Search Results (218)

In recent years, Transformer-based methods have demonstrated proficiency in capturing complex patterns for time series forecasting. However, their quadratic complexity relative to input sequence length poses a significant bottleneck for scalability and real-world deployment. Recently, the Mamba architecture has emerged as a compelling alternative by mitigating the prohibitive computational overhead and latency inherent in Transformers. Nevertheless, a vanilla Mamba backbone often struggles to adequately characterize intricate temporal dynamics, particularly long-term trend shifts and non-stationary behaviors. To bridge the gap between Mamba’s global scanning and local dependency modeling, we propose C-T-Mamba, a hybrid framework that synergistically integrates a Mamba block, channel attention, and a temporal convolution block. Specifically, the Mamba block is leveraged to capture long-range temporal dependencies with linear scaling, the channel attention mechanism filters redundant information, and the temporal convolution block extracts multi-scale local and global features. Extensive experiments on five public benchmarks demonstrate that C-T-Mamba consistently outperforms state-of-the-art (SOTA) baselines (e.g., PatchTST and iTransformer), achieving average reductions of 4.3–18.5% in MSE and 3.9–16.2% in MAE compared to representative Transformer-based and CNN-based models. Inference scaling analysis reveals that C-T-Mamba effectively breaks the computational bottleneck; at a horizon of 1536, it achieves an $8.8\times$ reduction in GPU memory and over 10× speedup compared to standard Transformers. At 2048 steps, its latency remains as low as 8.9 ms, demonstrating superior linear scaling. These results underscore that C-T-Mamba achieves SOTA accuracy while maintaining a minimal computational footprint, making it highly effective for long-term multivariate time series forecasting. Full article

Emerging multi-unmanned aerial vehicle (multi-UAV) applications in smart cities must navigate cluttered airspace while meeting tight mobile edge computing (MEC) deadlines. Classical grid planners, including A-star (A*), D-star Lite (D* Lite), and conflict-based search with D-star Lite (CBS-D*) and metaheuristics such asparticle swarm optimization (PSO), either replan too slowly in dynamic scenes or waste energy on long detours. This paper presents PPO-adjusted incremental refinement (PAIR), a decentralized hybrid planner that couples an A* global backbone with a continuous PPO refinement module for multi-UAV navigation on two-dimensional (2-D) urban grids. A* produces feasible waypoint routes, while a shared risk-aware PPO policy applies local offsets from a compact state encoding. MEC tasks are allocated by a separate heterogeneous scheduler; PPO optimizes geometric objectives (path length, risk, and a normalized propulsion-energy surrogate). Across nine benchmark scenarios with static and Markovian dynamic obstacles, PAIR achieves 100% mission success (matching the strongest baselines) while delivering the best energy surrogate (104.9 normalized units) and shortest mean travel time (207.8 s) on a reproducible $100\times 100$ grid at fixed UAV speed. Relative to the strongest non-learning baseline (PSO), PAIR reduces energy by about 4% and travel time by about 3%, and yields roughly 10–20% gains over the remaining planners. An obstacle-density sweep with 5–30 moving obstacles further shows that PAIR maintains shorter paths and the lowest cumulative replanning time, supporting real-time multi-UAV navigation in dynamic urban MEC environments. Full article

This study introduces a fully uncertainty-aware forecasting framework for NBA games that integrates team-level performance metrics, rolling-form indicators, and spatial shot-chart embeddings. The predictive backbone is a recurrent neural network equipped with Monte Carlo dropout, yielding calibrated sequential probabilities. The model is evaluated against strong baselines including logistic regression, XGBoost, convolutional models, a GRU sequence model, and both market-only and non-market-only benchmarks. All experiments rely on strict chronological partitioning (train ≤ 2022, validation 2023, test 2024), ablation tests designed to eliminate any circularity with bookmaker odds, and cross-season robustness checks spanning 2012–2024. Predictive performance is assessed through accuracy, Brier score, log-loss, AUC, and calibration metrics (ECE/MCE), complemented by SHAP-based interpretability to verify that only pre-game information influences predictions. To quantify economic value, calibrated probabilities are fed into a frictionless betting simulator using fractional-Kelly staking, an expected-value threshold, and bootstrap-based uncertainty estimation. Empirically, the uncertainty-aware model delivers systematically better calibration than non-Bayesian baselines and benefits materially from the combination of shot-chart embeddings and recent-form features. Economic value emerges primarily in less-efficient segments of the market: The fused predictor outperforms both market-only and non-market-only variants on moneylines, while spreads and totals show limited exploitable edge, consistent with higher pricing efficiency. Sensitivity studies across Kelly multipliers, EV thresholds, odds caps, and sequence lengths confirm that the findings are robust to modelling and decision-layer perturbations. The paper contributes a reproducible, decision-focused framework linking uncertainty-aware prediction to economic outcomes, clarifying when predictive lift can be monetized in NBA markets, and outlining methodological pathways for improving robustness, calibration, and execution realism in sports forecasting. Full article

Due to the critical role of channel coding, convolutional code recognition has attracted growing interest, particularly in non-cooperative communication scenarios such as spectrum surveillance. Deep learning-based approaches have emerged as promising techniques, offering improved classification performance. However, most existing works focus on single-parameter recognition and ignore the inherent correlations between code parameters. To address this, we propose a novel framework named Hybrid Multi-Task Network (HMT-Net), which adopts multi-task learning to simultaneously identify both the code rate and constraint length of convolutional codes. HMT-Net combines dilated convolutions with attention mechanisms and integrates a Transformer backbone to extract robust multi-scale sequence features. It also leverages a Channel-Wise Transformer to capture both local and global information efficiently. Meanwhile, we enhance the dataset by incorporating a comprehensive sequence dataset and further improve the recognition performance by extracting the statistical features of the sequences. Experimental results demonstrate that HMT-Net outperforms single-task models by an average recognition accuracy of 2.89%. Furthermore, HMT-Net exhibits even more remarkable performance, achieving enhancements of 4.57% in code rate recognition and 4.31% in constraint length recognition compared to other notable multi-tasking frameworks such as MAR-Net. These findings underscore the potential of HMT-Net as a robust solution for intelligent signal analysis, offering significant practical value for efficient spectrum management in next-generation communication systems. Full article

In recent years, there has been increasing investment in the deployment of massive commercial Low Earth Orbit (LEO) constellations to provide global Internet connectivity. These constellations, now equipped with inter-satellite links, can serve as low-latency Internet backbones, requiring LEO satellites to act not only as access nodes for ground stations, but also as in-orbit core routers. Due to their high velocity and the resulting frequent handovers of ground gateways, LEO networks highly stress mobility procedures at both the sender and receiver endpoints. On the other hand, a growing trend in networking is the use of technologies based on the Information Centric Networking (ICN) paradigm for servicing IoT networks and sensor networks in general, as its addressing, storage, and security mechanisms are usually a good match for IoT needs. Furthermore, ICN networks possess additional characteristics that are beneficial for the massive LEO scenario. For instance, the mobility of the receiver is helped by the inherent data-forwarding procedures in their architectures. However, the mobility of the senders remains an open problem. This paper proposes a comprehensive solution to the mobility problem for massive LEO constellations using the Named-Data Networking (NDN) architecture, as it is probably the most mature ICN proposal. Our solution includes a scalable method to relate content to ground gateways and a way to address traffic to the gateway that does not require cooperation from the network routing algorithm. Moreover, our solution works without requiring modifications to the actual NDN protocol itself, so it is easy to test and deploy. Our results indicate that, for long enough handover lengths, traffic losses are negligible even for ground stations with just one satellite in sight. Full article

Transformers for time series forecasting rely on positional encoding to inject temporal order into the permutation-invariant self-attention mechanism. Classical sinusoidal absolute encodings are fixed and purely geometric; learnable absolute encodings often overfit and fail to extrapolate, while relative or advanced schemes can impose substantial computational overhead without being sufficiently tailored to temporal data. This work introduces a family of window-statistics positional encodings that explicitly incorporate local temporal semantics into the representation of each timestamp. The base variant (WinStat) augments inputs with statistics computed over a sliding window; WinStatLag adds explicit lag-difference features; and hybrid variants (WinStatFlex, WinStatTPE, WinStatSPE) learn soft mixtures of window statistics with absolute, learnable, and semantic positional signals, preserving the simplicity of additive encodings while adapting to local structure and informative lags. We evaluate proposed encodings on four heterogeneous benchmarks against state-of-the-art proposals: Electricity Transformer Temperature (hourly variants), Individual Household Electric Power Consumption, New York City Yellow Taxi Trip Records, and a large-scale industrial time series from heavy machinery. All experiments use a controlled Transformer backbone with full self-attention to isolate the effect of positional information. Across datasets, the proposed methods consistently reduce mean squared error and mean absolute error relative to a strong Transformer baseline with sinusoidal positional encoding and state-of-the-art encodings for time series, with WinStatFlex and WinStatTPE emerging as the most effective variants. Ablation studies that randomly shuffle decoder inputs markedly degrade the proposed methods, supporting the conclusion that their gains arise from learned order-aware locality and semantic structure rather than incidental artifacts. A simple and reproducible heuristic for setting the sliding-window length—roughly one quarter to one third of the input sequence length—provides robust performance without the need for exhaustive tuning. Full article

Rock fracture connectivity is a developing concept that demonstrates the effectiveness of fracture networks in facilitating the preferential flow of fluid through the medium. This study demonstrates the significance and impact of fracture parameters in determining the connectivity of fracture networks. An attempt is made to define fracture parameters, such as fracture density, length, and the quotient of dispersion in their orientation, in addition to understanding the characteristics of fracture and the connectivity of the fracture network in a specified domain. The results based on field observations and measurements at outcrops of the Khairi Murat Range, including the study of field photographs and images, indicate that the fractional connected area (FCA) significantly determines the connectivity of fracture networks and, conversely, depends upon the fracture parameters. Eight fracture sets identified in the study area represent the intensity of dispersion of the strike angles of the fractures. The angular dispersion, i.e., the Fisher coefficient of strike angle of the fracture sets, ranges from 0.26 to 1, indicating that the fracture sets are systematic and concentrated in one direction. Although fracture density and length establish a linear relationship, fracture network connectivity is surprisingly independent of length. Scale-dependent fracture length plays a significant role in serving as the “backbone” of the network in the connectivity of the fracture system. Instead of the length and size of the cluster, fracture network connectivity is affected by fracture orientation and density. Characterization of the fracture properties-based approach successfully explores the connectivity of fracture networks on an outcrop scale. Full article

Biodegradable bioplastics have emerged as a promising sustainable alternative to minimize the environmental impact of traditional plastics. Nevertheless, many of them degrade slowly under natural or industrial conditions, raising concerns about their practical biodegradability. This fact is related to the high-order structure of the polymer backbones, i.e., high molar mass and high crystallinity. Research efforts are being devoted to the development of technologies capable of reducing the length of polymer segments by accelerated chain scission, which could help improve biodegradation rates upon disposal of bioplastic products. The objective of this review is to examine the current state of the art of abiotic degradation techniques, physically driven by temperature, mechanical stress, UV/gamma/microwave irradiation, or plasma or dielectric barrier discharge, and chemically induced by ozone, water, or acidic/basic solutions, with the aim of enhancing the subsequent biodegradation of bioplastics in controlled valorization scenarios such as composting and anaerobic digestors. Particular attention is given to pretreatment degradation technologies that modify surface properties to enhance microbial adhesion and enzymatic activity. Technologies such as ozonation and plasma-driven treatments increase surface hydrophilicity and introduce functional groups with oxygen bonds, facilitating subsequent microbial colonization and biodegradation. Irradiation-based techniques directly alter the chemical bonds at the polymer surface, promoting the formation of free radicals, chain scission, and crosslinking, thereby modifying the polymer structure. Pretreatments involving immersion in aqueous solutions may induce solution sorption and diffusion, together with hydrolytic chain breakage in bulk, with a relevant contribution to the ulterior biodegradation performance. By promoting abiotic degradation and increasing the accessibility of biopolymers to microbial systems, these pretreatment strategies can offer effective tools to enhance biodegradation and, therefore, the end-of-life management of bioplastics, supporting the transition toward sustainable cradle-to-cradle pathways within a biocircular economy. Full article

Foot-and-mouth disease (FMD), a vesicular disease, causes lesions in the mouth, nose, teats, and feet of cloven-hoofed animals. Vaccination remains the most effective method to prevent FMD outbreaks. Since 2010, South Korea has implemented nationwide vaccination and developed multiple domestic vaccine strains to achieve vaccine self-sufficiency. Here, we aimed to construct an infectious clone using the A/SKR/Yeoncheon/2017 virus, which exhibits the highest antigen productivity among previously developed vaccine strains. An infectious clone was constructed based on the A/Yeoncheon/SKR/2017 virus isolated during an FMD outbreak in Korea in 2017. The viral genome was amplified in two fragments and assembled into a full-length clone, from which infectious recombinant virus was successfully rescued. The rescued virus was confirmed via serotyping and transmission electron microscopy to exhibit canonical 25–30 nm icosahedral morphology. Under optimized culture conditions using suspension-adapted BHK-21 cells (multiplicity of infection 0.001; 12 h post-infection), the recombinant virus achieved titers of 10⁸ TCID₅₀/mL and produced 6.2 μg/mL of 146S antigen, comparable to its parental counterpart. The experimental vaccine formulated with the rescued virus (15 μg/dose), 1% saponin, 1% aluminum hydroxide gel, and ISA 206 VG, induced protective immunity in eight-week-old pigs, with vaccinated animals exhibiting no clinical signs following homologous challenge. To our knowledge, this study represents the first successful construction of an infectious clone derived from a field-isolated serotype A FMDV in South Korea. In the future, this A/SKR/Yeoncheon/2017 infectious clone can serve as a platform backbone for the rapid development of next-generation, high-yield vaccine seed strains through targeted epitope exchange. Full article

Background: Foot-and-mouth disease (FMD) is a highly contagious viral disease of cloven-hoofed animals such as cattle and pigs, characterized by vesicular lesions in the mouth, nose, teats, and feet. Globally, the most commonly used FMD vaccines are inactivated vaccines produced by chemical inactivation of the infectious FMD virus (FMDV). This study aimed to establish an infectious clone of the O/Boeun/SKR/2017 virus that has demonstrated the highest antigen productivity among the various type O vaccine strains developed in South Korea to date. Methods: An infectious clone was generated from a type O virus isolated during the 2017 FMD outbreak in South Korea. The viral genome was divided into two fragments, each amplified separately, and subsequently ligated to produce a full-length infectious clone. Results: Rescue of infectious FMDV was confirmed using a commercial antigen detection kit and electron microscopy. Under optimized culture conditions, the rescued virus titer reached 2 × 10⁷ TCID₅₀/mL, and the antigen yield was 6.4 µg/mL. Following inactivation, the antigen was formulated into a vaccine and administered to pigs. Four weeks post-vaccination, challenge with the live virus resulted in no clinical symptoms, demonstrating complete protective efficacy. Conclusions: To the best of our knowledge, this is the first report describing the construction of an infectious clone derived from a field FMDV isolate in South Korea and its application in vaccine development. The O/Boeun/SKR/2017 infectious clone may serve as a genetic backbone for the rapid generation of new FMD vaccine candidates with high antigen productivity by substituting epitopes from other FMDV. Full article

Maritime remote sensing ship detection has long been plagued by two major issues: the failure of geometric priors due to the extreme length-to-width ratio of ships; and the sharp drop in edge signal-to-noise ratio caused by the overlapping chromaticity domain between ships and seawater, which leads to unsatisfactory accuracy of existing detectors in such scenarios. Therefore, this paper proposes an optical remote sensing ship detection model combining channel shuffling and bilinear interpolation, named CSBI-YOLO. The core innovations include three aspects: First, a group shuffling feature enhancement module is designed, embedding parallel group bottlenecks and channel shuffling mechanisms into the interface between the YOLOv8 backbone and neck to achieve multi-scale semantic information coupling with a small number of parameters. Second, an edge-gated upsampling unit is constructed, using separable Sobel magnitude as structural prior and a learnable gating mechanism to suppress low-contrast noise on the sea surface. Third, an R-IoU-Focal loss function is proposed, introducing logarithmic curvature penalty and adaptive weights to achieve joint optimization in three dimensions: location, shape, and scale. Dual validation was conducted on the self-built SlewSea-RS dataset and the public DOTA-ship dataset. The results show that on the SlewSea-RS dataset, the mAP₅₀ and mAP_50–95 values of the CSBI-YOLO model increased by 6% and 5.4%, respectively. On the DOTA-ship dataset, comparisons with various models demonstrate that the proposed model outperforms others, proving the excellent performance of the CSBI-YOLO model in detecting maritime ship targets. Full article

We propose a novel hybrid deep learning framework that synergistically integrates Convolutional Neural Networks (CNNs), Spiking Neural Networks (SNNs), and Generative Adversarial Networks (GANs) for robust and accurate classification of high-resolution frontal and sagittal human gait video sequences—capturing both lower-limb kinematics and upper-body posture—from subjects with Knee Osteoarthritis (KOA), Parkinson’s Disease (PD), and healthy Normal (NM) controls, classified into three disease-type categories. Our approach first employs a tailored CNN backbone to extract rich spatial features from fixed-length clips (e.g., 16 frames resized to 128 × 128 px), which are then temporally encoded and processed by an SNN layer to capture dynamic gait patterns. To address class imbalance and enhance generalization, a conditional GAN augments rare severity classes with realistic synthetic gait sequences. Evaluated on the controlled, marker-based KOA-PD-NM laboratory public dataset, our model achieves an overall accuracy of 99.47%, a sensitivity of 98.4%, a specificity of 99.0%, and an F1-score of 98.6%, outperforming baseline CNN, SNN, and CNN–SNN configurations by over 2.5% in accuracy and 3.1% in F1-score. Ablation studies confirm that GAN-based augmentation yields a 1.9% accuracy gain, while the SNN layer provides critical temporal robustness. Our findings demonstrate that this CNN–SNN–GAN paradigm offers a powerful, computationally efficient solution for high-precision, gait-based disease classification, achieving a 48.4% reduction in FLOPs (1.82 GFLOPs to 0.94 GFLOPs) and 9.2% lower average power consumption (68.4 W to 62.1 W) on Kaggle P100 GPU compared to CNN-only baselines. The hybrid model demonstrates significant potential for energy savings on neuromorphic hardware, with an estimated 13.2% reduction in energy per inference based on FLOP-based analysis, positioning it favorably for deployment in resource-constrained clinical environments and edge computing scenarios. Full article

4,6-Diamino-1,3,5-triazine (DT) derivatives typically exhibit excellent liquid crystal properties, attracting numerous researchers interested in enhancing their performance. In this paper, two DT molecules (DT−10 and DT−12) are employed to elucidate the effects of their backbone length and number of branches in the tail chains on self-assembled nanostructures using scanning tunneling microscopy (STM) at the 1-octanoic acid/highly ordered pyrolytic graphite interface, compared to our previous report (2TDT−n, n = 10,12,16,18). DT−10 features a short backbone and a trialkoxy chain tail, whereas DT−12 possesses a long backbone and bifurcated chain tails. STM results reveal that DT−10 assembles into a cross-shaped nanostructure with DT head groups arranged in a head-to-head configuration stabilized by a pair of N–H···N hydrogen bindings (HBs). In contrast, DT−12 assembles into a two-row linear pattern, where DT head groups exhibit a side-by-side arrangement mediated by a pair of N–H···N HBs. Comparison with our previous findings indicates that although variations in backbone length and tail chain branching can modulate the nanostructural features of DT derivatives, the chain length of DT molecules emerges as a pivotal factor governing their assembly architecture. Full article

We address the challenge that occlusions in on-branch soybean images impede accurate pod-level phenotyping. We propose a lab on-branch pipeline that couples a prior-guided synthetic data generator (producing synchronized visible and amodal labels) with an amodal instance segmentation framework based on an improved Swin Transformer backbone with a Simple Attention Module (SimAM) and dual heads, trained via three-stage transfer (synthetic excised → synthetic on-branch → few-shot real). Guided by complete (amodal) masks, a morphology-driven module performs pose normalization, axial geometric modeling, multi-scale fused density mapping, marker-controlled watershed, and topological consistency refinement to extract seed per pod (SPP) and geometric traits. On real on-branch data, the model attains Visible Average Precision (AP) 50/75 of 91.6/77.6 and amodal AP50/75 of 90.1/74.7, and incorporating synthetic data yields consistent gains across models, indicating effective occlusion reasoning. On excised pod tests, SPP achieves a mean absolute error (MAE) of 0.07 and a root mean square error (RMSE) of 0.26; pod length/width achieves an MAE of 2.87/3.18 px with high agreement (R² up to 0.94). Overall, the co-designed data–model–task pipeline recovers complete pod geometry under heavy occlusion and enables non-destructive, high-precision, and low-annotation-cost extraction of key traits, providing a practical basis for standardized laboratory phenotyping and downstream breeding applications. Full article

A series of PTT-b-PTMG copolyesters was synthesized via direct esterification followed by melt polycondensation using purified terephthalic acid (PTA), bio-based 1,3-propanediol (PDO), and poly(tetramethylene glycol) (PTMG) of varying molecular weights (650–3000 g/mol). The resulting materials were comprehensively characterized in terms of chemical structure, molecular weight, thermal behavior, phase morphology, crystalline architecture, and mechanical performance using a range of analytical techniques: Fourier-transform infrared spectroscopy (FTIR), ¹H-NMR, gel permeation chromatography (GPC), differential scanning calorimetry (DSC), thermogravimetric analysis (TGA), wide-angle X-ray scattering (WAXS), small-angle X-ray scattering (SAXS), dynamic mechanical thermal analysis (DMA), tensile testing, and other standard physical methods. FTIR, ¹H-NMR, and GPC data confirmed the successful incorporation of both PTT-hard and PTMG-soft segments into the copolymer backbone. As the PTMG molecular weight increased, the average sequence length of the PTT-hard segments (L_n,T) also increased, leading to higher melting (T_m) and crystallization (T_c) temperatures, albeit with a slight reduction in overall crystallinity. DMA results indicated enhanced microphase separation between hard and soft domains with increasing PTMG molecular weight. WAXS and SAXS analyses further revealed that the crystalline structure and long-range ordering were strongly dependent on the copolymer composition and block architecture. Mechanical testing showed that tensile strength at break remained relatively constant across the series, while Young’s modulus increased significantly with higher PTMG molecular weight—concurrently accompanied by a decrease in elongation at break. Furthermore, the elastic deformability and recovery behavior of PTT-b-PTMG block copolymers were evaluated through cyclic tensile testing. TGA confirmed that all copolyesters exhibited excellent thermal stability. This study demonstrates that the physical and mechanical properties of bio-based PTT-b-PTMG elastomers can be effectively tailored by adjusting the molecular weight of the PTMG-soft segment, offering valuable insights for the rational design of sustainable thermoplastic elastomers with tunable performance. Full article