Non-orthogonal multiple access (NOMA) with successive detection receivers, e.g., successive interference cancellation (SIC), is a potential technology for satellite multi-user communication due to its lower complexity. However, within a spot beam, multi-user interference (MUI) is complicated by channel-induced time-frequency offset, while the path loss differences that the receiver relies on for MUI suppression almost disappear. To overcome the above obstacle, this paper exploits the delay-Doppler (D-D) domain circular shifting property under time-frequency offsets and proposes a D-D domain spectral shaping multiple access (SSMA) technique. By analyzing the influence of D-D domain spectrum on channel capacity, we identify that an enlarged inter-user power gap can be derived at the receiver by constructing a non-uniform D-D domain spectrum. Inspired by this, a D-D domain multi-branch structure-based shaping framework is proposed to flexibly construct the user-consistent power envelope. Meanwhile, two additional signal designs are introduced to ensure that the D-D domain information density and constellation fit to the constructed power envelope. First, by adjusting the transmission rate of the signal on each branch, we optimize the information density with a non-uniform pattern. Second, by introducing a branch-wise phase rotation and deploying an iterative variational approximation method, the shape of the composite constellation is reconstructed. In addition, we also design a branch-bundling-based successive detection receiver using an alternating direction method of multipliers. This receiver can flexibly combine detectable branch signals while maintaining the complexity close to the traditional SIC receiver. Analysis and simulation results reveal that the proposed D-D domain SSMA has a higher achievable rate and can provide$1\sim 4.5$dB bit error rate performance gain compared to the typical D-D domain NOMA.

Researchers have applied 3D Lookup Tables (LUTs) in cameras, offering new possibilities for enhancing image quality and achieving various tonal effects. However, these approaches often overlook the non-uniformity of color distribution in the original images, which limits the performance of learnable LUTs. To address this issue, we introduce a lightweight end-to-end image enhancement method called Simulated Infrared Fusion Guided Image-adaptive 3D Lookup Tables (SIRLUT). SIRLUT enhances the adaptability of 3D LUTs by reorganizing the color distribution of images through the integration of simulated infrared imagery. Specifically, SIRLUT consists of an efficient Simulated Infrared Fusion (SIF) module and a Simulated Infrared Guided (SIG) refinement module. The SIF module leverages a cross-modal channel attention mechanism to perceive global information and generate dynamic 3D LUTs, while the SIG refinement module blends simulated infrared images to match image consistency features from both structural and color aspects, achieving local feature fusion. Experimental results demonstrate that SIRLUT outperforms state-of-the-art methods on different tasks by up to 0.88 ~ 2.25dB while reducing the number of parameters. Code is available at https://github.com/riversky2025/SIRLUT.git .

The densely deployment of satellites enables the realization of direct-to-satellite Internet-of-things system with tremendous terminals through multi-satellite cooperation. Multi-user detection (MUD) based on cooperative satellite network can dramatically increase the detection performance. However, it is chained by the limited number of inter-satellite link (ISL) bandwidth resources. To cope with the stringent constraints on ISLs, we propose a novel auxiliary node (AN)-aided factor graph and the corresponding multi-user detection (MUD) algorithm named auxiliary node-cooperative message passing algorithm (AN-CMPA). Simulation results show that our proposed algorithm achieves only 0.5dB loss with 75% decreased information cost under effectively designed information filter criterion.

With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress. However, it remains a great challenge to accurately extract disparities from real-world image pairs taken by consumer-level devices like smartphones, due to practical complicating factors such as thin structures, non-ideal rectification, camera module inconsistencies and various hard-case scenes. In this paper, we propose a set of innovative designs to tackle the problem of practical stereo matching: 1) to better recover fine depth details, we design a hierarchical network with recurrent refinement to update disparities in a coarse-to-fine manner, as well as a stacked cascaded architecture for inference; 2) we propose an adaptive group correlation layer to mitigate the impact of erroneous rectification; 3) we introduce a new synthetic dataset with special attention to difficult cases for better generalizing to real-world scenes. Our results not only rank 1ston both Middlebury and ETH3D benchmarks, outperforming existing state-of-the-art methods by a notable margin, but also exhibit high-quality details for real-life photos, which clearly demonstrates the efficacy of our contributions.

Due to the rich relational information of graph-structured data, graph neural networks (GNNs) have been widely used for fraud detection tasks, where the suspiciousness of nodes is identified by aggregating information about the neighbors of different relations. To bypass such detection, fraudsters camouflage themselves by providing seemingly legitimate feedback (i.e., feature camouflage) or connecting many legitimate users (i.e., relation camouflage). Moreover, when the label distribution of nodes is severely skewed, GNN-based algorithms may have limitations. To counteract the effect of disguised fraudsters under imbalanced graphs on fraud detection, we propose a cascaded GNN fraud detector with dual features (CGDF-GNN) in this paper. It tackles the impact of feature camouflage by applying a dual-feature parallel aggregation method and uses a cascaded neighbor aggregator to deal with the single-level learning problem arising from relational camouflage. Experiments on graph-based fraud detection tasks on two real-world datasets demonstrate the effectiveness of our model compared to current state-of-the-art baselines.

The ongoing roll-out of cloud–edge computing and Internet of Things (IoT) has been simulating the boom of new advance reservation (AR) services, such as bulk-data migration and virtual machine backup, driving the development of substrate elastic optical networks (EONs). These AR requests are initial-delay-insensitive if they are guaranteed to be completed before a predefined deadline. Therefore, the routing, modulation, and spectrum assignment (RMSA) problem is extended to the time-spectrum domain rather than the single spectrum domain. Traditional heuristic RMSA algorithms follow static procedures under handcrafted rules and assumptions, and thus cannot be optimized automatically. To solve this problem, we propose a deep reinforced deadline-driven allocation (DRDA) algorithm. To the best of our knowledge, this work is the first to leverage deep reinforcement learning (DRL) methods to solve the AR resource allocation problem. Moreover, compared with the single experiment scenario of many existing works, the DRDA algorithm is evaluated in both static and dynamic scenarios. Simulation results show that our DRDA algorithm outperforms the other leading algorithms in both static scenario and dynamic scenario.

Deep learning has been exploited to tackle the multi-user detection problem of non-orthogonal multiple access (NOMA), for its high detection accuracy and low computational delay. Existing deep learning algorithms adopt an offline training and online deploying method. When the online system configuration, such as the number of the users, differs from that in offline training, existing deep learning algorithms fail to work due to the mismatch of the output dimensions. In this paper, we propose an online reconfigurable deep learning framework for multi-user detection which can adapt to diversified number of the users. Inspired by the factor graph representation of NOMA, the framework is designed as the composition of several interlinked deep neural network branches where each branch is dedicated for the detection of a single user. The connections among the branches are configurable to achieve online dynamic extension or clipping so as to match the varying number of NOMA users. Experiments validate the online reconfigurability and the performance gain of the proposed deep learning framework.

Cloud-fog computing emerges to satisfy the low latency and high computation requirements of Internet of Things (IoT) services. Elastic optical networks (EONs) are excellent substrate communication networks between fog datacenters and cloud datacenters. However, the uneven traffic of massive cloud-fog services incurs many spectrum fragments, leading to high extra energy consumption. To solve this problem, we propose an energy-efficient deep reinforced traffic grooming (EDTG) algorithm based on deep reinforcement learning. Unlike existing manually network features extracting methods, we convert the traditional network modal and the service routing path into colored network images to represent their states and extract the features automatically by MobilenetV3 according to these images. With the extracted features, we implement an advantage actor-critic (A2C) algorithm, whose actor module and critic module share an artificial neural network (ANN) to get optimal grooming actions. Additionally, after repeated attempts and experiments, we set up an objective reward and punishment mechanism to evaluate the grooming actions. We conduct extensive simulations for performance evaluation, and the results have shown that EDTG can significantly reduce energy consumption compared with two well-performed traffic grooming algorithms.