Search Results (2,461)

This paper presents whole-body vibration prediction in an agricultural tractor based on selected operational parameters using machine learning. Experiments were performed using a Landini Powerfarm 100 model tractor on farmlands and service roads located at the Osijek School of Agriculture and Veterinary Medicine. The methodology adhered to the HRN ISO 5008 protocols for establishing test surfaces, including a smooth 100 m track and a rugged 35 m track. Whole-body vibrational exposure assessments were carried out in alignment with the HRN ISO 2631-1 and HRN ISO 2631-4 guidelines, which outline procedures for evaluating mechanical oscillations in occupational settings. The obtained whole-body vibration data were divided into three datasets (one for each axis) and processed using linear regression as a baseline and compared against three machine learning models (gradient boosting regressor; support vector machine regressor; multi-layer perception). The most accurate machine learning model according to the R² metric was the gradient boosting regressor for the x-axis (R²: 0.98) and the y-axis (R²: 0.98), and for the z-axis (R²: 0.95), the most accurate machine learning model was the SVM regressor. The application of machine learning methods indicates that machine learning models can be used to predict whole-body vibrations more accurately than linear regression. Full article

With the rapid development of e-commerce, logistics UAVs (unmanned aerial vehicles) have shown great potential in the field of urban logistics. However, the large-scale operation of logistics UAVs has brought challenges to air traffic management, and the competitiveness of UAV logistics is still weak compared with traditional ground logistics. Therefore, this paper constructs a double-layer route network structure that separates logistics transshipment from terminal delivery. In the delivery layer, a door-to-door distribution mode is adopted, and the transshipment node service location model is constructed, so as to obtain the location of the transshipment node and the service relationship. In the transshipment layer, the index of the route betweenness standard deviation (BSD) is introduced to construct the route network planning model. In order to solve the above model, a double-layer algorithm was designed. In the upper layer, the multi-objective simulated annealing algorithm (MOSA) is used to solve the transshipment node service location issue, and in the lower layer, the multi-objective non-dominated sorting genetic algorithm II (NSGA-II) is adopted to solve the network planning model. Based on real obstacle data and the demand situation, the double-layer network was constructed through simulation experiments. To verify the network rationality, actual flights were carried out on some routes, and it was found that the gap between the UAV’s autonomous flight route time and the theoretical calculations was relatively small. The simulation results show that compared with the single-layer network, the total distance with the double-layer network was reduced by 62.5% and the structural intersection was reduced by 96.9%. Compared with the minimum spanning tree (MST) algorithm, the total task flight distance obtained with the NSGA-II was reduced by 42.4%. The BSD factors can mitigate potential congestion risks. The route network proposed in this paper can effectively reduce the number of intersections and make the UAV passing volume more balanced. Full article

For occupant safety in vehicular networks, emergency messages derived from vehicular incidents should be exchanged only during their validity period and in zones containing involved entities. Problems arise for mobile entities in vehicular networks that change their location over time, where data may be further communicated in out-of-context space and time. Current solutions extend from the naive assumption of notifying every entity in the network about emergencies with data flooding and clusters and by means of specific communication only in the affected zones—geo-routing—of incidents’ relative data. However, delivering useless data to uninvolved entities results in wasted resources and more overheads in the former cases and the work of obtaining knowledge and secondary site services from neighbors in the latter. In this paper, we propose that the common task of disseminating emergency messages for occupant safety among entities should only be communicated only where and when useful, namely, if spatio-temporal constraints apply regarding those incidents. Our solution is inspired by the communication of working social insects that exchange data through pheromones regardless of closeness or knowledge among colony members for food retrieval. The results show that communication based on space–time constraints makes better use of resources than other solutions. Full article

Large parks play a key role in the identity of urban public spaces and as destinations for residents’ urban walks, with the social benefits they provide being irreplaceable by other types of green spaces. This study examines the accessibility of large urban parks in Rizhao, China, focusing on spatial distribution, service equity, and optimization strategies. Using GIS-based walking route proximity analysis, the study identifies significant accessibility gaps in high-density urban areas. Rizhao is a typical coastal tourist city, selected as the study area due to its low level of urbanization and the underutilization of its natural resources. This study uses online map data to evaluate the service efficiency and supply–demand heterogeneity of large parks from multiple perspectives, proposing targeted, practical, and micro-intervention-based spatial measures based on typical case analysis. The results show that 70.52% of the population in the study area is served by park entrances within a 1500 m walking distance, indicating that a considerable portion of residents remain beyond a reasonable walking distance. In the context of urban renewal and sustainable development, this study proposes practical improvements to park accessibility, including suggestions for determining suitable locations for new large parks as a long-term goal, alongside low-cost interventions such as increasing park entrances to maximize the use of existing resources and optimizing pedestrian routes (including opening gated communities and adding crossing facilities) to improve park walking service catchment in smaller environments. This study provides insights for urban park renewal, retrofitting, and expansion, supporting accessibility measures in planning practices, and is expected to provide valuable references for urban managers and policymakers. Furthermore, the study suggests that policy adjustments are necessary to integrate green spaces into urban development more effectively, particularly in rapidly urbanizing areas. Full article

The integration of Global Navigation Satellite Systems (GNSS) has revolutionized geodetic positioning, with techniques like Precise Point Positioning with Ambiguity Resolution (PPP-AR) offering highly accurate results with reduced convergence times. The full deployment of the BeiDou Navigation Satellite System-3 (BDS-3) has spurred interest in assessing its standalone and combined performance with GPS in PPP-AR applications. This study evaluates the performance of BDS-3-based PPP-AR across diverse geographical regions considering space weather conditions (SWCs) for the first time. GNSS data from six International GNSS Service (IGS) stations located in the Asia–Pacific, Europe, Africa, and the Americas were processed for 15 consecutive days. The three scenarios (BDS-3 only, GPS only, and BDS-3 + GPS) were analyzed using the open-source raPPPid v2.3 software developed in 2023. The estimated coordinates were statistically compared to the IGS-derived coordinates to assess accuracy. Results demonstrate that BDS-3 PPP-AR can independently deliver reliable positioning for many applications and that the accuracy of BDS-3-based PPP-AR is relatively low in the Americas. However, combining BDS-3 with GPS significantly enhances horizontal and vertical accuracies, especially in the Americas, achieving improvements of up to 86% and 82%, respectively. These findings highlight the potential of BDS-3 for complementing GPS for precise geodetic applications. Full article

Background/Objectives: Falls are the most common adverse in-hospital event, resulting in a considerable social and economic burden on individuals, their families, and the healthcare system. This study aims to develop and implement an automatic coding system using large language models (LLMs) to extract and categorize free-text information (including the location of the fall and any resulting injury) from in-hospital fall records. Methods: The study used the narrative description of the falls reported through the Incident Reporting system to the Risk Management Service of an Italian Local Health Authority in Italy (name not disclosed as per research agreement). The OpenAI application programming interface (API) was used to access the generative pre-trained transformers (GPT) models, extract data from the narrative description of the falls, and perform the classification task. The GPT-4-turbo models were used for the classification task. Two independent reviewers manually coded the information, representing the gold standard for the classification task. Sensitivity, specificity, and accuracy were calculated to evaluate the performance of the task. Results: The analysis included 187 fall records with free-text event descriptions detailing the location of the fall and 93 records providing information about the presence or absence of an injury. GPT-4-turbo showed excellent performance, with specificity, sensitivity, and accuracy values of at least 0.913 for detecting the location and 0.953 for detecting the injury. Conclusions: The GPT models effectively extracted and categorized the information, even though the text was not optimized for GPT-based analysis. This shows their potential for the use of LLMs in clinical risk management research. Full article

To reduce airport operational costs and minimize environmental pollution, an increasing number of airports are transitioning from fuel-powered to electric ground-handling vehicles. However, the limited battery capacity of electric vehicles and the need for charging make the scheduling of these vehicles more complex. To address this scheduling problem, this paper proposes an electric ground-handling vehicle scheduling algorithm that combines the MAMBA model with an attention-based neural network. The MAMBA model is designed to process multi-dimensional features such as flight information, vehicle locations, service demands, and time window constraints. Subsequently, an attention mechanism-based neural network is developed to dynamically integrate vehicle states, service records, and operational and charging constraints, in order to select the most suitable flights for electric ground-handling vehicles to service. The experiments use flight data from Xiamen Gaoqi International Airport and compare the proposed method with CPLEX solvers, existing heuristic algorithms, and custom heuristic algorithms. The results demonstrate that the proposed method not only effectively solves the electric ground-handling vehicle scheduling problem and provides high-quality solutions, but also exhibits good scalability in different parameter settings and real-time scheduling scenarios. Full article

Background/Objectives: Early detection and diagnosis are important when treating gallbladder (GB) diseases. Poorer clinical outcomes and increased patient symptoms may result from any error or delay in diagnosis. Many signs and symptoms, especially those related to GB diseases with similar symptoms, may be unclear. Therefore, highly qualified medical professionals should interpret and understand ultrasound images. Considering that diagnosis via ultrasound imaging can be time- and labor-consuming, it may be challenging to finance and benefit from this service in remote locations. Methods: Today, artificial intelligence (AI) techniques ranging from machine learning (ML) to deep learning (DL), especially in large datasets, can help analysts using Content-Based Image Retrieval (CBIR) systems with the early diagnosis, treatment, and recognition of diseases, and then provide effective methods for a medical diagnosis. Results: The developed model is compared with two different textural and six different Convolutional Neural Network (CNN) models accepted in the literature—the developed model combines features obtained from three different pre-trained architectures for feature extraction. The cosine method was preferred as the similarity measurement metric. Conclusions: Our proposed CBIR model achieved successful results from six other different models. The AP value obtained in the proposed model is 0.94. This value shows that our CBIR-based model can be used to detect GB diseases. Full article

The rapid advancement of the Internet of Things (IoT) and mobile devices has made location-based services (LBSs) increasingly prevalent, significantly improving daily convenience and work efficiency. However, this widespread usage has raised growing concerns about privacy and security, particularly during data outsourcing to cloud servers, where users’ location information and related data are susceptible to breaches by malicious actors or attackers. Traditional privacy-preserving spatial keyword schemes often employ Bloom filters for data encoding and storage. While Bloom filters offer high lookup speeds, they suffer from limitations such as a relatively high false positive rate in certain scenarios and poor space efficiency. These issues can adversely affect query accuracy and overall user experience. Furthermore, existing schemes have not sufficiently addressed the multi-attribute characteristics of spatial textual data. At the same time, relying solely on cloud servers for large-scale data processing introduces additional challenges, including heavy computational overhead, high latency, and substantial communication costs. To address these challenges, we propose a cloud–edge collaborative privacy-preserving dynamic spatial keyword query scheme with multi-attribute cost constraints. This scheme introduces a novel index structure that leverages security-enhanced Xor filter technology and Geohash techniques. This index structure not only strengthens query security and efficiency but also significantly reduces the false positive rate, thereby improving query accuracy. Moreover, the proposed scheme supports multi-attribute cost constraints and dynamic data updates, allowing it to adapt flexibly to practical requirements and user-specific needs. Finally, through security analysis and experimental evaluation, we demonstrate that the proposed scheme is both secure and effective. Full article

In disaster scenarios, e.g., earthquakes, tsunamis, and wildfires, communication infrastructure often becomes severely damaged. To rapidly restore damaged communication systems, we propose a UAV-based mobile base station equipped with Public Safety LTE (PS-LTE) technology to provide standalone communication capabilities. The proposed system includes PS-LTE functionalities, mission-critical push-to-talk, proximity-based services, and isolated E-UTRAN operation to ensure the reliable and secure communication for emergency services. We provide a simulation result to achieve the radio coverage of mobile base station. By using this radio coverage, we find an appropriate location of the end device for performing the outdoor experiments. We develop a prototype of a proposed mobile base station and test its operation in an outdoor environment. The experimental results provide a sufficient data rate to make an independent mobile base station to restore communication infrastructure in areas that experienced environmental disasters. This prototype and experimental results offer a significant step forward in creating agile and efficient communication solutions for emergency scenarios. Full article

This paper presents a novel dual-band antenna design for simultaneous 5G communication and localization services in high-speed train (HST) scenarios. It operates in the frequency range 1 (FR1) n78 band at 3.5 GHz and the FR2 n258 band at 26.2 GHz. The design combines a dielectric resonator antenna (DRA) and a planar patch antenna to achieve dual-band functionality. This provides efficient performance across both mid-band and millimeter-wave frequencies for advanced 5G applications. The dual-band configuration is motivated by the need to balance wide coverage and high data rates within a single, compact antenna design, addressing the specific challenges of maintaining stable connectivity and efficient spectrum utilization in high-speed, data-intensive environments. A common challenge in dual-band antenna designs is the interference between low- and high-frequency antennas, which can significantly degrade performance or even cause antenna failure. Our design addresses this issue by minimizing interference between the patch and DRA elements, ensuring stable operation across both frequency bands. As a result, the antenna achieves impressive gains and bandwidth, with a maximum gain of 6.8 dBi and an impedance bandwidth of 22.5% for the dual-band configuration. Also, both radiators present high total efficiency above 90%. The compact size of the antenna makes it highly suitable to be mounted on the roof of the train to enable 5G communication and location-based services for both safety-critical and liability-critical applications in HST scenarios. Full article

The Australian Bureau of Meteorology provides flood forecasting and warning services across Australia for most major rivers in Australia, in cooperation with other government, local agencies and emergency services. As part of this service, the Bureau issues a flood watch product to provide early advice on a developing situation that may lead to flooding up to 4 days prior to an event. This service is based on (a) an ensemble of available Numerical Weather Prediction (NWP) rainfall forecasts, (b) antecedent soil moisture, stream and dam conditions, (c) hydrological forecasts using event-based models and (d) expert meteorological and hydrological input by Bureau of Meteorology staff, to estimate the risk of reaching pre-specified river height thresholds at locations across the continent. A flood watch provides information about a developing weather situation including forecasting rainfall totals, catchments at risk of flooding, and indicative severity where required. Although there is uncertainty attached to a flood watch, its early dissemination can help individuals and communities to be better prepared should flooding eventuate. This paper investigates the utility of forecasts of daily gridded national runoff to inform the risk of riverine flooding up to 7 days in advance. The gridded national water balance model (AWRA-L) runoff outputs generated using post-processed 9-day Numerical Weather Prediction hindcasts were evaluated as to whether they could accurately predict exceedance probabilities of runoff at gauged locations. The approach was trialed over 75 forecast locations across North East Australia (Queensland). Forecast 3-, 5- and 7-day accumulations of runoff over the catchment corresponding to each location were produced, identifying whether accumulated runoff reached either 95% or 99% historical levels (analogous to minor, moderate and major threshold levels). The performance of AWRA-L runoff-based flood likelihood was benchmarked against that based on precipitation only (i.e., not rainfall–runoff transformation). Both products were evaluated against the observed runoff data measured at the site. Our analysis confirmed that this runoff-based flood likelihood guidance could be used to support the generation of flood watch products. Full article

Location-based services provide significant economic and social benefits. The ubiquity, low cost, and accessibility of geomagnetism are highly advantageous for localization. However, the existing geomagnetic localization methods suffer from location ambiguity. To address these issues, we propose a fusion localization algorithm based on particle swarm optimization. First, we construct a five-dimensional hybrid LSTM (5DHLSTM) neural network model, and the 5DHLSTM network structure parameters are optimized via particle swarm optimization (PSO) to achieve geomagnetic localization. The eight-dimensional BiLSTM (8DBiLSTM) algorithm is subsequently proposed for heading estimation in dead reckoning, which effectively improves the heading accuracy. Finally, fusion localization is achieved by combining geomagnetic localization with an improved pedestrian dead reckoning (IPDR) based on an extended Kalman filter (EKF). To validate the localization performance of the proposed PSO-5DHLSTM-IPDR method, several extended experiments using Xiaomi 10 and Hi Nova 9 are conducted in two different scenarios. The experimental results demonstrate that the proposed method improves localization accuracy and has good robustness and flexibility. Full article

The relationship between the service of public transport (PT) and its use is complex but can be simplified through the use of indicators. These indicators should be able to accurately reflect PT use so that improvements in the indicators lead to increases in PT use. Although researchers and planners use similar indicators to describe the access of PT stops, the indicators used to assess the accessibility of destinations differ. Researchers use specific location-based methods to analyze accessibility to spatially dispersed destinations, while practitioners often focus on connectivity to central (business) districts. This raises the question of which approach better reflects the use of PT. By combining the German National Household Travel Survey with nationwide timetable data, we examine the relationship between PT use and two indicators of PT service: (1) travel time to the nearest central district and (2) cumulative opportunity accessibility, both calculated as the ratio of PT to car travel. The results of our binary logit models indicate that the travel time ratio does not have a relevant influence on the choice of motorized transport mode, but the accessibility ratio does. Therefore, we suggest that practitioners should use location-based accessibility methods such as the cumulative opportunity ratio to evaluate and improve PT service planning. Full article

This study introduces a new method for nowcasting UV Index maps developed within the framework of the Austrian Solar UV Measurement Network. While we focus on the DACH region (Germany, Austria, and Switzerland) in this study, the same methods are routinely applied to nowcast UV Index maps for Europe. The primary objective is to improve public health measures by providing timely and area-wide UV Index values. The UV Index maps are based on clear-sky calculations using data from the Copernicus Atmosphere Monitoring Service. Cloud effects are integrated using cloud modification factors determined from Meteosat Second Generation satellite imagery. To assess the representativeness of the calculated UV Index maps, the corresponding pixel values are compared to ground-based measurements for the year 2022 at 27 locations in the DACH region. For all sky conditions, the satellite-derived UV Index values are within ±1.0 UV Index of the ground-measured UV Index for at least 91% of the data at stations below 500 m a.s.l. and in flatter landscapes. For high-altitude sites and in more pronounced topographies, the values for U1.0 decrease, with the lowest agreement of 74.8% found for the Sonnblick station located at 3109 m a.s.l. Discrepancies arise due to differences in the measurement methods: ground-based measurements capture the local conditions, while satellite-derived values represent the average values over larger areas. The clear-sky deviations are most pronounced at high-altitude, snow-covered sites due to uncertainties in the surface albedo. Under all sky conditions, cloud variability adds further uncertainties, particularly in complex terrain or broken cloud cover scenarios, where satellite cloud data lack the resolution to capture local fluctuations. This study discusses these uncertainties while also highlighting the potential of the generated UV Index maps to provide area-wide information to the population as a valuable complement to ground-based measurements. Full article