Search Results (787)

Foreign object intrusion in railway perimeter areas poses significant risks to train operation safety. To address the limitation of current visual detection technologies that overly focus on target identification while lacking quantitative risk assessment, this paper proposes a railway intrusion risk quantification method integrating track semantic segmentation and spatiotemporal features. An improved BiSeNetV2 network is employed to accurately extract track regions, while physical-constrained risk zones are constructed based on railway structure gauge standards. The lateral spatial distance of intruding objects is precisely calculated using track gauge prior knowledge. A lightweight detection architecture is designed, adopting ShuffleNetV2 as the backbone to reduce computational complexity, with an incorporated Dilated Transformer module to enhance global context awareness and sparse feature extraction, significantly improving detection accuracy for small-scale objects. The comprehensive risk assessment formula integrates object category weights, lateral risk coefficients in intrusion zones, longitudinal distance decay factors, and dynamic velocity compensation. Experimental results demonstrate that the proposed method achieves 84.9% mean average precision (mAP) on our proprietary dataset, outperforming baseline models by 3.3%. By combining lateral distance detection with multidimensional risk indicators, the method enables quantitative intrusion risk assessment and graded early warning, providing data-driven decision support for active train protection systems and substantially enhancing intelligent safety protection capabilities. Full article

To address the logistical challenges of traffic congestion and environmental concerns associated with carbon emissions in last-mile delivery, this paper explores the potential of vehicle–drone cooperative delivery. The existing studies are predominantly confined to single-drone scenarios, failing to simultaneously consider the constraints of drone payload capacity and endurance. This limitation leads to task allocation imbalance in large-scale customer deliveries and low distribution efficiency. Firstly, a mathematical model for vehicle–multi-drone collaborative delivery with payload and endurance constraint (VMDCD-PEC) is proposed. Secondly, an improved genetic algorithm (IGA) is developed, as follows: 1. designing a hybrid selection strategy to achieve symmetrical equilibrium between exploration and exploitation by adjusting the weights of dynamic fitness–distance balance, greedy selection, and random selection; and 2. introducing the local search operator composed of gene sequence reversal, single-gene slide-down, and random half-swap to improve the neighborhood quality solution mining efficiency. Finally, the experimental results show that compared with a traditional genetic algorithm (GA) and adaptive large neighborhood search (ALNS), the IGA requires less time to find solutions in various test cases and reduces the average cost of the optimal solution by up to 30%. In addition, an analysis of drone payload sensitivity showed that drone payload capacity is negatively correlated with delivery time, and that larger customer sizes corresponded to higher sensitivity. Full article

In the cybersecurity attack and defense space, the “attacker” and the “defender” form a dynamic and symmetrical adversarial pair. Their strategy iterations and capability evolutions have long been in a symmetrical game of mutual restraint. We will introduce modern Intrusion Detection Systems (IDSs) from the defender’s side to counter the techniques designed by the attacker (APT attack). One major challenge faced by IDS is to identify complex attack paths from a vast provenance graph. By constructing an attack behavior tracking graph, the interactions between system entities can be recorded, but the malicious activities of attackers are often hidden among a large number of normal system operations. Although traditional methods can identify attack behaviors, they only focus on the surface association relationships between entities and ignore the deep causal relationships, which limits the accuracy and interpretability of detection. Existing graph anomaly detection methods usually assign the same weight to all interactions, while we propose a Causal Autoencoder for Graph Explanation (CAGE) based on reinforcement learning. This method extracts feature representations from the traceability graph through a graph attention network(GAT), uses Q-learning to dynamically evaluate the causal importance of edges, and highlights key causal paths through a weight layering strategy. In the DARPA TC project, the experimental results conducted on the selected three datasets indicate that the precision of this method in the anomaly detection task remains above 97% on average, demonstrating excellent accuracy. Moreover, the recall values all exceed 99.5%, which fully proves its extremely low rate of missed detections. Full article

As cities transition toward intelligent traffic systems, hybrid networks combining AI and traditional intersections raise challenges for efficiency and sustainability. Existing studies primarily focus on global intelligence assumptions, overlooking the practical complexities of hybrid control environments. Moreover, the decision-making processes of AI-based controllers remain opaque, limiting their reliability in dynamic traffic conditions. To address these challenges, this study investigates the following realistic scenario: a Deep Reinforcement Learning (DRL) intersection surrounded by max–pressure-controlled neighbors. A spatiotemporal pressure perception agent is proposed, which (a) uses a novel Holistic Traffic Dynamo State (HTDS) representation that integrates real-time queue, predicted vehicle merging patterns, and approaching traffic flows and (b) innovatively proposes Neighbor–Pressure–Adaptive Reward Weighting (NP-ARW) mechanism to dynamically adjust queue penalties at incoming lanes based on relative pressure differences. Additionally, spatial–temporal pressure features are modeled using 1D convolutional layers (Conv1D) and attention mechanisms. Finally, our Strategy Imitation–Mechanism Attribution framework leverages XGBoost and Decision Trees to systematically analyze traffic condition impacts on phase selection, fundamentally enabling explainable control logic. Experimental results demonstrate the following significant improvements: compared to fixed-time control, our method reduces average travel time by 65.45% and loss time by 85.04%, while simultaneously decreasing average queue lengths and pressure at neighboring intersections by 91.20% and 95.21%, respectively. Full article

Traditional median filtering with a fixed window easily leads to edge blurring and adaptive median filtering requires manual presetting of the maximum window parameter and has insufficient retention of details when dealing with high-density salt-and-pepper noise. Aiming at these problems, this paper proposes a hybrid decision-making adaptive median filtering algorithm with dual-window detection in collaboration with particle swarm optimization (PSO). The algorithm quickly locates suspected noise points through a 3 × 3 small window and enhances noise identification accuracy by using a PSO dynamically optimized 5–35-pixel large window. Meanwhile, a hybrid decision-making mechanism based on local statistical properties was introduced to dynamically select median filtering, weighted average based on spatial distance, or pixel preservation strategy to balance noise suppression and detail preservation, and the PSO algorithm was used to automatically find the optimal parameters of the large window’s size to avoid the manual parameter-tuning process. Experiments were conducted on standard grayscale and color images and compared with four traditional methods and two more advanced methods. The experiments showed that the algorithm improved the peak signal-to-noise ratio (PSNR) value by 2–4 dB and the structural similarity index measure (SSIM) metric by 0.05–0.2 under high salt-and-pepper noise density compared with the traditional methods, which effectively improved the contradiction between noise suppression and detail retention in traditional filtering algorithms and provided a highly efficient and intelligent solution for image denoising in high-noise scenarios. Full article

Atmospheric aerosols are recognized as a major air pollutant with significant impacts on human health, air quality, and climate. Yet, the chemical composition and seasonal variability of aerosols remain underexplored in several Western Mediterranean regions. This study presents a year-long investigation of PM_2.5 and PM₁₀ in Tetouan, Northern Morocco, where both local emissions and regional transport influence air quality. PM_2.5 and PM₁₀ samples were collected and analysed for total mass and comprehensive chemical characterization, including organic carbon (OC), elemental carbon (EC), water-soluble ions (WSIs), and sugar tracers (levoglucosan, arabitol, and glucose). Concentration-weighted trajectory (CWT) modelling and air mass back-trajectory analyses were used to assess potential source regions and transport pathways. PM_2.5 concentrations ranged from 4.2 to 41.8 µg m⁻³ (annual mean: 18.0 ± 6.4 µg m⁻³), while PM₁₀ ranged from 11.9 to 66.3 µg m⁻³ (annual mean: 30.8 ± 9.7 µg m⁻³), with peaks in winter and minima in spring. The PM_2.5-to-PM₁₀ ratio averaged 0.59, indicating a substantial accumulation of particle mass within the fine fraction, especially during the cold season. Carbonaceous aerosols dominated the fine fraction, with total carbonaceous aerosol (TCA) contributing ~52% to PM_2.5 and ~34% to PM₁₀. Secondary organic carbon (SOC) accounted for up to 90% of OC in PM_2.5, reaching 7.3 ± 3.4 µg m⁻³ in winter. WSIs comprised ~39% of PM_2.5 mass, with sulfate, nitrate, and ammonium as major components, peaking in summer. Sugar tracers exhibited coarse-mode dominance, reflecting biomass burning and biogenic activity. Concentration-weighted trajectory and back-trajectory analyses identified the Mediterranean Basin and Iberian Peninsula as dominant source regions, in addition to local urban emissions. Overall, this study attempts to fill a critical knowledge gap in Southwestern Mediterranean aerosol research by providing a comprehensive characterization of PM_2.5 and PM₁₀ chemical composition and their seasonal dynamics in Tetouan. It further offers new insights into how a combination of local emissions and regional transport shapes the aerosol composition in this North African urban environment. Full article

Background: Efficient decoding of motor imagery (MI) electroencephalogram (EEG) signals is essential for the precise control and practical deployment of brain-computer interface (BCI) systems. Owing to the complex nonlinear characteristics of EEG signals across spatial, spectral, and temporal dimensions, efficiently extracting multidimensional discriminative features remains a key challenge to improving MI-EEG decoding performance. Methods: To address the challenge of capturing complex spatial, spectral, and temporal features in MI-EEG signals, this study proposes a multi-branch deep neural network, which jointly models these dimensions to enhance classification performance. The network takes as inputs both a three-dimensional power spectral density tensor and two-dimensional time-domain EEG signals and incorporates four complementary feature extraction branches to capture spatial, spectral, spatial-spectral joint, and temporal dynamic features, thereby enabling unified multidimensional modeling. The model was comprehensively evaluated on two widely used public MI-EEG datasets: EEG Motor Movement/Imagery Database (EEGMMIDB) and BCI Competition IV Dataset 2a (BCIIV2A). To further assess interpretability, gradient-weighted class activation mapping (Grad-CAM) was employed to visualize the spatial and spectral features prioritized by the model. Results: On the EEGMMIDB dataset, it achieved an average classification accuracy of 86.34% and a kappa coefficient of 0.829 in the five-class task. On the BCIIV2A dataset, it reached an accuracy of 83.43% and a kappa coefficient of 0.779 in the four-class task. Conclusions: These results demonstrate that the network outperforms existing state-of-the-art methods in classification performance. Furthermore, Grad-CAM visualizations identified the key spatial channels and frequency bands attended to by the model, supporting its neurophysiological interpretability. Full article

Synthetic Aperture Radar (SAR) plays a pivotal role in remote-sensing target detection. However, domain shift caused by distribution discrepancies across sensors, coupled with the scarcity of target-domain samples, severely restricts the generalization and practical performance of SAR detectors. To address these challenges, this paper proposes a few-shot SAR target-detection framework tailored for cross-sensor scenarios (CS-FSDet), enabling efficient transfer of source-domain knowledge to the target domain. First, to mitigate inter-domain feature-distribution mismatch, we introduce a Multi-scale Uncertainty-aware Bayesian Distribution Alignment (MUBDA) strategy. By modeling features as Gaussian distributions with uncertainty and performing dynamic weighting based on uncertainty, MUBDA achieves fine-grained distribution-level alignment of SAR features under different resolutions. Furthermore, we design an Adaptive Cross-domain Interactive Coordinate Attention (ACICA) module that computes cross-domain spatial-attention similarity and learns interaction weights adaptively, thereby suppressing domain-specific interference and enhancing the expressiveness of domain-shared target features. Extensive experiments on two cross-sensor few-shot detection tasks, HRSID→SSDD and SSDD→HRSID, demonstrate that the proposed method consistently surpasses state-of-the-art approaches in mean Average Precision (mAP) under 1-shot to 10-shot settings. Full article

Accurate and automated detection of diseases is crucial for sustainable strawberry production. However, the challenges posed by small size, mutual occlusion, and high intra-class variance of symptoms in complex agricultural environments make this difficult. Mainstream deep learning detectors often do not perform well under these demanding conditions. We propose a novel detection framework designed for superior accuracy and robustness to address this critical gap. Our framework introduces four key innovations: First, we propose a novel attention-driven detection head featuring our Parallel Pyramid Attention (PPA) module. Inspired by pyramid attention principles, our module’s unique parallel multi-branch architecture is designed to overcome the limitations of serial processing. It simultaneously integrates global, local, and serial features to generate a fine-grained attention map, significantly improving the model’s focus on targets of varying scales. Second, we enhance the core feature fusion blocks by integrating Monte Carlo Attention (MCAttn), effectively empowering the model to recognize targets across diverse scales. Third, to improve the feature representation capacity of the backbone without increasing the parametric overhead, we replace standard convolutions with Frequency-Dynamic Convolutions (FDConv). This approach constructs highly diverse kernels in the frequency domain. Finally, we employ the Scale-Decoupled Loss function to optimize training dynamics. By adaptively re-weighting the localization and scale losses based on target size, we stabilize the training process and improve the Precision of bounding box regression for small objects. Extensive experiments on a challenging dataset related to strawberry diseases demonstrate that our proposed model achieves a mean Average Precision (MAP) of 81.1%. This represents an improvement of 2.1% over the strong YOLOv12-n baseline, highlighting its practical value as an effective tool for intelligent disease protection. Full article

In multi-criteria decision-making (MCDM) environments characterized by uncertainty and data irregularities, the reliability of weighting methods becomes critical for ensuring robust and accurate decisions. This study introduces a novel hybrid objective weighting method—IQRBOW-E (Interquartile Range-Based Objective Weighting with Entropy)—which dynamically combines the statistical robustness of the IQRBOW method with the information sensitivity of Entropy through a tunable parameter $\beta$. The method allows decision-makers to flexibly control the trade-off between robustness and information contribution, enhancing the adaptability of decision support systems. A comprehensive experimental design involving ten simulation scenarios was implemented, in which the number of criteria, alternatives, and outlier ratios were varied. The IQRBOW-E method was integrated into the VIKOR framework and evaluated through average $Q$ values, stability ratios, SRD scores, and the Friedman test. The results indicate that the proposed hybrid approach achieves superior decision stability and performance, particularly in data environments with increasing outlier contamination. Optimal $\beta$ values were shown to shift systematically depending on data conditions, highlighting the model’s sensitivity and adaptability. This study not only advances the methodological landscape of MCDM by introducing a parameterized hybrid weighting model but also contributes a robust and generalizable weighting infrastructure for modern decision-making under uncertainty. Full article

Deep-learning-based multiple label chest X-ray classification has achieved significant success, but existing models still have three main issues: fixed-scale convolutions fail to capture both large and small lesions, standard pooling is lacking in the lack of attention to important regions, and linear classification lacks the capacity to model complex dependency between features. To circumvent these obstacles, we propose CONVFCMAE, a lightweight yet powerful framework that is built on a backbone that is partially frozen (77.08 % of the initial layers are fixed) in order to preserve complex, multi-scale features while decreasing the number of trainable parameters. Our architecture adds (1) an intelligent global pooling module that is learnable, with $1\times 1$ convolutions that are dynamically weighted by their spatial location, and (2) a multi-head attention block that is dedicated to channel re-calibration, along with (3) a two-layer MLP that has been enhanced with ReLU, batch normalization, and dropout. This module is used to enhance the non-linearity of the feature space. To further reduce the noise associated with labels and the imbalance in class distribution inherent to the NIH ChestXray14 dataset, we utilize a combined loss that combines BCEWithLogits and Focal Loss as well as extensive data augmentation. On ChestXray14, the average ROC–AUC of CONVFCMAE is 0.852, which is 3.97 percent greater than the state of the art. Ablation experiments demonstrate the individual and collective effectiveness of each component. Grad-CAM visualizations have a superior capacity to localize the pathological regions, and this increases the interpretability of the model. Overall, CONVFCMAE provides a practical, generalizable solution to the problem of extracting features from medical images in a practical manner. Full article

For the decision-making challenge of ensuring vehicle lane-changing safety, this study proposes a context-dependent causal inference-based model for safe lane changes. Emphasizing multi-vehicle interactions within dynamic traffic scenarios, we construct a three-layer decision-making framework that relies on real-time data collection of speed, acceleration, and spacing information from both the target vehicle and adjacent-lane vehicles. The framework consists of (1) a context-aware layer that extracts standardized dynamic features; (2) an attention mechanism layer that dynamically assigns weights to critical risk factors; and (3) a counterfactual causal reasoning layer where lane-changing risks are quantified through virtual interventions, with multi-objective safety strategies optimized via particle swarm algorithms. The simulation results indicate significant enhancements in high-density traffic conditions. When compared to traditional safety distance models and built-in models from simulation software (SUMO v1.18.0), the proposed model achieves reductions in average conflict counts by 63.0% (from 12.7 to 4.7 instances) and by 37.3% (from 7.5 to 4.7 instances), respectively. Additionally, lane-changing durations are reduced by 10.9% (from 5.5 to 4.9 s) and by 31.9% (from 7.2 to 4.9 s), while fluctuations in risk values decrease by 53.3% (from 0.75 to 0.35) and by 36.4% (from 0.55 to 0.35), respectively. The experimental validation confirms that the integration of dynamic safety distance computation with causal reasoning significantly enhances decision-making robustness in complex scenarios through coordinated risk quantification and multi-objective optimization Full article

Automatic Modulation Classification (AMC) is vital for adaptive wireless communication, yet it faces challenges in complex environments, including insufficient feature extraction, feature redundancy, and high interclass similarity among modulation schemes. To address these limitations, this paper proposes the Multiscale Complex Convolution Spatiotemporal Attention Network (MCCSAN). In this work, we propose three key innovations tailored for AMC tasks: a multiscale complex convolutional module that directly processes raw I/Q sequences, preserving critical phase and amplitude information while extracting diverse signal features. A spatiotemporal attention mechanism dynamically weights temporal steps and feature channels to suppress redundancy and enhance discriminative feature focus. A combined loss function integrating cross-entropy and center loss improves intraclass compactness and interclass separability. Evaluated on the RML2018.01A dataset and RML2016.10A across SNR levels from −6 dB to 12 dB, MCCSAN achieves a state-of-the-art classification accuracy of 97.03% (peak) and an average accuracy improvement of 3.98% over leading methods. The study confirms that integrating complex-domain processing with spatiotemporal attention significantly enhances AMC performance. Full article

Age of Information (AoI) is a newly introduced metric that quantifies the freshness and timeliness of data, playing a crucial role in applications reliant on time-sensitive information. Minimizing AoI through optimal scheduling is challenging, especially in energy-constrained Internet of Things (IoT) networks. In this work, we begin by analyzing a simplified cognitive radio network (CRN) where a single secondary user (SU) harvests RF energy from the primary user and transmits status update packets when the PU spectrum is available. Time is divided into equal time slots, and the SU performs either energy harvesting, spectrum sensing, or status update transmission in each slot. To optimize the AoI within the CRN, we formulate the sequential decision-making process as a partially observable Markov decision process (POMDP) and employ dynamic programming to determine optimal actions. Then, we extend our investigation to evaluate the long-term average weighted sum of AoIs for a multi-SU CRN. Unlike the single-SU scenario, decisions must be made regarding which SU performs sensing and which SU forwards the status update packs. Given the partially observable nature of the PU spectrum, we propose an enhanced Deep Q-Network (DQN) algorithm. Simulation results demonstrate that the proposed policies significantly outperform the myopic policy. Additionally, we analyze the effect of various parameter settings on system performance. Full article

Lightning strikes pose a significant threat to the reliability of power distribution networks, with cascading effects on energy sustainability and community resilience. This paper proposes a lightning disaster risk prediction model for distribution networks, designing a lightning strike hazard matrix to classify historical fault records and incorporating future multi-source heterogeneous data to predict lightning-induced fault hazard levels and enhance the sustainability of grid operations. To address spatiotemporal imbalances in data distribution, we first propose diagnostic threshold settings for low-frequency elements alongside a method for calculating hazard diagnostic criteria. This approach systematically integrates high-hazard, low-frequency factors into risk analyses. Second, we introduce an adaptive weight optimization algorithm that dynamically adjusts risk factor weights by quantifying their contributions to overall system risk. This method overcomes the limitations of traditional frequency-weighted approaches, ensuring more robust hazard assessment. Experimental results demonstrate that, compared to baseline models, the proposed model achieves average improvements of 21%/8.3% in AUROC, 30.2%/47.4% in SE, and 20.5%/8.1% in CI, empirically validating its superiority in risk prediction and engineering applicability. Full article