The rapid development and malicious use of deepfakes pose a significant crisis of trust. To cope with the evolving deepfake technologies, an increasing number of detection methods adopt the continual learning paradigm, but they often suffer from catastrophic forgetting. Although replay-based methods mitigate this issue by storing a portion of samples from historical tasks, their sample selection strategies usually rely on a single metric, which may lead to the omission of critical samples and consequently hinder the construction of a robust instance memory bank. In this paper, we propose a novel Multi-perspective Sample Selection Mechanism (MSSM) for continual deepfake detection, which jointly evaluates prediction error, temporal instability, and sample diversity to preserve informative and challenging samples in the instance memory bank. Furthermore, we design a Hierarchical Prototype Generation Mechanism (HPGM) that constructs prototypes at both the category and task levels, which are stored in the prototype memory bank. Extensive experiments under two evaluation protocols demonstrate that the proposed method achieves state-of-the-art performance.

Classification of electroencephalogram-based motor imagery (MI-EEG) tasks is crucial in brain–computer interface (BCI). EEG signals require a large number of channels in the acquisition process, which hinders its application in practice. How to select the optimal channel subset without a serious impact on the classification performance is an urgent problem to be solved in the field of BCIs. This article proposes an end-to-end deep learning framework, called EEG channel active inference neural network (EEG-ARNN), which is based on graph convolutional neural networks (GCN) to fully exploit the correlation of signals in the temporal and spatial domains. Two channel selection methods, i.e., edge-selection (ES) and aggregation-selection (AS), are proposed to select a specified number of optimal channels automatically. Two publicly available BCI Competition IV 2a (BCICIV 2a) dataset and PhysioNet dataset and a self-collected dataset (TJU dataset) are used to evaluate the performance of the proposed method. Experimental results reveal that the proposed method outperforms state-of-the-art methods in terms of both classification accuracy and robustness. Using only a small number of channels, we obtain a classification performance similar to that of using all channels. Finally, the association between selected channels and activated brain areas is analyzed, which is important to reveal the working state of brain during MI.

Energy consumption is an important issue for resource-constrained wireless neural recording applications with limited data bandwidth. Compressed sensing (CS) is a promising framework for addressing this challenge because it can compress data in an energy-efficient way. Recent work has shown that deep neural networks (DNNs) can serve as valuable models for CS of neural action potentials (APs). However, these models typically require impractically large datasets and computational resources for training, and they do not easily generalize to novel circumstances. Here, we propose a new CS framework, termed APGen, for the reconstruction of APs in a training-free manner. It consists of a deep generative network and an analysis sparse regularizer. We validate our method on two in vivo datasets. Even without any training, APGen outperformed model-based and data-driven methods in terms of reconstruction accuracy, computational efficiency, and robustness to AP overlap and misalignment. The computational efficiency of APGen and its ability to perform without training make it an ideal candidate for long-term, resource-constrained, and large-scale wireless neural recording. It may also promote the development of real-time, naturalistic brain-computer interfaces.

Classification of electroencephalogram-based motor imagery (MI-EEG) tasks is crucial in brain computer interfaces (BCI). In view of the characteristics of non-stationarity, time-variability and individual diversity of EEG signals, a novel framework based on graph neural network is proposed for MI-EEG classification. First, an adaptive graph convolutional layer (AGCL) is constructed, by which the electrode channel information are integrated dynamically. We further propose an adaptive spatiotemporal graph convolutional network (ASTGCN), which fully exploits the characteristics of EEG signals in time domain and the channel correlations in spatial domain simultaneously. We execute the experiments using EEG signals recorded at motor imagery scenarios, where twenty-five healthy subjects performed MI movements of the right hand and feet to generate motor commands. Experimental results reveal that the proposed method outperforms state-of-the-art methods in terms of both classification quality and robustness. The advantages of ASTGCN include high accuracy, high efficiency, and robustness to cross-trial and cross-subject variations, making it an ideal candidate for long-term MI-EEG applications.

Classification of electroencephalogram-based motor imagery (MI-EEG) tasks raises a big challenge in the design and development of brain-computer interfaces (BCIs). In view of the characteristics of nonstationarity, time-variability, and individual diversity of EEG signals, a deep learning framework termed SSD-SE-convolutional neural network (CNN) is proposed for MI-EEG classification. The framework consists of three parts: 1) the sparse spectrotemporal decomposition (SSD) algorithm is proposed for feature extraction, overcoming the drawbacks of conventional time-frequency analysis methods and enhancing the robustness to noise; 2) a CNN is constructed to fully exploit the time-frequency features, thus outperforming traditional classification methods both in terms of accuracy and kappa value; and 3) the squeeze-and-excitation (SE) blocks are adopted to adaptively recalibrate channelwise feature responses, which further improves the overall performance and offers a compelling classification solution for MI-EEG applications. Experimental results on two datasets reveal that the proposed framework outperforms state-of-the-art methods in terms of both classification quality and robustness. The advantages of SSD-SE-CNN include high accuracy, high efficiency, and robustness to cross-trial and cross-session variations, making it an ideal candidate for long-term MI-EEG applications.

Single image dehazing is an important but challenging computer vision problem. For the problem, an end-to-end convolutional neural network, named multi-stream fusion network (MSFNet), is proposed in this paper. MSFNet is built following the encoder-decoder network structure. The encoder is a three-stream network to produce features at three resolution levels. Residual dense blocks (RDBs) are used for feature extraction. The resizing blocks serve as bridges to connect different streams. The features from different streams are fused in a full connection manner by a feature fusion block, with stream-wise and channel-wise attention mechanisms. The decoder directly regresses the dehazed image from coarse to fine by the use of RDBs and the skip connections. To train the network, we design a generalized smooth L1 loss function, which is a parametric loss family and permits to adjust the insensitivity to the outliers by varying the parameter settings. Moreover, to guide MSFNet to capture the valid features in each stream, we propose the multi-scale supervision learning strategy, where the loss at each resolution level is computed and summed as the final loss. Extensive experimental results demonstrate that the proposed MSFNet achieves superior performance on both synthetic and real-world images, as compared with the state-of-the-art single image dehazing methods.

Classification of slow cortical potential (SCP) signals is crucial for brain-computer interface (BCI) systems. This letter presents a new scheme to improve the classification performance of SCP signals. It consists of two parts: first, by fitting the wavelet coefficients of SCP signals with a second-order polynomial, the SCP trends are extracted; and second, a voting system based on the optimal training parameters of the support vector machines is developed to enhance the classification accuracy (CA). Experimental results reveal that the proposed scheme outperforms the state-of-the-art methods. The CA improvements for the dataset Ia of the BCI competition II and the TJU dataset (the dataset was collected in Tianjin University, termed TJU dataset) are reported.