Search Results (216)

With the increasing frequency of traffic safety issues and the rapid development of autonomous driving technology, traffic sign detection is highly susceptible to adverse weather conditions such as changes in light intensity, fog, rain, snow, and partial occlusion, which places higher demands on the accurate recognition of traffic signs. This paper proposes an improved DAYOLO model based on YOLOv8n, aiming to balance detection accuracy and model complexity. First, the Bottleneck in the C2f module of the YOLOv8n backbone network is replaced with Bottleneck DAttention. Introducing DAttention allows for more effective feature extraction, thereby improving model performance. Second, an ultra-lightweight and efficient upsampler, Dysample, is introduced into the neck network to further improve performance and reduce computational overhead. Finally, a Task-Aligned Dynamic Detection Head (TADDH) is introduced. TADDH enhances task interaction through a dynamic mechanism and utilizes shared convolutional modules to reduce parameters and improve efficiency. Simultaneously, an additional Layer2 detection head is added to the model to strengthen the extraction and fusion of features at different scales, thereby improving the detection accuracy of small traffic signs. Furthermore, replacing SlideLoss with NWDLoss can better handle prediction results with more complex distributions and more accurately measure the distance between predicted and ground truth boxes in the feature space during object detection. Experimental results show that DAYOLO achieves 97.2% mAP on the SDCCVP dataset, which is 5.3 higher than the baseline model YOLOv8n; the frame rate reaches 120, which is 37.8% higher than YOLOv8; and the number of parameters is reduced by 6.2%, outperforming models such as YOLOv3, YOLOv5, YOLOv6, and YOLOv7. In addition, DAYOLO achieves 80.8 mAP on the TT100K dataset, which is 9.2% higher than the baseline model YOLOv8n. The proposed method achieves a balance between model size and detection accuracy, meets the needs of traffic sign detection, and provides new ideas and methods for future research in the field of traffic sign detection. Full article

Accurate nitrogen dioxide (NO₂) forecasting is crucial for proactive emission control and issuing public health warnings. This study provides the first evaluation of the China Meteorological Administration’s (CMA) operational CUACE/Haze-Fog V3.0 numerical prediction system, assessing its daily NO₂ forecast accuracy against independent satellite measurements and in situ observations. We compare model forecasts with TROPOspheric Monitoring Instrument (TROPOMI) satellite column data and observations from 1677 Chinese ground monitoring stations, focusing on four key regions: the Yangtze River Delta, Pearl River Delta, Beijing–Tianjin–Hebei, and Urumqi. An optimal spatial resolution of 0.15° × 0.15° was determined for TROPOMI data processing. The results indicate a strong seasonal dependency in model performance. The model systematically underestimates NO₂ concentrations in winter but performs significantly better in summer. This systematic bias is confirmed by a Normalized Mean Bias (NMB) consistently below −20% in northern regions during the winter. In the Beijing–Tianjin–Hebei region, the Root Mean Square Error (RMSE) reached 3.57 × 10¹⁵ molec/cm² (vs. TROPOMI) and 1.09 × 10¹⁵ molec/cm³ (vs. ground stations) in winter, decreasing to 0.95 and 0.91, respectively, in summer. Critically, this winter bias pertains to pollution magnitude rather than temporal correlation; the model captures pollution trends but underestimates peak severity. Our study reveals a ‘vertical decoupling’ in the operational forecasting system. While the model utilizes surface data assimilation to correct surface pollutants, this study demonstrates that these corrections fail to propagate vertically to the total NO₂ column during winter stable boundary layer conditions. This finding has broader implications for chemical transport models (CTMs): relying solely on surface data assimilation is insufficient for constraining column burdens in regions with complex vertical stratification. We propose that future operational systems integrate satellite-based vertical constraints to resolve the systematic winter bias identified here. Full article

This paper is the first to reveal that the conventionally built aluminium alloy (AA) 7085-T7452 has mechanical properties, viz: a yield stress, ultimate strength, and an elongation to failure, that are similar to that of laser powder bed fusion (LPBF) built Scalmalloy^®. Following this observation, the growth of cracks that nucleated from corrosion pits in AA7085-T7452 specimens that had been exposed to a 5 wt% NaCl salt fog environment at 35 °C according to ASTM B117-19 standard for fourteen days is then studied. The specimen geometries were chosen to be identical to those associated with a similar study on Boeing Space, Intelligence, and Weapon Systems (BSI&WS) LPBF built Scalmalloy^®. This level of prior exposure led to pits in AA7085-T7452 that were approximately 0.5 mm deep with a surface width/diameter of up to approximately 1.5 mm. These pit sizes are broadly consistent with those leading to fatigue crack growth (FCG) in AA 7050-T7451 structural parts on the RAAF F/A-18 Classic Hornet fleet operating in a highly corrosive environment. Fatigue tests on these AA7085-T7452 specimens, under the same spectrum as used in the BSI&WS LPBF Scalmalloy^® study, reveals that AA7085-T7452 and Scalmalloy^® have similar crack growth histories. This, in turn, leads to the discovery that the growth of naturally occurring three-dimensional (3D) cracks in AA 7085-T7452 could be predicted using the crack growth equation developed for BSI&WS LPBF Scalmalloy^®, albeit with allowance made for their different fracture toughness’s. These findings suggest that Scalmalloy^® may be suitable for printing parts for both current and future attritable aircraft. Full article

With the rapid development of industries such as construction and port hoisting, the operational safety of truck cranes in crowded areas has become a critical issue. Under complex working conditions, traditional monitoring methods are often plagued by issues such as compromised image quality, increased parallax computation errors, delayed fence response times, and inadequate accuracy in dynamic target recognition. To address these challenges, this study proposes a personnel intrusion detection system based on multimodal sensor fusion and dynamic prediction. The system utilizes the combined application of a binocular camera and a lidar, integrates the spatiotemporal attention mechanism and an improved LSTM network to predict the movement trajectory of the crane boom in real time, and generates a dynamic 3D fence with an advance margin. It classifies intrusion risks by matching the spatiotemporal prediction of pedestrian trajectories with the fence boundaries, and finally generates early warning information. The experimental results show that this method can significantly improve the detection accuracy of personnel intrusion under complex environments such as rain, fog, and strong light. This system provides a feasible solution for the safety monitoring of truck crane operations and significantly enhances operational safety. Full article

Smart remote health monitoring requires time-critical medical data of patients from IoT-enabled cyber–physical systems (CPSs) to be securely transmitted and analysed in real time for early interventions and personalised patient care. Existing cloud architectures are insufficient for smart health systems due to their inherent issues with latency, bandwidth, and privacy. Fog architectures using data storage closer to edge devices introduce challenges in data management, security, and privacy for effective monitoring of a patient’s sensitive and critical health data. These gaps found in the literature form the main research focus of this study. As an initial modest step to advance research further, we propose an innovative fog-based framework which is the first of its kind to integrate secure communication with intelligent data prioritisation (IDP) integrated into an AI-based enhanced Random Forest anomaly and threat detection model. Our experimental study to validate our model involves a simulated smart healthcare scenario with synthesised health data streams from distributed wearable devices. Features such as heart rate, SpO₂, and breathing rate are dynamically prioritised using AI strategies and rule-based thresholds so that urgent health anomalies are transmitted securely in real time to support clinicians and medical experts for personalised early interventions. We establish a successful proof-of-concept implementation of our framework by achieving high predictive performance measures with an initial high score of 93.5% accuracy, 90.8% precision, 88.7% recall, and 89.7% F1-score. Full article

The volatile nature of cryptocurrency markets demands real-time analytical capabilities that traditional centralized computing architectures struggle to provide. This paper presents a novel hybrid cloud–edge computing framework for cryptocurrency market forecasting, leveraging distributed systems to enable low-latency prediction models. Our approach integrates machine learning algorithms across a distributed network: edge nodes perform real-time data preprocessing and feature extraction, while the cloud infrastructure handles deep learning model training and global pattern recognition. The proposed architecture uses a three-tier system comprising edge nodes for immediate data capture, fog layers for intermediate processing and local inference, and cloud servers for comprehensive model training on historical blockchain data. A federated learning mechanism allows edge nodes to contribute to a global prediction model while preserving data locality and reducing network latency. The experimental results show a 40% reduction in prediction latency compared to cloud-only solutions while maintaining comparable accuracy in forecasting Bitcoin and Ethereum price movements. The system processes over 10,000 transactions per second and delivers real-time insights with sub-second response times. Integration with blockchain ensures data integrity and provides transparent audit trails for all predictions. Full article

Soiling is one of the main performance risks for bifacial photovoltaic (PV) technology, particularly in arid environments such as the Atacama Desert, where dust is deposited asymmetrically on the front and rear surfaces of the modules. This study evaluates one year (July 2022 to June 2023) of soiling behavior in bifacial modules installed in fixed-tilt and horizontal single-axis tracking (HSAT) configurations, enabling a comparison to be made between static and moving structures. The average dust accumulation was found to be 0.33 mg/cm² on the front surface and 0.15 mg/cm² on the rear surface of the fixed modules. In contrast, the respective values for the HSAT systems were found to be lower at 0.25 mg/cm² and 0.035 mg/cm². These differences resulted in performance losses of 5.8% for fixed modules and 3.7% for HSAT systems. Microstructural analysis revealed that wetting and drying cycles had formed dense, cemented layers on the front surface of fixed modules, whereas tracking modules exhibited looser deposits. Natural cleaning events, such as fog, dew and frost, only provided partial and temporary mitigation. These findings demonstrate that bifaciality introduces differentiated soiling dynamics between the front and rear surfaces, emphasizing the importance of tailored cleaning strategies and the integration of monitoring systems that consider bifacial gain as a key operational parameter. These insights are crucial for developing predictive models and cost-effective O&M strategies in large-scale bifacial PV deployments under desert conditions. Full article

The accurate prediction of atmospheric low-visibility events due to fog, haze or atmospheric pollution is an extremely important problem, with major consequences for transportation systems, and with alternative applications in agriculture, forest ecology and ecosystems management. In this paper, we provide a comprehensive literature review and analysis of AI-based methods applied to fog and low-visibility events forecasting. We also discuss the main general issues which arise when dealing with AI-based techniques in this kind of problem, open research questions, novel AI approaches and data sources which can be exploited. Finally, the most important new AI-based methodologies which can improve atmospheric visibility forecasting are also revised, including computational experiments on the application of ordinal classification approaches to a problem of low-visibility events prediction in two Spanish airports from METAR data. Full article

Freeway weaving sections’ states under adverse weather exhibit characteristics of randomness, vulnerability, and abruption. A deep learning-based model is proposed for traffic state identification and prediction, which can be used to formulate proactive management strategies. According to traffic characteristics under adverse weather, a hybrid model combining Random Forest and an improved k-prototypes algorithm is established to redefine traffic states. Traffic state prediction is accomplished using the Weather Spatiotemporal Graph Convolution Network (WSTGCN) model. WSTGCN decomposes flows into spatiotemporal correlation and temporal variation features, which are learned using spectral graph convolutional networks (GCNs). A Time Squeeze-and-Excitation Network (TSENet) is constructed to extract the influence of weather by incorporating the weather feature matrix. The traffic states are then predicted using Gated Recurrent Unit (GRU). The proposed models were tested using data under rain, fog, and strong wind conditions from 201 weaving sections on China’s G5 and G55 freeway, and U.S. I-5 and I-80 freeway. The results indicated that the freeway weaving sections’ states under adverse weather can be classified into seven categories. Compared with other baseline models, WSTGCN achieved a 3.8–8.0% reduction in Root Mean Square Error, a 1.0–3.2% increase in Equilibrium Coefficient, and a 1.4–3.1% improvement in Accuracy Rate. Full article

To characterize changes in markers of oxidative stress for the clinical evaluation of patients with long COVID, we assessed oxidative stress and antioxidant activity based on serum samples from patients who visited our clinic between May and November 2024. Seventy-seven patients with long COVID (41 [53%] females and 36 [47%] males; median age, 44 years) were included. Median [interquartile range] serum levels of diacron-reactive oxygen metabolites (d-ROM; CARR Unit), biological antioxidant potential (BAP; μmol/L), and oxidative stress index (OSI) were 533.8 [454.9–627.6], 2385.8 [2169.2–2558.1] and 2.0 [1.7–2.5], respectively. Levels of d-ROMs (579.8 vs. 462.2) and OSI (2.3 vs. 1.8), but not BAP (2403.4 vs. 2352.6), were significantly higher in females than in males. OSI levels positively correlated with age and body mass index, whereas BAP levels negatively correlated with these parameters. d-ROM and OSI levels were significantly associated with inflammatory markers, including C-reactive protein (CRP) and fibrinogen, whereas BAP levels were inversely correlated with CRP and ferritin levels. Notably, serum free thyroxine levels were negatively correlated with d-ROMs and OSI, whereas cortisol levels were positively correlated with d-ROMs. Among long COVID symptoms, patients reporting brain fog exhibited significantly higher OSI levels (2.2 vs. 1.8), particularly among females (d-ROMs: 625.6 vs. 513.0; OSI: 2.4 vs. 2.0). The optimal OSI cut-off values were determined to be 1.32 for distinguishing long COVID from healthy controls and 1.92 for identifying brain fog among patients with long COVID. These findings suggest that oxidative stress markers may serve as indicators for the presence or prediction of psycho-neurological symptoms associated with long COVID in a gender-dependent manner. Full article

This study presents an optimized methodology for the placement of water film thickness sensors, integrating information theory with experimental validation. Initially, the two-dimensional shallow-water equations are employed to simulate the spatiotemporal evolution of water film thickness across the entire runway, providing a comprehensive foundational dataset. By applying information entropy theory, the total information content at each runway grid point is quantified. Analysis indicates that grid points with higher total information content generally correspond to regions of greater water film thickness. The optimal placement for a single sensor is determined by identifying the location that maximizes total information content, and its effectiveness is validated through controlled rain–fog experiments. The results demonstrate that positioning a single sensor at a site with higher water film thickness reduces the overall mean estimation error by 57%, thereby enhancing prediction accuracy. By extending the single-sensor placement framework, the total information content across all runway points is recalculated, and additional rain–fog experiments are conducted to verify the optimal locations. By incorporating a correlation coefficient–distance (C–D) model to define each sensor’s influence radius, a collaborative multi-sensor placement strategy is developed and implemented at Seletar Airport, Singapore. The findings show that sensor locations with higher water film thickness correspond to increased total information content, and that expanding the number of deployed sensors further improves estimation accuracy. Compared with conventional placement approaches, which rely on subjective judgment and long-term operational experience, the proposed method enhances estimation accuracy by over 23% when deploying two sensors. These results provide a robust basis for the strategic placement of runway water film thickness sensors and contribute to more precise assessments of pavement surface conditions. Full article

The global market for fog computing is expected to reach USD 6385 million by 2032. Modern enterprises rely on fog computing since it offers computational resources at edge devices through decentralized computation mechanisms. One of the crucial components of fog computing is the proper placement of applications on fog nodes (edge devices, Internet of Things (IoT)) for servicing. Large-scale, geographically distributed fog networks and heterogeneity of fog nodes make application placement a challenging task. Quantile Temporal Difference Learning (QTDL) is a promising distributed form of a reinforcement learning algorithm. It is superior compared to traditional reinforcement learning as it learns the act of prediction based on the full distribution of returns. QTDL is enriched by a small language model (SLM), which results in low inference latency, reduced costs of operation, and also enhanced rates of learning. The SLM, being a lightweight model, has policy-shaping capability, which makes it an ideal choice for the resource-constrained environment of edge devices. The data-driven quantiles of temporal difference learning are blended with the informed heuristics of the SLM to prevent quantile loss and over- or underestimation of the policies. In this paper, a novel SLM-guided QTDL framework is proposed to perform task scheduling among fog nodes. The proposed framework is implemented using the iFogSim simulator by considering both certain and uncertain fog computing environments. Further, the results obtained are validated using expected value analysis. The performance of the proposed framework is found to be satisfactory with respect of the following performance metrics: energy consumption, makespan time violations, budget violations, and load imbalance ratio. Full article

Unmanned Aerial Vehicles have started to be used more and more due to the benefits they bring. Failure of Unmanned Aerial Vehicle components may result in loss of control, which may cause property damage or personal injury. In order to increase the operational safety of the Unmanned Aerial Vehicle, the implementation of a Predictive Maintenance system using the Internet of Things is required. In this paper, the authors propose a new architecture of Predictive Maintenance system for Unmanned Aerial Vehicles that is able to identify the fault type of Brushless DC electric motor and determine the Remaining Useful Life of the Li-ion batteries. In order to create the Predictive Maintenance system within the Unmanned Aerial Vehicle, an architecture based on Fog Computing was proposed and Machine Learning was used to extract knowledge from the data. The proposed architecture was practically validated. Full article

Basalt-fiber-reinforced polymer (BFRP) composites, utilizing a natural high-performance inorganic fiber, exhibit excellent weathering resistance, including tolerance to high and low temperatures, salt fog, and acid/alkali corrosion. They also possess superior mechanical properties such as high strength and modulus, making them widely applicable in aerospace and shipbuilding. This study experimentally investigated the mechanical properties of BFRP plates under various strain rates (10⁻⁴ s⁻¹ to 10³ s⁻¹) and directions using an electronic universal testing machine and a split Hopkinson pressure bar (SHPB).The results demonstrate significant strain rate dependency and pronounced anisotropy. Based on experimental data, relationships linking the strength of BFRP composites in different directions to strain rate were established. These relationships effectively predict mechanical properties within the tested strain rate range, providing reliable data for numerical simulations and valuable support for structural design and engineering applications. The developed strain rate relationships were successfully validated through finite element simulations of low-velocity impact. Full article

Lidar technology is a key sensor for autonomous driving due to its precise environmental perception. However, adverse weather and atmospheric conditions involving fog, rain, snow, dust, and smog can impair lidar performance, leading to potential safety risks. This paper introduces a comprehensive methodology to simulate lidar systems under such conditions and validate the results against real-world experiments. Existing empirical models for the extinction and backscattering of laser beams are analyzed, and new models are proposed for dust storms and smog, derived using Mie theory. These models are implemented in the CARLA simulator and evaluated using Robot Operating System 2 (ROS 2). The simulation methodology introduced allowed the authors to set up test experiments replicating real-world conditions, to validate the models against real-world data available in the literature, and to predict the performance of the lidar system in all weather conditions. This approach enables the development of virtual test scenarios for corner cases representing rare weather conditions to improve robustness and safety in autonomous systems. Full article