision connectivity analysis over time and frequency domain in multivariate coupling nonstationary systems, and applies it to source electroencephalogram (EEG) signals to reveal dynamic interaction patterns in oscillatory neocortical sensorimotor networks. Methods: The Geweke's spectral measure is combined with the time-varying autoregressive with exogenous input (TVARX) modeling approach, which uses multiwavelet-based ultra-regularized orthogonal least squares (UROLS) algorithm, aided by adjustable prediction error sum of squares (APRESS), to obtain high-resolution time-varying CGC representations. The UROLS-APRESS algorithm, which adopts both the regularization technique and the ultra-least squares criterion to measure not only the signal themselves, but also the weak derivatives of them, is a novel powerful method in constructing time-varying models with good generalization performance, and can accurately track smooth and fast changing causalities. The generalized measurement based on CGC decomposition is able to eliminate indirect influences in multivariate systems. Results: The proposed method is validated on two simulations, and then applied to source level motor imagery (MI) EEGs, where the predicted distributions are well recovered with high TF precision, and the detected connectivity patterns of MI-EEGs are physiologically interpretable and yield new insights into the dynamical organization of oscillatory cortical networks. Conclusion: Experimental results confirm the effectiveness of the TF-CGC method in tracking rapidly varying causalities of EEG-based oscillatory networks. Significance: The novel TF-CGC method is expected to provide important information of neural mechanisms of perception and cognition.