Search Results (3,462)

Classic machine learning and regime identification methods applied to financial time series lack theoretical guarantees and exhibit systematic failure modes: heavy-tails invalidate moment-based geometry, rendering distances and centroids dominated by extremes or unstable; jumps violate smoothness, destabilizing local regressions, kernel methods, and gradient-based learning; and non-stationarity disrupts neighborhood relations, so distances in classical feature spaces no longer reflect meaningful proximity. To address these challenges, we propose a topology-based machine-learning framework grounded on probabilistic reconstruction of state-space geometry, which replaces moment- and smoothness-dependent representations with deformation-stable summaries of state-space geometry, preserving neighborhoods, adjacency, and topology. The finite-sample validity of homeomorphic state-space reconstruction, required for topology-based machine learning, is assessed through numerical studies on synthetic data with heavy tails, jumps, and known ground-truth regimes. Further diagnostics of local invertibility and bounded geometric distortion quantify when embedding windows are consistent with local diffeomorphic behavior, enabling metric-sensitive, geometry-aware learning. Clustering of Hilbert-space summaries accurately recovers underlying market tail-risk regimes with robust results across selected filtrations. Temporal, feature-space, and cluster-label null tests confirm that topology-based clustering captures genuine topological structure rather than noise or artifacts, and encodes temporal dependencies at local, mesoscopic, and network levels associated with market regimes. Full article

Background/Objectives: Accurate and reproducible lymph node (LN) measurement is essential for oncologic staging and therapy monitoring but is subject to inter-reader variability. This study evaluated the accuracy and reproducibility of a fully automated artificial intelligence (AI)-based LN measurement workflow in contrast-enhanced chest CT, using multi-reader manual measurements as reference. Methods: Sixty thoracic LNs from seven patients were independently measured by 13 radiologists in two reading rounds. The median of all measurements served as the ground truth (GT). Automated short- and long-axis diameters were derived from fully automated 3D CNN-based segmentations. Agreement between AI and manual measurements was assessed using Friedman testing, intraclass correlation coefficients (ICCs), and concordance correlation coefficients (CCCs). Measurement stability was evaluated across repeated runs on different hardware systems. Results: A total of 2280 manual measurements were analyzed. Manual assessment showed significant inter-reader variability (p < 0.01), while intra-reader agreement was high. No significant differences were observed between AI-based measurements and the GT (all p > 0.01). Agreement was good, with CCC values of 0.86 (SAD) and 0.79 (LAD). AI-based measurements were numerically stable across hardware configurations. Conclusions: Fully automated AI-based LN measurements in chest CT scans provide strong agreement with multi-reader consensus and high numerical stability. Automated measurement may support more standardized and reproducible oncologic imaging assessment. Full article

This study examined how social media content influences value co-creation among organic product consumers through the mediating roles of environmental awareness, green truth, and environmental attitude. Grounded in the Stimulus-Organism-Response (SOR) framework, social media content is conceptualized as a stimulus, environmental awareness, green trust, and environmental attitude as internal organism states, and value co-creation as the behavioral response. A cross-sectional quantitative design was applied using a 20-item questionnaire administered to 739 organic-product consumers. Data were analyzed using partial least-squares structural equation modeling (PLS-SEM). The results indicate that social media content does not directly affect value co-creation but significantly influences environmental awareness, green trust, and environmental attitude. Environmental awareness and green trust positively affect both environmental attitude and value co-creation, and environmental attitude emerges as the strongest direct predictor of value co-creation. These findings confirm the mediating role of cognitive and attitudinal mechanisms in transforming digital sustainability content into collaborative consumer behavior. This study contributes to the literature on sustainable consumption by integrating communication, cognitive, and attitudinal variables in a single explanatory model. Practically, the findings suggest that sustainability communication strategies in digital environments should prioritize credibility and environmental knowledge to foster consumer participation in value co-creation. Full article

In size, weight, and power (SWaP)-constrained optical systems, such as spaceborne LiDAR, high-precision centroid localization often relies on focal-plane measurements without dedicated wavefront sensors. Under such conditions, the nonlinear coupling between optical aberrations and sensor noise introduces systematic bias that is difficult to mitigate using conventional centroiding methods. To address this issue, we propose a physics-conditioned feature correction framework based on an aberration-conditioned attention mechanism. A hybrid CNN–Transformer architecture is employed to predict and compensate for systematic centroid bias. Specifically, convolutional layers encode the degraded spot morphology, while a multi-head attention mechanism leverages Seidel aberration coefficients to adaptively modulate spatial features for precise regression. Given the unavailability of absolute ground-truth coordinates in empirical scenarios, a physics-consistent simulation framework based on scalar diffraction theory is constructed to generate synthetic data for supervised learning. Simulation results indicate that the proposed method objectively reduces anisotropic systematic bias, achieving a localization root-mean-square error (RMSE) of 0.011 to 0.021 pixels, and maintains stable sub-pixel accuracy even under a 10% empirical prior perturbation. To evaluate generalization performance and engineering reliability, a wedge-based double-spot platform is developed to verify physical consistency via geometric invariance. Experimental results demonstrate a measured spacing standard deviation (SD) of 0.015 to 0.039 pixels. This validates the framework’s transferability from theoretical simulation to controlled physical measurements, providing an algorithmic foundation for precision optical metrology in hardware-constrained environments. Full article

Hyperspectral remote sensing (HRS) is gaining widespread adoption within the geoscience and Earth observation communities. It fosters diverse applications, including precision agriculture, soil science, mineral exploration, and carbon detection, to name a few. Recent technological advancements facilitated a growing number of satellite missions as well as an increase in the availability of commercial sensors and platforms, such as drones. A significant challenge in deploying the varied platforms and sensors is the design and optimization of the hyperspectral surveys. Forward modelling simulators are valuable for optimizing mission parameters and estimating imaging performance. Limited accessibility of open-source simulators presents an obstacle for users who seek to benefit from such tools. To bridge this gap, HySIMU (Hyperspectral SIMUlator) was developed and described herein. It is an open-source, forward modelling toolkit that combines and integrates a primary processing pipeline with various open-source packages into a transparent and modular workflow. It offers a cost-effective approach to evaluating the performance of hyperspectral surveys. HySIMU is designed to simulate hyperspectral imagery based on user-defined targets, platforms, and sensor parameters. Features include (i) a ground truth data cube builder for customizable input parameters, (ii) a terrain-based solar and view geometry calculator for illumination modelling, (iii) integrated open-source radiative transfer models for incorporating atmospheric effects, and (iv) spatial resampling filters. In this manuscript, the initial framework for HySIMU is presented with some example applications, including two validation studies with real hyperspectral images. As remote sensing technologies advance, forward modelling toolkits such as HySIMU play a crucial role in refining mission designs and assessing survey feasibility. The scalability for arbitrary hyperspectral sensors, platforms, and spectral libraries ensures broad applicability. Of particular importance is support for parameter optimization for both scientific and commercial HRS campaigns. Full article

Cataract diagnosis requires a comprehensive dilated examination by an ophthalmologist using a slit lamp; there is currently no effective means to objectively screen for cataracts in the community using portable devices without dilation. We hypothesized that it would be possible to predict cataract severity using deep learning on images taken using a portable smartphone-based slit lamp prototype, with and without dilation. In this prospective cross-sectional pilot study, slit lamp images were captured from eligible patients with cataracts in a tertiary clinic using a portable slit lamp prototype attached to a smartphone. The Pentacam nuclear staging score (PNS, Pentacam^®, Oculus, Inc., Arlington, WA, USA) was taken from the dilated pupils and served as ground truth. A transformer prototypical network with the Swin transformer on the images was trained to assign the class label corresponding to the highest predicted probability. Heat maps were generated based on attribution masks to identify the anatomical areas of concern. A total of 1900 images from 198 eyes of 99 patients were captured. The average age was 65.3 ± 10.4 years (range, 41.0 to 88.0 years) and the average PNS score was 1.57 ± 0.81 (range, 0 to 4). The model achieved an average accuracy of 81.25% and 74.38% for undilated and dilated eyes, respectively. Heat map visualization using the integrated gradient method successfully identified the anatomical area of interest in certain images. This study suggests the possibility of estimating cataract density using a portable smartphone slit lamp device without dilation. Further work is under way to validate this technique in a larger and more diverse group of eyes with cataracts. Full article

This study investigates the application of computational hemodynamic modeling, involving both FSI and CFD models, using SimVascular to simulate blood flow in the right pulmonary artery for patient-specific cardiovascular assessment. The artery’s three-dimensional geometry was reconstructed from a computed tomography (CT) image, and pressure measurements from a CardioMEMS™ device were used as clinical ground truth for validation. To represent the arterial hemodynamics, we initially formulated a fluid–structure interaction (FSI) approach to capture wall mechanics. However, given the high computational cost of fully patient-specific FSI simulations for routine clinical decision-making, we evaluated the validity of key simplifications by assuming rigid vessel walls coupled with a three-element Windkessel (3WK) model and applying a half-sine inflow waveform derived from the patient’s cardiac output. These simplifications yielded results with minimal error: the rigid-wall assumption introduced a 1.1% deviation, while the idealized waveform resulted in a 0.56 mmHg offset. Crucially, while wall rigidity was acceptable, we found that arterial compliance in the boundary conditions is non-negotiable; reducing the model to a pure resistance approach resulted in non-physiological pressures (130 mmHg). A subsequent parametric analysis examined how varying resistance (R) and compliance (C) distinctively alter the pressure waveform morphology. The results underscore the potential of combining remote monitoring data with validated computational simulations to deepen the understanding of cardiovascular dynamics and enhance diagnostic and therapeutic approaches for cardiovascular diseases. Full article

Background: Accurate dietary assessment is vital for preventing malnutrition in aging populations, particularly in home-care settings. Although Large Multimodal Models (LMMs) for nutrient estimation are evolving, their nutrient-specific accuracy requires rigorous validation. Methods: Fifteen standardized hospital meals were photographed under controlled conditions (90-degree angle, 500 lux). Ground truth values were determined by direct weighing. Estimates for energy and macronutrients were performed by 10 registered dietitians (RDs) and 10 AI models (including ChatGPT-4o and Gemini 1.5 Pro). Accuracy was assessed using Pearson’s correlation, Mean Absolute Error (MAE), and Bland–Altman analysis to quantify systematic bias. Results: For energy and carbohydrates, RDs and top-performing AI models (notably ChatGPT-4o and Gemini 1.5 Pro) demonstrated practical accuracy (r > 0.8, frequently within ±10% range). However, accuracy for protein and lipids was significantly lower across all AI models. Specifically, all AI models exhibited a substantial systematic overestimation of lipids (Mean Bias > +20%, p < 0.01), highlighting a critical “invisible nutrient” bias. Conclusions: Current AI tools show potential for caloric and carbohydrate monitoring but struggle with lipid and protein density. These findings emphasize the need for human–AI collaboration (“human-in-the-loop”) and the integration of cooking metadata to improve clinical utility in geriatric nutrition. Full article

Collisions between over-height vehicles and low-clearance bridges cause infrastructure damage and pose safety risks. Existing detection systems rely primarily on optical sensors, which suffer from performance degradation in adverse weather conditions. This paper presents an alternative approach based on a 94 GHz millimeter-wave radar that achieves velocity-independent height measurement. The proposed technique exploits the ratio of Doppler shifts from two scattering centers on a vehicle, specifically the roof and the wheel–road interface. This ratio depends only on the measurement geometry, as the unknown vehicle velocity cancels algebraically, enabling direct height computation without speed measurement. The paper provides a closed-form height estimation model, analyzes the trade-off between frequency resolution and geometric constancy during integration, and presents experimental validation using a scaled laboratory testbed. An optical tracking system is used solely for ground-truth validation in the laboratory and is not required for operational deployment. Results across six test cases with heights ranging from 20 cm to 46 cm demonstrate an average absolute error of 0.60 cm and relative errors below 3.3 percent. A scaling analysis for representative full-scale geometries indicates that at highway speeds of 80 km/h, integration times in the millisecond range (approximately 3–18 ms for representative 20–50 m measurement standoff) are feasible; warning distance can be extended independently by upstream radar placement. The expected advantage in fog, rain, and dust is based on established W-band propagation characteristics; dedicated adverse-weather and full field validation (including multipath, clutter, and multi-vehicle scenarios) remain future work. Full article

The deterministic simplification of parking maneuvers in traditional traffic models presents a critical challenge for the safe integration of Autonomous Vehicles (AVs). This study establishes a stochastic human baseline to provide a naturalistic ground truth dataset essential for calibrating perception and prediction sensors in mixed traffic scenarios. Through the analysis of 1038 maneuvers observed in a university shared space in Catania, Generalized Linear Models and Kaplan–Meier estimators were applied to quantify the impact of geometric constraints on 0°, 45°, and 90° configurations. Results identify 45° angled parking as the Pareto-optimal solution regarding stability and speed, achieving an average maneuver time of 7.54 s. Furthermore, a vertical parking paradox emerges: in the presence of narrow aisles, entry times increase drastically, generating bottlenecks with an 85th percentile exceeding 50 s. Finally, a structural functional asymmetry reveals that exit maneuvers require approximately 54% of the time needed for entry. These findings provide empirical metrics essential for validating human behavior models and fine-tuning decision-making and timeout logic in autonomous driving systems. Full article

Inertial localization is particularly valuable in GPS-denied environments such as indoors. However, localization using only Inertial Measurement Units (IMUs) suffers from drift caused by motion-process noise and sensor biases. This paper introduces Uncertainty-aware Map-constrained Inertial Localization (UMLoc), an end-to-end framework that jointly models IMU uncertainty and map constraints to achieve drift-resilient positioning. UMLoc integrates two coupled modules: (1) a Long Short-Term Memory (LSTM) quantile regressor, which estimates the specific quantiles needed to define $68\%$, $90\%$ and $95\%$ prediction intervals serving as a measure of localization uncertainty and (2) a Conditioned Generative Adversarial Network (CGAN) with cross-attention that fuses IMU dynamic data with distance-based floor-plan maps to generate geometrically feasible trajectories. The modules are trained jointly, allowing uncertainty estimates to propagate through the CGAN during trajectory generation. UMLoc was evaluated on three datasets, including a newly collected 2-h indoor benchmark with time-aligned IMU data, ground-truth poses and floor-plan maps. Results show that the method achieves a mean drift ratio of $5.9\%$ over a $70\mathrm{m}$ travel distance and an average Absolute Trajectory Error (ATE) of $1.36\mathrm{m}$, while maintaining calibrated prediction bounds. Full article

The topology identification (TI) of low-voltage distribution networks (LVDNs) is the foundation for their intelligent operation and lean management. However, the existing identification methods may produce inconsistent results under measurement noise, missing data, and heterogeneous load behaviors. Without principled multiple method fusion and meter-level confidence quantification, the reliability of the identification results is questionable in the absence of ground-truth topology. To address these challenges, a confidence-aware TI (Ca-TI) method for the LVDN based on weakly supervised learning (WSL) and Dempster–Shafer (D-S) evidence theory is proposed, aiming to infer each meter’s latent topology connectivity label and quantify the meter-level confidence without ground truth by fusing different identification methods. Specifically, within the framework of data programming (DP) in WSL, different TI methods were modeled as labeling functions (LFs), and a weakly supervised label model (WSLM) was adopted to learn each method’s error pattern and each meter’s posterior responsibility; within the framework of D-S evidence theory, an uncertainty-aware basic probability assignment (BPA) was constructed from each meter’s posterior responsibility, with posterior uncertainty allocated to ignorance, and was further discounted according to the missing data rate; subsequently, a consensus-calibrated conflict-gated (CCCG)-enhanced D-S fusion rule was proposed to aggregate the TI results of multiple methods, producing the final TI decisions with meter-level confidence. Finally, the test was carried out in both simulated and actual low-voltage distribution transformer areas (LVDTAs), and the robustness of the proposed method under various measurement noise and missing data was tested. The results indicate that the proposed method can effectively integrate the performances of various TI methods, is not adversely affected by extreme bias from any single method, and provides the meter-level confidence for targeted on-site verification. Further, an engineering deployment scheme with cloud–edge collaboration is further discussed to support scalable implementation in utility environments. Full article

High-quality Fourier Transform Infrared (FTIR) imaging usually needs extensive signal averaging to reduce noise and drift, which severely limits clinical speed. Deep learning can accelerate imaging by reconstructing spectra from rapid, single-scan inputs. However, separating noise and baseline drift simultaneously without ground truth is an ill-posed inverse problem. Standard black-box architectures often rely on statistical approximations that introduce spectral hallucinations or fail to generalize to unstable atmospheric conditions. To solve these issues, we propose a physics-informed cascade Unet that separates denoising and baseline correction tasks using a new, deterministic Physics Bridge. This architecture forces the network to separate random noise from chemical signals using an embedded SNIP layer to enforce spectroscopic constraints instead of learning statistical approximations. We benchmarked this approach against a standard single Unet and a traditional Savitzky–Golay smoothing followed by SNIP baseline correction workflow. We used a dataset of human hypopharyngeal carcinoma cells (FaDu). The cascade model outperformed all other methods, achieving a 51.3% reduction in RMSE compared to raw single-scan inputs, surpassing both the single Unet (40.2%) and the traditional workflow (33.7%). Peak-aware metrics show that the cascade architecture eliminates spectral hallucinations found in standard deep learning. It also preserves peak intensity with much higher fidelity than traditional smoothing. These results show that the cascade Unet is a robust solution for diagnostic-grade FTIR imaging. It enables imaging speeds 32 times faster than current methods. Full article

Wildfires cause major damage, and their accurate detection is crucial. A common approach to near-real-time detection uses Geostationary (GEO) satellite algorithms. A standard scheme for evaluating the accuracy of a GEO-based algorithm is to compare its detections with higher-resolution Low Earth Orbit (LEO) images, considering the latter as ground truth. The primary objective of this study is to quantify the prevalence of GOES ABI/VIIRS fire detection misalignments and assess their impact on the accuracy evaluation of the GOES Fire Detection and Characterization (FDC) product. Thus, the key question is how this evaluation should be performed. To this end, a large dataset of matching FDC/VIIRS fire detections across Western U.S., Amazonas, and Patagonia was constructed. Our finding is that for nearly 12% of fire events, there are spatial misalignments between FDC and VIIRS detections. Next, we show that using VIIRS as ground truth without considering these misalignments yields highly biased estimates. This affects the evaluation of the FDC product detection capabilities. Finally, we demonstrate that using a GOES FDC/VIIRS buffer window substantially mitigates the effect of misalignments. For example, the estimated false alarm rate ranges between 26% and 36% without a window, whereas using a $3\times 3$ window yields values between 7% and 15%. Full article

This study examines information recovery under structured partial observation in multi-informant questionnaire systems. Rather than predicting an external ground truth, we evaluate the recoverability of an operational full-information decision rulewhen only partial informant views are available. In the empirical SNAP-IV calibration study, this reference is intentionally defined as a deterministic function of the combined informant views, so the combined-view result is treated only as an oracle-style ceiling and the substantive analysis concerns how single-view recovery degrades when one informant is withheld. To examine whether a similar qualitative pattern extends beyond this calibration setting, we additionally evaluate a latent-state simulation in which the reference decision is generated from an unobserved latent state and informant views are noisy observations. Across both settings, single-view recoverability declines as inter-rater disagreement increases, whereas combined-view representations remain more stable. In the empirical study, combined-view models achieved near-ceiling recovery performance (e.g., 90.9% for Logistic Regression and 91.3% for MLP), while Teacher-only recovery dropped from approximately 78% to 63% under higher disagreement ($p=0.0005$, Cohen’s $d=1.9$). Additional non-learned single-rater score-threshold baselines exhibited the same qualitative degradation pattern, indicating that the effect is not specific to fitted machine learning models. Importantly, this work is methodological: it does not propose new learning algorithms or clinical prediction models, but instead presents a conceptual–methodological framework, together with model-agnostic recoverability quantities, for quantifying missing-view information loss under incomplete, heterogeneous observations. Full article