Search Results (6,532)

Multi-class object detectors often suffer from the class imbalance issue, where substantial model performance discrepancies exist between classes. Generative adversarial networks (GANs), an emerging deep learning research topic, are able to learn from existing data distributions and generate similar synthetic data, which might serve as valid training data for improving object detectors. The current study investigated the utility of lightweight unconditional GAN in addressing weak object detector class performance by incorporating synthetic data into real data for model retraining, under an agricultural context. AriAplBud, a multi-growth stage aerial apple flower bud dataset was deployed in the study. A baseline YOLO11n detector was first developed based on training, validation, and test datasets derived from AriAplBud. Six FastGAN models were developed based on dedicated subsets of the same YOLO training and validation datasets for different apple flower bud growth stages. Positive sample rates and average instance number per image of synthetic data generated by each of the FastGAN models were investigated based on 1000 synthetic images and the baseline detector at various confidence thresholds. In total, 13 new YOLO11n detectors were retrained specifically for the two weak growth stages, tip and half-inch green, by including synthetic data in training datasets to increase total instance number to 1000, 2000, 4000, and 8000, respectively, pseudo-labeled by the baseline detector. FastGAN showed its resilience in successfully generating positive samples, despite apple flower bud instances being generally small and randomly distributed in the images. Positive sample rates of the synthetic datasets were negatively correlated with the detector confidence thresholds as expected, which ranged from 0 to 1. Higher overall positive sample rates were observed for the growth stages with higher detector performance. The synthetic images generally contained fewer detector-detectable instances per image than the corresponding real training images. The best achieved YOLO11n AP improvements in the retrained detectors for tip and half-inch green were 30.13% and 14.02% respectively, while the best achieved YOLO11n mAP improvement was 2.83%. However, the relationship between synthetic training instance quantity and detector class performances had yet to be determined. GAN was concluded to be beneficial in retraining object detectors and improving their performances. Further studies are still in need to investigate the influence of synthetic training data quantity and quality on retrained object detector performance. Full article

Background: The regionalisation of perinatal care emphasises the importance of transferring high-risk pregnancies “in utero” to minimise risks; yet, neonatal inter-facility transport remains necessary. Neonatal Emergency Transport Services (NETSs) play a crucial role in reducing transportation risks, especially for very preterm infants. Italy’s healthcare system, which is decentralised in nature, leads to variations in NETS organisation and resources across the country, resulting in disparities in access and quality of care. Methods: A questionnaire regarding neonatal transfer practices and NETS activity was sent to the 55 NETSs operating in twenty Italian regions. Demographic data were obtained from the Italian National Statistical Institute (ISTAT). Results: Survey Overview. A 2022 national survey by the Italian Society of Neonatology aimed to assess the status of NETS in Italy, achieving a 100% response rate from the 55 NETS. The 2022 data highlighted the transport of 6494 neonatal, of which 92% were primary transports (transferred to higher-level care) and 553 were back-transports (returning stabilised neonates to lower-level care). Subgroup analysis identified 544 transports of neonates born at 30–34 weeks of gestation and 305 transports of neonates born at under 30 weeks of gestation. This was shown to have regional variability. NETS coverage: 18 regions have full NETS coverage. Sicily offers partial coverage. Sardinia, despite an approved plan, lacks an operational NETS. Operational models: all NETS provide a 24/7 service; 50 NETSs rely on an on-call basis using NICU staff for transport. Only five NETS have dedicated teams exclusively for neonatal transport. This decentralisation results in heterogeneity in service availability, access, and quality. Conclusions: This study highlights that although differences still exist, the NETS in Italy is adequately structured and effective. The presence of NETS operating with limited transport volumes puts a strain on maintaining skilled staff and cost-effective operations. Regional disparities: inequities in NETS access (e.g., in Sicily and Sardinia regions) underline the need to improve regional collaboration. While Italy has made progress in organising NETS, regional discrepancies persist in access and service quality, reflecting the decentralised nature of its healthcare system. Full article

Background/Objectives: Laryngeal squamous cell carcinoma (LSCC) is one of the most prevalent and challenging malignancies of the head and neck. Clinical staging (cTNM) plays a pivotal role in therapeutic decision-making. However, current imaging modalities often fall short, resulting in discrepancies between cTNM and pathological staging (pTNM). This systematic review aimed to critically evaluate the existing literature on the concordance between clinical and pathological staging of LSCC, quantifying staging inaccuracies and highlighting the prevalence of both under- and overstaging at diagnosis. Methods: A comprehensive search of the English-language literature was conducted across multiple databases, including PubMed, Embase, Scopus, the Cochrane Library, and Web of Science. Eligibility was limited to retrospective case series and observational studies reporting sufficient data to directly correlate individual patients’ cTNM and pTNM classifications. Results: Thirty-one studies comprising 7939 patients met the inclusion criteria. The overall concordance rate between cT and pT was approximately 86.43%. The concordance rates between cT and pT were 82.41%, 82.03%, 78.14%, and 89.64% for cT1, cT2, cT3, and cT4, respectively. Most discordant cases in cT2 and cT3 involved understaging at clinical diagnosis. Conclusions: The limited accuracy of clinical staging in reflecting the true extent of disease remains a critical challenge in the management of LSCC. The inability of current imaging techniques to reliably detect the subtle invasion of key anatomical structures contributes to both under- and overstaging, with significant clinical implications. For patients undergoing non-surgical organ-preservation strategies, these inaccuracies may adversely affect oncologic outcomes. Full article

Medical report generation has made significant progress in recent years. However, generated reports still suffer from issues such as poor readability, incomplete and inaccurate descriptions of lesions, and challenges in capturing fine-grained abnormalities. The primary obstacles include low image resolution, poor contrast, and substantial cross-modal discrepancies between visual and textual features. To address these challenges, we propose an Anomaly-Driven Cross-Modal Contrastive Network (ADCNet), which aims to enhance the quality and accuracy of medical report generation through effective cross-modal feature fusion and alignment. First, we design an anomaly-aware cross-modal feature fusion (ACFF) module that introduces an anomaly embedding vector to guide the extraction and generation of anomaly-related features from visual representations. This process enhances the capability of visual features to capture lesion-related abnormalities and improves the performance of feature fusion. Second, we propose a fine-grained regional feature alignment (FRFA) module, which dynamically filters visual and textual features to suppress irrelevant information and background noise. This module computes cross-modal relevance to align fine-grained regional features, ensuring improved semantic consistency between images and generated reports. The experimental results from the IU X-Ray and MIMIC-CXR datasets demonstrate that the proposed ADCNet method significantly outperforms existing approaches. Specifically, ADCNet achieves notable improvements in natural language generation metrics, as well as the accuracy, completeness, and fluency of medical report generation. Full article

This article provides an in-depth analysis of blockchain research in the energy sector, focusing on projects funded by the U.S. Department of Energy (DOE) and comparing them with industry-funded initiatives. A total of 110 funded activities within the U.S. power industry were successfully tracked and mapped into a newly developed categorization framework. This framework is designed to help research agencies to systematically understand their funded portfolio. Such characterization is expected to help them make effective investments, identify research gaps, measure impact, and advance technological progress to meet national goals. In line with this need, the proposed framework proposes a 2-D categorization matrix to systematically classify blockchain efforts within the energy sector.Under the proposed framework, the Energy System Domain serves as the primary classification dimension, categorizing use cases into 30 distinct applications. The second dimension, Blockchain Properties, captures the specific needs and functionalities provided by Blockchain technology. The aim was to capture blockchain’s applicability and functionality: where and why blockchain? Principles behind the selection of the viewpoint dimensions were carefully defined based on consensus obtained through the Blockchain for Optimized Security and Energy Management (BLOSEM) project. The mapped results show that activities within the Grid Automation, Coordination, and Control (31.8%), Marketplaces and Trading (25.5%), Foundational Blockchain Research (19.1%), and Supply Chain Management (17.3%) domains have been actively pursued to date. The three leading specific use case applications were identified as Transactive Energy Management for Marketplaces and Trading, Asset Management for Supply Chain Management, and Fundamental Blockchain for Foundational Blockchain Research. The Marketplaces and Trading and Retail Services Enablement domains stood out as being favored by industry by a factor greater than 2 (2.3 and 2.6, respectively), yet there seemed to be little to zero investment from DOE. Approximately 76% of the total projects prioritized Immutability, Identity Management, and Decentralization and/or Disintermediation compared to Asset Digitization and/or Tokenization, Automation, and Privacy and/or Anonymity. The greatest discrepancies between DOE and industry were in Asset Digitization and/or Tokenization and Automation. The industry efforts (36% in Asset Digitization/Tokenization and 22% in Automation) was 14 times and 2.4 times, respectively, more intensive than the DOE-sponsored efforts, indicating a significant discrepancy in industry versus government priorities. Overall, quantifying DOE-sponsored projects and industry activities through mapping provides clarity on portfolio investments and opportunities for future research. Full article

Abstract: This study addresses the challenges of integrating heterogeneous environmental geospatial data by proposing a framework based on ontology-based data access (OBDA). Geospatial data are important for decision-making in various domains, such as environmental monitoring, disaster management, and urban development. Data integration is a common challenge within these domains due to data heterogeneity and semantic discrepancies. The proposed framework uses semantic web technologies to enhance data interoperability, accessibility, and usability. Several practical examples were demonstrated to validate its effectiveness. These examples were based in Lake Mjøsa, Norway, addressing both spatial and non-spatial scenarios to test the framework’s potential. By extending the GeoSPARQL ontology, the framework supports SPARQL queries to retrieve information based on user requirements. A web-based SPARQL Query Interface (SQI) was developed to execute queries and display the retrieved data in tabular and visual format. Utilizing free and open-source software (FOSS), the framework is easily replicable for stakeholders and researchers. Despite some limitations, the study concludes that the framework is able to enhance cross-domain data integration and semantic querying in various informed decision-making scenarios. Full article

Uniform design is a powerful and robust experimental methodology that is particularly advantageous for multidimensional numerical integration and high-level experiments. As its applications expand across diverse disciplines, the theoretical foundation of uniform design continues to evolve. In real-world scenarios, experimental factors are often subject to one or more linear constraints, which pose challenges in constructing efficient designs within constrained high-dimensional experimental spaces. These challenges typically require sophisticated algorithms, which may compromise uniformity and robustness. Addressing these constraints is critical for reducing costs, improving model accuracy, and identifying global optima in optimization problems. However, existing research primarily focuses on unconstrained or minimally constrained hypercubes, leaving a gap in constructing designs tailored to arbitrary linear constraints. This study bridges this gap by extending the inverse Rosenblatt transformation framework to develop innovative methods for constructing uniform designs over arbitrary hyperplanes and hyperspheres within unit hypercubes. Explicit construction formulas for these constrained domains are derived, offering simplified calculations for practitioners and providing a practical solution applicable to a wide range of experimental scenarios. Numerical simulations demonstrate the feasibility and effectiveness of these methods, setting a new benchmark for uniform design in constrained experimental regions. Full article

Atrial Fibrillation can be considered a geriatric syndrome for its prevalence and incidence, its impact on patients’ quality of life, and Health Systems’ economy. The European Society of Cardiology 2024 guidelines introduce a recommendation for maintaining vitamin K antagonist therapy over switching to direct oral anticoagulants in clinically stable elderly patients with atrial fibrillation. This article explores the implications of this indication for the geriatric clinical context. The focus will also be devoted to the need for the stratification of older patients with atrial fibrillation, making an appropriate distinction between frailty and disability. Full article

This study uses eye-tracking technology (ETT) to investigate discrepancies between seafarers’ perceived and actual performance during simulated maritime operations. The primary objective is to explore how misperceptions regarding the use of navigational tools—such as visual observation, radar, and ECDIS—may contribute to discrepancies in situational awareness, which is critical for safe navigation. By comparing participants’ self-reported perceptions with objective data recorded by ETT, the study highlights cognitive biases that influence navigational decision-making. Data were collected from a simulation scenario involving 32 seafarers with varying levels of maritime experience. The results reveal that participants tend to overestimate their reliance on visual observation and ECDIS, while underestimating their use of radar. These discrepancies may affect decision-making processes and could contribute to an inaccurate perception of situational awareness, although further research is needed to fully establish their direct impact on actual navigational performance. Additionally, the application of ETT identifies differences in the navigational strategies between more and less experienced seafarers, offering insights that could inform the development of training programs aimed at improving situational awareness. Statistical analyses, including Analysis of Variance (ANOVA) and Kruskal–Wallis tests, were conducted to assess the influence of demographic factors on performance. These findings suggest that ETT can be a valuable tool for identifying perceptual biases, potentially improving decision-making and enhancing training for real-world navigational tasks. Full article

Background: Arterial mechanics are crucial to cardiovascular functionality. The pressure–strain elastic modulus often delineates mechanical properties. Emerging methods use non-linear continuum mechanics and non-convex minimization to identify tissue-specific parameters in vivo. Reliability of these methods, particularly their accuracy in representing the in vivo stress state, is a significant concern. This study aims to compare the predicted stress state and the collagen-attributed load-bearing fraction with the stress state from in silico experiments. Methods: Our team has evaluated an in vivo parameter identification method through in silico experiments involving finite element models and demonstrated good agreement with the parameters of a healthy abdominal aorta. Results: The findings suggest that the circumferential stress state is well represented for an abdominal aorta with a low transmural stress gradient. Larger discrepancies are observed in the axial direction. The agreement deteriorates in both directions with an increasing transmural stress gradient, attributed to the membrane model’s inability to capture transmural gradients. The collagen-attributed load-bearing fraction is well predicted, particularly in the circumferential direction. Conclusions: These findings underscore the importance of investigating both isotropic and anisotropic aspects of the vessel wall. This evaluation advances the parameter identification method towards clinical application as a potential tool for assessing arterial mechanics. Full article

In the intelligent transportation field, the Internet of Things (IoT) is commonly applied using 3D object detection as a crucial part of Vehicle-to-Everything (V2X) cooperative perception. However, challenges arise from discrepancies in sensor configurations between vehicles and infrastructure, leading to variations in the scale and heterogeneity of point clouds. To address the performance differences caused by the generalization problem of 3D object detection models with heterogeneous LiDAR point clouds, we propose the Dual-Channel Generalization Neural Network (DCGNN), which incorporates a novel data-level downsampling and calibration module along with a cross-perspective Squeeze-and-Excitation attention mechanism for improved feature fusion. Experimental results using the DAIR-V2X dataset indicate that DCGNN outperforms detectors trained on single datasets, demonstrating significant improvements over selected baseline models. Full article

Incorrect sensor readings can cause serious problems in Wireless Sensor Networks (WSNs), potentially disrupting the operation of the entire system. As shown in the literature, they can arise from various reasons; therefore, addressing this issue has been a significant challenge for the scientific community over the past few decades. In this paper, we examine the applicability of seven distributed consensus gossip-based algorithms for sensor fusion (namely, the Randomized Gossip algorithm, the Geographic Gossip algorithm, three initial configurations of the Broadcast Gossip algorithm, the Push-Sum protocol, and the Push-Pull protocol) to compensate for incorrect data in WSNs. More specifically, we consider a scenario where the sensor-measured data (measured by a set of independent sensor nodes) are skewed due to Gaussian noise with a various standard deviation σ, resulting in discrepancies between the measured values and the true value of observed physical quantities. Subsequently, the aforementioned algorithms are employed to mitigate this skewness in order to improve the accuracy of the measured data. In this paper, WSNs are modeled as random geometric graphs with various connectivity, and the performance of the algorithms is evaluated using two metrics (specifically, the mean square error (MSE) and the number of sent messages required for an algorithm to be completed). Based on the presented results, it is identified that all the examined algorithms can significantly suppress incorrect sensor readings (MSE without sensor fusion = −0.42 dB if σ = 1, and MSE without sensor fusion = 14.05 dB if σ = 5), and the best performance is achieved by PS in dense graphs and by GG in sparse graphs (both algorithms achieve the maximum precision MSE = −24.87 dB if σ = 1 and MSE = −21.02 dB if σ = 5). Additionally, the performance of the analyzed distributed consensus gossip algorithms is compared to the best deterministic consensus algorithm applied for the same purpose. Full article

Actinobacillus pleuropneumoniae is a major swine pathogen, classified into 19 serotypes based on capsular polysaccharide (CPS) loci. This study aimed to improve the diagnostic method to differentiate between serotypes 9 and 11, which are challenging to distinguish using conventional serological and molecular methods. A novel qPCR assay based on locked nucleic acid (LNA) probes was developed and validated using a collection of reference strains representing all known 19 serotypes. The assay demonstrated specificity in detecting the nucleotide variation characteristic of the serotype 9 reference strain. However, the analysis of a clinical isolate collection identified discrepancies between LNA-qPCR and serological results, prompting further investigation of the cps and O-Ag loci. Subsequent nanopore sequencing and whole-genome sequencing of a collection of 31 European clinical isolates, previously identified as serotype 9, 11, or undifferentiated 9/11, revealed significant genetic variations in the cps and O-Ag loci. Ten isolates had a cpsF sequence identical to that of the serotype 11 reference strain, while six isolates had single-nucleotide polymorphisms that were unlikely to cause significant coding changes. In contrast, 15 isolates had interruptions in the cpsF gene, distinct from that found in the serotype 9 reference strain, potentially leading to a serotype 9 CPS structure. In the O-Ag loci, differences between serotypes 9 and 11 were minimal, although some isolates had mutations potentially affecting O-Ag expression. Overall, these findings suggest that multiple genetic events can lead to the formation of a serotype 9 CPS structure, hindering the development of a single qPCR assay capable of detecting all cpsF gene mutations. Our results suggest that, currently, a comprehensive analysis of the cpsF gene is necessary to accurately determine whether the capsule of an isolate corresponds to serotype 9 or 11. Although such analyses are feasible with the advent of third-generation sequencing technologies, their accessibility, cost, and time to result limit their use in routine diagnostic applications. Under these circumstances, the designation of the hybrid serovar 9/11 remains a valid approach. Full article

As wildfires become more frequent and severe in the face of global environmental change, it becomes crucial not only to assess, prevent, and suppress them but also to manage the aftermath effectively. Given the temporal interconnections between these issues, we explored the concept of the “wildfire science loop”—a framework categorizing wildfire research into three stages: “before”, “during”, and “after” wildfires. Based on this partition, we performed a systematic review by linking particular topics and keywords to each stage, aiming to describe each one and quantify the volume of published research. The results from our review identified a substantial imbalance in the wildfire research landscape, with the post-fire stage being markedly underrepresented. Research focusing on the “after” stage is 1.5 times (or 46%) less prevalent than that on the “before” stage and 1.8 (or 77%) less than that on the “during” stage. This discrepancy is likely driven by a historical emphasis on prevention and suppression due to immediate societal needs. Aiming to address and overcome this imbalance, we present our perspectives regarding a strategic agenda to enhance our understanding of post-fire processes and outcomes, emphasizing the socioecological impacts of wildfires and the management of post-fire recovery in a multi-level and transdisciplinary approach. These proposals advocate integrating knowledge-driven research on burn severity and ecosystem mitigation/recovery with practical, application-driven management strategies and strategic policy development. This framework also supports a comprehensive agenda that spans short-term emergency responses to long-term adaptive management, ensuring that post-fire landscapes are better understood, managed, and restored. We emphasize the critical importance of the “after-fire” stage in breaking negative planning cycles, enhancing management practices, and implementing nature-based solutions with a vision of “building back better”. Strengthening a comprehensive and balanced research agenda focused on the “after-fire” stage will also enhance our ability to close the loop of socioecological processes involved in adaptive wildfire management and improve the alignment with international agendas such as the UN’s Decade on Ecosystem Restoration and the EU’s Nature Restoration Law. By addressing this research imbalance, we can significantly improve our ability to restore ecosystems, enhance post-fire resilience, and develop adaptive wildfire management strategies that are better suited to the challenges of a rapidly changing world. Full article

Anaerobic digestion (AD) is a promising and yet a complex waste-to-energy technology. To optimize such a process, precise modeling is essential. Developing complex, mechanistically inspired AD models can result in an overwhelming number of parameters that require calibration. This study presents a novel approach that considers the role of trace metals (Ca, K, Mg, Na, Co, Cr, Cu, Fe, Ni, Pb, and Zn) in the modeling, numerical simulation, and optimization of the AD process in a batch bioreactor. In this context, BioModel is enhanced by incorporating the influence of metal activities on chemical, biochemical, and physicochemical processes. Trace metal-related parameters are also included in the calibration of all model parameters. The model’s reliability is rigorously validated by comparing simulation results with experimental data. The study reveals that perturbations of 5% in model parameter values significantly increase the discrepancy between simulated and experimental results up to threefold. Additionally, the study highlights how precise optimization of metal additives can enhance both the quantity and quality of biogas production. The optimal concentrations of trace metals increased biogas and CH₄ production by 5.4% and 13.5%, respectively, while H₂, H₂S, and NH₃ decreased by 28.2%, 43.6%, and 42.5%, respectively. Full article