Search Results (57)

The performance of remote sensing object detectors often degrades severely when deployed in new operational environments due to covariate shift in the data distribution. Existing evaluation paradigms, which primarily rely on aggregate performance metrics such as mAP, generally lack the analytical depth to provide insights into the mechanisms behind such generalization failures. To fill this critical gap, we propose the GRADE (Generalization Robustness Assessment via Distributional Evaluation) framework, a multi-dimensional, systematic methodology for assessing model robustness. The framework quantifies shifts in background context and object-centric features through a hierarchical analysis of distributional divergence, utilizing Scene-level Fréchet Inception Distance (FID) and Instance-level FID, respectively. These divergence measures are systematically integrated with a standardized performance decay metric to form a unified, adaptively weighted Generalization Score (GS). This composite score serves not only as an evaluation tool but also as a powerful analytical tool, enabling the fine-grained attribution of performance loss to specific sources of domain shift—whether originating from scene variations or anomalies in object appearance. Compared to conventional single-dimensional evaluation methods, the GRADE framework offers enhanced interpretability, a standardized evaluation protocol, and reliable cross-model comparability, establishing a principled theoretical foundation for cross-domain generalization assessment. Extensive empirical validation on six mainstream remote sensing benchmark datasets and multiple state-of-the-art detection models demonstrates that the model rankings produced by the GRADE framework exhibit high fidelity to real-world performance, thereby effectively quantifying and explaining the cross-domain generalization penalty. Full article

Background and Objectives: Large language models (LLMs) offer promising applications in healthcare, including drafting referral letters. However, access to LLMs specifically designed for medical practice remains limited. While ChatGPT is widely available, its ability to generate comprehensive and clinically appropriate neurology referral letters remains uncertain. This study aimed to systematically evaluate the completeness and quality of neurology referral letters generated by ChatGPT for standardized clinical scenarios. Materials and Methods: Five standardized clinical scenarios representing common neurological complaints encountered in family medicine settings (headache, memory problems, stroke/TIA, tremor, radiculopathy) were used. Using a consistent prompt, ChatGPT (GPT-4o, 2025 release) generated 10 referral letters per scenario (50 letters in total). A dual board-certified neurologist and family physician scored the letters using a 30-point rubric across multiple domains: completeness (demographics, chief complaint, history of present illness, physical exam findings, management, and consultation questions) and quality (language level, structure, and letter length). Descriptive statistics and inferential analyses (ANOVA and Kruskal–Wallis tests) were applied to assess performance across scenarios. Results: The mean total score was 25.76/30 (95% CI: 24.85–26.67). Completeness averaged 87%, while language and structure consistently scored above 90%. Content gaps appeared in 36 out of 50 letters (72%), mainly in the history of present illness and physical examination sections. Variability was observed across letters, though not statistically significant between scenarios (ANOVA: F = 1.14, p = 0.352; Kruskal–Wallis: H = 3.52, p = 0.475). Conclusions: ChatGPT produced neurology referral letters of high linguistic quality but variable completeness, especially for clinically complex content. The variability pattern among letters reflected model inconsistency rather than case type. The reliance on a single rater and use of a non-validated rubric represent limitations. Future studies should include multiple raters, inter-rater reliability testing, and validated scoring frameworks. Ultimately, access to tailored LLMs exclusively trained for medical documentation could improve outcomes while safeguarding patient privacy. Full article

Event cameras provide microsecond temporal resolution, high dynamic range, and low latency by asynchronously capturing per-pixel luminance changes, thereby introducing a novel sensing paradigm. These advantages render them well-suited for high-speed applications such as autonomous vehicles and dynamic environments. Nevertheless, the sparsity of event data and the absence of dense annotations are significant obstacles to supervised learning for motion segmentation from event streams. Domain adaptation is also challenging due to the considerable domain shift in intensity images. To address these challenges, we propose a two-phase cross-modality adaptation framework that translates motion segmentation knowledge from labeled RGB-flow data to unlabeled event streams. A dual-branch encoder extracts modality-specific motion and appearance features from RGB and optical flow in the source domain. Using reconstruction networks, event voxel grids are converted into pseudo-image and pseudo-flow modalities in the target domain. These modalities are subsequently re-encoded using frozen RGB-trained encoders. Multi-level consistency losses are implemented on features, predictions, and outputs to enforce domain alignment. Our design enables the model to acquire domain-invariant, semantically rich features through the use of shallow architectures, thereby reducing training costs and facilitating real-time inference with a lightweight prediction path. The proposed architecture, alongside the utilized hybrid loss function, effectively bridges the domain and modality gap. We evaluate our method on two challenging benchmarks: EVIMO2, which incorporates real-world dynamics, high-speed motion, illumination variation, and multiple independently moving objects; and MOD++, which features complex object dynamics, collisions, and dense 1kHz supervision in synthetic scenes. The proposed UDA framework achieves 83.1% and 79.4% accuracy on EVIMO2 and MOD++, respectively, outperforming existing state-of-the-art approaches, such as EV-Transfer and SHOT, by up to 3.6%. Additionally, it is lighter and faster and also delivers enhanced mIoU and F1 Score. Full article

Nicotinamide adenine dinucleotide (NAD⁺) is an essential metabolite, and abnormal NAD⁺ metabolism has been linked to numerous human diseases. The nicotinamide mononucleotide adenylyl transferases (NMNATs) catalyze NAD⁺ production through both de novo and salvage pathways. NMNATs are multi-functional enzymes with NAD⁺ synthesis activity and chaperone activity. Interestingly, NMNATs are involved in neuroprotection, and whether these neuroprotective effects require NAD⁺ synthesis activity appears to vary depending on the context. Nevertheless, NMNATs can modulate cellular processes primarily through supporting NAD⁺ homeostasis. In this review, we discuss the roles of NMNATs in NAD⁺ homeostasis, their functional domains, and how their subcellular localizations influence the compartmentalized NAD⁺ pools. We present an integrative framework to help understand the diverse impacts of NMNATs in human diseases, with a focus on neurological disorders caused by different insults. To address knowledge gaps, we integrate the regulation of NMNATs in both human and model organisms. We also discuss the current understanding and limitations of NMNAT activators and inhibitors to help evaluate their translational significance as therapeutic targets for NAD⁺ modulation. Full article

Background: Surgical resection remains central to the curative treatment of locally advanced gastric cancer (GC), yet global variability persists in defining resectability, particularly in complex scenarios such as multivisceral invasion, positive peritoneal cytology (CY1), or oligometastatic disease. The Intercontinental Criteria of Resectability for Gastric Cancer (ICRGC) project was developed to address this gap by combining expert surgical input with artificial intelligence (AI)-based reasoning. Methods: A two-stage prospective survey was conducted during the 2024 European Gastric Cancer Association (EGCA) meeting. Fifty-eight surgical oncologists completed a 36-item questionnaire on resectability, strategy, and quality metrics. Subsequently, they reviewed AI-generated responses based on current clinical guidelines and completed a second round. Concordance between human and AI responses was classified as full, partial, or discordant, and changes in surgeon opinions were statistically analyzed. Results: Substantial agreement was observed in evidence-based domains. Seventy-nine percent of surgeons agreed with AI on distinguishing technical from oncological resectability. In cT4b cases, 61% supported restricting multivisceral resection to high-volume centers. Similar alignment was found in CY1 (54%) and N3 nodal disease (63%). Partial concordance appeared in areas requiring individualized judgment, such as peritonectomy or bulky-N disease. After AI exposure, surgeon responses shifted toward guideline-consistent decisions, including increased support for cytoreductive surgery only when CC0/1 was achievable and stricter classification of R2 resections as unresectable. Following AI exposure, 27.1% of surgeons changed at least one answer in alignment with AI recommendations, with statistically significant shifts observed in items related to surgical margin definition (p = 0.015), anatomical resection criteria (p < 0.05), and hospital stay benchmarks (p = 0.031). Conclusions: The ICRGC study demonstrates that AI-driven consensus modeling can replicate expert reasoning in complex surgical oncology and serve as a catalyst for harmonizing global practice. These findings suggest that AI-supported consensus modeling may complement expert surgical reasoning and promote greater consistency in decision-making, particularly in controversial or ambiguous cases. Full article

An electric field applied to the Bernal-stacked bilayer graphene opens an energy gap; its reversal in some regions creates domain walls and leads to the appearance of one-dimensional chiral gapless states localized at the walls. Here, we investigate the energy structure of bilayer graphene with superlattice potential defined by an external electric field. The calculations are performed within an atomistic π-electron tight-binding approximation. We study one-dimensional and two-dimensional superlattices formed by arrays of electric-field walls in the zigzag and armchair directions and investigate different field polarizations. Chiral gapless states discretize due to the superlattice potential and transform into minibands in the energy gap. As the main result, we show that the minibands can cross at the Fermi level for some field polarizations. This leads to a new kind of two-dimensional gapless states of topological character that form Dirac-like cones at the crossing points. This also has application potential: changing the field polarization can close the energy gap and change the character of the superlattice from semiconducting to metallic. Full article

As the field of prosthetic engineering advances, questions around whether these new prosthetics hold the ability to outperform biological limbs become more relevant. To further clarify such a debate and discover gaps in our understanding, a narrative review of the present literature on this topic is needed. The purpose of the present review was to explore whether prosthetic legs grant amputee athletes an unfair advantage over traditional athletes by reviewing 11 articles pertaining to the running performance and potential among athletes with transtibial amputations. The findings of the included articles were categorized into three domains of running performance, chosen due to their precedence in the current literature: propulsion forward, limb repositioning, and physiological limitations. Our review indicated that the present literature alludes to transtibial amputee runners having a potential competitive advantage over able-bodied runners, with the caveat that some performance domains appear not to be differentiated. The present findings offer a unique perspective on understanding the impact of prosthetics on the running performance among para-athletes and suggest future research directions. As the depth of this area of literature increases, future systematic reviews and meta-analyses may be able to answer with greater certainty whether transtibial prosthetics allow for supra-biological running performances. Full article

Background/Objectives: Cognitive decline and Alzheimer’s disease (AD) pose a major challenge for the ageing population, with impaired synaptic plasticity playing a central role in their pathophysiology. This article explores the hypothesis that cortico–cortical paired associative stimulation (ccPAS), a non-invasive brain stimulation technique, can restore synaptic function by targeting impaired spike-timing-dependent plasticity (STDP), a key mechanism disrupted in AD. Methods: We reviewed existing studies investigating the effects of ccPAS on neuroplasticity in both ageing and AD populations. Results: Findings suggest age-specific effects, with ccPAS improving motor performance in young adults but showing limited efficacy in older adults, likely due to age-related declines in synaptic plasticity and cortical excitability. In AD, ccPAS studies reveal significant impairments in long-term potentiation (LTP)-like plasticity, while long-term depression (LTD)-like mechanisms appear relatively preserved, emphasising the need for targeted neuromodulation approaches. Conclusions: Despite promising preliminary results, evidence remains limited and largely focused on motor function, with the impact of ccPAS on cognitive domains still underexplored. To bridge this gap, future research should focus on larger and more diverse cohorts to optimise ccPAS protocols for ageing and AD populations and investigate its potential for enhancing cognitive function. By refining stimulation parameters and integrating neuroimageing-based personalisation strategies, ccPAS may represent a novel therapeutic approach for mitigating neuroplasticity deficits in ageing and neurodegenerative conditions. Full article

The food and agriculture sector is a cornerstone of critical infrastructure (CI), underpinning global food security, public health, and economic stability. However, the increasing digitalization and connectivity of operational technologies (OTs) in this sector expose it to significant cybersecurity risks. Blockchain technology (BT) has emerged as a transformative solution for addressing these challenges by enhancing network security, traceability, and system resilience. This study presents a comprehensive review of BT applications in OT security for food and agriculture CI, employing bibliometric and content analysis methods. A total of 124 relevant articles were identified from six databases, including the Web of Science Core Collection and MEDLINE^®. Bibliometric analysis was conducted across five dimensions: publication year, literature type, journal distribution, country contributions, and keyword trends. The findings are meticulously organized through tables, charts, and graphs. The year 2018 marked a surge in research within this domain, with the IEEE Internet of Things Journal and IEEE ACESS emerging as the most prolific journals, each boasting nine publications. The United States, China, and India are at the forefront in terms of journal citation counts. Our analysis determined that a reference count of 37 serves as an appropriate threshold. Otoum Safa stands out as the author with the highest number of published articles, totaling four. Keywords such as “blockchain”, “internet of things”, “smart contract”, “security”, and “critical infrastructure” appear with significant frequency. The statistics, trends, and insights gleaned from this bibliometric analysis can guide researchers in the OTCI field to forge a coherent and logical research trajectory. Content analysis further identified six key research areas within this domain: identity authentication and data verification, secure access control, attack detection and perception, data security and protection, data backup and recovery, and attack assessment and attribution. Based on these insights, a general framework is proposed to guide future research and practical applications of BT in securing OT within food and agriculture CI. This study systematically analyzes the current research landscape, challenges, and opportunities for BT in securing the OT critical to food and agriculture CI. By bridging the gap between blockchain innovations and the operational needs of the food and agriculture sector, this work contributes to advancing strategic implementation and improving the security of CI systems. Full article

Affective computing is an emerging area of education research and has the potential to enhance educational outcomes. Despite the growing number of literature studies, there are still deficiencies and gaps in the domain of affective computing in education. In this study, we systematically review affective computing in the education domain. Methods: We queried four well-known research databases, namely the Web of Science Core Collection, IEEE Xplore, ACM Digital Library, and PubMed, using specific keywords for papers published between January 2010 and July 2023. Various relevant data items are extracted and classified based on a set of 15 extensive research questions. Following the PRISMA 2020 guidelines, a total of 175 studies were selected and reviewed in this work from among 3102 articles screened. The data show an increasing trend in publications within this domain. The most common research purpose involves designing emotion recognition/expression systems. Conventional textual questionnaires remain the most popular channels for affective measurement. Classrooms are identified as the primary research environments; the largest research sample group is university students. Learning domains are mainly associated with science, technology, engineering, and mathematics (STEM) courses. The bibliometric analysis reveals that most publications are affiliated with the USA. The studies are primarily published in journals, with the majority appearing in the Frontiers in Psychology journal. Research gaps, challenges, and potential directions for future research are explored. This review synthesizes current knowledge regarding the application of affective computing in the education sector. This knowledge is useful for future directions to help educational researchers, policymakers, and practitioners deploy affective computing technology to broaden educational practices. Full article

We demonstrate the band gap programming of inverse opals by fabrication of different wall thickness by atomic layer deposition (ALD). The opal templates were synthesized using polystyrene and carbon nanospheres by the vertical deposition method. The structure and properties of the TiO₂ inverse opal samples were investigated using Scanning Electron Microscope (SEM) and Focused Ion Beam Scanning Electron Microscopy (FIB-SEM), Energy Dispersive X-ray analysis (EDX), X-ray Diffraction (XRD) and Finite Difference Time Domain (FDTD) simulations. The photonic properties can be well detected by UV-Vis reflectance spectroscopy, while diffuse reflectance spectroscopy appears to be less sensitive. The samples showed visible light photocatalytic properties using Raman microscopy and UV-Visible spectrophotometry, and a newly developed digital photography-based detection method to track dye degradation. In our work, we stretch the boundaries of a working inverse opal to make it commercially more available while avoiding fully filling and using cheaper, but lower-quality, carbon nanosphere sacrificial templates. Full article

Patient safety in psychiatric inpatient facilities remains under-researched despite its crucial importance. This study aims to address this gap by using expert opinion to estimate the frequency of diverse patient safety incidents (PSIs) in psychiatric settings and to compare it with the existing literature. Utilizing a seven-step approach, a questionnaire based on the World Health Organization’s International Classification for Patient Safety was developed and deployed. A total of 33 expert opinions were collected. Results showed a higher estimated incidence of PSIs in psychiatric settings compared to general healthcare, highlighting categories such as patient behavior, medication, and infrastructure as significant contributors. Experts emphasized the prevalence of incidents related to behavioral issues and inadequate infrastructure, areas often overlooked in the existing literature. Unlike general settings, psychiatric facilities appear more vulnerable to specific PSIs, such as those related to medication and building safety, underscoring the need for targeted safety measures. Our study suggests the existence of significant discrepancies between expert opinion and available research, with several underexplored domains in psychiatric patient safety. Full article

Accurate posture detection of elderly people is crucial to improve monitoring and provide timely alerts in homes and elderly care facilities. Human posture recognition is experiencing a great leap in performance with the incorporation of deep neural networks (DNNs) such as YOLOv9. Unfortunately, DNNs require large amounts of annotated data for training, which can be addressed by using virtual reality images. This paper investigates how to address the appearance domain that lies between synthetic and natural images. Therefore, four experiments (VIRTUAL–VIRTUAL; HYBRID–VIRTUAL; VIRTUAL–REAL; and HYBRID–REAL) were designed to assess the feasibility of recognising the postures of virtual or real elderly people after training with virtual and real images of elderly people. The results show that YOLOv9 achieves the most outstanding accuracy of 98.41% in detecting and discriminating between standing, sitting, and lying postures after training on a large number of virtual images complemented by a much smaller number of real images when testing on real images. Full article

Edible coatings and films have gained substantial attention as a promising and sustainable technology for fruit preservation. This study employed a bibliometric analysis to identify core research areas, research gaps, and emerging trends, thus providing a comprehensive roadmap for future research on the use of edible coatings and films for fruit quality preservation. The study involved 428 research articles related to edible coatings and films for fruit preservation published in the Scopus database before 06 October 2023. Utilizing Vosviewer and R for network analysis, we generated network visualization maps, research performance statistics, and identified key contributors and their collaborations. The results show the evolution of this field into three distinct phases: Initial Exploration (1998–2007), Growing Interest (2008–2015), and Rapid Expansion (2016–2023). The study revealed contributions from 1713 authors, with the first article appearing in 1998. Brazil and China emerged as the most productive countries in this domain. The core research areas focus on biomaterials, functional properties, and natural substances. Identified research gaps include pilot and industrial-scale applications, the lack of a regulatory framework and safety guidelines, and the application of artificial intelligence (AI), particularly deep learning and machine learning, in this field of edible coatings and films for fruit preservation. Overall, this study offers a scientific understanding of past achievements and ongoing research needs, thus aiming to boost a broader adoption of edible coatings and films by consumers and the food industry to preserve fruit quality, thereby enhancing their societal and environmental impact. Full article

The majority of Ethical Hacking (EH) tools utilised in penetration testing are developed by practitioners within the industry or underground communities. Similarly, academic researchers have also contributed to developing security tools. However, there appears to be limited awareness among practitioners of academic contributions in this domain, creating a significant gap between industry and academia’s contributions to EH tools. This research paper aims to survey the current state of EH academic research, primarily focusing on research-informed security tools. We categorise these tools into process-based frameworks (such as PTES and Mitre ATT&CK) and knowledge-based frameworks (such as CyBOK and ACM CCS). This classification provides a comprehensive overview of novel, research-informed tools, considering their functionality and application areas. The analysis covers licensing, release dates, source code availability, development activity, and peer review status, providing valuable insights into the current state of research in this field. Full article