Self-supervised image denoising methods have garnered significant research attention in recent years, for this kind of method reduces the requirement of large training datasets. Compared to supervised methods, self-supervised methods rely more on the prior embedded in deep networks themselves. As a result, most of the self-supervised methods are designed with Convolution Neural Networks (CNNs) architectures, which well capture one of the most important image prior, translation equivariant prior. Inspired by the great success achieved by the introduction of translational equivariance, in this paper, we explore the way to further incorporate another important image prior. Specifically, we first apply high-accuracy rotation equivariant convolution to self-supervised image denoising. Through rigorous theoretical analysis, we have proved that simply replacing all the convolution layers with rotation equivariant convolution layers would modify the network into its rotation equivariant version. To the best of our knowledge, this is the first time that rotation equivariant image prior is introduced to self-supervised image denoising at the network architecture level with a comprehensive theoretical analysis of equivariance errors, which offers a new perspective to the field of self-supervised image denoising. Moreover, to further improve the performance, we design a new mask mechanism to fusion the output of rotation equivariant network and vanilla CNN-based network, and construct an adaptive rotation equivariant framework. Through extensive experiments on three typical methods, we have demonstrated the effectiveness of the proposed method. The code is available at: https://github.com/liuhanze623/AdaReNet.

To satisfy the communication, localization, and energy demands of low-power IoT nodes, combining integrated sensing and communication (ISAC) and simultaneous wireless information and power transfer (SWIPT) can offer an innovative solution. However, carrying private information in wireless sensing beams critically increases the vulnerability of being eavesdropped by the target. In this paper, we propose a non-orthogonal multiple access (NOMA)-enhanced secure transmission strategy to counteract the internal eavesdropping for SWIPT-ISAC. We jointly optimize the transmit beamforming and power splitting to maximize the secrecy rate towards the eavesdropping by the target, ensuring the nonlinear energy harvesting (EH) and precise sensing beampatterns. Our approach enables the nodes to manage the interference through successive interference cancellation and to harvest energy from the transmitted signal. The original optimization problem is non-convex and difficult to tackle. Using the semidefinite relaxation, we convert it to convex form, and propose alternating optimization algorithm to derive the solutions. Simulation results indicate that the proposed scheme can effectively counteract the internal eavesdropping, while ensuring the nonlinear$\mathbf{E H}$and sensing performance.

As unmanned aerial vehicles (UAVs) increasingly operate in large-scale clusters, traditional routing protocols struggle to ensure efficient and time-sensitive packet path planning due to the growing network size and inherent mobility of UAVs. Meanwhile, despite deep learning (DL) based routing methods have shown promise in small UAV networks, their computational demands and limited scalability to large numbers of UAV nodes pose significant challenges. To address the challenges of scalability and computational demands in large-scale UAV networks, this paper proposes a novel decentralized global guided routing algorithm based on potential field. First, a potential field is constructed using a harmonic function to represent the current network status. Subsequently, leveraging this potential field, a global route is derived to define the overarching direction for data transmission. Finally, a compact neural network deployed at each node utilizes the global guidance direction and the local potential field information obtained from its surroundings to establish a specific data forwarding path within its maximum perception range. Simulation results illustrate the advantages of our proposed approach for establishing UAV paths in large-scale UAV networks.

To satisfy the communication, localization, and energy demands of low-power IoT nodes, combining integrated sensing and communication (ISAC) and simultaneous wireless information and power transfer (SWIPT) can offer an innovative solution. However, carrying private information in wireless sensing beams critically increases the vulnerability of being eavesdropped. In this paper, we propose two non-orthogonal multiple access (NOMA)-enhanced secure transmission strategies to counteract the internal and external eavesdropping for SWIPT-ISAC. First, we jointly optimize the transmit beamforming and power splitting to maximize the secrecy rate towards the internal eavesdropping by the target, ensuring the nonlinear energy harvesting (EH) and precise sensing beampatterns. Then, facing a more severe scenario with L external eavesdroppers, we exploit the artificial jamming with the highest power allocation to mitigate both the internal and external eavesdropping. Our approach enables the nodes to manage the interference through successive interference cancellation and to harvest energy from the jamming. The original optimization problems in both scenarios are non-convex and difficult to tackle. Using the semidefinite relaxation, we convert them to convex forms, and propose alternating optimization algorithms to derive the solutions. Simulation results indicate that the proposed schemes can effectively counteract the internal and external eavesdropping, while ensuring the nonlinear EH and sensing performance.

Multi-hop packet routing is critical for unmanned aerial vehicle (UAV) networks to enable efficient communication between terminals in diverse environments. However, the complexity of routing design exacerbates due to interference from the environment and link instability caused by high-speed mobility. To address this challenge, we propose a harmonic function-based potential field to assess the impact of interference on UAV networks quantitatively. The proposed field maps the communication quality in terms of interference and mobility onto a virtual three-dimensional plane, providing a metric to establish routing paths. Based on this, two routing algorithms are designed to address two distinct routing requirements of UAV networks, timeliness and losslessness. Leveraging the natural adaptation to the potential field, the two proposed routing algorithms can effectively avoid interference while meeting different requirements. Simulation results demonstrate the effectiveness of the proposed potential field in representing the influences of interference and mobility. Additionally, the results validate the ability of the two routing algorithms to fulfill data communication requirements in terms of delay and accuracy while effectively mitigating interference.

Multi-hop packet routing is critical for unmanned aerial vehicle (UAV) networks to enable efficient communication between terminals in diverse environments. However, the complexity of routing design exacerbates due to interference from the environment and link instability caused by high-speed mobility. To address this challenge, we propose a harmonic function-based potential field to assess the impact of interference on UAV networks quantitatively. The proposed field maps the communication quality in terms of interference and mobility onto a virtual three-dimensional plane, providing a metric to establish routing paths. Based on this, two routing algorithms are designed to address two distinct routing requirements of UAV networks, timeliness and losslessness. Leveraging the natural adaptation to the potential field, the two proposed routing algorithms can effectively avoid interference while meeting different requirements. Simulation results demonstrate the effectiveness of the proposed potential field in representing the influences of interference and mobility. Additionally, the results validate the ability of the two routing algorithms to fulfill data communication requirements in terms of delay and accuracy while effectively mitigating interference.

Industrial Internet of Things (IIoT) is regarded as the basis of the future industrial system. The interaction between nodes in IIoT shows strong regularity or sociality, which has the potential to improve the efficiency of IIoT. This article focuses on the investigation of the relationship of social activity and data transmission, and proposes a novel routing protocol to enhance QoS of social and cognitive IIoT networks. In accordance with practical requirements of an application, the routing protocol owns two purposes: one is to meet the requirement of delay-sensitive information transmission, and the other focuses on the load balance of the social and cognitive IIoT network. As a special feature of social and cognitive IIoT, the mechanism for protection of social activities is proposed while data transmission is adopted in the proposed protocol. System-level evaluation shows that the proposed protocol can achieve better performances compared with existing routing protocols for social and cognitive IIoT networks.