Processing math: 0%
 
 
Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (4,964)

Search Parameters:
Keywords = map calculation

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
12 pages, 4574 KiB  
Article
Tectonic Evolution of the Upper Paleozoic Erathem in the Northeastern Part of the Sulige Gas Field in the Ordos Basin and Its Effect on Reservoir Control
by Xinghui Ning, Aiguo Wang, Yufei Wang, Bin Fu and Yijun Li
Appl. Sci. 2025, 15(3), 1036; https://doi.org/10.3390/app15031036 - 21 Jan 2025
Abstract
Sandstone bodies are distributed across a large area in the northeastern part of the Sulige gas field in the Ordos Basin. However, the production characteristics of gas wells in different areas are significantly different, and the success rate of drilling effective reservoirs is [...] Read more.
Sandstone bodies are distributed across a large area in the northeastern part of the Sulige gas field in the Ordos Basin. However, the production characteristics of gas wells in different areas are significantly different, and the success rate of drilling effective reservoirs is low. Therefore, studies on the patterns of natural gas enrichment are urgently needed. In this study, from the perspective of tectonic evolution, the mudstone sonic transit time method was used to calculate the denudation thickness of the study area in the Late Cretaceous; the denudation thickness was between 820 m and 1200 m, and the paleo-tectonic map of the top of He 8, which was the main layer at that time, was restored and analyzed in comparison with the present structure at the top of He 8, revealing that tectonic evolution has a controlling effect on the migration, accumulation and dispersion of natural gas after formation. During the critical period of hydrocarbon accumulation at the end of the Early Cretaceous, the short-axis nose uplift zone remaining in the central and western regions, and the long-axis nose uplift zone remaining in the central and eastern regions were favorable areas for natural gas migration and accumulation. The up-dip direction has lithological traps, and the gas reservoirs have survived to the present day. The short-axis nose uplift zone and anticline at the western margin disappeared through tectonic adjustment; thus, the paleo-gas reservoirs that formed there were destroyed, and the natural gas was adjusted to new traps. Full article
(This article belongs to the Special Issue Technologies and Methods for Exploitation of Geological Resources)
Show Figures

Figure 1

21 pages, 7811 KiB  
Article
Research on Broiler Mortality Identification Methods Based on Video and Broiler Historical Movement
by Hongyun Hao, Fanglei Zou, Enze Duan, Xijie Lei, Liangju Wang and Hongying Wang
Agriculture 2025, 15(3), 225; https://doi.org/10.3390/agriculture15030225 - 21 Jan 2025
Viewed by 59
Abstract
The presence of dead broilers within a flock can be significant vectors for disease transmission and negatively impact the overall welfare of the remaining broilers. This study introduced a dead broiler detection method that leverages the fact that dead broilers remain stationary within [...] Read more.
The presence of dead broilers within a flock can be significant vectors for disease transmission and negatively impact the overall welfare of the remaining broilers. This study introduced a dead broiler detection method that leverages the fact that dead broilers remain stationary within the flock in videos. Dead broilers were identified through the analysis of the historical movement information of each broiler in the video. Firstly, the frame difference method was utilized to capture key frames in the video. An enhanced segmentation network, YOLOv8-SP, was then developed to obtain the mask coordinates of each broiler, and an optical flow estimation method was employed to generate optical flow maps and evaluate their movement. An average optical flow intensity (AOFI) index of broilers was defined and calculated to evaluate the motion level of each broiler in each key frame. With the AOFI threshold, broilers in the key frames were classified into candidate dead broilers and active live broilers. Ultimately, the identification of dead broilers was achieved by analyzing the frequency of each broiler being judged as a candidate death in all key frames within the video. We incorporated the parallelized patch-aware attention (PPA) module into the backbone network and improved the overlaps function with the custom power transform (PT) function. The box and mask segmentation mAP of the YOLOv8-SP model increased by 1.9% and 1.8%, respectively. The model’s target recognition performance for small targets and partially occluded targets was effectively improved. False and missed detections of dead broilers occurred in 4 of the 30 broiler testing videos, and the accuracy of the dead broiler identification algorithm proposed in this study was 86.7%. Full article
(This article belongs to the Special Issue Modeling of Livestock Breeding Environment and Animal Behavior)
Show Figures

Figure 1

31 pages, 2921 KiB  
Article
A Reconstruction of the Shrine of the Prophet Nahum: An Analysis of 3D Documentation Methods and Data Transfer Technology for Virtual and Augmented Realities
by Karel Pavelka, Karel Pavelka and Lukáš Běloch
Appl. Sci. 2025, 15(2), 1000; https://doi.org/10.3390/app15021000 - 20 Jan 2025
Viewed by 330
Abstract
This article focuses on modern methods of documentation and visualization for a historic object. Digital photogrammetry and terrestrial laser scanning (TLS), which are essential tools for documenting cultural heritage in view of their rapid development in recent years, were used, compared, and analyzed. [...] Read more.
This article focuses on modern methods of documentation and visualization for a historic object. Digital photogrammetry and terrestrial laser scanning (TLS), which are essential tools for documenting cultural heritage in view of their rapid development in recent years, were used, compared, and analyzed. Furthermore, the use of available 3D computer graphics technologies for visualization is described and an optimal procedure for converting the object into VR and AR is proposed and implemented. The technologies presented in this article were tested within the context of a project on the reconstruction of the shrine of the Prophet Nahum in the city of Alqosh in northern Iraq, taking the shrine as a case study. Funded by ARCH Int. and provided by GemaArt Int., the restoration project started in 2018 and was completed in 2021. The ongoing documentation was prepared by the CTU and it used the materials for research purposes. Accurate documentation using photogrammetry, drones, and TLS was key to the restoration. Leica BLK360, Faro Focus S150, and GeoSlam laser scanners were used, as well as photogrammetric methods. In particular, the documentation process involved the creation of 3D textured models from the photogrammetry, which were compared to the TLS data to ensure accuracy. These models were necessary to track changes during the reconstruction phases and to calculate the volumes of rubble removed and materials added. Our data analysis revealed significant differences between the construction logs and the analysis of the accurate 3D models; the results showed an underestimation of the displaced material statements by 13.4% for removed material and 4.6% for added material. The use of heat maps and volumetric analyses helped to identify areas of significant change that guided the reconstruction and documented significant changes to the building for the investor. These findings are important for use in the construction industry with respect to historic sites as well as for further research focused on visualization using VR (virtual reality) and AR (augmented reality). The conversion of existing 3D models into VR and AR is rapidly evolving and significant progress was made during this project. The Unreal Engine (UE) game engine was used. Despite the significantly improved performance of the new UE 5 version, the data for conversion to VR and AR needs to be decimated to reduce the amount—in our case, this was by up to 90%. The quality appearance of the objects is then ensured by textures. An important outcome of this part of the research was the debugged workflow developed to optimize the 3D models for VR, which was essential for creating a virtual museum that shows the restoration process. Full article
(This article belongs to the Special Issue Advanced Technologies in Cultural Heritage)
24 pages, 8039 KiB  
Article
Hybrid Probabilistic Road Map Path Planning for Maritime Autonomous Surface Ships Based on Historical AIS Information and Improved DP Compression
by Gongxing Wu, Liepan Guo, Danda Shi, Bing Han and Fan Yang
J. Mar. Sci. Eng. 2025, 13(1), 184; https://doi.org/10.3390/jmse13010184 - 20 Jan 2025
Viewed by 233
Abstract
A hybrid probabilistic road map (PRM) path planning algorithm based on historical automatic identification system (AIS) information and Douglas–Peucker (DP) compression is proposed to address the issues of low path quality and the need for extensive sampling in the traditional PRM algorithm. This [...] Read more.
A hybrid probabilistic road map (PRM) path planning algorithm based on historical automatic identification system (AIS) information and Douglas–Peucker (DP) compression is proposed to address the issues of low path quality and the need for extensive sampling in the traditional PRM algorithm. This innovative approach significantly reduces the number of required samples and decreases path planning time. The process begins with the collection of historical AIS data from the autonomous vessel’s navigation area, followed by comprehensive data-cleaning procedures to eliminate invalid and incomplete records. Subsequently, an enhanced DP compression algorithm is employed to streamline the cleaned AIS data, minimizing waypoint data while retaining essential trajectory characteristics. Intersection points among various vessel trajectories are then calculated, and these points, along with the compressed AIS data, form the foundational dataset for path searching. Building upon the traditional PRM framework, the proposed hybrid PRM algorithm integrates the B-spline algorithm to smooth and optimize the generated paths. Comparative experiments conducted against the standard PRM algorithm, A*, and Dijkstra algorithms demonstrate that the hybrid PRM approach not only reduces planning time but also achieves superior path smoothness. These improvements enhance both the efficiency and accuracy of path planning for maritime autonomous surface ships (MASS), marking a significant advancement in autonomous maritime navigation. Full article
(This article belongs to the Special Issue Unmanned Marine Vehicles: Perception, Planning, Control and Swarm)
Show Figures

Figure 1

20 pages, 6378 KiB  
Article
Edge Computing-Based Machine Vision for Non-Invasive and Rapid Soft Sensing of Mushroom Liquid Strain Biomass
by Libin Wu, Guimiao Xiao, Deyao Huang, Xiandong Zhang, Dapeng Ye and Haiyong Weng
Agronomy 2025, 15(1), 242; https://doi.org/10.3390/agronomy15010242 - 20 Jan 2025
Viewed by 455
Abstract
Biomass monitoring of mushroom liquid strains during the fermentation process demands real-time analysis with minimal manual intervention, highlighting the urgent need for intelligent surveillance. This study introduced a soft sensor method based on edge computing machine vision, termed Edge CV, for in situ [...] Read more.
Biomass monitoring of mushroom liquid strains during the fermentation process demands real-time analysis with minimal manual intervention, highlighting the urgent need for intelligent surveillance. This study introduced a soft sensor method based on edge computing machine vision, termed Edge CV, for in situ non-invasive estimation of biomass. In our experiment, the hardware of the Edge CV system includes the Jetson Nano with 4 GB RAM, 64 GB ROM, and a 128-core Maxwell GPU for executing intelligent machine vision tasks, along with embedded cameras for image data acquisition. Furthermore, a cascaded machine vision model was developed to enable biomass evaluation on the Edge CV system. The cascaded machine vision model mainly consists of three steps: first, the object detection task to locate the observation window, achieving a mean Average Precision (mAP50:95) of 82.3% with 78.7 GFLOPs; then, the segmentation task to extract liquid strain data within the observation window, yielding a mean intersection over union (MIoU) of 85.9% with 110.4 GFLOPs; and finally, calculating mycelium biomass indices via the morphological image processing task. The correlation between Edge CV inference and manual measurement showed an R2 of 0.963 and an RMSE of 0.027 for normalized biomass indices, demonstrating a robust and consistent trend. Therefore, this study illustrates the practical application of edge computing-based machine vision for biomass soft sensing during the fermentation process. Full article
Show Figures

Figure 1

19 pages, 4376 KiB  
Article
Tracing the 2018 Sulawesi Earthquake and Tsunami’s Impact on Palu, Indonesia: A Remote Sensing Analysis
by Youshuang Hu, Aggeliki Barberopoulou and Magaly Koch
J. Mar. Sci. Eng. 2025, 13(1), 178; https://doi.org/10.3390/jmse13010178 - 19 Jan 2025
Viewed by 403
Abstract
The 2018 Sulawesi Earthquake and Tsunami serves as a backdrop for this work, which employs simple and straightforward remote sensing techniques to determine the extent of the destruction and indirectly evaluate the region’s vulnerability to such catastrophic events. Documenting damage from tsunamis is [...] Read more.
The 2018 Sulawesi Earthquake and Tsunami serves as a backdrop for this work, which employs simple and straightforward remote sensing techniques to determine the extent of the destruction and indirectly evaluate the region’s vulnerability to such catastrophic events. Documenting damage from tsunamis is only meaningful shortly after the disaster has occurred because governmental agencies clean up debris and start the recovery process within a few hours after the destruction has occurred, deeming impact estimates unreliable. Sentinel-2 and Maxar WorldView-3 satellite images were used to calculate well-known environmental indices to delineate the tsunami-affected areas in Palu, Indonesia. The use of NDVI, NDSI, and NDWI indices has allowed for a quantifiable measure of the changes in vegetation, soil moisture, and water bodies, providing a clear demarcation of the tsunami’s impact on land cover. The final tsunami inundation map indicates that the areas most affected by the tsunami are found in the urban center, low-lying regions, and along the coast. This work charts the aftermath of one of Indonesia’s recent tsunamis but may also lay the groundwork for an easy, handy, and low-cost approach to quickly identify tsunami-affected zones. While previous studies have used high-resolution remote sensing methods such as LiDAR or SAR, our study emphasizes accessibility and simplicity, making it more feasible for resource-constrained regions or rapid disaster response. The scientific novelty lies in the integration of widely used environmental indices (dNDVI, dNDWI, and dNDSI) with threshold-based Decision Tree classification to delineate tsunami-affected areas. Unlike many studies that rely on advanced or proprietary tools, we demonstrate that comparable results can be achieved with cost-effective open-source data and straightforward methodologies. Additionally, we address the challenge of differentiating tsunami impacts from other phenomena (et, liquefaction) through index-based thresholds and propose a framework that is adaptable to other vulnerable coastal regions. Full article
(This article belongs to the Special Issue Coastal Disaster Assessment and Response)
Show Figures

Figure 1

23 pages, 25322 KiB  
Article
Prediction of Winter Wheat Parameters with Planet SuperDove Imagery and Explainable Artificial Intelligence
by Gabriele De Carolis, Vincenzo Giannico, Leonardo Costanza, Francesca Ardito, Anna Maria Stellacci, Afwa Thameur, Sergio Ruggieri, Sabina Tangaro, Marcello Mastrorilli, Nicola Sanitate and Simone Pietro Garofalo
Agronomy 2025, 15(1), 241; https://doi.org/10.3390/agronomy15010241 - 19 Jan 2025
Viewed by 516
Abstract
This study investigated the application of high-resolution satellite imagery from SuperDove satellites combined with machine learning algorithms to estimate the spatiotemporal variability of some winter wheat parameters, including the relative leaf chlorophyll content (RCC), relative water content (RWC), and aboveground dry matter (DM). [...] Read more.
This study investigated the application of high-resolution satellite imagery from SuperDove satellites combined with machine learning algorithms to estimate the spatiotemporal variability of some winter wheat parameters, including the relative leaf chlorophyll content (RCC), relative water content (RWC), and aboveground dry matter (DM). The research was carried out within an experimental field in Southern Italy during the 2024 growing season. Different machine learning (ML) algorithms were trained and compared using spectral band data and calculated vegetation indices (VIs) as predictors. Model performance was assessed using R2 and RMSE. The ML models tested were random forest (RF), support vector regressor (SVR), and extreme gradient boosting (XGB). RF outperformed the other ML algorithms in the prediction of RCC when using VIs as predictors (R2 = 0.81) and in the prediction of the RWC and DM when using spectral bands data as predictors (R2 = 0.71 and 0.87, respectively). Model explainability was assessed with the SHAP method. A SHAP analysis highlighted that GNDVI, Cl1, and NDRE were the most important VIs for predicting RCC, while yellow and red bands were the most important for DM prediction, and yellow and nir bands for RWC prediction. The best model found for each target was used to model its seasonal trend and produce a variability map. This approach highlights the potential of integrating ML and high-resolution satellite imagery for the remote monitoring of wheat, which can support sustainable farming practices. Full article
(This article belongs to the Section Precision and Digital Agriculture)
Show Figures

Figure 1

28 pages, 8147 KiB  
Article
INterpolated FLOod Surface (INFLOS), a Rapid and Operational Tool to Estimate Flood Depths from Earth Observation Data for Emergency Management
by Quentin Poterek, Alessandro Caretto, Rémi Braun, Stephen Clandillon, Claire Huber and Pietro Ceccato
Remote Sens. 2025, 17(2), 329; https://doi.org/10.3390/rs17020329 - 18 Jan 2025
Viewed by 375
Abstract
The INterpolated FLOod Surface (INFLOS) tool was developed to meet the operational needs of the Copernicus Emergency Management Service (CEMS) Rapid Mapping (RM) component, which delivers critical crisis information within hours during and after disasters. With increasing demand for accurate and real-time flood [...] Read more.
The INterpolated FLOod Surface (INFLOS) tool was developed to meet the operational needs of the Copernicus Emergency Management Service (CEMS) Rapid Mapping (RM) component, which delivers critical crisis information within hours during and after disasters. With increasing demand for accurate and real-time flood depth estimates, INFLOS provides a rapid, adaptable solution for estimating floodwater depth across diverse flood scenarios, using remotely sensed data and high-resolution Digital Terrain Models (DTMs). INFLOS calculates flood depth by interpolating water surface elevation from sample points along flooded area boundaries, derived from satellite imagery. This tool is capable of delivering flood depth estimates in a rapid mapping context, leveraging a multistep interpolation and filtering process for improved accuracy. Tested across fourteen regions in Europe and South America, INFLOS has been successfully integrated into CEMS RM operations. The tool’s computational optimisations further enhance efficiency, improving computation times by up to 15-fold, compared to similar techniques. Indeed, it is able to process areas of up to 6000 ha in a median time of 5.2 min, and up to 30 min at most. In conclusion, INFLOS is currently operational and consistently generates flood depth products quickly, supporting real-time emergency management and reinforcing the CEMS RM portfolio. Full article
Show Figures

Figure 1

14 pages, 659 KiB  
Article
County-Level Food Insecurity and Hepatocellular Carcinoma Risk: A Cross-Sectional Analysis
by Rebecca D. Kehm, Chrystelle L. Vilfranc, Jasmine A. McDonald and Hui-Chen Wu
Int. J. Environ. Res. Public Health 2025, 22(1), 120; https://doi.org/10.3390/ijerph22010120 - 18 Jan 2025
Viewed by 325
Abstract
Food insecurity (FI) is associated with several known hepatocellular carcinoma (HCC) risk factors, but few studies have directly examined FI in association with HCC risk. We aimed to investigate whether county-level FI is associated with HCC risk. We used data from 21 registries [...] Read more.
Food insecurity (FI) is associated with several known hepatocellular carcinoma (HCC) risk factors, but few studies have directly examined FI in association with HCC risk. We aimed to investigate whether county-level FI is associated with HCC risk. We used data from 21 registries in the Surveillance Epidemiology and End Results database to obtain county-level counts of HCC cases from 2018 to 2021. We obtained the county-level FI rates for 2018–2021 from Feeding America’s Map the Meal Gap. We used multi-level Poisson regression models with robust standard errors to calculate incidence rate ratios (IRRs) and 95% confidence intervals (CIs). Overall, a one-standard-deviation (SD) increase in county-level FI was associated with an 8% increase in HCC risk in the fully adjusted model (IRR = 1.08, 95% CI = 1.06, 1.10). When stratified by age at diagnosis, a one-SD increase in county-level FI was associated with a 2% higher risk of HCC in the ≥65 age group (IRR = 1.02, 95% CI = 1.00, 1.05) and a 15% higher risk in the <65 age group (IRR = 1.15, 95% CI = 1.11, 1.19; interaction p-value < 0.001). If confirmed in other studies, these findings support the need for interventions and policies addressing FI in populations at increased risk for HCC. Full article
(This article belongs to the Section Global Health)
Show Figures

Figure 1

17 pages, 7356 KiB  
Article
Increasing Neural-Based Pedestrian Detectors’ Robustness to Adversarial Patch Attacks Using Anomaly Localization
by Olga Ilina, Maxim Tereshonok and Vadim Ziyadinov
J. Imaging 2025, 11(1), 26; https://doi.org/10.3390/jimaging11010026 - 17 Jan 2025
Viewed by 325
Abstract
Object detection in images is a fundamental component of many safety-critical systems, such as autonomous driving, video surveillance systems, and robotics. Adversarial patch attacks, being easily implemented in the real world, provide effective counteraction to object detection by state-of-the-art neural-based detectors. It poses [...] Read more.
Object detection in images is a fundamental component of many safety-critical systems, such as autonomous driving, video surveillance systems, and robotics. Adversarial patch attacks, being easily implemented in the real world, provide effective counteraction to object detection by state-of-the-art neural-based detectors. It poses a serious danger in various fields of activity. Existing defense methods against patch attacks are insufficiently effective, which underlines the need to develop new reliable solutions. In this manuscript, we propose a method which helps to increase the robustness of neural network systems to the input adversarial images. The proposed method consists of a Deep Convolutional Neural Network to reconstruct a benign image from the adversarial one; a Calculating Maximum Error block to highlight the mismatches between input and reconstructed images; a Localizing Anomalous Fragments block to extract the anomalous regions using the Isolation Forest algorithm from histograms of images’ fragments; and a Clustering and Processing block to group and evaluate the extracted anomalous regions. The proposed method, based on anomaly localization, demonstrates high resistance to adversarial patch attacks while maintaining the high quality of object detection. The experimental results show that the proposed method is effective in defending against adversarial patch attacks. Using the YOLOv3 algorithm with the proposed defensive method for pedestrian detection in the INRIAPerson dataset under the adversarial attacks, the mAP50 metric reaches 80.97% compared to 46.79% without a defensive method. The results of the research demonstrate that the proposed method is promising for improvement of object detection systems security. Full article
(This article belongs to the Section Image and Video Processing)
Show Figures

Figure 1

17 pages, 1284 KiB  
Article
Methods for Calculating Greenhouse Gas Emissions in the Baltic Sea Ports: A Comparative Study
by Mari-Liis Tombak, Ulla Tapaninen and Jonne Kotta
Sustainability 2025, 17(2), 639; https://doi.org/10.3390/su17020639 - 15 Jan 2025
Viewed by 500
Abstract
Ports are vital nodes of maritime transport. To be able to decrease their GHG emissions, ports have developed various automated or semiautomated tools for emission assessment. In this study, we focus on an open-source tool called EVISA and compare how seven Baltic Sea [...] Read more.
Ports are vital nodes of maritime transport. To be able to decrease their GHG emissions, ports have developed various automated or semiautomated tools for emission assessment. In this study, we focus on an open-source tool called EVISA and compare how seven Baltic Sea ports are using this tool. We found that the results of these assessments are incomparable, all the ports use the tool differently, and report different numbers of emissions. We also compare how one port, the Port of Tallinn, uses two different tools and ends up with different numbers of emissions. The study offers a detailed comparison of the port-specific methods, data collection processes, and calculation principles, evaluating their effectiveness in measuring emissions from maritime transport in ports. Additionally, it highlights the pressing need for standardised greenhouse gas emission mapping methodologies in ports. The results highlight the need to create a cohesive, easy-to-use tool that complies with established standards like the GHG Protocol, IPCC guidelines, and ISO 14064. Full article
(This article belongs to the Section Air, Climate Change and Sustainability)
Show Figures

Figure 1

21 pages, 3280 KiB  
Article
Autonomous, Multisensory Soil Monitoring System
by Valentina-Daniela Băjenaru, Simona-Elena Istrițeanu and Paul-Nicolae Ancuța
AgriEngineering 2025, 7(1), 18; https://doi.org/10.3390/agriengineering7010018 - 15 Jan 2025
Viewed by 332
Abstract
The research investigates the advantages of real-time soil quality monitoring for various land management applications. We emphasize the crucial role of soil modeling and mapping by visualizing and understanding aridity trends across different regions. The primary objective is to develop an innovative soil [...] Read more.
The research investigates the advantages of real-time soil quality monitoring for various land management applications. We emphasize the crucial role of soil modeling and mapping by visualizing and understanding aridity trends across different regions. The primary objective is to develop an innovative soil monitoring system utilizing Internet of Things (IoT) technology. This system, equipped with intelligent sensors, will operate autonomously, collecting real-time data to identify key trends in soil conditions. Our system employs smart soil sensors to measure macronutrient values up to a depth of 80 cm. These sensors will transmit data wirelessly. Laboratory research involved a two-month evaluation of the system’s performance across three distinct soil types collected from diverse geographical locations. Analysis of the three soil types yielded a model accuracy estimate of 0.01. A strong positive linear correlation (0.92) between moisture and macronutrients has been observed in two out of the three soil types. The results, particularly related to soil moisture, were averaged over the testing period. While precipitation values were not directly integrated into the modeling framework, they were calculated in l/m2 to ensure accurate real-time estimates. The need for such advanced monitoring systems is critical for optimizing key soil macronutrients and enabling spatiotemporal mapping. This information is essential for developing effective strategies to mitigate soil aridification and prevent desertification. Full article
(This article belongs to the Section Sensors Technology and Precision Agriculture)
Show Figures

Figure 1

15 pages, 2715 KiB  
Article
Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion Generation
by Pengnan Liu, Yanchen Wang, Yunlong Li, Deqiang Cheng and Feixiang Xu
Sensors 2025, 25(2), 473; https://doi.org/10.3390/s25020473 - 15 Jan 2025
Viewed by 357
Abstract
Aiming at the problems caused by a lack of feature matching due to occlusion and fixed model parameters in cross-domain person re-identification, a method based on multi-branch pose-guided occlusion generation is proposed. This method can effectively improve the accuracy of person matching and [...] Read more.
Aiming at the problems caused by a lack of feature matching due to occlusion and fixed model parameters in cross-domain person re-identification, a method based on multi-branch pose-guided occlusion generation is proposed. This method can effectively improve the accuracy of person matching and enable identity matching even when pedestrian features are misaligned. Firstly, a novel pose-guided occlusion generation module is designed to enhance the model’s ability to extract discriminative features from non-occluded areas. Occlusion data are generated to simulate occluded person images. This improves the model’s learning ability and addresses the issue of misidentifying occlusion samples. Secondly, a multi-branch feature fusion structure is constructed. By fusing different feature information from the global and occlusion branches, the diversity of features is enriched. This enrichment improves the model’s generalization. Finally, a dynamic convolution kernel is constructed to calculate the similarity between images. This approach achieves effective point-to-point matching and resolves the problem of fixed model parameters. Experimental results indicate that, compared to current mainstream algorithms, this method shows significant advantages in the first hit rate (Rank-1), mean average precision (mAP), and generalization performance. In the MSMT17→DukeMTMC-reID dataset, after re-ranking (Rerank) and time-tift (Tlift) for the two indicators on Market1501, the mAP and Rank-1 reached 80.5%, 84.3%, 81.9%, and 93.1%. Additionally, the algorithm achieved 51.6% and 41.3% on DukeMTMC-reID→Occluded-Duke, demonstrating good recognition performance on the occlusion dataset. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

35 pages, 3375 KiB  
Article
Optimization in Symmetric Trees, Unicyclic Graphs, and Bicyclic Graphs with Help of Mappings Using Second Form of Generalized Power-Sum Connectivity Index
by Muhammad Yasin Khan, Gohar Ali and Ioan-Lucian Popa
Symmetry 2025, 17(1), 122; https://doi.org/10.3390/sym17010122 - 15 Jan 2025
Viewed by 348
Abstract
The topological index (TI), sometimes referred to as the connectivity index, is a molecular descriptor calculated based on the molecular graph of a chemical compound. Topological indices (TIs) are numeric parameters of a graph used to characterize its topology and are usually graph-invariant. [...] Read more.
The topological index (TI), sometimes referred to as the connectivity index, is a molecular descriptor calculated based on the molecular graph of a chemical compound. Topological indices (TIs) are numeric parameters of a graph used to characterize its topology and are usually graph-invariant. The generalized power-sum connectivity index (GPSCI) for the graph is ΩYα(Ω)=ζϱE(Ω)(dΩ(ζ)dΩ(ζ)+dΩ(ϱ)dΩ(ϱ))α, while the second form of the GPSCI is defined as Yβ(Ω)=ζϱE(Ω)(dΩ(ζ)dΩ(ζ)×dΩ(ϱ)dΩ(ϱ))β. In this paper, we investigate Yβ in the family of trees, unicyclic graphs, and bicyclic graphs. We determine optimal graphs in the desired families for Yβ using certain mappings. For graphs with maximal values, two mappings are used, namely A and B, while for graphs with minimal values, mapping C and mapping D are considered. Full article
(This article belongs to the Special Issue Symmetry and Graph Theory, 2nd Edition)
Show Figures

Figure 1

26 pages, 8715 KiB  
Article
Interpretable Deep Learning for Pneumonia Detection Using Chest X-Ray Images
by Jovito Colin and Nico Surantha
Information 2025, 16(1), 53; https://doi.org/10.3390/info16010053 - 15 Jan 2025
Viewed by 278
Abstract
Pneumonia remains a global health issue, creating the need for accurate detection methods for effective treatment. Deep learning models like ResNet50 show promise in detecting pneumonia from chest X-rays; however, their black-box nature limits the transparency, which fails to meet that needed for [...] Read more.
Pneumonia remains a global health issue, creating the need for accurate detection methods for effective treatment. Deep learning models like ResNet50 show promise in detecting pneumonia from chest X-rays; however, their black-box nature limits the transparency, which fails to meet that needed for clinical trust. This study aims to improve model interpretability by comparing four interpretability techniques, which are Layer-wise Relevance Propagation (LRP), Adversarial Training, Class Activation Maps (CAMs), and the Spatial Attention Mechanism, and determining which fits best the model, enhancing its transparency with minimal impact on its performance. Each technique was evaluated for its impact on the accuracy, sensitivity, specificity, AUC-ROC, Mean Relevance Score (MRS), and a calculated trade-off score that balances interpretability and performance. The results indicate that LRP was the most effective in enhancing interpretability, achieving high scores across all metrics without sacrificing diagnostic accuracy. The model achieved 0.91 accuracy and 0.85 interpretability (MRS), demonstrating its potential for clinical integration. In contrast, Adversarial Training, CAMs, and the Spatial Attention Mechanism showed trade-offs between interpretability and performance, each highlighting unique image features but with some impact on specificity and accuracy. Full article
Show Figures

Figure 1

Back to TopTop