In recent years, neural network algorithms have demonstrated tremendous potential for modulation classification. Deep learning methods typically take raw signals or convert signals into time–frequency images as inputs to convolutional neural networks (CNNs) or recurrent neural networks (RNNs). However, with the advancement of graph neural networks (GNNs), a new approach has been introduced involving transforming time series data into graph structures. In this study, we propose a CNN-transformer graph neural network (CTGNet) for modulation classification, to uncover complex representations in signal data. First, we apply sliding window processing to the original signals, obtaining signal subsequences and reorganizing them into a signal subsequence matrix. Subsequently, we employ CTGNet, which adaptively maps the preprocessed signal matrices into graph structures, and utilize a graph neural network based on GraphSAGE and DMoNPool for classification. Extensive experiments demonstrated that our method outperformed advanced deep learning techniques, achieving the highest recognition accuracy. This underscores CTGNet’s significant advantage in capturing key features in signal data and providing an effective solution for modulation classification tasks.

Low-density parity-check (LDPC) codes have been chosen for the fifth-generation (5G) new radio (NR) enhanced Mobile Broad Band (eMBB) data channel. Since NR LDPC codes puncture the first two block columns of the parity-check matrix, the decoding complexity is reduced, but it slows down the convergence rate. In this paper, we propose a fixed schedule that decodes the layers with the least-punctured edges and those with the highest-degree (LPHD), which has much faster convergence speed than conventional schemes. The fixed scheduling schemes cannot take full advantage of the dynamic changes of decoding messages. As a result, the residual-based layered belief propagation (RB-LBP) is proposed to rearrange the layers dynamically among different iterations. Compared with some informed dynamic scheduling (IDS) strategies, RB-LBP reduces the decoding complexity with slight performance loss.

The transverse momentum $(p_t)$ dependence, the centrality dependence, and the rapidity dependence of the elliptic flow of thermal photons in $\mathrm{Au}+\mathrm{Au}$ collisions at $\sqrt{s_{\mathit{NN}}}=200$ GeV are predicted on the basis of a three-dimensional ideal hydrodynamic description of the hot and dense matter. The elliptic flow parameter $v_2$, i.e., the second Fourier coefficient of azimuthal distribution, of thermal photons first increases with $p_t$ and then decreases for $p_t>2$ GeV/$c$, because of the weak transverse flow at the early stage. The $p_t$-integrated $v_2$ first increases with centrality, reaches a maximum at about 50% centrality, and then decreases. The rapidity dependence of the elliptic flow $v_2(y)$ of direct photons (mainly thermal photons) is very sensitive to the initial energy density distribution along the longitudinal direction, which provides a useful tool to extract the realistic initial condition from measurements.

Solid-state drives (SSDs) are widely used in current storage systems. SSD manufacturers usually aggregate physical blocks across planes into one superblock to improve SSD performance. However, due to the wear endurance variations among blocks and pages, the standard superblock scheme leads to lifetime and space waste of SSDs. Superblock granularity also causes higher and more uncertain garbage collection overhead. To address these problems, this work proposes endurance-driven dynamic superblock management called EddySuperblock to provide a longer lifetime and higher space utilization with a faster and deterministic response time, which designs a dynamic superblock organization strategy that links free strong blocks into one superblock according to the real-time wear index of each block and introduces page-level wear management to further unlock the lifetime potential of pages. To reduce the high garbage collection overhead caused by superblocks, a nonblocking parallel garbage collection policy is proposed, which can reclaim space and serve requests simultaneously with low overhead. We conduct a set of experiments on a real hardware experiment platform. Both the proposed EddySuperblock and representative superblock schemes have been implemented on the experiment platform. The experimental results show that our scheme greatly reduces the average system response time by 47.6% and prolongs the lifetime by 75.6% compared with the state-of-the-art superblock scheme, and the final-state flash utilization reaches 95.4%. In the end, this article presents the application status of our work in real-world scenarios.

The Five-hundred-meter Aperture Spherical radio Telescope (FAST) is the largest single-dish radio telescope in the world, and is now being commissioned after the first light in September 2016. Very long baseline interferometry (VLBI) is among the key science topics according to the original design. The FAST VLBI system has been established, and the first VLBI fringe has been successfully obtained. FAST will significantly improve the sensitivity of the existing VLBI networks in the future, and some science projects in need of high sensitivity will benefit from its participation.