Hyperspectral image (HSI) change detection is a technique that can identify the changes occurring between the bitemporal HSIs covering the same geographic area. The field of change detection has witnessed the proposal and successful implementation of numerous methods. However, a majority of these approaches adhere to the centralized learning paradigm, which requires data transmission to a central server for training. The sensitivity of remote sensing data generally prohibit their sharing across different clients. Furthermore, manual labeling is a costly effort in practically. In this paper, we propose a spatial-spectral-temporal collaborative Mamba-based active federated hyperspectral change detection (MambaFedCD) framework, which utilizes the limited labeled samples from multiple clients to achieve change detection while ensuring the data privacy of each client. Specifically, there are three key characteristics: 1) a spatial-spectral-temporal collaborative Mamba-based change detection ( ${{\text {S}}^{2}}{\text {TMamba}}$ ) model is proposed to efficiently synergize the temporal and global spatial-spectral information of the bitemporal HSIs for change detection; 2) a difference feature diversity correction-based model aggregation (DFDCMA) strategy is devised to incorporate the diversity of difference features for rational allocation of weight factors among clients and to facilitate effective aggregation of the global model; 3) we propose a multi-decision federated active learning (MDFAL) strategy that selects both error-prone and valuable samples for model training to alleviate the burden of sample labeling. Comprehensive experiments conducted on commonly utilized datasets demonstrate that the proposed method outperforms other state-of-the-art methods. The code is available at https://github.com/Jiahuiqu/MambaFedCD.

A spontaneous electroencephalogram (EEG)-based brain-computer interface (BCI) is an ideal form of brain-computer interaction. The classical decoding methods can achieve classification by using meaningful manual features, but their performance is poor. The neural network (NN) methods have significantly improved the performance, but their interpretability and computational efficiency are much lower than those of the classical methods. This is because NN abandons the strong a priori knowledge of neuroscience and completely relies on training to extract EEG features. How to integrate the characteristics of neural signals into the design of the basic operator of the NNs while retaining its learning ability is the focus of this work. In this work, we proposed a function predefined convolutional NN (FPCNN) to search for the best frequency points and channel weights to decode spontaneous EEG signals. Among the FPCNN, a novel function predefined convolutional (FPC) layer adopts a learnable way to search for the key spatial-frequency parameters of spontaneous EEG, making its parameters have clear physical meanings. Furthermore, a trainable quadrature detector (TQD) based on FPC was constructed, and the quadrature characteristic was utilized to ensure the capture of complex phase change signals. The core contribution of our method lies in the proposal of a novel NN operator for decoding spontaneous EEG, and a quadrature scheme for handling the phase changes of signals. The experimental results show that the proposed FPCNN significantly improves the performance by 2.09% ( ${}^{\ast } $ ), 3.08% ( ${}^{\ast } $ ), and 3.41% ( ${}^{\ast \ast }$ ), respectively, compared with the state-of-the-art (SOTA) methods on three spontaneous EEG datasets. Moreover, the training and testing time cost of FPCNN in a non-GPU environment only takes 67.96 and 19.36 s per epoch. Its savings in computing resources and time are very beneficial for EEG processing in diverse environments. In addition, visualization experiments demonstrated the interpretability and stability of the proposed FPCNN. The experimental results show that our method is efficient, stable, and interpretable. This work has effectively improved the decoding efficiency of spontaneous EEG signals and demonstrated the power of combining traditional signal processing methods with NNs.

Electroencephalogram (EEG)-based emotion recognition has achieved remarkable success in both subject-dependent and subject-independent scenarios. However, overcoming the challenges associated with reduced performance in EEG emotion recognition across devices, time, space, and subjects (i.e., cross-dataset) remains a significant obstacle for affective brain-computer interfaces (aBCIs). The key issue lies in the distributional mismatch between source and target domain EEG signals. To tackle the significant inter-domain differences in cross-dataset EEG emotion recognition, this paper introduces an innovative framework termed the Emotional EEG Style Transfer Network (E$^{2}$STN), which aims to effectively capture the emotional content information from the source domain and the style features from the target domain, facilitating the reconstruction of stylized emotion EEG representations. These stylized EEG representations significantly enhance the discriminative prediction performance in cross-dataset EEG emotion recognition. Specifically, E$^{2}$STN consists of three key modules: a Transfer Module for domain style transfer, a Transfer Evaluation Module for evaluating transfer quality, and a Discriminative Module for making discriminative predictions. Extensive experiments demonstrate that E$^{2}$STN achieves the state-of-the-art performance in cross-dataset emotion EEG recognition. To the best of our knowledge, this is the first work to explicitly address cross-dataset emotion EEG recognition. The experimental results provide a valuable benchmark for future research in this area.

The joint classification methods of hyperspectral image (HSI) and light detection and ranging (LiDAR) data based on deep learning have demonstrated exceptional classification performance with sufficient labeled samples. However, it is expensive and time-consuming to acquire labeled data. To address this limitation, we propose a shared-private decoupling-based multilevel feature alignment semisupervised (SASS) learning method for HSI and LiDAR classification, which introduces the idea of domain adaptation (DA) to capture the shared features of labeled and unlabeled data for classification and circularly selects reliable pseudolabels based on these features to retrain the model. Specifically, we treat labeled data as the source domain (SD) and unlabeled data as the target domain (TD) and propose a shared-private feature decoupling (SPFD) module to acquire shared representations of SD and TD by separating domain private features. The multilevel shared feature alignment (MSFA) strategy is designed to synthetically consider both spatial details and semantic information by minimizing the maximum mean discrepancy (MMD) between these shared features. In addition, we design a graph transformer-based class-balanced pseudolabel generation (GBPG) strategy for iterative model training with reliable pseudolabels, which exploits the graph transformer network-based sample acquisition (GTSA) strategy to select valuable samples and generate corresponding pseudolabels using the adaptive class-specific threshold-based sample annotation (ATSA) strategy. Experimental results on three public datasets validate the effectiveness of the proposed method. The code is available athttps://github.com/Jiahuiqu/SASS.

Stainless steel plate heat sink has the characteristics of good low-temperature performance, short production cycle and low production cost. Stainless steel plate heat sink has been widely used in the environment simulation test equipment of spacecraft around the world, which is a new trend of heat sink development. In order to master the processing technology of stainless-steel heat sink, this paper established the finite element analysis model of stainless steel heat sink hydroforming, calculated the relationship between the forming pressure and the height of runner, and investigated the effects of process parameters such as preforming procedure, boundary pressure and solder joint layout on runner height and forming uniformity. Therefore, the key technology of stainless steel heat sink was mastered. By studying the hydroforming process of heat sink, the deformation law of heat sink was deeply analyzed, and the reasonable process parameters were obtained, which can be used as the guidance for test and production to optimize the process parameters, shorten the trial production time, thus reduce the test and production costs.

In this paper, we address physical layer security for amplify-and-forward (AF) multi-antenna relay systems in the presence of multiple eavesdroppers. A robust joint design of cooperative beamforming (CB) and artificial noise (AN) is proposed with imperfect channel state information (CSI) of both the destination and the eavesdroppers. We aim to maximize the worst-case secrecy rate subject to the sum power and the per-antenna power constraints at the relay. Such joint design problem is non-convex. By utilizing the semidefinite relaxation (SDR) technique, S-procedure and the successive convex approximation (SCA) algorithm, the original non-convex optimization problem is recast into a series of semidefinite programs (SDPs) which can be efficiently solved using interior-methods. Simulation results are presented to verify the effectiveness of the proposed design.

In this work, a robust artificial noise (AN) aided transmit method is proposed for a multicast multiple-input single-output (MISO) system in the presence of multiple single-antenna eavesdroppers. With the imperfect covariance-based channel state information (CSI), we aim to minimize the transmit power at the transmitter under the multicast secrecy rate constraint and the maximum transmit power constraint. The resulting optimization problem involves the joint optimization of the beamforming vector and AN covariance matrix. After using the semidefinite relaxation (SDR) technique, we derive the exact reformulation of the original optimization through the Lagrange duality. Then this non-convex problem is transformed into a one-variable optimization problem, which can be handled by solving a series of semidefinite programs (SDPs). Simulation results demonstrate the effectiveness of the proposed robust transmit method.