Search Results (9,406)

Background: The accuracy and consistency of complete-arch digital impressions are fundamental for long-term success of implant-supported rehabilitations. Recently, artificial intelligence (AI)-assisted tools, such as SmartX (Medit Link v3.4.2, MEDIT Corp., Seoul, South of Korea), have been introduced to enhance scan body recognition and data alignment during intraoral scanning. Objective: This in vitro study aimed to evaluate the impact of SmartX on impression accuracy, consistency, operator confidence, and technique sensitivity in complete-arch implant workflows. Methods: Seventy-two digital impressions were recorded on edentulous mandibular models with four dummy implants, using six experimental subgroups based on scan body design (double- or single-wing), scanning technique (occlusal or combined straight/zigzag), and presence/absence of SmartX tool. Each group was scanned by both an expert and a novice operator (n = 6 scans per subgroup). Root mean square (RMS) deviation and scanning time were assessed. Data were tested for normality (Shapiro–Wilk). Parametric tests (t-test, repeated measures ANOVA with Greenhouse–Geisser correction) or non-parametric equivalents (Mann–Whitney U, Friedman) were applied as appropriate. Post hoc comparisons used Tukey HSD or Dunn–Bonferroni tests (α = 0.05). Results: SmartX significantly improved consistency and operator confidence, especially among novices, although it did not yield statistically significant differences in scan accuracy (p > 0.05). The tool mitigated early scanning errors and reduced dependence on operator technique. SmartX also enabled successful library alignment with minimal data; however, scanning time was generally longer with its use, particularly for beginners. Conclusions: While SmartX did not directly enhance trueness, it substantially improved scan reliability and user experience in complete-arch workflows. Its ability to minimize technique sensitivity and improve reproducibility makes it a valuable aid in both training and clinical settings. Further clinical validation is warranted to support its integration into routine practice. Full article

Wastewater treatment plants (WWTPs) function as engineered ecosystems in which microbial consortia mediate nutrient cycling, xenobiotic degradation, and heavy metal detoxification. This review discusses a forward-looking roadmap that integrates microbial ecology, multi-omics diagnostics, and artificial intelligence (AI) for next-generation treatments. Meta-analyses suggest that a globally conserved core microbiome indicates sludge functions, with high predictive value for treatment stability. Multi-omics approaches, including metagenomics, metatranscriptomics, and environmental DNA (eDNA) profiling, have integrated microbial composition with greenhouse gas (GHG) emissions, showing that WWTPs contribute 2–5% of anthropogenic nitrous oxide (N₂O) emissions. Emerging AI-enhanced eDNA models have achieved >90% predictive accuracy for effluent quality and antibiotic resistance gene (ARG) prevalence, facilitating near-real-time monitoring and adaptive control of effluent quality. Key advances include microbial strategies for degrading organic pollutants, pesticides, and heavy metals and monitoring industrial effluents. This review highlights both translational opportunities, including engineered microbial consortia, AI-driven digital twins and molecular indices, and persistent barriers, including ARG dissemination, resilience under environmental stress and regulatory integration. Future WWTPs are envisioned as adaptive, climate-conscious biorefineries that recover resources, mitigate ecological risks, and reduce their carbon footprint. Full article

Background: Papilledema, an ophthalmic finding associated with increased intracranial pressure, is often induced by dermatological medications, including corticosteroids, isotretinoin, and tetracyclines. Early detection is crucial for preventing irreversible optic nerve damage, but access to ophthalmologic expertise is often limited in rural settings. Artificial intelligence (AI) may enable the automated and accurate detection of papilledema from fundus images, thereby supporting timely diagnosis and management. Objective: The primary objective of this study was to explore the diagnostic capability of ChatGPT-4o, a general large language model with multimodal input, in identifying papilledema from fundus photographs. For context, its performance was compared with a ResNet-based convolutional neural network (CNN) specifically fine-tuned for ophthalmic imaging, as well as with the assessments of two human ophthalmologists. The focus was on applications relevant to dermatological care in resource-limited environments. Methods: A dataset of 1094 fundus images (295 papilledema, 799 normal) was preprocessed and partitioned into a training set and a test set. The ResNet model was fine-tuned using discriminative learning rates and a one-cycle learning rate policy. GPT-4o and two human evaluators (a senior ophthalmologist and an ophthalmology resident) independently assessed the test images. Diagnostic metrics including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and Cohen’s Kappa, were calculated for each evaluator. Results: GPT-4o, when applied to papilledema detection, achieved an overall accuracy of 85.9% with substantial agreement beyond chance (Cohen’s Kappa = 0.72), but lower specificity (78.9%) and positive predictive value (73.7%) compared to benchmark models. For context, the ResNet model, fine-tuned for ophthalmic imaging, reached near-perfect accuracy (99.5%, Kappa = 0.99), while two human ophthalmologists achieved accuracies of 96.0% (Kappa ≈ 0.92). Conclusions: This study explored the capability of GPT-4o, a large language model with multimodal input, for detecting papilledema from fundus photographs. GPT-4o achieved moderate diagnostic accuracy and substantial agreement with the ground truth, but it underperformed compared to both a domain-specific ResNet model and human ophthalmologists. These findings underscore the distinction between generalist large language models and specialized diagnostic AI: while GPT-4o is not optimized for ophthalmic imaging, its accessibility, adaptability, and rapid evolution highlight its potential as a future adjunct in clinical screening, particularly in underserved settings. These findings also underscore the need for validation on external datasets and real-world clinical environments before such tools can be broadly implemented. Full article

The emergence of Industry 5.0 brings a paradigm shift towards collaborative environments where humans and intelligent robots work side-by-side, enabling personalized, flexible, and resilient manufacturing. However, integrating humans and robots introduces new operational and safety risks that require proactive and adaptive control strategies. This study proposes an intelligent multi-criteria decision-making framework for smart risk assessment and the selection of optimal adaptive control strategies in human–robot collaborative manufacturing settings. The proposed framework integrates advanced risk analytics, real-time data processing, and expert knowledge to evaluate alternative control strategies, such as real-time wearable sensor integration, vision-based dynamic safety zones, AI-driven behavior prediction models, haptic feedback, and self-learning adaptive robot algorithms. A cross-disciplinary panel of ten experts structures six main and eighteen sub-criteria spanning safety, adaptability, ergonomics, reliability, performance, and cost, with response time and implementation/maintenance costs modeled as cost types. Safety receives the most significant weight; the most influential sub-criteria are collision avoidance efficiency, return on investment (ROI), and emergency response capability. The framework preserves linguistic semantics from elicitation to aggregation and provides a transparent, uncertainty-aware tool for selecting and phasing adaptive control strategies in Industry 5.0 collaborative cells. Full article

Accurately predicting the reception area of the Automatic Identification System (AIS) is critical for ship tracking and anomaly detection, as errors in signal interpretation may lead to incorrect vessel localization and behavior analysis. However, traditional propagation models, whether they are deterministic, empirical, or semi-empirical, face limitations when applied to dynamic environments due to their reliance on detailed atmospheric and terrain inputs. Therefore, to address these challenges, we propose a data-driven approach based on graph neural networks (GNNs) to model AIS reception as a function of environmental and geographic variables. Specifically, inspired by attention mechanisms that power transformers in large language models, our framework employs the SAmple and aggreGatE (GraphSAGE) framework convolutions to aggregate neighborhood features, then combines layer outputs through Jumping Knowledge (JK) with Bidirectional Long Short-Term Memory (BiLSTM)-derived attention coefficients and integrates an attentional pooling module at the graph-level readout. Moreover, trained on real-world AIS data enriched with terrain and meteorological features, the model captures both local and long-range reception patterns. As a result, it outperforms classical baselines—including ITU-R P.2001 and XGBoost in F1-score and accuracy. Ultimately, this work illustrates the value of deep learning and AIS sensor networks for the detection of positioning anomalies in ship tracking and highlights the potential of data-driven approaches in modeling sensor reception. Full article

Blockchain technologies have profoundly transformed information systems by providing decentralized infrastructures that enhance transparency, security, and traceability. Ethereum, in particular, supports smart contracts and facilitates the development of decentralized finance (DeFi), non-fungible tokens (NFTs), and Web3 applications. However, its openness also enables illicit activities, including fraud and money laundering, through anonymous wallets. Identifying wallets involved in large transfers or abnormal transactional patterns is therefore critical to ecosystem security. This study proposes an AI-based framework employing XGBoost, LightGBM, and CatBoost to detect suspicious Ethereum wallets, achieving test accuracies between 95.83% and 96.46%. The system provides near real-time predictions for individual or recent wallet addresses using a pre-trained XGBoost model. To improve interpretability, SHAP (SHapley Additive exPlanations) visualizations are integrated, highlighting the contribution of each feature. The results demonstrate the effectiveness of AI-driven methods in monitoring and securing Ethereum transactions against fraudulent activities. Full article

Cultural organizations have traditionally been viewed as resistant to change, often bound by legacy structures, public dependency, and non-commercial missions. However, recent advances in digital technologies—ranging from AI and VR to IoT and big data—are reshaping the operational and strategic landscape of these institutions. Despite this shift, academic literature has yet to comprehensively map how technological innovation transforms cultural organizations into practice. This paper addresses this gap by introducing the concept of the Cultural Organizational System (COS)—a holistic framework that captures the multi-component structure of cultural entities, including space, tools, performance, management, and networks. Using a PRISMA-based scoping review methodology, we analyze over 90 sources to identify the types, functions, and strategic roles of technological innovations across COS components. The findings reveal a taxonomy of innovation use cases, a mapping to Oslo innovation categories, and a quadrant model of enablers and barriers unique to the cultural sector. By offering an integrated view of digital transformation in cultural settings, this study advances innovation theory and provides practical guidance for cultural leaders and policymakers seeking to balance mission-driven goals with sustainability and modernization imperatives. Full article

The integration of AI-driven optimization into Electronic Design Automation (EDA) enables smarter and more adaptive circuit design, where symmetry and asymmetry play key roles in balancing performance, robustness, and manufacturability. This work presents a model-driven optimization methodology for sizing low-phase-noise LC voltage-controlled oscillators (VCOs) at 5 GHz, targeting Wi-Fi, 5G, and automotive radar applications. The approach uses the EKV transistor model for analytical CMOS device characterization and applies a diverse set of metaheuristic algorithms for both single-objective (phase noise minimization) and multi-objective (joint phase noise and power) optimization. A central focus is on how symmetry—embedded in the complementary cross-coupled LC-VCO topology—and asymmetry—introduced by parasitics, mismatch, and layout constraints—affect optimization outcomes. The methodology implicitly captures these effects during simulation-based optimization, enabling design-space exploration that is both symmetry-aware and robust to unavoidable asymmetries. Implemented in CMOS 180 nm technology, the approach delivers designs with improved phase noise and power efficiency while ensuring manufacturability. Yield analysis confirms that integrating symmetry considerations into metaheuristic-based optimization enhances performance predictability and resilience to process variations, offering a scalable, AI-aligned solution for high-performance analog circuit design within EDA workflows. Full article

This study aimed to evaluate the performance of seven advanced AI Large Language Models (LLMs)—ChatGPT 4o, ChatGPT O3 Mini, ChatGPT O1, DeepSeek V3, DeepSeek R1, Gemini 2.0 Flash, and Grok-3—in answering multiple-choice questions (MCQs) in optics and refractive surgery, to assess their role in medical education for residents. The AI models were tested using 134 publicly available MCQs from national ophthalmology certification exams, categorized by the need to perform calculations, the relevant subspecialty, and the use of images. Accuracy was analyzed and compared statistically. ChatGPT O1 achieved the highest overall accuracy (83.5%), excelling in complex optical calculations (84.1%) and optics questions (82.4%). DeepSeek V3 displayed superior accuracy in refractive surgery-related questions (89.7%), followed by ChatGPT O3 Mini (88.4%). ChatGPT O3 Mini significantly outperformed others in image analysis, with 88.2% accuracy. Moreover, ChatGPT O1 demonstrated comparable accuracy rates for both calculated and non-calculated questions (84.1% vs. 83.3%). This is in stark contrast to other models, which exhibited significant discrepancies in accuracy for calculated and non-calculated questions. The findings highlight the ability of LLMs to achieve high accuracy in ophthalmology MCQs, particularly in complex optical calculations and visual items. These results suggest potential applications in exam preparation and medical training contexts, while underscoring the need for future studies designed to directly evaluate their role and impact in medical education. The findings highlight the significant potential of AI models in ophthalmology education, particularly in performing complex optical calculations and visual stem questions. Future studies should utilize larger, multilingual datasets to confirm and extend these preliminary findings. Full article

Background: Deep vein thrombosis (DVT) is a serious thromboinflammatory complication of acute ischemic stroke (AIS). The true incidence, mechanistic risk factors, and optimal prophylactic strategies remain uncertain, particularly in the era of reperfusion therapy. Methods: This systematic review and meta-analysis (IRIS-DVT) searched PubMed, Embase, Cochrane, Scopus, and Web of Science for studies reporting DVT incidence, risk factors, or prophylaxis in AIS (2004–2025). Random-effects models were used to generate pooled prevalence and effect estimates, and the certainty of evidence was graded using the GRADE framework. Results: Forty-two studies (n = 6,051,729 patients) were included. The pooled prevalence of DVT was 7% (95% CI, 6–9%), approximately seventy-fold higher than in the general population, with wide heterogeneity influenced by screening timing and diagnostic modality. Pathophysiological risk factors included higher stroke severity (NIHSS; SMD 0.41; 95% CI, 0.38–0.43), older age (SMD 0.32; 95% CI, 0.18–0.46), elevated D-dimer (SMD 0.55; 95% CI, 0.38–0.72), female sex (OR 1.33; 95% CI, 1.19–1.50), and malignancy (OR 2.69; 95% CI, 1.56–5.22), supported by moderate-certainty evidence. Respiratory infection and admission hyperglycemia showed weaker, low-certainty associations. Traditional vascular risk factors (hypertension, diabetes, atrial fibrillation, dyslipidemia) were not significantly related to DVT risk. Evidence for prophylaxis with low-molecular-weight heparin, direct oral anticoagulants, or intermittent pneumatic compression was limited and graded very low certainty. Conclusions: DVT complicates approximately one in fourteen AIS cases, reflecting a distinct thromboinflammatory process driven more by acute neurological severity, systemic hypercoagulability, and malignancy than by conventional vascular risk factors. Early systematic screening (≤72 h) and consistent use of mechanical prophylaxis are warranted. Dedicated AIS-specific mechanistic and interventional trials are urgently needed to refine prevention strategies and improve post-stroke outcomes. Full article

Surface drifter trajectory prediction is essential for applications in environmental management, maritime safety, and climate studies. This survey paper reviews research from the past two decades, and systematically classifies the evolution of methodologies into six successive generations, including numerical models, data assimilation, statistical and probabilistic approaches, machine learning, deep learning, and hybrid or AI-based data assimilation (1st–5.5th Generation). To our knowledge, this is the first systematic generational classification of trajectory prediction methods. Each generation revealed distinct strengths and limitations. Numerical models ensured physical consistency but suffered from accumulated forecast errors in observation-sparse regions. Data assimilation improved short-term accuracy as observing networks expanded, while machine learning and deep learning enhanced short-range forecasts but faced challenges such as error accumulation and insufficient physical constraints in longer horizons. More recently, hybrid frameworks and AI-based data assimilation have emerged, combining physical models with deep learning and traditional statistical techniques, thereby opening new possibilities for accuracy improvements. By comparing methodologies across generations, this survey provides a roadmap that helps researchers and practitioners select appropriate approaches depending on observation density, forecast lead time, and application objectives. Finally, this paper highlights that future systems should shift focus from deterministic tracks toward credible uncertainty estimates, region-aware designs, and physically consistent prediction frameworks. Full article

The process of time-series forecasting such as predicting trajectories of silicon content in blast furnaces is a difficult task. Most time-series approaches today focus on scalar-type MSE loss optimization. This optimization approach, while widely common, could benefit from the use of human expert or process-level preferences. In this paper, we introduce a novel alignment and fine-tuning approach that involves learning from a corpus of preferred and dis-preferred time-series prediction trajectories. Our contributions include (1) a preference annotation pipeline for time-series forecasts, (2) the application of Score-based Preference Optimization (SPO) to train decoder-only transformers from preferences, and (3) results showing improvements in forecast quality. The approach is validated on both proprietary blast furnace data and the UCI Appliances Energy dataset. The proposed preference corpus and training strategy offer a new option for fine-tuning sequence models in industrial settings. Full article

Despite the widespread adoption of network monitoring tools, Managed Service Providers (MSPs), specifically small- and medium-sized enterprises (SMEs), continue to face persistent challenges in achieving predictive, multi-tenant-aware visibility across distributed client networks. Existing monitoring systems lack integrated predictive analytics and edge intelligence. To address this, we propose an AI- and IoT-driven monitoring and visualisation framework that integrates edge IoT nodes (Raspberry Pi Prometheus modules) with machine learning models to enable predictive anomaly detection, proactive alerting, and reduced downtime. This system leverages Prometheus, Grafana, and Mimir for data collection, visualisation, and long-term storage, while incorporating Simple Linear Regression (SLR), K-Means clustering, and Long Short-Term Memory (LSTM) models for anomaly prediction and fault classification. These AI modules are containerised and deployed at the edge or centrally, depending on tenant topology, with predicted risk metrics seamlessly integrated back into Prometheus. A one-month deployment across five MSP clients (500 nodes) demonstrated significant operational benefits, including a 95% reduction in downtime and a 90% reduction in incident resolution time relative to historical baselines. The system ensures secure tenant isolation via VPN tunnels and token-based authentication, while providing GDPR-compliant data handling. Unlike prior monitoring platforms, this work introduces a fully edge-embedded AI inference pipeline, validated through live deployment and operational feedback. Full article

The rapid dissemination of health misinformation on the Internet and social media has become a growing challenge for public health, particularly in terms of health information credibility. Promising efforts have been made to detect misinformation using generative AI and large language models (LLMs). However, such tools still lack domain-specific knowledge that limits their performance. In this study, we examine the use of predefined knowledge data structures in the forms of debunk lists to augment existing LLMs’ capabilities. We evaluate five different LLMs, including Llama-3.1-8B-instruct, Mistral-large, GPT-4o-mini, Claude-3.5-haiku, and Gemini-1.5-flash, under three experimental settings: zero-shot and debunk-augmented (50 and 100 entities). Results show that external knowledge, in the form of debunk lists, can notably improve LLMs’ performance in detecting misinformation. While Llama shows minimal benefit, the F1 score improvement ranges from 2.63% (GPT-4o) to 11% (Claude). In addition, analysis of model justifications shows that frequent use of debunk lists does not necessarily relate to accurate predictions. This highlights the importance of a model’s ability in effectively using the debunk list rather than reporting superficial integration of external knowledge. Moreover, the proposed framework is generalizable to other misinformation domains and provides key insights for applying external knowledge and evaluating LLMs’ reasoning reliability. Full article

Agriculture remains the backbone of many countries; it plays a pivotal role in shaping a country’s overall economy. Accurate prediction in agriculture practices, particularly crop recommendations, can greatly enhance productivity and resource management. IoT and AI technologies have great potential for enhancing precision farming; traditional machine learning (ML) and ensemble learning (EL) models rely primarily on the training data for predictions. When the training data is noisy or limited, these models can result in inaccurate or unrealistic predictions. These limitations are addressed by incorporating physical laws into the ML framework, thereby ensuring that the predictions remain physically plausible. In this study, we conducted a detailed analysis of ML and EL models, both with and without optimization, and compared their performance against a physics-informed ML model. In the proposed stacking physics-informed ML model, the optimal temperature and the pH for each crop (physics law) are provided as input during the training process in addition to the training data. The physics-informed model was trained to simultaneously satisfy two objectives: (1) fitting the data, and (2) adhering to the physics law. This was achieved by including a penalty term within its total loss function, forcing the model to make predictions that are both accurate and physically feasible. Our findings indicate that the proposed novel stacking physics-informed model achieved a highest accuracy of 99.50% when compared to ML and EL models with optimization. Full article