<?xml version="1.0" encoding="utf-8"?>
    <rss version="2.0">
      <channel xmlns:content="http://purl.org/rss/1.0/modules/content/">
        <title>Frontiers in Artificial Intelligence | New and Recent Articles</title>
        <link>https://www.frontiersin.org/journals/artificial-intelligence</link>
        <description>RSS Feed for Frontiers in Artificial Intelligence | New and Recent Articles</description>
        <language>en-us</language>
        <generator>Frontiers Feed Generator,version:1</generator>
        <pubDate>2026-08-15T15:42:21.633+00:00</pubDate>
        <ttl>60</ttl>
        <item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1876322</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1876322</link>
        <title><![CDATA[Meditation styles are highly discriminable from EEG at the subject level with limited generalization across the population: a machine-learning study]]></title>
        <pubdate>2026-08-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Saqib Hayat</author><author>Francesco Goretti</author><author>Rachele Fabbri</author><author>Chiara Noferini</author><author>Elena Cravero</author><author>Paolo Mori</author><author>Alessandro Scaglione</author><author>Francesco S. Pavone</author>
        <description><![CDATA[Meditation has been associated with improvements in attention, emotional regulation, and mental wellbeing, motivating increasing interest in objective methods for assessing meditative states. In this study, we investigate whether EEG-based machine learning can reliably distinguish between multiple meditation styles and mind-wandering states. EEG data were recorded from experienced meditators performing three meditation styles, Shamatha, Vipassana, and Metta, together with an eyes-closed mind-wandering condition. EEG signals were preprocessed to remove artifacts, and features were extracted from frequency, time-frequency, and time domains. Classification was evaluated using both intra-subject and inter-subject strategies with multiple machine learning classifiers. Results demonstrate high intra-subject classification accuracy across meditation-vs.-mind-wandering and meditation-style comparisons, indicating strongly discriminative subject-specific neural signatures. In contrast, inter-subject performance decreased substantially, particularly for distinguishing meditation styles, suggesting considerable inter-individual variability in meditation-related EEG patterns. Furthermore, temporal analysis revealed that classification performance increases over time in some comparisons, particularly in VIP/MW, suggesting that the neural distinctions between certain meditation states may become more pronounced over time. Additionally, t-SNE visualization showed clear within-subject clustering but increased overlap across subjects, explaining the reduced inter-subject generalization. Overall, these findings highlight the potential of EEG-based machine learning for personalized assessment and monitoring of meditative states while emphasizing the challenges of developing subject-independent meditation classification systems.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1913343</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1913343</link>
        <title><![CDATA[AI ethics in hospitality and tourism: theoretical perspectives, ethical beliefs, and actionable outcomes]]></title>
        <pubdate>2026-08-14T00:00:00Z</pubdate>
        <category>Systematic Review</category>
        <author>Nasim Binesh</author><author>Ahmad Syah</author>
        <description><![CDATA[IntroductionAs AI becomes embedded across hospitality and tourism, its ethical implications remain fragmented and largely undertheorized; this scoping review synthesizes the evidence on AI ethics in the sector.MethodsFollowing a PRISMA-guided search and screening of Web of Science, Scopus, and Emerald, we reviewed 32 studies and organized findings into nine cross-cutting themes, with associated research gaps and future questions. To extend prior descriptive work, we interpret the literature through epistemology and the ethics of belief, examining how AI systems in service contexts form, justify, and act upon “beliefs” (e.g., inferred preferences, risk scores, and recommendations) and how unjustified beliefs can generate ethical harms.ResultsWe map ethical concerns across key hospitality and tourism sub-sectors (e.g., accommodation, transportation, entertainment) and translate them into actionable guidance. Specifically, we propose (1) a sectoral risk framework that classifies common AI applications from unacceptable to minimal risk, and (2) a structured AI life-cycle approach identifying ethical safeguards at problem definition, data collection, model development, deployment, and feedback.ConclusionThe review advances a theory-based understanding of AI ethics in human-centric service industries, offering practical implications for managers, policymakers, and researchers seeking responsible AI adoption.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1817529</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1817529</link>
        <title><![CDATA[Reassessing demographic bias in face attribute classification: a statistically grounded multi-model evaluation on FairFace and UTKFace]]></title>
        <pubdate>2026-08-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Andisani Nemavhola</author><author>Serestina Viriri</author><author>Colin Chibaya</author>
        <description><![CDATA[Face analysis systems are widely used in security, authentication, and public-sector applications; however, demographic bias and the statistical reliability of reported performance remain key concerns. Many studies rely on aggregate accuracy without quantifying subgroup disparities or uncertainty, potentially overstating model fairness. This study presents a statistically grounded evaluation of demographic bias in face attribute classification across three representative architectures, ResNet50, MobileNetV3, and a vision transformer (DeiT), using the FairFace and UTKFace datasets. Subgroup analysis is conducted across race and gender, incorporating disparity indices, bootstrap confidence intervals, and inferential statistical testing with effect size analysis. The evaluation uses an embedding-based nearest-neighbor approach to examine representation-level behavior consistently across models. Results show that race-based disparities are substantially larger than gender-based disparities across both datasets. On FairFace, race disparity gaps range from 0.1124 to 0.1266, while on UTKFace they increase significantly to 0.4726–0.4944, with large effect sizes (Cohen's d>1). In contrast, gender disparities remain smaller, with gaps between 0.0280 and 0.0582 on FairFace and 0.0194–0.0326 on UTKFace, and correspondingly small effect sizes (d < 0.13). Despite modest differences in overall accuracy across models, subgroup disparities remain statistically significant across all architectures. These findings emphasize the importance of subgroup-level evaluation, uncertainty quantification, and statistical validation for reliable fairness assessment in face analysis systems.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1823263</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1823263</link>
        <title><![CDATA[Explainable artificial intelligence in accounting and financial auditing: a systematic review]]></title>
        <pubdate>2026-08-14T00:00:00Z</pubdate>
        <category>Systematic Review</category>
        <author>Iván Patricio Arias-González</author><author>Gabriela Joseth Serrano-Torres</author><author>Eduardo Ramiro Dávalos-Mayorga</author><author>Norma Patricia Jiménez-Vargas</author>
        <description><![CDATA[Explainable Artificial Intelligence (XAI) has emerged as a response to the need to understand and make transparent the decisions of machine learning models, particularly in sensitive contexts such as accounting and financial auditing. In this domain, XAI enables the interpretation of results generated by automated systems applied to fraud detection, risk management, financial analysis, and regulatory compliance, thereby strengthening the trust of auditors and regulators. The objective of this study was to systematically analyze the literature on XAI in accounting and financial auditing in order to identify its application domains, the methods employed, and the main challenges reported. The research was conducted through a systematic literature review following the PRISMA protocol, based on studies retrieved from Scopus and Web of Science. The selected works were organized and synthesized using an analysis matrix, resulting in 85 primary studies. The findings indicate that XAI is mainly applied to fraud detection, credit assessment, financial auditing, and decision-support processes, with a predominance of techniques such as SHAP and LIME. Although these tools enhance transparency, limitations related to computational cost, data quality, explanation stability, and regulatory adaptation persist, highlighting the need to strengthen their integration into auditing processes.Systematic review registrationhttps://osf.io/pb5cy/.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1800407</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1800407</link>
        <title><![CDATA[LATTICE: a governance-first architecture for authorized autonomous AI operations]]></title>
        <pubdate>2026-08-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Elias Calboreanu</author>
        <description><![CDATA[Deploying autonomous AI agents in high-consequence operational environments requires organizational authorization, yet few frameworks provide end-to-end, testable governance mechanisms suitable for such authorization decisions. This paper introduces LATTICE (Layered Agentic Triad Topology for Intelligent Coordinated Execution), a governance-first architecture that reframes the authorization question from “do we trust this AI?” to “do we trust this architecture?” The latter question is answerable through engineering validation rather than assumptions about model behavior. LATTICE enforces separation of concerns across planning, execution, and governance functions through a 1+3 Grid Cell pattern, so that no single component can both decide actions and judge compliance. The architecture implements policy-as-code enforcement with deterministic verdicts, gated execution paths that, under stated trusted-infrastructure assumptions (A1–A5), prevent unauthorized actions, confidence-based escalation to human operators, and cryptographic audit trails that preserve complete decision provenance. Empirical results characterize the AEGIS reference implementation; architecture-level properties are analytic, under stated assumptions. The governance engine is released as open source and reproduces its core results on commodity hardware: deterministic verdicts with zero deviations across 13 configurations repeated 10,000 times each, and no bypass in a 21-vector adversarial suite (0/21 observed; one-sided 95% upper bound 13.3%). In a pre-specified, planner-invariant safety evaluation (not an autonomy benchmark) across four frontier planner families (GPT-5, Claude Sonnet 4.6, Gemini, Grok-4; 4,000 trajectories), a confidence-threshold baseline's false-allow rate ranged from 0.03 to 0.998 across planners, whereas the AEGIS reference implementation admitted zero unsafe actions (false-allow 0.0, recall 1.0) invariant to the planner, at a conservative operating point that auto-allowed no action; a separate live run additionally governed real operating-system actions with zero unsafe executions. Governance latency is low and host-specific (on an Apple M4 Pro: policy evaluation p50 ≈ 6.2 μs; full gated enforcement p50 ≈ 0.7 ms including audit I/O). LATTICE provides a pathway for responsible deployment of autonomous AI in defense, critical infrastructure, and regulated industries where authorization requires verifiable governance rather than trust in AI behavior.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1875232</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1875232</link>
        <title><![CDATA[Automated detection and counting of redbanded stink bugs in soybean using an improved computer vision model]]></title>
        <pubdate>2026-08-14T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Saurav Upadhyaya</author><author>Jeffrey A. Davis</author><author>Ivan Grijalva</author>
        <description><![CDATA[The redbanded stink bug (RBSB), Piezodorus guildinii, is a major economic pest of soybean, with feeding damage that leads to significant yield losses and increased reliance on pesticide applications. Current management practices depend on manual identification and repeated field counting, which are labor-intensive, time-consuming, and prone to human error, particularly across large production areas. To address these limitations, this study evaluated the potential of computer vision models to automatically detect and count RBSB adults using imagery. A total of 2,281 field images were collected under varying stink bug densities using different sensors. These images were used to train multiple YOLOv8 model variants for automated detection and counting. The best-performing model was further enhanced by integrating a convolutional block attention module (CBAM) and adaptive spatial feature fusion (ASFF) to improve detection accuracy and counting performance, which are critical for informed pest management decisions. The improved YOLOv8m model achieved 96.30% precision, 76.40% recall, F1-score of 85.20, 82.00% mean average precision (mAP50), and 75.30% mean average precision (mAP50-95) for detecting and counting RBSB adults in images, outperforming the baseline model, which showed lower performance with 95.68% precision, 76.69% recall, F1-score of 85.13, 78.70% mAP50, and 66.00% mAP50-95. The enhanced model was deployed in a prototype web application to evaluate its practical capabilities. This application allows users to upload images and visualizes detection bounding boxes and RBSB counts, resulting in low misdetection error. Overall, the framework and results presented in this study provide a practical alternative to manual identification of RBSB adults in soybean systems using images and have the potential to improve traditional pest monitoring practices.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1836646</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1836646</link>
        <title><![CDATA[Recent advancements and future prospects on AI-integrated sensing techniques for non-invasive chronic kidney disease diagnosis: a review]]></title>
        <pubdate>2026-08-13T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Suchetha Manikandan</author><author>Preethi Senthilkumar</author><author>Shivani Selvachandran</author><author>Jim Elliot Christopherjames</author><author>Shabbir Syed Abdul</author>
        <description><![CDATA[Chronic Kidney Disease (CKD) has emerged as a major public health concern worldwide, and most patients with CKD are asymptomatic until the later stages, causing growing morbidity and mortality. Diabetes and hypertension are the main causative factors for the development of CKD, damaging the renal microcirculation system. In addition, the impact of Acute Kidney Injuries (AKI) may result in the recovery or progression to either CKD or renal failure. The conventional techniques for diagnosis, such as the measurement of blood creatinine levels, are invasive and time-consuming and may also overlook the early stages of CKD. The non-invasive technology for the diagnosis of CKD has experienced tremendous improvements with the development in the field of sensing technology and the revolution in the field of Artificial Intelligence. This review article covers the non-invasive sensing technology using the non-invasive biofluids/biological matrices, such as saliva, breath, and sweat, for the diagnosis of Chronic Kidney Disease. Additionally, the framework for incorporating Machine Learning models for the automated prediction of CKD in its early stages is analysed.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1797435</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1797435</link>
        <title><![CDATA[Improving LLM-based event extraction with annotation guidelines]]></title>
        <pubdate>2026-08-13T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Marcel Geromel</author><author>Philipp Cimiano</author>
        <description><![CDATA[Event extraction constitutes a foundational task in information extraction, but reliance on laborious and expensive human annotations severely restricts the availability of training datasets. While recent works have explored Large Language Models (LLMs) as example-driven (or zero-shot) annotators, they are substantially outperformed by supervised techniques on structured extraction tasks, such as event detection and argument extraction, possibly on account of underspecified task instructions. In this work, we investigate to which extent LLMs can benefit from dataset-specific, detailed annotation guidelines that more precisely represent the dataset's underlying (human) annotation procedures. To this end, we propose a guideline-based, three-stage LLM annotation framework for event extraction that incorporates detailed event annotation guidelines and supports multiple LLM annotators to improve robustness. Using the comprehensive and well-documented ACE 2005 English Annotation Guidelines for Events as a reference document, we evaluate four LLMs across three guideline-compliant benchmark datasets. Our findings indicate that, depending on model choice, guideline specificity, and the dataset's relative label accuracy, employing detailed guidelines can considerably boost event extraction performance, gaining up to 6.7 F1 points over commonly used bare-minimum instructions, with particularly remarkable improvements for reasoning-based models. Furthermore, we demonstrate that augmenting existing datasets with LLM-generated argument annotations can improve argument extraction performance under soft-matching evaluation. Overall, our experiments emphasize the importance of annotation guidelines (as well as their specificity) for LLM-based annotations, providing valuable insights on leveraging LLMs as guideline-compliant annotators.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1880282</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1880282</link>
        <title><![CDATA[Improved graph-based model for phishing website detection using multi-level web page graphs and dynamic heterogeneous graph attention network]]></title>
        <pubdate>2026-08-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>S. Kavya</author><author>D. Sumathi</author>
        <description><![CDATA[Modern phishing pages are challenging to detect because they can appear like legitimate brand sites using dynamic document object model (DOM) structures, misleading visual displays, and changing hyperlinks. Most conventional blacklists and URL-based methods do not capture the relationships at multiple levels of the web page structure. In this paper, we introduce a new graph-based phishing detection method to represent a web page with a Multi-Level Web Page Graph (MLWPG). MLWPGs incorporate DOM hierarchies, rendered visual blocks, and hyperlink relations into one heterogeneous graph. We use a novel Deep Learning Method called DHGAN that has Type-Aware Attention and Dynamic Convolution to learn how to differentiate discriminative interaction amongst structural, spatial, and navigation elements. APDA will be used in feature space to enhance robustness to evasive phishing versions. Using a balanced data set of 50,000 web pages, our complete pipeline showed a 97.0% accuracy, 96.8% F1-Score, 3.0% False Positive Rate, and 95.5% Robustness to Adversaries. The proposed MLWPG-DHGAN-APDA framework outperformed all baseline models. Our experimental results demonstrate that multi-level graph models provide improvements to both detection accuracy and reliability of operation for real-time phishing defenses.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1886896</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1886896</link>
        <title><![CDATA[Predicting influenza in the post-COVID era: assessing LSTM, GRU, and transformer robustness to covariate shift]]></title>
        <pubdate>2026-08-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Atiqa Naeem Alam Din</author><author>Woldegebriel Assefa Woldegerima</author><author>Jianhong Wu</author>
        <description><![CDATA[Forecasting influenza has become increasingly challenging due to post-COVID disruptions in seasonality and strain circulation. This work compares the performance of Long Short Term Memory Networks (LSTM), Gated Recurrent Unit (GRU), and transformer models in forecasting influenza spread using multivariate epidemiological and environmental data, with a focus on robustness under post-COVID non-stationarity. We compare LSTM, GRU, and transformer architectures within a multivariate deep learning framework using influenza and temperature data from Ontario (2014–2025), with data split into training, validation, and testing periods. Although recurrent models outperform transformers on limited, noisy data, all architectures exhibit marked performance collapse under post-COVID non-stationarity. The GRU and LSTM track pre-COVID seasonal peaks more closely, yet both substantially under-estimate the post-COVID resurgence, indicating that none of the models generalize across the regime shift. These findings position our study as a diagnostic of how architectural inductive biases break down under covariate shift. Furthermore, this manuscript assesses how the COVID-19 pandemic affected the accuracy and performance of machine learning algorithms and notes the integration of transfer learning and attention mechanisms to improve model performance.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1784973</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1784973</link>
        <title><![CDATA[What really happens when a dev vibes with the code? An empirical study on LLM behavioral divergence in response to expressive code comments]]></title>
        <pubdate>2026-08-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Angela N. Johnson</author>
        <description><![CDATA[IntroductionWe investigate how expressive inline code comments written in various developer styles, functional to progressively poetic, philosophical, and misleading, affect large language model (LLM) behavior during code optimization.MethodsIn this pilot study, we used a controlledmerge sort implementation across five stylistic variants and evaluated GPT-5 and Claude Opus 4.1 under standardized console prompts, isolating the effect of embedded comment semiotic variation. Seven expert developers (three senior, four mid-level) scored model outputs against adapted ISO/IEC 25010 criteria and novel LLM suggestibility index (LSI) framework.ResultsSemiotic character of comments measurably altered code quality, with consensus-score reliability ICC(2, k) = 0.65–0.81 for six of seven dimensions; single-rater Krippendorff's α = 0.232 reflects substantial interpretive variability. Claude exhibited higher interpretive sensitivity (mean behavioral divergence 4.00; SD 1.16), while GPT-5 maintained stronger architectural fidelity (mean divergence 3.58; SD 1.26). Reflective comments (philosophical, conversational) were associated with Claude's highest maintainability scores in our panel (both M = 4.00, ~8% above stock M = 3.71), while the same philosophical comments reduced GPT-5 maintainability (M = 2.86), suggesting asymmetric model responses to expressive context.ConclusionsThese findings position inline comments as model-sensitive latent semantic prompts, with implications for AI-in-the-loop development and design of comment conventions for AI-assisted maintenance.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1826633</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1826633</link>
        <title><![CDATA[A systematic literature review exploring the application of deep learning in electric vehicles from 2015 to 2025]]></title>
        <pubdate>2026-08-11T00:00:00Z</pubdate>
        <category>Systematic Review</category>
        <author>John Vianney Ssennono</author><author>Javeed Kittur</author><author>Sabah-Ud-Din Waqar</author>
        <description><![CDATA[IntroductionElectric vehicles (EVs) are rapidly gaining popularity and global recognition, driven by their reliability, flexibility, simplicity, and scalability. This paper provides a systematic literature review of research at the intersection of electric vehicles and deep learning, aiming to identify current advancements and explore their potential for future scalability.MethodsA total of 92 publications from 2015 to 2025 were included in the final synthesis phase of the review. These works were categorized into five key themes: data-driven research on electric vehicles and deep learning, societal integration of electric vehicles, implications of electric vehicle adoption, software considerations, and challenges and solutions enabled by deep learning. Crucially, the scope of this synthesis extends into state-of-the-art frameworks spanning 2025 and 2026, evaluating deep learning’s dual footprint in vehicle-level mechanical safety systems, such as machine learning-driven brake-blending policies optimizing regenerative energy capture and fleet-level performance logistics via neural network-driven predictive maintenance optimization.ResultsThe findings for each theme and their implications for research and practice are thoroughly discussed. Additionally, a descriptive analysis of research trends shows: (1) a steady increase in publications each year; (2) a majority of contributions originating from China; (3) diverse deep learning approaches being applied to tackle various challenges within the electric vehicle industry; and (4) significant opportunities for the development, testing, and deployment of deep learning technologies and algorithms in the electric vehicle domain.DiscussionThe findings highlight the growing applicwation of deep learning across the electric vehicle domain and demonstrate significant opportunities for the continued development, testing, and deployment of deep learning technologies and algorithms to support future advancements and scalability in electric vehicles.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1948766</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1948766</link>
        <title><![CDATA[Correction: Assessing the utility of advanced adoption models for AI-based financial services: insights into automated and hybrid robo-advisors]]></title>
        <pubdate>2026-08-11T00:00:00Z</pubdate>
        <category>Correction</category>
        <author>Balraj Verma</author><author>Laxmi Remer</author><author>Divya Goswami</author><author>Somesh Kumar Sinha</author>
        <description></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1883357</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1883357</link>
        <title><![CDATA[Application of dimensionality reduction and clustering techniques for the analysis of Carrion's disease cases in the period 2000–2024]]></title>
        <pubdate>2026-08-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Moisés Evangelista Gamarra</author><author>Jerremi Aron Chancan Labajos</author><author>Pamela Estefani Figueroa Rosas</author><author>Ronaldo Edilberto Alvarez Manrique</author>
        <description><![CDATA[The heterogeneous geographic distribution and the complex dynamics of Carrion's disease challenge conventional epidemiological surveillance in Peru. To address this, this study applied unsupervised machine learning to 43,534 national records (2000–2024). Following a rigorous data cleaning process—which resolved duplicate records, missing information, and outliers using Tukey's interquartile range (IQR)—the dimensionality reduction approaches MCA and FAMD coupled with the K-Means algorithm were evaluated. The calibration of the Silhouette, Davies–Bouldin, and Calinski–Harabasz indices determined that the combination of FAMD and K-Means provided the best clustering quality, identifying two clearly differentiated epidemiological profiles. An ablation control experiment demonstrated that, even after excluding the ICD-10 diagnostic coding, the geometric structure of the clusters remained highly stable, indicating that the temporal, geographic, and demographic variables contain sufficient information to preserve the clustering structure. This internal consistency was indicated through bootstrap resampling simulations. In conclusion, the coupling of FAMD and K-Means establishes a stable and reproducible framework for advanced exploratory epidemiology, constituting a valuable complementary tool to support public health surveillance and guide strategic decision-making in public health.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1884843</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1884843</link>
        <title><![CDATA[Automated evaluation of dental cavity preparation quality using deep learning and anatomically informed geometric analysis]]></title>
        <pubdate>2026-08-11T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Abdullah F. Alshammari</author><author>Bassam A. Anazi</author><author>Mahvish Khan</author><author>Hamdan A. Alshammari</author><author>Najmah A. Almowina</author><author>Yousef E. Alenezi</author><author>Saif Khan</author><author>Shafiul Haque</author><author>Ahmed A. Madfa</author>
        <description><![CDATA[BackgroundThe quality of cavity preparation critically influences the longevity and success of restorative dental treatments. Current assessment methods remain largely subjective, relying on visual inspection and examiner judgment, which are prone to variability and limited reproducibility. Although three-dimensional (3D) imaging enables quantitative evaluation, its routine use in clinical and educational settings is limited by cost, accessibility, and workflow complexity.ObjectiveThis study aimed to develop an automated, objective, and clinically interpretable framework for evaluating dental cavity preparation quality using standard two-dimensional (2D) images, with optional integration of 3D depth information.MethodsA deep learning pipeline based on enhanced U-Net architectures was developed to automatically segment cavity and cusp regions from 2D molar photographs. Anatomically informed geometric analyses were applied to quantify cavity-shape similarity, intercuspal distance, isthmus width, and cavity proportionality. Global cavity-shape conformity was assessed using Elliptic Fourier Descriptors (EFDs), enabling scale-, rotation-, and translation-invariant comparisons with reference preparations. When 3D STL data were available, cavity depth and cavity-bed smoothness were additionally quantified. These measurements were integrated into a transparent Cavity Quality Score (CQS) ranging from 1 to 10.ResultsThe cavity segmentation model achieved an internal validation Dice coefficient of 0.81 and an Intersection-over-Union of 0.74, while cusp segmentation achieved a Dice coefficient of 0.83. External validation using measurements from three independent experts demonstrated close agreement between automated predictions and expert consensus for EFD cavity-shape similarity (MAE = 1.32 percentage points; r = 0.981), pooled isthmus-width measurements (MAE = 0.03 mm; r = 0.995), pooled cusp-pair distances (MAE = 0.08 mm; r = 0.999), and cavity depth estimation (absolute error ≈ 0.01 mm).ConclusionThis study presents a hybrid, explainable artificial intelligence framework for objective assessment of dental cavity preparation using widely available 2D images. By integrating deep learning with anatomically informed geometric analysis, the proposed CQS offers a transparent and scalable tool for formative feedback in clinical and competency-based dental education. Further validation against expert summative grading is required before high-stakes implementation.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1909177</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1909177</link>
        <title><![CDATA[Deep learning and hybrid architectures for atypical and complex bone fracture diagnosis: a systematic review of performance and clinical validity]]></title>
        <pubdate>2026-08-10T00:00:00Z</pubdate>
        <category>Review</category>
        <author>Fatma Atitallah</author><author>Johannes C. Ayena</author><author>Assem Thabet</author><author>Neila Mezghani</author>
        <description><![CDATA[Artificial intelligence (AI) is reshaping fracture diagnosis in medical imaging. Despite these advances, accurately identifying atypical fractures (such as stress or pathological fractures) and complex fractures (including comminuted and pelvic fractures) remains a significant clinical challenge. This systematic review evaluates the current evidence on AI models, including advanced architectures, for detecting, classifying, and segmenting atypical and complex bone fractures in humans. A total of 40 studies published between 2015 and 2026 met the predefined inclusion criteria. Eligible studies used real-world imaging modalities (X-ray, CT, or MRI), focused on atypical or complex fractures, employed AI-based approaches with expert-validated reference standards, and reported quantitative performance metrics. Studies based exclusively on synthetic data, restricted to simple fractures, or lacking adequate validation were excluded. Advanced AI models, including hybrid frameworks such as 3D U-Net variants and DeepLabV3+MobileNetV3, were associated with improved performance in several studies, particularly for identifying subtle and multi-fragment fractures. However, substantial heterogeneity in study design, datasets, validation strategies, and evaluation metrics limits direct comparisons across models. Hybrid systems, particularly CNN-based architectures combined with level-set methods or multi-network pipelines, also appeared effective in capturing complex fracture patterns in several studies, although this observation is based on a limited and heterogeneous body of evidence. Overall, the available evidence suggests that advanced AI models have considerable potential to improve the detection, classification, and segmentation of atypical and complex fractures. Nevertheless, the predominance of single-center studies, the limited use of external or prospective validation, and methodological heterogeneity indicate that further standardized, multicenter clinical validation is required before these models can be widely implemented in routine clinical practice.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1885655</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1885655</link>
        <title><![CDATA[Use of artificial intelligence in building personal branding and intercultural leadership]]></title>
        <pubdate>2026-08-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Omer Cruz Caro</author><author>Doris Tarrillo Perez</author><author>Heily Consepcion Portocarrero Ramos</author><author>Yuri Reina Marín</author><author>Judith Nathaly Alva Tuesta</author><author>Jonathan Alberto Campos Trigoso</author><author>River Chávez Santos</author>
        <description><![CDATA[The integration of AI tools reshaping how professionals learn, build reputation, and project their value in digitally and culturally diverse environments. Therefore, this study aims to analyze the relationships among AI tool use, personal branding, and leadership in intercultural contexts. A quantitative, non-experimental, cross-sectional, and correlational study was conducted with 169 university graduates from Peru, Ecuador, and Mexico. Data were collected using a Likert-scale questionnaire and analyzed through descriptive analysis, exploratory factor analysis, principal component analysis (PCA), and K-means clustering. The results indicate that 89.3% reported familiarity with AI tools, even though 79.3% had not received specialized training. Two profiles were also identified: one with moderate familiarity and another with greater technological appropriation, professional visibility, and intercultural competence. The PCA showed that the first two components explained 47.7% of the variance, with intercultural leadership, professional visibility, and technology adoption forming the central dimensions of the model. The results suggest that the use of artificial intelligence tools is associated with better career prospects when accompanied by critical judgment, authenticity, and cultural sensitivity. They also highlight the need to develop digital, ethical, and intercultural competencies in universities and organizations in order to guide relevant and responsible professional development processes.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1895239</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1895239</link>
        <title><![CDATA[GA-AFedOD: gradient-aligned active federated learning for resource-aware object detection in edge industrial IoT]]></title>
        <pubdate>2026-08-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Zepeng Wang</author><author>Xiaogang Yuan</author><author>Jie Chen</author>
        <description><![CDATA[Visual object detection is essential for defect inspection and process monitoring in edge-deployed Industrial Internet of Things (IIoT). Yet, training accurate detectors across distributed factories faces stringent constraints on data privacy, annotation budgets, and uplink communication. Standard federated learning (FL) preserves locality but often wastes labeling resources on redundant frames and overlooks detection-specific gradient alignment when scheduling clients. To bridge this gap, we propose Gradient-Aligned Active Federated Object Detection (GA-AFedOD), a unified framework that jointly optimizes annotation selection, client participation, and model aggregation as a constrained stochastic program. A novel utility metric integrates box-level uncertainty, prototype diversity, gradient alignment, and resource pricing, enabling edge clients to perform locally guided active querying while the server solves a lightweight primal-dual problem for budget-aware client scheduling. We prove a submodular approximation guarantee for the greedy sampling rule and establish a non-convex convergence bound that explicitly captures the impact of label budgets, client drift, and compression noise. This article further clarifies the relationship with recent federated active learning and industrial detection studies, adds parameter and theory-diagnostic analyses, and distinguishes controlled simulation evidence from real-world deployment validation on industrial datasets such as RasPiDets, Electric Power Fitting Dataset (EPFD), and Diverse Insulator Dataset (DINS). Controlled simulation results show that GA-AFedOD achieves considerably higher mean average precision (mAP) while reducing both annotation costs and uplink consumption by over 40% compared with competitive baselines.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1868693</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1868693</link>
        <title><![CDATA[Fear-driven predator–prey dynamics with prey refuge: analytical framework and physics-informed neural network approach]]></title>
        <pubdate>2026-08-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>G. Ramraj</author><author>T. Poornima</author>
        <description><![CDATA[Ecological communities are governed not only by direct consumption but also by indirect behavioral responses triggered by perceived predation risk. Predator-induced fear substantially suppresses prey reproductive output and foraging efficiency even when lethal predation is absent, a mechanism documented across a wide range of taxa including songbirds, ungulates, and marine invertebrates. Motivated by this observation, we formulate a deterministic two-species model that simultaneously incorporates fear-mediated prey growth reduction, partial prey refuge, density-dependent intraspecific regulation, and predator self-interference. The proposed model is distinguished from existing fear–refuge frameworks by jointly embedding four ecological mechanisms within a single functional-response denominator 1 + kv + αu, producing qualitatively novel stability thresholds absent in models incorporating only subsets of these effects. Biological admissibility is rigorously established through positivity and uniform boundedness proofs. The boundedness condition cβ(1-δ)<2aη is derived from first principles by applying Sylvester's criterion to the cross-interaction quadratic form. Three ecologically meaningful equilibria are identified and their local stability is characterized via carefully re-derived Jacobian linearization and the Routh–Hurwitz criterion. Numerical experiments via the fourth-order Runge–Kutta method reveal convergence to a stable coexistence equilibrium across the explored parameter ranges, with the approach transitioning from a stable node to a stable focus as predation intensifies; no sustained oscillations are observed. A physics-informed neural network (PINN) is constructed with four hidden layers of 64 neurons each, tanh activations, Adam followed by L-BFGS training over 10,000 iterations, and 200 collocation points, achieving maximum absolute errors of 7.98 × 10−3 (prey) and 5.83 × 10−3 (predator) relative to the RK4 reference. Comparison with a data-driven neural network of identical architecture shows a fivefold accuracy improvement from the physics-informed loss. Numerical evidence for global stability is reported; rigorous Lyapunov-based analysis is identified as future work.]]></description>
      </item><item>
        <guid isPermaLink="true">https://www.frontiersin.org/articles/10.3389/frai.2026.1813948</guid>
        <link>https://www.frontiersin.org/articles/10.3389/frai.2026.1813948</link>
        <title><![CDATA[Scanner-agnostic MRI harmonization via SSIM-guided disentanglement]]></title>
        <pubdate>2026-08-10T00:00:00Z</pubdate>
        <category>Original Research</category>
        <author>Luca Caldera</author><author>Lara Cavinato</author><author>Francesca Ieva</author><author>the Alzheimer's Disease Neuroimaging Initiative </author>
        <description><![CDATA[IntroductionThe variability introduced by differences in MRI scanner models, acquisition protocols, and imaging sites hinders consistent analysis and generalizability across multicenter studies.MethodsWe present a novel image-based harmonization framework for 3D T1-weighted brain MRI, which disentangles anatomical content from scanner- and site-specific variations. The model incorporates a differentiable loss based on the Structural Similarity Index Measure (SSIM) to preserve biologically meaningful features while reducing inter-site variability. This formulation allows luminance, contrast, and structural components to be modeled separately during optimization. Training and validation were performed on multiple publicly available datasets spanning diverse scanners and sites, with testing on both healthy individuals and populations with pathological conditions. The proposed approach was evaluated across multiple target settings, including scanner-site-specific targets and a style-agnostic target, and compared with representative image-based harmonization benchmark methods.ResultsAcross these target settings, harmonization produced consistent and high-quality outputs. Visual comparisons, voxel intensity distributions, and SSIM-based metrics demonstrated that harmonized images achieved improved alignment across acquisition settings while preserving anatomical fidelity. In the style-agnostic setting, within-subject original–harmonized comparisons showed high anatomical preservation, with the structural component of SSIM reaching 0.975 ± 0.007. Appearance consistency also improved, with Wasserstein distances between mean voxel intensity distributions decreasing from 8.45 ± 5.35 before harmonization to 1.77 ± 0.62, and luminance similarity increasing from 0.952 ± 0.037 to 0.982 ± 0.017. Downstream analyses further confirmed the effectiveness of the proposed approach. For brain age prediction, mean absolute error decreased from 4.08 ± 1.16 to 2.81 ± 0.55 years following style-agnostic harmonization. For Alzheimer's disease classification, the area under the ROC curve improved from 0.857 ± 0.038 to 0.899 ± 0.024. Compared with the considered benchmark methods, the proposed framework showed stronger image-level harmonization and more consistent downstream improvements under the adopted evaluation protocol.DiscussionOverall, the proposed framework enhances cross-site image consistency, preserves anatomically relevant information, and improves downstream predictive performance, providing a robust and generalizable solution for large-scale multicenter neuroimaging studies.]]></description>
      </item>
      </channel>
    </rss>