Search Results (413)

Rolling contact fatigue cracks at the contact surface between a wheel and rail are evaluated based on the results of an external inspection (visual inspection). We developed a rail damage assessment technique using a fast regional convolutional neural network deep learning-based image analysis framework. We collected rail specimens from in-service tracks and performed scanning electron microscopy to correlate surface damage with subsurface crack formation, including crack depth, length, and angle. This data was input into an artificial neural network (ANN) to assess internal crack conditions using visual information obtained from rail surface damage. The resulting model achieved an average accuracy of 94.9%, outperforming other algorithms. We integrated this model into a developed rail damage diagnosis app with deep learning that links field photographs with cloud-based big data to learn, quantitatively diagnose, and present the type and scale of rail damage. We examined the field applicability of the application at a rail damage site. The standard deviation of the rail damage diagnosis results was 0.2–1.5% between different users. Appropriateness of the rail damage assessment technique using the proposed ANN image analysis technique was verified experimentally. Consistent diagnosis results could be derived regardless of the inspector, minimizing human error. Full article

Animal welfare is a key component of sustainable poultry production and is routinely monitored through official veterinary inspections. The aim of this study was to determine the level of welfare compliance among different poultry species and production categories, to compare compliance levels across these groups, and to assess long-term trends using official inspection data. The study was based on the results of supervisory inspections conducted by veterinary inspectors in poultry farms in the Czech Republic between 2016 and 2024. Welfare compliance was evaluated in laying hens, broiler chickens, turkeys, ducks, and geese using a standardized system of welfare assessment checkpoints applied during official controls. Inspections were classified as compliant or non-compliant based on the presence or absence of deficiencies, and overall compliance levels were calculated as the proportion of animals kept in farms with compliant inspections. Across the entire study period, the proportion of poultry kept in farms with compliant inspections ranged from 82.8% to 98.4%, with the highest compliance level observed in turkeys, followed by ducks and broiler chickens, while the lowest compliance level was recorded in geese. Differences among poultry species and categories were statistically significant (p < 0.05). Comparison of two time periods (2016–2018 and 2022–2024) revealed significant improvements in compliance for broiler chickens, ducks, and geese, whereas significant declines were observed for laying hens and turkeys (p < 0.001). These results demonstrate clear differences in welfare compliance among poultry species and categories and indicate that compliance trends over time are not uniform across the poultry sector. Official veterinary inspection data provide a valuable tool for large-scale assessment of welfare compliance and for identifying poultry sectors that may benefit from targeted welfare improvement measures. Full article

Reliable structural safety risk diagnosis and control of prestressed concrete bridges is essential for safe operation. Unfortunately, current practice relies heavily on inspectors’ engineering knowledge, field experience, and subjective judgments. In addition, existing general-purpose large language models (LLMs) often underperform in bridge defect diagnosis because of missing domain terminology and hallucinated technical statements. Therefore, there is a need to establish a trustworthy and explainable method for structural safety risk diagnosis and control. This study develops a domain knowledge-graph-enhanced framework, the prestressed concrete bridge defect knowledge-graph-enhanced LLM (PCBDK-LLM), to support defect diagnosis and treatment recommendations for prestressed concrete bridges. First, a prestressed concrete bridge defect knowledge graph is constructed using a hybrid approach that combines direct text-driven extraction from standards, peer-reviewed literature, and inspection reports with an ontology-based schema and consistency axioms. Then, the authors propose a retrieval module (REM) that performs ontology-aware chunking and hybrid similarity search to ground a locally deployed dialogue model (DeepSeek-R1) on verified domain knowledge. Eight real rehabilitation cases (eight bridges) are used to evaluate model recommendations against a reference solution documented in the project materials. Results indicate that the proposed PCBDK-LLM generates treatment suggestions that are more consistent with the reference plan than the baseline LLM and the ablation variants. Full article

In recent years, more and more studies have been published on the impact of air pollution on the increase in the incidence of type 1 diabetes mellitus (T1DM) in children and adolescents. To confirm this, we attempted to show whether there are differences between the impact of air pollution in 2017–2018 compared to the impact of air pollution during the lockdown period, i.e., 2020–2021, and its potential relationship with the incidence rates of new cases of T1DM. Methods: We obtained the number of new cases of T1DM in 2017–2018 and 2020–2021 in the Lublin Voivodeship. Data on the annual average concentrations of nitrogen dioxide (NO₂), nitric oxides (NO_x), sulphur dioxide (SO₂) and particulate matter (PM₁₀ and PM_2.5) were obtained from Annual Air Quality Assessment reports from 2017–2018 and 2020–2021, made available by the Provincial Inspectorate of Environmental Protection (WIOS) in Lublin. Results: In 2017–2018, air pollution in the entire Lublin Voivodeship was higher than during the lockdown period, i.e., 2020–2021. Moreover, in 2017 and 2018 in the Lublin Voivodeship, strong statistically significant positive correlations were found between NO₂ and PM_2.5 concentrations and the occurrence of T1DM in children. Conclusions: The research results indicate that air pollution is one of the factors that may suggest a potential association with the development of T1DM. Therefore, every effort should be made to minimize air pollution, which will reduce the risk of developing T1DM and other diseases. Full article

Automated verification of preflight aircraft inspection—a critical safety procedure—is addressed by integrating multi-camera tracking with procedural knowledge through a symmetry-aware spatio-temporal graph model. Departing from conventional tracking paradigms, the framework encodes operational protocols and structural symmetries of the aircraft as explicit constraints for trajectory association. Semantically consistent inspection zones are derived from geometric symmetry, and reliable tracklets extracted within them are connected using rules that enforce temporal order and identity consistency. Verification is formulated as a constrained shortest-path search over this graph, ensuring sequential and complete coverage of all mandatory zones by a single inspector. Evaluated on real-world airport surveillance data across diverse conditions, the proposed approach achieves a Complete Inspection Success Rate of 86.5%, significantly outperforming state-of-the-art tracking and re-identification baselines. The results demonstrate that explicit procedural integration substantially enhances the reliability and interpretability of automated compliance verification in safety-critical industrial monitoring. Full article

The growing number of older bridges has resulted in an increase in structural flaws, demanding frequent inspections and maintenance. Structural degradation accelerates post-damage recovery, emphasizing the necessity of preventive interventions. The use of Uncrewed Aerial Vehicle Systems (UASs) for bridge inspections represents a significant development in structural health monitoring (SHM). Traditional inspection methods are labor-intensive, time-consuming, expensive, and require access to high or difficult-to-reach areas, posing safety risks to inspectors. This study focuses on identifying drones that can efficiently support bridge inspection activities. Key factors influencing UAS selection include flight performance, flying modes, cost, sensor capabilities, payload capacity, and controller communication. The primary objective of this paper is to provide guidance to inspectors and transportation agencies regarding the capabilities and limitations of commercially available drones. It also outlines potential cost considerations associated with drone selection, including pilot skill level, platform cost, and sensor integration. These factors may vary depending on the type and complexity of the bridge being inspected. By addressing these aspects, this paper aims to assist decision-makers in making informed choices regarding the use of UASs for bridge inspection applications. Full article

The manufacturing industry is rapidly moving toward Artificial Intelligence (AI)-driven autonomous manufacturing, which requires distributed Edge AI architectures in which intelligent devices collaborate in real time. However, the practical deployment of Edge AI is hindered by the lack of standardized, asset-centric integration across heterogeneous devices. This study presents an Asset Administration Shell (AAS)-based Edge AI framework that enables interoperable and coordinated operation among Edge devices through standardized digital asset representations and OPC UA-based communication. In the proposed framework, each Edge device is represented as an AAS-compliant digital assets, enabling both direct inter-edge coordination and centralized asset management. To demonstrate the feasibility of the framework, a functional prototype was implemented consisting of a Raspberry Pi-based Vision Inspector, an autonomous mobile robot (AMR), and an AAS-based monitoring server. Vision-based fault detection is performed directly at the Edge and transmitted in real time to the AMR and the AAS Server, enabling event-driven autonomous response and system-level monitoring. Experimental results show that real-time fault detection and response can be achieved on resource-constrained edge devices while maintaining standardized, asset-level information exchange and interoperability across heterogeneous assets. These results indicate that the AAS-based Edge AI framework provides a practical and scalable foundation for asset-centric autonomous manufacturing systems requiring both real-time operational intelligence and systematic asset management. Full article

The assessment of structural degradation in reinforced concrete bridges is a crucial task for infrastructure maintenance and safety. Traditional inspection methods are often time-consuming, dependent on expert interpretation and weather conditions. This study explores the potential of artificial intelligence to support inspectors in the detection of typical deterioration patterns in reinforced (RC) and prestressed concrete (PRC) bridges, developing the VIADUCT (Visual Inspection and Automated Damage Understanding by Computer vision Techniques) software tool. Unlike previous studies, focusing only on a limited variety of possible defects (e.g., cracks, water stains), this study aims to train a deep learning model to be able to recognise a larger range of defects, such as those foreseen by the current Italian code for the assessment of existing bridges. The methodology relies on the YOLOv8n object detection model, which was trained, validated, and tested using a dataset including 1045 either wide-angle or detailed photographs taken during routine inspections. With these kinds of images being challenging for object detection algorithms (they include large parts of the background), multimodal attention mechanisms were implemented in the Graphical User Interface (GUI) through the semantic segmentation of the bridge surface using both the SAM and the U-Net model, as well as a tile reduction approach. These attention mechanisms allow the object detection model to focus on the relevant portions of the image (i.e., the bridge), while suppressing background information. Despite the limitation of the small size dataset used for training, results showed promising detection capabilities and precision. Furthermore, VIADUCT is ready to accept and use newer and more efficient versions of the object detection model, as soon as they become available. Full article

This article discusses public transport fare evasion from the point of view of the relations between inspection actions and detected evasion, with the aim of improving the efficacy of the former. By applying spatial statistics methods to a large dataset from Lisbon, Portugal, namely, entropy-based local bivariate relationships (LBR) and geographically weighted regression (GWR), it is shown that the two variables are associated in a widespread manner throughout the city, mostly in a linear way. Mapping out marginal gains from inspection actions then shows where they detect the most evaders, allowing transport companies to relocate their inspector teams in a more effective manner. Results for Lisbon show that gains in effectiveness of circa 50% can be obtained, mostly by moving some inspector teams from the centre of the city to the periphery during daytime. The methodology requires only inspection/detection databases, which transport companies usually have, making it a valuable, practical tool to combat fare evasion. Full article

Food fraud represents a growing global challenge with significant implications for public health, market integrity, sustainability, and consumer trust. Beyond economic losses, fraudulent practices undermine the environmental and social sustainability of food systems by distorting markets, misusing natural resources, and weakening incentives for authentic and responsible production. Despite the establishment of harmonized frameworks of the European Union for official controls, the increasing complexity of food supply chains has exposed persistent gaps in fraud detection, particularly for high-value products such as those with PDO (Protected Designation of Origin) and PGI (Protected Geographical Ιndication) Certification. This study investigates the perceptions, attitudes, and experiences of frontline inspectors in Greece to assess current challenges and opportunities for strengthening official food fraud controls. Data were collected through a structured questionnaire, validated by experts and administered nationwide, involving 122 participants representing all major national food inspection authorities. Statistical analysis revealed significant institutional differences in perceptions of fraud prevalence, with mislabeling of origin, misleading organic claims, ingredient substitution, and documentation irregularities identified as the most common fraudulent practices. Olive oil, honey, meat, and dairy emerged as the most vulnerable product categories. Inspectors reported relying primarily on consumer complaints and institutional databases as key tools for identifying fraud risks. Food fraud was perceived to contribute strongly to losses in consumer trust in food safety and product authenticity, as well as to the erosion of sustainable production models that depend on transparency, fair competition, and responsible resource use. Overall, the findings highlight detection gaps, uneven resources across authorities, and the need for improved coordination and capacity-building to support more efficient, transparent, and sustainability-oriented food fraud control in Greece. Full article

Emerging technologies are transforming Facilities Management (FM), enabling more efficient and accurate building inspections and maintenance. Mixed Reality (MR), which integrates virtual content into real-world environments, has shown potential for improving operational performance and technician training. This study presents the development and evaluation of an MR-assisted system designed to support facility operations in academic buildings. The system was tested across three case scenarios, namely plumbing, lighting, and fire sprinkler systems, using Microsoft HoloLens^®. A mixed-methods approach combined a post-use questionnaire and semi-structured interviews with twelve FM professionals, including technicians, inspectors, and managers. Results indicated that 66.67% of participants found the MR interface highly effective in visualizing systems and guiding maintenance steps. 83.33% agreed that checklist integration enhanced accuracy and learning. Technical challenges, including model drift, latency, and occasional software crashes, were also observed. Overall, the study confirms the feasibility of MR for FM training and inspection, offering a foundation for broader implementation and future research. The findings provide valuable insights into how MR-based visualization and interaction tools can enhance efficiency, learning, and communication in facility operations. Full article

This paper mainly studies tax inspection decision-making technology, aiming to improve the accuracy and robustness of target recognition, state estimation, and autonomous decision making in complex environments by constructing an application that integrates visual, radar, and inertial navigation information. Tax inspection is a universally complex phenomenon, but little is known about the use of innovative technology to arm tax auditors with tools in monitoring it. Thus, based on the legitimacy theory, there is an agreement between taxpayers and the tax authorities regarding adequate compliance with tax legislation. The use of systemic controls by tax authorities is essential to track stakeholders’ contracts and ensure the upholding of this mandate. The case study is exploratory, using participant observation, and interventionist approach to a tax auditing. The results indicated that partnership between experienced tax auditors and IT tax auditors offered several tangible benefits to the in-house development and monitoring of an innovative application. It also indicates that OCR supports a data lake for inspectors in which stored information is available on standby during inspection. Furthermore, auditors’ use of mobile applications programmed with intelligent perception and tracking resources instead of using searches on mainframes streamlined the inspection process. The integration of professional skepticism, empathy among users, and technological innovation created a surge in independence among tax auditors and ensured focus. This paper’s contribution lies in the discussion of the enhancement of tax inspection through target recognition, drawing on legitimacy theory to rethink the relationship between taxpayers and tax authorities regarding adequate compliance with tax legislation, and presenting an exploratory case study using a participant observation, interventionist approach focused on a tax auditor. The implications of this study for policy makers, auditors, and academics are only the peak of the iceberg, as innovation in public administration presupposes efficiency. As a suggestion for future dimensions of research, we recommend the infusion of AI into these tools for further efficacy and effectiveness to mitigate fraud in the undue appropriation of taxes and undue competition. Full article

Across their wide geographic range (Neotropics, and as invasives in New Guinea and Florida), Nasutitermes corniger (conehead termites) live primarily above the ground surface. They build arboreal nests and foraging tunnels, or epigeal nests and tunnels on the ground surface. There are brief reports of below-ground portions of N. corniger nests and foraging tunnels as rare occurrences of structures extending underground. The entirely and partially underground nests and foraging tunnels described in this paper are distinct and novel from previous observations. They are based on multiple discoveries in areas of Broward County, Florida, where invasive conehead termite activity below ground is common. This paper expands understanding of habitat options for this ecologically agile, adaptable, economically important species. It also serves to alert inspectors in invasive termite eradication programs or pest management situations to explore cryptic locations where nests of all sizes may hide. Effective approaches for treating underground N. corniger activities are described. Full article

Phalaenopsis orchids are one of Taiwan’s key floral export products, and maintaining consistent quality is crucial for international competitiveness. To improve production efficiency, many orchid farms outsource the early flask seedling stage to contract growers, who raise the plants to the 2.5-inch potted seedling stage before returning them for further greenhouse cultivation. Traditionally, the quality of these outsourced seedlings is evaluated manually by inspectors who visually detect defects and assign quality grades based on experience, a process that is time-consuming and subjective. This study introduces a smart image-based deep learning system for automatic quality grading of Phalaenopsis potted seedlings, combining computer vision, deep learning, and machine learning techniques to replace manual inspection. The system uses YOLOv8 and YOLOv10 models for defect and root detection, along with SVM and Random Forest classifiers for defect counting and grading. It employs a dual-view imaging approach, utilizing top-view RGB-D images to capture spatial leaf structures and multi-angle side-view RGB images to assess leaf and root conditions. Two grading strategies are developed: a three-stage hierarchical method that offers interpretable diagnostic results and a direct grading method for fast, end-to-end quality prediction. Performance comparisons and ablation studies show that using RGB-D top-view images and optimal viewing-angle combinations significantly improve grading accuracy. The system achieves F1-scores of 84.44% (three-stage) and 90.44% (direct), demonstrating high reliability and strong potential for automated quality assessment and export inspection in the orchid industry. Full article

Timely and accurate inspection of concrete bridges is critical to ensuring structural integrity and public safety. Traditional visual inspections conducted by human inspectors are labour-intensive, inconsistent, and often limited in their ability to access all structural components, particularly in hazardous or inaccessible areas. Image-based inspection techniques have emerged as a safer and more efficient alternative, and recent advancements in deep learning have significantly enhanced their diagnostic capabilities. This systematic review critically evaluates 77 studies that applied deep learning approaches to the detection and classification of surface defects in concrete bridges using 2D images. Relevant publications were retrieved from major scientific databases, screened for eligibility, and analyzed in terms of model type, training strategies, and evaluation metrics. The reviewed works encompass a wide spectrum of algorithms—spanning classification, object detection, and image segmentation models—highlighting their architectural features, strengths, and trade-offs in terms of accuracy, computational complexity, and real-time applicability. Key findings reveal that transfer learning, data augmentation, and careful dataset composition are pivotal in improving model performance. Moreover, the review identifies emerging research trajectories, such as integrating deep learning with Building Information Modeling (BIM), leveraging edge computing for real-time monitoring, and developing rich annotated datasets to enhance model generalizability. By mapping the current state of knowledge and outlining future research directions, this study provides a foundational reference for researchers and practitioners aiming to deploy deep learning technologies in bridge inspection and infrastructure monitoring. Full article