In EEG based driving fatigue detection, the redundant EEG channels would increase the probability of introducing noise and heaving calculation burden. Aiming at this point, we built up an EEG dataset with thirty electrodes from every brain lobe, proposed a driving fatigue detection approach based on brain functional network. And provide a possible way for the key EEG electrode and rhythm investigation with these brain networks. First, a simulation driving experiment was set up to obtain EEG of multiple subjects during a long-term monotonous cognitive task. The feasibility of the collected data was verified with PSD. For brain functional network construction, partial directed coherence (PDC) is used to calculate the correlation between EEG channels. Then, four graph related features (i.e., node degree, clustering coefficient, characteristic path length and local efficiency) are extracted for fatigue detection with SVM as classifier. After that, we get the key electrodes with the feature of betweenness centrality. The results show that the low frequency rhythms are more distinguishable than that of high frequency. The best classification accuracy of 87.16% is achieved in delta, which is 18.9% higher than that of the baseline method with PSD. At last, we verified the effectiveness of the selected key electrodes, and drew the conclusion that the key EEG rhythm corresponding to different features may not be consistent.

Low-dose CT (LDCT) images have been widely applied in the medical imaging field due to the potential risk of exposing patients to X-ray radiations. Given the fact that reducing the radiation dose may result in increased noise and artifacts, methods that can eliminate the noise and artifacts in the LDCT image have drawn increasing attentions and produced impressive results over the past decades. However, recent proposed methods mostly suffer from noise remaining, over-smoothing structures or false lesions derived from noise. In this paper, we propose a generative adversarial network (GAN) with novel architecture and loss function for restoring the LDCT image. Firstly, the inception-residual block and residual mapping are incoporated in the U-Net structure. The modified U-Net is applied as the generator of the GAN network so that the noise feature can be eliminated during the forward propagation. Secondly, a novel multi-level joint discriminator is designed by concatenating multiple convolutional neural networks (CNNs) where the output of each deconvolutional layer in the generator is compared with the corresponding down-sampled ground truth image. The adversarial training can be sensitive to noise and artifacts in different scales with this discriminator. Thirdly, we novely define a loss function consisting of the least square adversarial loss, VGG based perceptual loss, MSE based pixel loss and the noise loss, so that the differences in pixel, visual perception and noise distribution are comprehensively considered to optimize the network. Experimental results on both simulated and official simulated clinical images have demonstrated that the proposed method can provide superior performance to the state-of-the-art methods in noise removal, structure preservation and false lesions elimination.

The state-of-the-arts in action recognition are suffering from three challenges: (1) How to model spatial transformations of action since it is always geometric variation over time in videos. (2) How to develop the semantic action-aware temporal features from one video with a large proportion of irrelevant frames to the labeled action class, which hurt the final performance. (3) The action recognition speed of most existing models is too slow to be applied to actual scenes. In this paper, to address these three challenges, we propose a novel CNN-based action recognition method called SAST including three important modules, which can effectively learn semantic action-aware spatial-temporal features with a faster speed. Firstly, to learn action-aware spatial features (spatial transformations), we design a weight shared 2D Deformable Convolutional network named 2DDC with deformable convolutions whose receptive fields can be adaptively adjusted according to the complex geometric structure of actions. Then, we propose a light Temporal Attention model called TA to develop the action-aware temporal features that are discriminative for the labeled action category. Finally, we apply an effective 3D network to learn the temporal context between frames for building the final video-level representation. To improve the efficiency, we only utilize the raw RGB rather than optical flow and RGB as the input to our model. Experimental results on four challenging video recognition datasets Kinetics-400, Something-Something-V1, UCF101 and HMDB51 demonstrate that our proposed method can not only achieve comparable performances but be 10x to 50x faster than most of state-of-the-art action recognition methods.