Search Results (254)

Node-state uncertainty in dynamic spatial networks is commonly characterized by posterior covariance. However, under non-Gaussian outliers, unmodeled systematic biases, and geometric degeneracy, a small posterior covariance does not necessarily correspond to high physical reliability and may lead to overconfident assessments of anomalous nodes. To address the inability of a single uncertainty indicator to adequately support node-state quality evaluation and anomaly-related decision making, this paper proposes a measure-theoretic framework for formalizing node-state quality in dynamic spatial networks. First, the conventional node-state is extended to a generalized state tuple comprising the posterior state estimate, covariance structure, observation evidence set, and environmental metadata, and the posterior reliability that the node belongs to the physically valid state domain is defined as the theoretical quality. Second, a four-dimensional evidence vector consisting of residual consistency, posterior uncertainty, geometric constraint balance, and environmental stability is constructed. A computable quality measure is then obtained through direction-consistent normalization and Soft Logical AND product coupling, satisfying boundedness, direction-consistent monotonicity, and the marginal veto property. On this basis, the inheritance of component-wise convergence by the aggregated quality measure is analyzed and an adaptive observation stopping criterion combining the quality level with marginal variation is established. Controllable quality sequences are constructed according to statistically characterized degradation patterns, including heavy-tailed errors and abnormal degradation modes observed in UrbanNav and M2DGR datasets, for numerical verification. The results show that, while maintaining a comparable mean score for normal nodes, the proposed method reduces the mean scores of outlier-contaminated, geometrically degraded, and overconfident-biased nodes from 0.6151, 0.6371, and 0.6569 under the linear model to 0.4910, 0.4303, and 0.4885, respectively. The corresponding false acceptance rates due to overestimation decrease from 10.14%, 23.46%, and 58.04% to 1.22%, 1.94%, and 1.96%, respectively. Under the current parameter settings, 73.74% of the normal nodes trigger adaptive stopping, whereas none of the three anomalous node types incorrectly triggers acceptance-based stopping. These results indicate that the proposed framework limits the compensation of locally failed evidence by high-quality components and provides a unified quantitative basis for node-state quality evaluation, anomalous-node screening, and observation-process management in dynamic networks. Full article

Plant pests and diseases pose a major global threat to food security and agricultural sustainability, making accurate assessment of plant symptoms important. This study proposes a simple and practical method for quantifying visual symptom severity using binary deep learning classifiers trained only on asymptomatic and severely affected images. Visual symptom severity was estimated from class probabilities, and classification accuracy is additionally used when image groups with similar symptom severity are available. While the framework enables symptom severity quantification at the group level, direct application to individual images is challenging due to overconfident predictions for mildly symptomatic cases. To address this issue, temperature scaling and label smoothing were evaluated, and label smoothing was found to improve reliability for individual image assessment. The method was validated using mosaic and wilting symptoms across multiple architectures. Results showed close agreement in classification accuracy and class probabilities across architectures, with maximum differences of 4.8% (mosaic) and 9.7% (wilting). The estimated visual symptom severity was generally consistent with expert visual assessment under the conditions examined in this study. The proposed method requires only minimal annotation and uses standard model outputs, making it simple, interpretable, and potentially applicable to other visually assessed traits. Full article

Background/Objectives: AI chatbots may shape patient expectations before professional consultation. This scenario-based first-response study evaluated whether four user-facing chatbots provided orthodontic treatment-direction advice concordant with an expert benchmark and whether responses contained safety, referral, or overconfidence concerns. Methods: Forty fictional Turkish patient-oriented scenarios across eight categories were independently coded by three orthodontists as clear aligners, fixed appliances, both options, examination required, or advanced specialist/surgical evaluation required. Each scenario was submitted once to ChatGPT, Claude, Copilot, and Gemini on 20 May 2026. Two independent non-author orthodontists coded 160 archived first responses using a predefined framework, with adjudication before analysis. Results: Inter-expert agreement was moderate (Fleiss kappa = 0.491; Gwet AC1 = 0.528). Under the majority benchmark, exact concordance was 82.5% for ChatGPT, 67.5% for Claude, 42.5% for Copilot, and 37.5% for Gemini (Cochran Q = 34.105, p < 0.001). The overall difference remained significant in the 17 unanimous scenarios (Q = 11.455, p = 0.010), but a post hoc alternative-reference analysis that adopted the dissenting expert code in the 23 non-unanimous scenarios attenuated the rates to 57.5%, 52.5%, 52.5%, and 42.5%, respectively (Q = 4.222, p = 0.238). Coded safety-concern rates ranged from 15.0% to 62.5%. Conclusions: The sampled first responses differed in treatment direction and safety coding, but estimates were sensitive to the expert reference definition. Under the tested single-date, single-language, and single-run conditions, the findings represent a conditional snapshot rather than a time-invariant ranking of model capability. Patient-facing chatbots should support nondirective pre-consultation education and referral, not autonomous appliance selection. Full article

Background/Objectives: Anthropometric machine-learning models may approximate body-composition classifications, but performance can be inflated by inconsistent preprocessing, non-independent validation records, and incomplete calibration reporting. This study evaluated a sex-specific bioelectrical impedance analysis (BIA)-defined high-adiposity phenotype using simple anthropometric variables in adults with and without hypertension. Methods: Of 583 prespecified records, 11 with invalid placeholder-coded values in required anthropometric or body-composition fields were excluded, leaving 572 participants (385 normotensive and 187 hypertensive). A high-adiposity phenotype was defined as BIA-derived body fat ≥ 25% in males or ≥35% in females. Predictors were sex, height, body weight, waist circumference, and hypertension status; body mass index and body-fat percentage were excluded. Eight algorithms were assessed using 10 repetitions of stratified five-fold group cross-validation, with identical predictor profiles kept within the same fold. Continuous predictors were standardized within training folds. Performance was estimated from averaged out-of-fold probabilities with 2000 stratified bootstrap confidence intervals, calibration measures, and SHAP analysis. Results: A high-adiposity phenotype was present in 441 participants (77.1%). Random forest achieved the highest discrimination (ROC AUC = 0.959, PR AUC = 0.980). Gradient boosting provided the strongest threshold-dependent performance (accuracy = 0.937, balanced accuracy = 0.895, sensitivity = 0.973, specificity = 0.817, precision = 0.947, F1 score = 0.960, MCC = 0.817) and the lowest Brier score (0.057), but its calibration slope was 0.462, indicating overconfident probabilities. SHAP analysis identified waist circumference as the largest attribution within the fitted gradient-boosting model; this result must be interpreted jointly with the ablation analysis because sex, height, and body weight are inputs to the proprietary Tanita equation. Conclusions: Simple anthropometric variables classified the prespecified Tanita BIA-derived high-adiposity threshold with strong internal performance after duplicate-aware validation. Sex, height, and body weight alone achieved a ROC AUC of 0.920; adding waist circumference produced a small and uncertain increase in discrimination (ΔROC AUC = 0.0054, 95% CI −0.0060 to 0.0153), whereas hypertension status added a negligible value. The findings represent internal validation of a device-defined outcome, not prediction of an independent biological reference, and require external validation against criterion body-composition methods before clinical application. Full article

This study investigates how behavioral biases influence the investment decisions of retail investors in Kolkata, India, with particular emphasis on the moderating roles of financial literacy and financial awareness. Despite the rapid expansion of India’s financial markets and increased retail participation, investors often exhibit irrational behavior driven by psychological biases. This study seeks to answer the following research question: To what extent do behavioral biases affect the investment decisions of retail investors in Kolkata, India, and how effectively do financial literacy and financial awareness mitigate these effects? Using primary data collected from 444 retail investors in Kolkata, this study employs Partial Least Squares Structural Equation Modeling (PLS-SEM) to test the conceptual framework. The findings reveal that behavioral biases—namely overconfidence, anchoring, herd behavior, and loss aversion—significantly and negatively affect investment decisions. However, financial literacy and financial awareness not only positively influence decision-making but also significantly moderate the relationship between behavioral biases and investment outcomes. This study contributes to behavioral finance literature by distinguishing between financial literacy and financial awareness as separate constructs and demonstrating their dual role as both direct and moderating factors. The findings have important implications for policymakers, financial educators, and investment advisors in designing targeted interventions to improve investor decision-making. Full article

Chronic kidney disease (CKD) is a global health disease that must be recognized and monitored early to prevent major consequences and improve the health of patients, yet modern gradient boosting algorithms often produce dangerous false positives due to overconfidence and static ensemble weighting. To address this, we propose the Hyper-Fidelity Dynamic Ensemble framework for CKD diagnosis (HFDE–CKD). Our approach utilizes a rigid quad-fold data isolation protocol and applies Standard SMOTE to the training manifold. By removing direct diagnostic identifiers (e.g., eGFR, creatinine, and albumin), the framework is forced to rely on underlying early indications. We quantify predictive doubt using Shannon entropy and inter-model variance, concatenating these measurements with calibrated probability vectors into a multidimensional uncertainty matrix optimized via a logistic meta-learner. Evaluated on an imbalanced dataset of 11,933 records, HFDE–CKD achieved an accuracy of $0.8596$, a sensitivity of $0.8900$, and an F1-score of $0.8979$. Furthermore, HFDE–CKD’s superiority over the best-performing baseline was confirmed through McNemar’s test, which was statistically significant ($p<0.001$). Emphasizing diagnostic safety, the model yielded a Brier score of $0.1012$, an NLL of $0.3225$, and a specificity of $0.7907$, significantly reducing the risk of false positives. Furthermore, ablation testing confirmed the advantage of uncertainty injection, while SHAP analysis validated clinical dependency on early metabolic biomarkers. The proposed HFDE–CKD framework systematically leverages epistemic uncertainty to bypass the traditional sensitivity-versus-false-positive trade-off, providing a precisely calibrated, robust decision-support tool for early CKD screening. Full article

Generative AI tutors have become a common tool for independent learning, yet their capacity to support self-regulated learning (SRL) is poorly understood. This simulation-based textual analysis of prompt design evaluates a frontier large language model (Claude Sonnet 4.6) as a tutor across 60 scripted sessions on a single topic (density), crossing three levels of SRL-informed system prompting (Minimal, Moderate, Extensive) with four learner-behavior variants (Standard, Misconception, Disengagement, Overconfidence). Tutoring transcripts were scored on a 14-dimension framework spanning SRL phases, SRL developmental stages, self-determination theory principles, and Merrill’s First Principles of Instruction, applied via an LLM judge. Adding SRL context to the system prompt raised total tutoring scores, but only at the Extensive SRL support level. Minimal and Moderate prompting produced the same performance, near 36 on a 70-point scale, and Extensive prompting raised it to 40, a statistically significant effect (partial η² = 0.24). The learner’s behavior in the session had a larger effect than the prompt did (partial η² = 0.37), with disengaged learners scoring lowest. The threshold pattern held under an independent judge from a different developer than the tutor model. The findings support a method for evaluating GenAI tutors empirically and point to dynamic, dialogue-aware prompting alongside explicit SRL scaffolding. Full article

Uncertainty quantification (UQ) in medical image segmentation is essential for ensuring the reliability and interpretability of deep learning models in clinical decision-making. While convolutional neural networks (CNNs) and transformer-based architectures have achieved remarkable segmentation performance, they often provide deterministic outputs without accounting for uncertainty, which can lead to overconfident predictions in ambiguous cases. This paper presents a comprehensive survey of UQ techniques in medical image segmentation, categorizing existing approaches into Bayesian methods, deep ensembles, deterministic methods, test-time data augmentation, and hybrid models, while treating foundation-model-based UQ as a separate cross-cutting category. We examine key methodologies, including Monte Carlo dropout, Bayesian neural networks, variational inference, and ensemble learning, discussing their advantages and limitations in addressing aleatoric and epistemic uncertainties. Additionally, we explore the clinical relevance of UQ by reviewing its applications in brain tumor segmentation, cardiac imaging, lung nodule detection, and other medical domains. The paper also highlights key evaluation metrics, such as calibration errors, uncertainty–error correlation, and visual interpretability, to assess the effectiveness of UQ methods. Finally, we discuss challenges and future research directions, emphasizing the need for scalable, interpretable, and clinically actionable uncertainty quantification strategies to improve trust in AI-assisted medical image analysis. Full article

Wear prediction for agricultural soil-engaging components is computationally demanding when discrete element method (DEM) simulations are repeatedly used for design evaluation and operating-parameter screening. In this study, an Archard-inspired Gaussian process regression (GPR) residual-learning surrogate was developed for rapid prediction of the total wear volume calculated by EDEM for a ploughshare. The physical prior was a monotonic operational-parameter proxy motivated by the load and sliding trends in Archard theory, which did not directly use DEM-derived normal force, sliding distance, or frictional work. A soil–ploughshare interaction model was used to generate 100 full-factorial samples with tillage depth, tillage speed, and penetration angle as inputs. The Archard-inspired prior, cubic polynomial Ridge regression, standard GPR, and prior-guided residual GPR were evaluated by cross-validation, repeated random splits, and boundary-level extrapolation tests. Across 30 repeated 90%/10% splits, standard and Archard-inspired GPR achieved mean R² values of 0.9927 ± 0.0014 and 0.9908 ± 0.0021, respectively. In the 200 mm tillage-depth extrapolation test, the latter performed best, with R² = 0.9752, RMSE = 0.000252 mm³, and MAPE = 2.68%; however, the former was more accurate in the tillage-speed and penetration-angle extrapolation tests, and the 48% interval coverage of the prior-guided model in the penetration-angle test indicated overconfidence when the prior was biassed. These results show a conditional, rather than universal, benefit of the Archard-inspired prior: it improved extrapolation plausibility for the load-dominated tillage-depth case but did not improve all boundary predictions. The surrogate predicts EDEM-simulated wear, and its engineering validity depends on DEM calibration, the selected wear coefficient, and future soil-bin or field validation. Full article

Background: This study examines how four canonical behavioral biases (overconfidence, herding, anchoring, and loss aversion) influence investor decision-making in the Saudi stock market (Tadawul), and whether overconfidence and loss aversion operate as moderating forces on herding and anchoring, respectively. Methods: Employing a quantitative, cross-sectional design with a stratified sample of 384 retail investors, the study applies Partial Least Squares Structural Equation Modelling (PLS-SEM) to test six hypotheses derived from Modern Portfolio Theory and Behavioral Finance frameworks. The measurement model satisfies established thresholds for reliability, convergent validity, and discriminant validity. Results: Results confirm that loss aversion is the dominant predictor of behaviorally influenced decision-making (β = 0.402, p < 0.001, f² = 0.188), followed by herding (β = 0.234, p < 0.001) and overconfidence (β = 0.164, p = 0.001), while anchoring does not exert a statistically significant independent effect (β = 0.102, p = 0.084 one-tailed, p = 0.168 two-tailed). Neither the overconfidence × herding (β = 0.005, p = 0.920, two-tailed) nor the loss aversion × anchoring (β = −0.039, p = 0.330, two-tailed) interaction terms reach significance, indicating that these bias pairs operate as independent additive forces rather than compounding systems. The model explains 55.7% of the variance in investor decision-making (R² = 0.557). Conclusion: The findings advance behavioral finance theory in GCC and Islamic equity markets by (1) demonstrating non-equivalence of anchoring effects relative to Western-market benchmarks, (2) resolving competing theoretical predictions about bias interaction effects, and (3) providing context-specific evidence that loss aversion subsumes anchoring cognition in the Saudi market. Practical implications for the Capital Market Authority, financial educators, and individual investors are discussed and contextualized within the Saudi market setting. Full article

This study aims to examine the moderating effect of board gender diversity in the relationship between the overconfidence of the CEO and corporate tax avoidance of listed firms in Jordan. Based on upper echelons theory, agency theory, and resource dependence theory, it examines the potential influence of female board representation on the tax implications of managerial overconfidence in an emerging-market context. The study uses panel data of 70 industrial and service enterprises listed on the Amman Stock Exchange (ASE) for the period (2019–2024), yielding 420 firm-year observations. To measure corporate tax avoidance, we use the effective tax rate (ETR) and cash flow effective tax rate (CFETR), and CEO overconfidence is measured by a composite index of observable executive characteristics. The level of board gender diversity is computed as the percentage of female directors, and the hypotheses are tested with panel regression models that include relevant firm-level control variables. The results indicate that CEO overconfidence is negatively and significantly related to ETR, suggesting that the overconfident CEO is more likely to engage in tax avoidance. The moderating results also indicate that the relationship between board gender diversity and tax avoidance is reshaped by enhancing accrual-based tax avoidance and curbing cash-based tax avoidance. The results contribute to the literature on executive traits, corporate governance, and tax behavior by providing evidence from Jordan and by applying a practical measure of CEO overconfidence suitable for contexts with limited data availability. Full article

Dynamic community detection seeks to identify changing structural groups in temporal graphs; however, current neural methodologies are susceptible to misinterpreting transient edges, noisy temporal variations, or unusual spectral disturbances as authentic structural changes. This research introduces TriMeta-BFNet, a tri-meta stacked atypical-frequency Bayesian Fourier neural network designed for hallucination-resistant community discovery. The proposed system presents a three-dimensional meta-counterbalance mechanism that includes topological consistency, Fourier-domain atypical frequency modeling, and Bayesian posterior uncertainty estimation. Initially, temporal graph signals are converted into the Fourier domain to distinguish stable low-frequency community patterns from erratic high-frequency disturbances. Secondly, unusual frequency points are detected by spectral energy deviation and integrated into a stacked neural representation module, enabling the model to differentiate significant structural alterations from extraneous oscillations. Third, Bayesian inference is employed to assess posterior uncertainty regarding community assignments, therefore mitigating overconfident predictions in the presence of ambiguous or noisy graph evolution. The three components are simultaneously optimized via a cohesive objective function that integrates community detection loss, structural consistency regularization, atypical-frequency penalty, temporal stability management, and Bayesian calibration loss. The resultant structure offers both resilient community divisions and comprehensible hallucination-risk assessments. TriMeta-BFNet theoretically conceptualizes hallucination in dynamic community detection as an imbalance of structural, spectral, and uncertainty factors, and it develops a mathematically rigorous counterbalance mechanism to mitigate erroneous community evolution. The suggested model presents a novel approach to uncertainty-aware, frequency-sensitive, and interpretable dynamic graph learning. Full article

Background: Dedicated artificial intelligence (AI) systems for fracture detection already exist, yet general-purpose multimodal models are increasingly accessible to clinicians despite not being developed or formally validated as medical devices. Their behavior in focused orthopedic imaging tasks remains insufficiently characterized. Purpose: To characterize how two accessible general-purpose multimodal models interpret AP pelvis radiographs with hip fractures, focusing on context dependence, overconfidence, and complementary error patterns within a surgically confirmed positive-only cohort. This was a behavioral characterization study of a fracture-positive cohort, not a diagnostic accuracy evaluation. Methods: In April 2026, we retrospectively studied 214 surgically confirmed hip fractures on AP pelvis radiographs using two general-purpose multimodal models under six prompting conditions. In runs A–D, the models were explicitly told that a hip fracture was present and were asked to classify it; in runs E–F, they were not told whether a hip fracture was present. Each image was rerun de novo in a separate chat session through vendor APIs using a fixed base prompt and no image preprocessing. We recorded hip-fracture detection, correct laterality, coarse fracture pattern, intracapsular displacement, AO/OTA grading, subtrochanteric identification, and self-reported confidence. Because the cohort contained hip fractures only, we report fracture-detection rates and classification performance within a positive-only cohort rather than full diagnostic-accuracy metrics. Results: Using the more conservative endpoint of hip-fracture detection with correct laterality, GPT-5.4 was correct in 79.0% and 86.4% of cases in runs E and F, whereas Gemini was correct in 80.4% and 93.5%, respectively. When outputs from both models were combined, this endpoint reached 89.7% in run E and 96.7% in run F, indicating complementary rather than redundant error patterns. Incorrect laterality cues markedly degraded performance, from 90.7% to 66.4% in GPT-5.4 and from 97.7% to 57.0% in Gemini. Performance remained limited for treatment-relevant subtyping, particularly AO/OTA grading and subtrochanteric identification. Both models frequently remained highly confident when wrong, and self-reported confidence did not reliably distinguish correct from incorrect outputs. Conclusions: Accessible general-purpose multimodal models showed partial capability for coarse hip-fracture interpretation, but they remained context-sensitive, unreliable for treatment-relevant subtyping, and highly confident even when incorrect. Their complementary error patterns are hypothesis-generating rather than evidence of clinical readiness. On the basis of these findings, we do not support unvalidated or uncontrolled clinical use of such models. As access to these tools expands, explicit usage boundaries, minimum performance expectations, repeated local revalidation, and sustained human oversight become increasingly necessary. Full article

Global retail e-commerce sales have surged, yet product fit uncertainty remains a significant challenge, leading to rising product return rates. To address consumer concerns about return shipping costs, major Chinese online retail platforms have introduced return shipping insurance (RSI). Retailers can choose between Retailer-RSI (RRSI), which is provided by the retailer, and Customer-RSI (CRSI), which is purchased by consumers. Despite these options, information asymmetry causes insurers to assess return rates with bias—referred to as managerial confidence bias. Consequently, platforms are increasingly partnering with insurers to enhance their RSI offerings. This study develops a game-theoretical model to examine the dynamics between a platform and an insurer, as well as the impact of managerial confidence bias on RSI strategies. Our analysis reveals that the platform–insurer relationship is crucial in determining the optimal RSI strategy. Under an independent insurer, RSI is viable only if the insurer underestimates product return rates (i.e., exhibits overconfidence bias); RRSI is preferred if the bias is sufficiently strong, whereas CRSI is chosen otherwise. In contrast, under a dependent insurer, CRSI is favored by the retailer only when its return handling costs are substantially high; otherwise, RRSI is preferred. Furthermore, RSI consistently increases consumer surplus by reducing return hassle costs while only mildly raising the product price. However, the independent insurer’s bias leads to its own profit loss, resulting in a “loss–win–win–win” scenario across stakeholders. In contrast, the dependent insurer, supported by platform subsidies, can yield a “win–win–win–win” outcome that aligns stakeholder interests and enhances long-term platform benefits. Full article

The study investigates the state-dependent dynamics of overconfidence in the Bangladesh equity market by exploring the relationship between market returns and trading volume within a nonlinear information-theoretic framework. Building up on the traditional return–volume literature, the study differentiates between total market returns and unexpected returns, with the latter representing unexpected information shocks obtained using the Market Index Model. Transfer Entropy with bootstrap inference estimates the directional and asymmetric information flows across five different market states, namely: bullish, bearish, crisis, extended crisis, and COVID-19. The evidence suggests that the overconfidence biases in aggregate market returns are small and intermittent and are reflected in poor and unstable information flow between market returns and trading volume. In comparison, unexpected market returns have a directionally significant impact on trading behavior, which supports the behavior of state-dependent overconfidence. The findings also reveal that overconfidence is higher in normal and bullish market situations but drops significantly in crisis-based situations. The asymmetric analysis indicates increased trading responses to negative returns shocks, as it is more evident that investors are more sensitive to losses and recovery expectations. The research adds to behavioral finance literature on frontier markets through an unexpected return decomposition with nonlinear causality model. The results have serious implications on market surveillance, assessment of investor behavior and design of regulatory policies. Full article