Search Results (28,963)

Producing high-quality analytical reports for the environmental domain is typically time-consuming and requires significant human expertise. This paper describes MeteoChat, a semi-automatic framework for efficiently generating specialized environmental reports from heterogeneous environmental data. MeteoChat utilizes a Large Language Model (LLM) fine-tuned and integrated with Retrieval-Augmented Generation (RAG). The system’s core is its plug-and-play philosophy, which separates analytical reasoning from the data source and the report’s intended audience. The fine-tuning phase uses data-agnostic, parameterized question–context–answer triples defined by an environmental expert to teach the LLM domain-specific analytical logic and audience-appropriate communication styles. Subsequently, the RAG phase integrates the model with actual datasets, which are processed via an Extract–Transform–Load (ETL) workflow to generate statistical summaries. This architectural separation ensures that the same reporting engine can operate on different sources, such as meteorological time series, satellite imagery, or geographical data, without additional training. Users interact with the system via a web-based conversational interface, where responses are tailored for either technical experts (using explicit calculations and tables) or the general public (using simplified, narrative language). MeteoChat has been tested with real data extracted from the micrometeorological network of ARPA Lazio. Full article

Spaceborne infrared ship detection holds critical strategic significance in both military and civilian domains. As a crucial data source for ship detection, infrared remote sensing imagery offers the advantages of all-weather detection and strong anti-interference capability. However, existing methods often overlook the detailed features of small ships and fail to effectively suppress interference, leading to missed detections and false alarms in complex backgrounds. To tackle this issue, this study proposes a hierarchical frequency- and spatial-feature attention network (HFS-Net) for fast and accurate ship detection in spaceborne infrared images. The main motivation is to aggregate frequency-spatial information for improved feature extraction, while devising novel hybrid attention-based structures to facilitate interaction among semantic information. Specifically, we design an adaptive frequency-spatial feature attention (AFSA) module to enrich the feature representation. In particular, AFSA integrates information from spatial and frequency domains and introduces channel attention to adaptively extract important features and edge details of ship targets. In addition, we propose an attention-based component-wise feature interaction (ACFI) module that combines multi-head self-attention to capture long-range feature dependencies and component-wise feature aggregation to further enhance the interaction of high-level semantic information. Extensive experiments demonstrate that HFS-Net achieves higher detection accuracy than several representative detectors in maritime infrared scenes with small ships and complex backgrounds, while maintaining real-time efficiency and moderate computational complexity. Full article

Frequent accidents involving heavy trucks and the inadequacy of existing dynamic monitoring technologies pose significant challenges to accurate early warning risk and safety management. To address these issues, this study proposes a multi-dimensional risk measurement and real-time early warning method for heavy truck driving behavior based on trajectory data. By extracting multi-dimensional trajectory features such as lateral position, speed, and acceleration, quantitative indicators for driving stability and car-following risk were constructed. Integrated with the CRITIC objective weighting method and the K-means++ clustering algorithm, a comprehensive risk measurement model was established to systematically characterize the dynamic evolution of driving behavior, overcoming the limitations of single-dimensional risk analysis. Experimental results based on the CQSkyEyeX trajectory dataset demonstrate that the proposed method categorizes driving behavior into six risk levels. Low-risk behavior accounted for 66.70%, while medium- to high-risk behaviors mainly included serpentine driving (26.69%) and close following (4.18%). High-risk behavior constituted only 0.03%. A multi-strategy real-time warning mechanism was further developed, achieving a warning accuracy of 98.36% with the final-value method, significantly outperforming the mode method (83.62%). The outcomes of this study demonstrate the effectiveness and practical utility of the proposed model for risk identification and early warning. On a practical level, the developed risk classification framework and management strategy establish a quantitative basis for differentiated supervision, enabling a closed-loop management process of “identification–intervention–optimization”. Future work will focus on three key directions: integrating multi-source data, extending the model to other typical operational scenarios, and incorporating advanced machine learning techniques to further enhance its generalization capability and warning accuracy. Overall, this research provides a feasible technical pathway for the precise quantification, dynamic monitoring, and tiered intervention of driving behavior in heavy-duty trucks, thereby contributing to enhanced safety in road freight transportation. Full article

Background: Falls are a leading cause of morbidity and mortality among older adults, creating a need for technologies that can automatically detect falls and summon timely assistance. The rapid evolution of sensor technologies and artificial intelligence has led to a proliferation of fall detection systems (FDS). This systematic review synthesizes the recent literature to provide a comprehensive overview of the current technological landscape. Objective: The objective of this review is to systematically analyze and synthesize the evidence from the academic literature on fall detection technologies. The review focuses on three primary areas: the sensor modalities used for data acquisition, the computational models employed for fall classification, and the emerging trend of shifting from reactive detection to proactive fall risk prediction. Methods: A systematic search of electronic databases was conducted for studies published between 2008 and 2025. Following the PRISMA guidelines, 130 studies met the inclusion criteria and were selected for analysis. Information regarding sensor technology, algorithm type, validation methods, and key performance outcomes was extracted and thematically synthesized. Results: The analysis identified three dominant categories of sensor technologies: wearable systems (primarily Inertial Measurement Units), ambient systems (including vision-based, radar, WiFi, and LiDAR), and hybrid systems that fuse multiple data sources. Computationally, the field has shown a progression from threshold-based algorithms to classical machine learning and is now dominated by deep learning architectures, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. Many studies report high performance, with accuracy, sensitivity, and specificity often exceeding 95%. An important trend is the expansion of research from post-fall detection to proactive fall risk assessment and pre-impact fall prediction, which aim to prevent falls before they cause injury. Conclusions: The technological capabilities for fall detection are well-developed, with deep learning models and a variety of sensor modalities demonstrating high accuracy in controlled settings. However, a critical gap remains; our analysis reveals that 98.5% of studies rely on simulated falls, with only two studies validating against real-world, unanticipated falls in the target demographic. Future research should prioritize real-world validation, address practical implementation challenges such as energy efficiency and user acceptance, and advance the development of integrated, multi-modal systems for effective fall risk management. Full article

Coal mining is a major source of methane emissions globally, and monitoring these emissions has become a sustained area of interest in both scientific research and policy-making. Coal mine methane emissions typically manifest as discrete point sources, such as individual mines or ventilation shafts, and spatially concentrated area sources, such as mining clusters. In recent years, satellite remote sensing technology has become a key tool for monitoring and assessing methane emissions from coal mines. Notable progress has been made in quantifying emissions through point-source inversion using high-resolution satellite data, such as GF-5B/AHSI, and in estimating regional-scale area-source emissions using wide-swath instruments, such as S5P/TROPOMI. However, there remains a lack of systematic comparison between inversion results derived from these two types of satellite data with differing spatial resolutions. This study comprehensively analyzes the strengths and limitations of the GF-5B/AHSI and S5P/TROPOMI sensors for quantifying methane emissions. It conducts a spatiotemporal comparative analysis of point-source and area-source methane emission datasets from the coal-mining regions of Shanxi Province. The research aims to clarify the intrinsic relationship between remote-sensing data at different observational scales and to systematically evaluate how prior information on emission-source locations influences emission quantification results. The comparative analysis between TROPOMI grid-level emissions and GF-5B/AHSI point-source emissions indicates that TROPOMI-gridded emission data, owing to its longer time series, can more effectively characterize the annual-average methane emission levels in mining areas. Meanwhile, high-resolution observations from GF-5B/AHSI show distinct advantages in detecting small-scale plumes and attributing emissions to specific facilities. Although the regional-average emissions derived from TROPOMI are significantly higher than point-source emission rate estimates, their data ranges overlap within their uncertainty intervals, demonstrating substantial consistency between the monitoring results of the two methods. Furthermore, the study reveals that when key emission facilities, such as ventilation shafts, are located far from the core operational areas of mines, relying solely on point-source observations may not fully capture the spatial distribution pattern of methane emissions at the mine scale. Full article

Thermal runaway events in energy storage power stations exhibit distinct acoustic characteristic signals. Three-dimensional localization of the sound source is of significant importance for achieving precise firefighting interventions. This study proposes an internal fault localization method for power stations based on the acoustic signals from pressure relief valves of energy storage battery packs. By deploying four microphones to capture the acoustic signals from the battery pack pressure relief valves, the spatial location of the faulty pack can be calculated using a three-dimensional localization model trained on a Back Propagation (BP) neural network. The localization accuracy of this model is better than 0.5 m, with the majority of measurement points achieving an accuracy of less than 0.3 m, meeting the requirements for battery pack-level localization. A key advantage of this method is its low sensitivity to time delay measurement errors caused by reverberation and reflections in enclosed spaces. Reliable and stable localization of pressure relief sound sources can be achieved through multiple training sessions within the battery cabin, which facilitates practical deployment. Full article

The attosecond (10⁻¹⁸ s) light pulse represents the fastest time scale currently mastered by the scientific community, which enables the observation of electron dynamics within atoms and molecules, offering powerful tools to probe chemical reaction mechanisms and advance research in photovoltaic materials and biological processes. In this work, we investigate the generation of visible attosecond optical pulses via spectral broadening in Hollow-Core Fiber (HCF), followed by coherent recombination using a Three-Channel Light Field Synthesizer (TCLFS). The influence of the input pulse duration on Group Delay Dispersion (GDD), Third-Order Dispersion (TOD), and spectral broadening is systematically analyzed. Furthermore, the effects of GDD, TOD, and the carrier–envelope phase (CEP) on waveform synthesis are quantitatively examined for the first time. These findings provide valuable insights into dispersion management strategies essential for developing high-quality visible attosecond light sources, paving the way for future applications in ultrafast spectroscopy and light field-driven electron dynamics. Full article

The poultry sector plays a crucial role in global food production by meeting the growing demand for affordable, nutritious protein sources. However, it faces significant challenges in providing sustainable and cost-effective nutritional solutions that improve poultry health, performance, and product quality. Recent advancements in artificial intelligence (AI) have the potential to enhance poultry nutrition through the development of precise feeding strategies. AI helps monitor and optimize nutrient intake, thereby boosting feed efficiency, reducing waste, and lowering costs. This article examines how AI-driven innovations may advance the management of poultry feed ingredients, nutrient monitoring, and dietary formulations. By utilizing AI tools such as machine learning algorithms and real-time data analytics, poultry producers can track and assess the nutritional needs of individual birds. This allows for the development of more precise feed formulations tailored to the specific needs of different age groups, breeds, and environmental conditions. These AI technologies help select the best feed ingredients and enable precise adjustments to nutrient composition. This results in healthier birds, better feed conversion rates, and higher-quality poultry products. Additionally, AI advancements help reduce the environmental impact of poultry farming by reducing feed waste and resource consumption. This article highlights how AI-driven insights enhance decision-making, enabling the poultry industry to grow sustainably while promoting animal welfare, increasing efficiency, and producing high-quality poultry products that meet consumer expectations for both sustainability and nutritional value. Full article

This study investigates the impact of various data-augmentation techniques on the performance of neural networks in EEG-based motor imagery three-class event classification. EEG data were obtained from a publicly available open-source database, and a subset of 25 patients was selected for analysis. The classification task focused on detecting two types of motor events: imagined movements of the left hand and imagined movements of the right hand. EEGNet, a convolutional neural network architecture optimized for EEG signal processing, was employed for classification. A comprehensive set of augmentation techniques was evaluated, including five time-domain transformations, three frequency-domain transformations, two spatial-domain transformations and two generative approaches. Each method was tested individually, as well as in selected two- and three-method cascade combinations. The augmentation strategies were tested using three data-splitting methodologies and applying four ratios of original-to-generated data: 1:0.25, 1:0.5, 1:0.75 and 1:1. Our results demonstrate that the augmentation strategies we used significantly influence classification accuracy, particularly when used in combination. These findings underscore the importance of selecting appropriate augmentation techniques to enhance generalization in EEG-based brain–computer interface applications. Full article

Accurate modeling of residual limb geometry is essential for prosthetic socket design, yet current scanning techniques can be costly, operator-dependent, or impractical for repeated clinical use. This study presents a fully automated, low-cost photogrammetry workflow capable of generating metrically accurate 3D models of lower-limb residual limbs using video and still images acquired with a standard smartphone or a full-frame digital camera. The pipeline integrates adaptive frame selection, deep learning-based background removal, robust metric scaling via ArUco markers, and open-source Structure-from-Motion and Multi-View Stereo reconstruction, requiring no manual post-processing or proprietary software. Accuracy and repeatability were evaluated using four 3D-printed limb phantoms and high-resolution CT-derived meshes as ground truth. Smartphone video and full-frame camera acquisitions achieved sub-millimeter surface accuracy, volume and perimeter errors within ±1%, and high inter-session repeatability, all within clinically accepted thresholds for prosthetic socket fabrication. In contrast, smartphone still-photo reconstructions showed larger deviations and reduced stability. Acquisition time was under five minutes, and complete reconstruction required approximately 1 h and 30 min. These results demonstrate that smartphone video-based photogrammetry provides a practical, scalable, and clinically viable alternative for residual limb modeling, particularly in resource-constrained or remote care settings. Full article

This paper tackles the growing uncertainty in distribution networks caused by distributed generation, load fluctuations, and frequent topological changes. It proposes a multi-source data fusion framework using enhanced selective convolution (SKNet) and graph attention networks (GAT). First, heterogeneous measurement data, including Phasor Measurement Unit (PMU) and Supervisory Control and Data Acquisition (SCADA) data, are processed through a unified normalization and outlier elimination technique to ensure data quality. Second, SKNet is utilized to extract spatiotemporal multi-scale features, improving the detection of both rapid disturbances and long-term trends. Third, the extracted features are fed into GAT to model node electrical couplings, while power flow residual constraints are embedded in the loss function to enforce the physical validity of the estimated states. This physics-informed design overcomes a key limitation of pure data-driven models and enables an end-to-end framework that integrates data-driven learning with physical mechanism constraints. Finally, comprehensive validation is performed on the improved IEEE 33-node and IEEE 123-node test systems. The test scenarios include Gaussian measurement noise, data outliers, missing measurements, and topological changes. The results show that the proposed method outperforms baseline models such as Multi-Scale Graph Attention Network (MS-GAT), Bidirectional Long Short-Term Memory (BiLSTM), and traditional weighted least squares (WLS). It achieves Root Mean Square Error (RMSE) reductions of up to 18% and Mean Absolute Error (MAE) reductions of up to 15%. The average inference latency is only 10–18 ms. Even under unknown topological changes, the estimation error increases by only 15–25%. These results demonstrate the superior accuracy, robustness, and real-time performance of the proposed method for intelligent distribution network state estimation. Full article

With the relentless expansion of installed capacity in renewable energy (RE) sources, including wind and photovoltaic power, the operational landscape of the power system has witnessed a substantial surge in uncertainty and complexity. The conventional unit commitment (UC) model falls short when it comes to addressing the challenges posed by a high proportion of RE integration and the collaborative involvement of multiple entities, especially within the electricity market framework. UC now faces a dual challenge: it must not only grapple with the pronounced uncertainty on the source–load side but also harmonize the operational characteristics of emerging entities, such as independent energy storage (ES) systems and virtual power plants. All of this must be achieved while strictly adhering to market regulations and grid safety constraints. To tackle these issues, this paper proposes an intelligent scheduling model built upon a composite neural network. This model enables real-time optimization of scheduling for thermal power, renewable energy, and ES systems through multi-agent collaboration. By doing so, it effectively mitigates the uncertainty associated with RE sources and enhances the safety, economic efficiency, and flexibility of the power system. Full article

Background: Despite the implementation of numerous evidence-based interventions, the 2024 Point-in-Time count in the United States (U.S.) reported that 259,473 people in families with children under 18 years old were experiencing homelessness, a record high since the count began in 2007. Recent findings suggest that co-developed interventions may increase engagement with vulnerable populations and, in turn, the effectiveness of health-based programs among them. Objective: In this review, we sought to systematically search and assess the current evidence on co-developed community-based interventions with and for children under age 18 and families experiencing homelessness (CFEH) in high-income countries and their impact on health and well-being outcomes. Methods: Seven databases (e.g., Medline, CINAHL, Embase) and four additional scholarly sources (e.g., Health CASCADE) were searched (publication dates between January 2000 and February 2025). In our analysis, methodological “quality” was assessed through two primary criteria: internal validity and the extent of CFEH involvement. Results: A total of 1617 studies were screened for eligibility, and nine studies were found to have co-developed interventions with CFEH in the U.S. (n = 6) and the United Kingdom (n = 3). These were categorized thematically by socio-structural, behavioral, and combined intervention types. Five studies reported positive engagement among families and staff, whereas three reported improved mental health outcomes. Conclusions: This review highlights the potential impact of co-developed interventions on CFEH’s mental and physical well-being as well as process-based outcomes. Limitations include different definitions of “co-” terminology and homelessness across studies, as well as a lack of transparency about the extent of CFEH’s involvement in these studies. The dearth of evidence indicates that future research should employ community-based participatory research while striking a balance of working with CFEH and other partners and ensuring the data are reliable and reproducible. Full article

This study investigates how the origin and language of public attention influence financial markets during geopolitical conflict, using Israel’s experience during the 2023–2025 Gaza War as a case study. We use Google Trends data—in Hebrew, English, and Arabic, sourced both worldwide and domestically—to explain fluctuations in the Tel Aviv Stock Exchange’s TA-35 Index and the Israeli shekel’s exchange rates (USD/ILS and EUR/ILS). The results uncover a striking asymmetry: international searches, especially those in Hebrew and English, have significant power to explain Israeli market performance, while local, domestic searches are largely insignificant. Specifically, global Hebrew attention is positively associated with the shekel appreciating, suggesting that expressions of confidence or solidarity from the diaspora may actively reinforce market stability. In contrast, spikes in global English-language searches correspond with lower equity returns and temporary shekel depreciation, consistent with heightened international risk perception. These findings demonstrate that transnational behavioral networks and diaspora attention critically shape financial resilience during war. By integrating behavioral finance, conflict economics, and computational analytics, this research shows that the geographic and linguistic origin of attention, not just its sheer volume, is the key determinant of market reactions in times of crisis. Full article

As a renewable energy source, solar energy holds significant potential for addressing future energy and environmental challenges. Concurrently, hydrogen (H₂), as a clean and renewable energy carrier, has garnered substantial attention. Photoelectrocatalytic water splitting to produce H₂ represents an emerging green technology for converting solar energy into hydrogen energy, which has been highly valued by researchers. The key to advancing this technology lies in identifying photoelectrode materials with high catalytic activity and stability. In this study, dendritic α-Fe was synthesized via electrodeposition at the optimal potential of −1.4 V vs. Ag/AgCl for 300 s, and the photoelectrocatalytic performance of α-Fe₂O₃@Fe was enhanced through partial oxidation annealing at 300 °C for 6 h. This approach effectively addressed the issue of the short carrier transport distance in α-Fe₂O₃. The resulting partially oxidized α-Fe₂O₃@Fe(300 °C, 6 h) exhibited a photocurrent density of 281.1 μA/cm² at +0.55 V vs. Ag/AgCl, which was 2.23 times higher than that of the fully oxidized dendritic α-Fe₂O₃(500 °C, 2 h) (125.8 μA/cm²). The influence of deposition potential on photoelectrocatalytic performance was systematically explored, and the optimal deposition potential was identified. Additionally, surface modification with 0.15 wt% Pt (ultra-low loading) was employed to further improve the photocatalytic stability of α-Fe₂O₃(500 °C, 2 h). After continuous operation for 2 h, the photocurrent of the surface-modified sample decreased by only 6.5%, indicating a substantial enhancement in stability. Full article