Search Results (5,717)

Unmanned aerial vehicles (UAVs) play an increasingly vital role in wilderness search and rescue (SAR) operations by enhancing situational awareness and extending the capabilities of human teams. Yet, a lack of standardized benchmarks has impeded the systematic evaluation of single- and multi-agent path-planning algorithms. This paper introduces an open-source dataset and evaluation framework to address this gap. The framework comprises 60 geospatial scenarios across four distinct European environments, featuring high-resolution probability maps. We present a lost person probabilistic model derived from statistical models of lost person behavior. We provide a suite of tools for evaluating search paths against four baseline methods: Concentric Circles, Pizza Zigzag, Greedy, and Random Exploration, using three quantitative metrics: Accumulated probability of detection, time-discounted probability of detection, and lost person discovery score. We provide an evaluation framework to facilitate the comparative analysis of single- and multi-agent path-planning algorithms, supporting both the baseline methods presented and custom user-defined path generators. By providing a structured and extensible framework, this work establishes a foundation for the rigorous and reproducible assessment of UAV search strategies in complex wilderness environments. Full article

Urbanization and traffic congestion caused by the surge in car ownership have exacerbated energy consumption and carbon emissions, and dynamic traffic flow prediction and energy-saving route planning have become the key to solving this problem. Dynamic traffic flow prediction accurately captures the spatio-temporal changes of traffic flow through advanced algorithms and models, providing prospective information for traffic management and travel decision-making. Energy-saving route planning optimizes travel routes based on prediction results, reduces the time vehicles spend on congested road sections, thereby reducing fuel consumption and exhaust emissions. However, there are still many shortcomings in the current relevant research, and the existing research is mostly isolated and applies a single model, and there is a lack of systematic comparison of the adaptability, generalization ability and fusion potential of different models in various scenarios, and the advantages of heterogeneous graph neural networks in integrating multi-source heterogeneous data in traffic have not been brought into play. This paper systematically reviews the relevant global studies from 2020 to 2025, focuses on the integration path of dynamic traffic flow prediction methods and energy-saving route planning, and reveals the advantages of LSTM, graph neural network and other models in capturing spatiotemporal features by combing the application of statistical models, machine learning, deep learning and mixed methods in traffic forecasting, and comparing their performance with RMSE, MAPE and other indicators, and points out that the potential of heterogeneous graph neural networks in multi-source heterogeneous data integration has not been fully explored. Aiming at the problem of disconnection between traffic prediction and path planning, an integrated framework is constructed, and the real-time prediction results are integrated into path algorithms such as A* and Dijkstra through multi-objective cost functions to balance distance, time and energy consumption optimization. Finally, the challenges of data quality, algorithm efficiency, and multimodal adaptation are analyzed, and the development direction of standardized evaluation platform and open source toolkit is proposed, providing theoretical support and practical path for the sustainable development of intelligent transportation systems. Full article

To address the challenges of dynamic coupling interference and time-frequency feature degradation in current approaches to Ultra-High-Frequency Radio-Frequency Identification (UHF RFID) behavior recognition, this study proposes a novel behavior recognition method integrating multi-feature analysis with a dual-path residual network. The proposed method mitigates interference by using phase difference methods to eliminate signal errors and cross-correlation, as well as adaptive equalization algorithms to decouple interfering signals. To identify the target tags participating in behavioral interactions, we construct a three-dimensional feature space and apply an improved weighted isolated forest algorithm to detect active tags during interactions. Subsequently, Doppler shift analysis extracts behavioral features, and multiscale wavelet-packet decomposition generates time-frequency representations. The dual-path residual network then fuses global and local features from these time-frequency representations for behavioral classification, thereby identifying interaction behaviors such as ‘taking away’, ‘putting back’, and ‘hesitation’ (characterized by picking up, then putting back). Experimental results demonstrate that the proposed scheme achieves behavioral recognition accuracy of 94% in complex scenarios, significantly enhancing the overall robustness of interaction behavior recognition. Full article

The large-scale integration of wind power into coastal power systems introduces significant challenges to reserve planning, especially under the threat of typhoons, which can cause extensive generation loss and threaten system security. Conventional reserve planning methods often fail to account for such extreme typhoon events. To fill the gap, this paper proposes a novel two-stage reserve planning framework that integrates economic optimization with operational security verification. In the first stage, a diverse set of high-impact typhoon scenarios are generated using a multivariate Markov chain Monte Carlo (MMCMC)–based path reconstruction method, which captures the dynamic evolution of key typhoon characteristics. In the second stage, the economically optimal reserve capacity is identified through cost-benefit analysis and then validated against the typhoon scenarios via N − 1 security verification. A case study on the modified IEEE RTS79 test system indicates that economically optimal reserve may be inadequate for ensuring security under severe typhoon conditions. However, a small increase in reserve capacity can effectively enhance system resilience with minimal additional cost. These results highlight the importance of incorporating typhoon scenario-based security verification into reserve planning especially for high-penetration wind power systems in coastal regions. Full article

Deep learning (DL) has revolutionized medical image analysis (MIA), enabling early anomaly detection, precise lesion segmentation, and automated disease classification. However, its clinical integration faces two major challenges: reliance on limited, narrowly annotated datasets that inadequately capture real-world patient diversity, and the inherent “black-box” nature of DL decision-making, which complicates physician scrutiny and accountability. Eye tracking (ET) technology offers a transformative solution by capturing radiologists’ gaze patterns to generate supervisory signals. These signals enhance DL models through two key mechanisms: providing weak supervision to improve feature recognition and diagnostic accuracy, particularly when labeled data are scarce, and enabling direct comparison between machine and human attention to bridge interpretability gaps and build clinician trust. This approach also extends effectively to multimodal learning models (MLMs) and vision–language models (VLMs), supporting the alignment of machine reasoning with clinical expertise by grounding visual observations in diagnostic context, refining attention mechanisms, and validating complex decision pathways. Conducted in accordance with the PRISMA statement and registered in PROSPERO (ID: CRD42024569630), this review synthesizes state-of-the-art strategies for ET-DL integration. We further propose a unified framework in which ET innovatively serves as a data efficiency optimizer, a model interpretability validator, and a multimodal alignment supervisor. This framework paves the way for clinician-centered AI systems that prioritize verifiable reasoning, seamless workflow integration, and intelligible performance, thereby addressing key implementation barriers and outlining a path for future clinical deployment. Full article

The effectiveness of industrial heritage conservation relies on the collaborative efforts of multiple stakeholders. However, existing research lacks systematic exploration of stakeholders’ perception of heritage value and the pathways through which such perception translates into conservation behaviors. This study takes the Shaanxi section of the Baocheng Railway, a typical linear industrial heritage, as a case study. Based on the “Cognitive Appraisal Theory of Emotions” (CATE) theory, it examines the mechanism between heritage value perception, place identity, and heritage responsibility behavior. Through structural equation modeling (SEM) analysis of 414 questionnaire responses, the study finds that heritage value perception of the Baocheng Railway’s Shaanxi section not only significantly positively influences stakeholders’ place identity but also directly promotes the formation of heritage responsibility behavior. Among these, the perception of social value has the most pronounced impact on place identity and responsibility behavior. Furthermore, place identity plays a key mediating role between value perception and responsibility behavior. This study introduces the CATE theory into industrial heritage research, revealing the mechanism of behavior generation from the path of “cognition → emotion → behavior”. By focusing on linear industrial heritage sites, it broadens the scope of heritage research and highlights the central role of social value perception in driving conservation intentions and behaviors. The study further enriches research on heritage responsibility behavior, and the proposed theoretical model and findings can provide theoretical references for the management and conservation of industrial heritage. Full article

The confined space of coal mines characterized by curved tunnels with rough surfaces and a variety of deployed production equipment induces severe signal attenuation and interruption, which significantly degrades the accuracy of conventional channel estimation algorithms applied in coal mine wireless communication systems. To address these challenges, we propose a modified Bilinear Generalized Approximate Message Passing (mBiGAMP) algorithm enhanced by intelligent reflecting surface (IRS) technology to improve channel estimation accuracy in coal mine scenarios. Due to the presence of abundant coal-carrying belt conveyors, we establish a hybrid channel model integrating both fast-varying and quasi-static components to accurately model the unique propagation environment in coal mines. Specifically, the fast-varying channel captures the varying signal paths affected by moving conveyors, while the quasi-static channel represents stable direct links. Since this hybrid structure necessitates an augmented factor graph, we introduce two additional factor nodes and variable nodes to characterize the distinct message-passing behaviors and then rigorously derive the mBiGAMP algorithm. Simulation results demonstrate that the proposed mBiGAMP algorithm achieves superior channel estimation accuracy in dynamic conveyor-affected coal mine scenarios compared with other state-of-the-art methods, showing significant improvements in both separated and cascaded channel estimation. Specifically, when the NMSE is ${10}^{-3}$, the SNR of mBiGAMP is improved by approximately 5 dB, 6 dB, and 14 dB compared with the Dual-Structure Orthogonal Matching Pursuit (DS-OMP), Parallel Factor (PARAFAC), and Least Squares (LS) algorithms, respectively. We also verify the convergence behavior of the proposed mBiGAMP algorithm across the operational signal-to-noise ratios range. Furthermore, we investigate the impact of the number of pilots on the channel estimation performance, which reveals that the proposed mBiGAMP algorithm consumes fewer number of pilots to accurately recover channel state information than other methods while preserving estimation fidelity. Full article

Efficient navigation of Automated Guided Vehicles (AGVs) in dynamic warehouse environments requires real-time and accurate path segmentation algorithms. However, traditional semantic segmentation models suffer from excessive parameters and high computational costs, limiting their deployment on resource-constrained embedded platforms. A lightweight image segmentation algorithm is proposed, built on an improved ESPNet-C architecture, combining Spatial Group-wise Enhance (SGE) and Efficient Channel Attention (ECA) with a dual-branch upsampling decoder. On our custom warehouse dataset, the model attains 90.5% Miou with 0.425 M parameters and runs at ~160 FPS, reducing parameters by ×116–×136 and computational costs by 70–92% in comparison with DeepLabV3+. The proposed model improves boundary coherence by 22% under uneven lighting and achieves 90.2% Miou on the public BDD100K benchmark, demonstrating strong generalization beyond warehouse data. These results highlight its suitability as a real-time visual perception module for AGV navigation in resource-constrained environments and offer practical guidance for designing lightweight semantic segmentation models for embedded applications. Full article

This study investigates the multi-objective path planning problem for unmanned surface vehicles (USVs), aiming to optimize both travel distance and energy consumption in maritime environments with obstacles, sea winds, and ocean currents. The proposed method accounts for practical constraints, including collision avoidance, kinematic boundaries, and speed limitations. The problem is formulated as a nonlinear multi-objective optimization model with generalized constraints and is solved using an improved particle swarm optimization algorithm enhanced by a vector-weighted fusion strategy. The algorithm adaptively balances exploration and exploitation to obtain diverse Pareto-optimal solutions. Simulation results under varying environmental conditions, along with real-world sea trials, validate the effectiveness of the proposed approach. The outcomes demonstrate that the method enables USVs to generate energy-efficient, smooth trajectories while maintaining robustness and adaptability, offering practical value for intelligent marine navigation. Full article

Staphylococcus aureus is the most common pathogen causing osteomyelitis, a hardly recoverable bone infection that generates significant burden to patients. Osteomyelitis mouse models have long and successfully served to provide phenomenological insights into both pathogenesis and host response. However, direct in situ monitoring of bone microbial pathogenesis and immune response at the cellular level is still conspicuously missing in the published literature. Here, we update a standard pyogenic osteomyelitis in Wistar rat model, in order to investigate bacterial localization and immune response in osteomyelitis of rat tibia upon adding in situ analyses by spectrally resolved Raman spectroscopy. Raman experiments were performed one and five weeks post infections upon increasing the initial dose of bacterial inoculation in rat tibia. Label-free in situ Raman spectroscopy clearly revealed the presence of Staphylococcus aureus through exploiting peculiar signals from characteristic carotenoid staphyloxanthin molecules. Data were collected as a function of both initial bacteria inoculation dose and location along the tibia. Such strong Raman signals, which relate to single and double bonds in the carbon chain backbone of carotenoids, served as efficient bacterial markers even at low levels of infection. We could also detect strong Raman signals from cytochrome c (and its oxidized form) from bone cells in response to infection and inflammatory paths. Although initial inoculation was restricted to a single location close to the medial condyle, bacteria spread along the entire bone down to the medial malleolus, independent of initial infection dose. Raman spectroscopic characterizations comprehensively and quantitatively revealed the metabolic state of bacteria through specific spectroscopic biomarkers linked to the length of staphyloxanthin carbon chain backbone. Moreover, the physiological response of eukaryotic cells could be quantified through monitoring the level of oxidation of mitochondrial cytochrome c, which featured the relative intensity of the 1644 cm⁻¹ signal peculiar to the oxidized molecules with respect to its pyrrole ring-breathing signal at 750 cm⁻¹, according to the previously published literature. In conclusion, we present here a novel Raman spectroscopic approach indexing bacterial concentration and immune response in bone tissue. This new approach enables locating and characterizing in situ bone infections, inflammatory host tissue reactions, and bacterial resistance/adaptation. Full article

This paper proposes an adaptive path-planning algorithm for unmanned ground vehicles (UGVs) in three-dimensional terrain environments. The algorithm first constructs an interference model between the UGV chassis and the three-dimensional terrain, taking into account the impact of terrain undulations on vehicle driving stability. A dynamic cost-adjustment mechanism for multi-task modes was designed, which introduces a learning model to automatically identify task types and dynamically adjust the weights of various cost factors in path planning accordingly. This paper constructs simulation environments for sparse obstacle scenes and high-density obstacle scenes, respectively, to verify the effectiveness of the path-planning results of the algorithm in different task modes. The experimental results show that the proposed method can generate smoother, safer, and more task-matched trajectory paths while ensuring path feasibility, verifying the good adaptability and robustness of this algorithm for complex unstructured environments under multi-task driving conditions. Full article

To resolve the conflict between global structure modeling and local detail preservation in image super-resolution, we propose SwinT-SRGAN, a novel framework integrating Swin Transformer with GAN. Key innovations include: (1) A dual-path generator where Transformer captures long-range dependencies via window attention while CNN extracts high-frequency textures; (2) An end-to-end Detail Recovery Block (DRB) suppressing artifacts through dual-path attention; (3) A triple-branch discriminator enabling hierarchical adversarial supervision; (4) A dynamic loss scheduler adaptively balancing six loss components (pixel/perceptual/high-frequency constraints). Experiments on CelebA-HQ and Flickr2K demonstrate: (1) Very good performance (max gains: 0.71 dB PSNR, 0.83% SSIM, 4.67 LPIPS reduction vs. Swin-IR); (2) Ablation studies validate critical roles of DRB. This work offers a robust solution for high-frequency-sensitive applications. Full article

Graph Neural Networks (GNNs) have shown strong performance in link prediction, a core task in graph analysis. However, recent studies reveal their vulnerability to backdoor attacks, which can manipulate predictions stealthily and pose significant yet underexplored security risks. The existing backdoor strategies for link prediction suffer from two key limitations: gradient-based optimization is computationally intensive and scales poorly to large graphs, while single-node triggers introduce noticeable structural anomalies and local feature inconsistencies, making them both detectable and less effective. To address these limitations, we propose a novel backdoor attack framework grounded in the principle of homophily, designed to balance effectiveness and stealth. For each selected target link to be poisoned, we inject a unique path-based trigger by adding a bridge node that acts as a shared neighbor. The bridge node’s features are generated through a context-aware probabilistic sampling mechanism over the joint neighborhood of the target link, ensuring high consistency with the local graph context. Furthermore, we introduce a confidence-based trigger injection strategy that selects non-existent links with the lowest predicted existence probabilities as targets, ensuring a highly effective attack from a small poisoning budget. Extensive experiments on five benchmark datasets—Cora, Citeseer, Pubmed, CS, and the large-scale Physics graph—demonstrate that our method achieves superior performance in terms of Attack Success Rate (ASR) while maintaining a low Benign Performance Drop (BPD). These results highlight a novel and practical threat to GNN-based link prediction, offering valuable insights for designing more robust graph learning systems. Full article

With the rapid evolution of 5G wireless communications, millimeter-wave (mmWave) technology has become a crucial enabler for high-speed, low-latency, and large-scale connectivity. As the critical interface for signal transmission, mmWave antennas directly affect system performance, reliability, and application scope. This paper reviews the current state of mmWave antenna technologies in 5G systems, focusing on antenna types, design considerations, and integration strategies. We discuss how the multiple-input multiple-output (MIMO) architectures and advanced beamforming techniques enhance system capacity and link robustness. State-of-the-art integration methods, such as antenna-in-package (AiP) and chip-level integration, are examined for their importance in achieving compact and high-performance mmWave systems. Material selection and fabrication technologies—including low-loss substrates like polytetrafluoroethylene (PTFE), hydrocarbon-based materials, liquid crystal polymer (LCP), and microwave dielectric ceramics, as well as emerging processes such as low-temperature co-fired ceramics (LTCC), 3D printing, and micro-electro-mechanical systems (MEMS)—are also analyzed. Key challenges include propagation path limitations, power consumption and thermal management in highly integrated systems, cost–performance trade-offs for mass production, and interoperability standardization across vendors. Finally, we outline future research directions, including intelligent beam management, reconfigurable antennas, AI-driven designs, and hybrid mmWave–sub-6 GHz systems, highlighting the vital role of mmWave antennas in shaping next-generation wireless networks. Full article

In recent decades, pollutant emissions from the combustion of fossil fuels have become increasingly serious for the environment. The present paper reports experimental results for research carried out under laboratory conditions for a Selective Catalytic Reduction (SCR) system, implemented in different configurations on an ISUZU 4JB1 diesel engine. The obtained results allow for a comparative analysis of NOx formation as a function of diesel engine load (χ = 25–100%), at 1350, 2100, 2850, and 3600 rpm, with the engine operating under either cold (T < 343 K) or warm (T > 343 K) regimes. A preheating system for AdBlue droplets, in the form of a metal honeycomb that uses electromagnetic induction and incorporates a high-frequency generator, was introduced in the flow path of the combustion gases and tested to compare the experimental results. This system enabled temperatures of up to 643 K. A magneto-strictive system was also introduced in the SCR structure to atomize the AdBlue droplets to a minimum diameter of 3.5 μm. Using this principle, combined with preheating, the effect of calefaction was compared with the classical case of the internal heating of the SCR catalyst. For experimental purposes, piezoelectric cells dedicated to the transformation of the AdBlue solution into micro- or nano-droplets, which were entrained into the SCR by an ejector, were also used. Experimental results are presented in graphical form and reveal that the use of preheating, heating, or piezoelectric cells leads to improved NOx conversion. The tested solutions showed reductions in NOx emissions of up to eight times depending on the diesel engine load, demonstrating their strong impact on NOx reduction. Full article