Transformer-based methods are recently popular in vision tasks because of their capability to model global dependencies alone. However, it limits the performance of networks due to the lack of modeling local context and global-local correlations of multi-scale features. In this paper, we present MISSFormer, a Medical Image Segmentation tranSFormer. MISSFormer is a hierarchical encoder-decoder network with two appealing designs: 1) a feed-forward network in transformer block of U-shaped encoder-decoder structure is redesigned, ReMix-FFN, which explore global dependencies and local context for better feature discrimination by re-integrating the local context and global dependencies; 2) a ReMixed Transformer Context Bridge is proposed to extract the correlations of global dependencies and local context in multi-scale features generated by our hierarchical transformer encoder. The MISSFormer shows a solid capacity to capture more discriminative dependencies and context in medical image segmentation. The experiments on multi-organ, cardiac segmentation and retinal vessel segmentation tasks demonstrate the superiority, effectiveness and robustness of our MISSFormer. Specifically, the experimental results of MISSFormer trained from scratch even outperform state-of-the-art methods pre-trained on ImageNet, and the core designs can be generalized to other visual segmentation tasks. The code has been released on Github: https://github.com/ZhifangDeng/MISSFormer.

We demonstrate in-plane field-free-switching spin-orbit torque (SOT) magnetic tunnel junction (MTJ) devices that are capable of low switching current density, fast speed, high reliability, and, most importantly, manufactured uniformly by the 200-mm-wafer platform. The performance of the devices is systematically studied, including their magnetic properties, switching behaviors, endurance and data retention. The successful integration of SOT devices within the 200-mm-wafer manufacturing platform provides a feasible way to industrialize SOT MRAMs. It is expected to obtain excellent performance of the devices by further optimizing the MTJ film stacks and the corresponding fabrication processes in the future.

In recent years, microgrids have attracted much attention as one of the typical applications of the Internet of Things (IoT). With the development of renewable energy, a bilayer energy-trading scenario of microgrids has emerged. In the upper layer, the microgrids trade energy with each other, and in the lower layer, users trade energy within the microgrid. Traditional management schemes based on the cooperation mode or island mode of the microgrids can no longer meet the needs of energy trading. In this article, we propose an energy-trading management solution for the bilayer energy-trading scenario. In order to maximize the bilayer’s [i.e., users’ and microgrid operators’ (MGOs)] utility functions under the condition of the local energy supply and demand, we propose a multiobjective optimization model. To solve the optimization model, we give a solution energy-trading management algorithm (ETMA) based on the nondominated sorting genetic algorithm (NSGA). Moreover, the proposed energy-trading framework that is based on the multiblockchain ensures the security and privacy of energy trading, and a consensus mechanism named the Delegated Proof of Reputation (DPoR) is proposed to urge users to complete the transaction according to their promised trading schemes. Experiments based on the real data of Guizhou are done to evaluate the performance of the proposed optimization model. The results show that our proposed model can achieve better performance in terms of users’ and MGOs’ utility functions in the bilayer energy-trading scenario compared with the traditional models.

Incorporating wireless power transfer (WPT) into mobile-edge computing (MEC) is an effective way to enhance the self-sustainability of the MEC network. However, it is susceptible to the effect of double-far-near. Meanwhile, inspired by the fact that nonorthogonal multiple access (NOMA) has shown its great potential in improving the spectral efficiency of the network over orthogonal multiple access, this article investigates a cooperative computation offloading scheme for a basic three-node wireless-powered MEC scenario with NOMA, where users overcome the effect of double-far-near through joint communication and computation cooperation. Specifically, we consider a “harvest-then-offload” protocol composed of three stages. In the first stage, users harvest wireless energy signals from the access point (AP). In the second and third stages, based on NOMA, users offload their partial computing tasks on the same time–frequency resource block by using the harvested energy, in which the near user can cooperatively compute and forward the computing task of the far user. We formulate an optimization problem to minimize the transmission energy consumption of the AP by jointly optimizing the transmission power, the offloading coefficient, and the duration of each stage. Due to the nonconvexity of the formulated problem, we first transform it into an equivalent one by using the variable substitution method. Then, we propose an efficient iterative algorithm based on the successive convex approximation (SCA) and Lagrangian duality method to solve this transformed problem. Simulation results show that the proposed algorithm has good convergence and the proposed scheme can achieve the best performance compared with several baseline schemes, which highlights the superiority of the proposed scheme.

During the COVID-19 epidemic, the news is overwhelming in people's daily life. So, we aim to extract key information from a large amount of public news. This paper focus on the daily sentiment distribution of news and public opinion on Weibo that refers to the key word COVID-19. First, we refining the key news from all the news in a day to deal with long and large news data. Second, we transformer the headline into a high-dimensional vector. And then, divided them into k categories on the strength of k-means clustering algorithm. Finally, choose the closet news to the mean vector as the key news of the day. Moreover, we conduct sentiment analysis on all key news and Weibo data. By comparing the sentiment trend of news and Weibo, this study provides a new channel to analyze social public opinion.

In the inter-domain network, route leaks can disrupt the Internet traffic and cause large outages. The accurate detection of route leaks requires the sharing of AS business relationship information. However, the business relationship information between ASes is confidential. ASes are usually unwilling to reveal this information to the other ASes, especially their competitors. In this paper, we propose a method named FL-RLD to detect route leaks while maintaining the privacy of business relationships between ASes by using a blockchain-based federated learning framework, where ASes can collaboratively train a global detection model without directly disclosing their specific business relationships. To mitigate the lack of ground-truth validation data in route leaks, FL-RLD provides a self-validation scheme by labeling AS triples with local routing policies. We evaluate FL-RLD under a variety of datasets including imbalanced and balanced datasets, and examine different deployment strategies of FL-RLD under different topologies. According to the results, FL-RLD performs better in detecting route leaks than the single AS detection, whether the datasets are balanced or imbalanced. Additionally, the results indicate that selecting ASes with the most peers to first deploy FL-RLD brings more significant benefits in detecting route leaks than selecting ASes with the most providers and customers.