Search Results (5,877)

The accurate interpretation of structural edges requires distinguishing geometry-driven discontinuities from reflectance- and illumination-induced variations. Conventional photogrammetric pipelines rely primarily on radiometric and geometric cues, which often lack physical interpretability under complex material and lighting conditions. This study proposes a photogrammetry–polarimetry fusion framework for physics-guided semantic classification of 3D structural edges. Radiometric, geometric, and polarimetric features are integrated within a noise-normalized representation to enable modality-independent interpretation. A rule-based classification scheme is introduced to assign edges to physically meaningful categories, including geometric, material, specular, illumination, and polarization-driven phenomena. The method is evaluated on a calibrated geometric object and a cultural heritage statue. Results show that polarization provides complementary information that reduces ambiguity between geometry-driven and reflectance-driven edge responses while preserving the underlying reconstructed geometry. On the calibrated dataset, edge detection achieves 88.4% precision, 95.5% recall, and an F1-score of approximately 0.92. Multi-view integration further improves the completeness of geometry-dominant 3D edges. The proposed framework introduces a physics-guided semantic sensing layer for multi-modal 3D perception, enabling more robust and interpretable structural analysis in photogrammetric workflows. Full article

Video-based action recognition for neural rehabilitation—spanning stroke recovery, Parkinsonian gait assessment, and cerebral palsy monitoring—faces critical challenges, including temporal ambiguity, non-causal motion correlations, and the absence of causally grounded dynamics modeling. While transformer-based architectures achieve strong performance, they often exploit spurious temporal and environmental cues, limiting reliability in safety-critical clinical settings. We propose NeuroPrisma, a neuro-prismatic video framework that integrates frequency-domain spectral decomposition with causal intervention under Structural Causal Models (SCMs) via the backdoor criterion. NeuroPrisma introduces (i) a Prismatic Spectral Attention (PSA) module, which applies discrete Fourier transforms to decompose temporal features into multi-scale frequency bands, disentangling slow postural dynamics from rapid corrective movements, and (ii) a Causal Intervention Layer (CIL), which performs do-calculus-based backdoor adjustment to remove confounding influences and produce causally invariant representations. PSA preconditions representations prior to intervention, improving confounder estimation and causal robustness. Extensive evaluation against seven state-of-the-art models (I3D, SlowFast, TimeSformer, ViViT, Video Swin Transformer, UniFormerV2, and VideoMAE) demonstrates that NeuroPrisma achieves 98.7% Top-1 accuracy on UCF101, 82.4% on HMDB51, 71.2% on Something-Something V2, and 91.5%/95.8% on NTU RGB+D (Cross-Subject/Cross-View), consistently outperforming prior methods. It further reduces the Causal Confusion Score (CCS) by 42.3%, indicating substantially lower reliance on spurious correlations, while maintaining real-time performance with 23.4 ms latency per 16-frame clip on an NVIDIA A100 GPU. All improvements are statistically significant (p < 0.001, Cohen’s d = 0.72–1.24). Evaluation was conducted exclusively on benchmark datasets (UCF101, HMDB51, Something-Something V2, and NTU RGB+D) under controlled conditions, without direct clinical validation on neurological patient cohorts. Overfitting was mitigated using three random seeds (42, 123, 456), RandAugment, Mixup (α = 0.8), weight decay (0.05), and early stopping. Cross-dataset generalization from UCF101 to HMDB51 without fine-tuning achieved 76.2% Top-1 accuracy. Future work will focus on prospective clinical validation across stroke, Parkinson’s disease, and cerebral palsy populations, including correlation with standardized clinical assessment scales such as Fugl–Meyer, UPDRS, and GMFCS. These results establish NeuroPrisma as a causally grounded and computationally efficient framework for reliable, real-time movement assessment in clinical rehabilitation systems. Full article

Precise object detection is critical for preventing damage to vehicle attachments during automatic car washing. However, the existing methods often suffer from low accuracy and false detections due to the diverse shapes and visual ambiguity of these attachments. To address these challenges, we propose a novel framework integrating a YOLOv11-based detector with a graph neural network. Specifically, we introduce a spatial graph module to refine object localization by capturing invariant spatial constraints within the car wash environment. Furthermore, we incorporate a class graph module to model inter-class semantic correlations, thereby improving the classification of visually ambiguous objects such as emblems. Experimental results on a real-world dataset demonstrate that our method achieves an mAP50 of 97.9%, outperforming state-of-the-art models including D-FINE 96.5% and RT-DETR 96.1%. These findings confirm the robustness of our approach under varying viewpoints and background conditions, offering a significant improvement in the safety and reliability of automatic car wash systems. Full article

In the context of the aesthetic economy and the rapid development of digital intelligence, product design is increasingly required to address not only functional performance but also users’ emotional needs. However, due to the ambiguity and subjectivity of perceptual requirements, it remains difficult to accurately translate user emotions into specific design solutions. To address this challenge, this study proposes an integrated Kansei Engineering–machine learning framework for optimizing product design. First, user perceptual data are collected through questionnaires and interviews, and key perceptual imagery words are extracted using the Latent Dirichlet Allocation (LDA) model and factor analysis. Then, product design elements are systematically decomposed, and their relative importance is determined using the fuzzy analytic hierarchy process (FAHP). Based on this, a mapping relationship between perceptual imagery and design elements is established. Subsequently, the XGBoost model is employed to predict and optimize design element combinations. The optimized design schemes are further generated using AIGC technology and validated through eye-tracking experiments and subjective evaluations.The results show that the proposed method achieves high predictive accuracy (R² = 0.87) and significantly improves the emotional expression of product design. This study contributes to the integration of Kansei Engineering and machine learning by providing a data-driven approach for emotional design optimization, offering theoretical, practical, and strategic guidance for intelligent product design in industrial contexts. Full article

Arctic sea ice is a critical indicator of global climate dynamics, directly influencing maritime navigation, polar biodiversity, and offshore engineering safety. The precise mapping of diverse ice types, such as frazil ice, slush, melt ponds, and open water, is essential for environmental monitoring; however, it remains a formidable challenge in satellite remote sensing. These difficulties arise from low-contrast imagery, overlapping spectral signatures, and the subtle textural nuances characteristic of polar regions. Traditional entropy-based thresholding techniques often falter when segmenting these complex scenes, as they typically rely on Gaussian distribution assumptions that do not align with the stochastic nature of Arctic data. To address these limitations, this paper presents a novel unsupervised segmentation framework based on symmetric cross-entropy (SCE). Unlike standard directional measures, SCE provides a more robust objective function for multi-level thresholding by simultaneously maximizing intra-class cohesion and minimizing inter-class ambiguity. The proposed method uses an optimized search strategy to identify intensity levels that best delineate complex Arctic features. We conducted an extensive entropy-based comparative study that benchmarked SCE against 25 state-of-the-art entropy measures, including Shannon, Kapur, Rényi, Tsallis, and Masi entropies. Our experimental results demonstrate that the SCE method: (i) achieves superior accuracy by consistently outperforming established models in segmentation precision and boundary definition; (ii) provides visual clarity by producing segments with significantly reduced noise, making them ideal for identifying small-scale melt ponds and slush zones; and (iii) demonstrates computational robustness by providing stable threshold values even in datasets with non-Gaussian class distributions and poor illumination. Ultimately, these improvements deliver high-quality ice feature data that enhance risk assessment, operational planning, and predictive modeling. This research marks a major step forward in Arctic sea studies and introduces a valuable new tool for wider image processing and computer vision communities. Full article

Cultural ecosystem services (CES) provide non-material benefits that support human well-being and motivate ecosystem conservation, yet their subjectivity and spatial ambiguity complicate quantitative assessment and management. Taking the Changbai Mountain tourism area as a case, we adopted the ecosystem service matrix method to assess the CES supply score based on the natural system and human system. The service coverage density was obtained through accessibility, thereby quantifying the available supply index for each tourist source area. In addition, we quantified CES demand using a questionnaire survey. Demand for 10 CES types was measured via preference ranking and integrated with the entropy weight method; statistical analysis and GIS mapping were used to examine spatial patterns and influencing factors. Results show that: (1) The overall CES demand in the Changbai Mountain tourism area exhibits clear spatial differentiation, with higher demand in the central and eastern regions and lower demand in the northwest. High-demand areas are mainly concentrated in cities relatively close to the Changbai Mountain tourism area. (2) Among individual CES, recreation (r = 6.58), natural landscapes (r = 6.35), and aesthetic value (r = 6.19) receive the highest demand, and demand structure is significantly associated with occupation, education level, consumption level, and spatial distance. The results indicate that cultural services dominated by knowledge-based services are significantly positively correlated with educational level (r = 0.549, p < 0.001). (3) CES supply capacity shows strong seasonal fluctuations, and is frequently overloaded during peak seasons, leading to prominent supply–demand conflicts; with the exception of Shenyang, Dalian, Jilin and Anshan, the other 17 cities exhibit supply–demand imbalance. By integrating multiple CES types and multiple drivers, this study reveals spatial matching patterns of CES supply and demand in a complex mountain ecotourism region and provides evidence to support ecotourism management, service capacity improvement, and sustainable development. Full article

The ambiguous evolution of the depositional system in the Pinghu Formation of Block K, Xihu Depression, East China Sea Basin, has long constrained the accuracy of reservoir prediction in this area. Based on petrological analysis, sedimentary system identification, and depositional model reconstruction, this study systematically elucidates the sedimentary evolution of the Pinghu Formation in Block K. The results indicate that the Pinghu Formation exhibits diverse lithologies and multiple types of grain-size distribution, reflecting complex hydrodynamic conditions. The early stage was dominated by tidal processes with fluvial influence, transitioning to fluvial dominance in the late stage. The depositional system evolved through a complete sequence: the early stage (E2pSQ1) was characterized by a tide-dominated delta, the middle stage (E2pSQ2) by fluvial-tidal interaction, and the late stage (E2pSQ3) by an overwhelmingly fluvial-dominated system. This evolution was controlled by the combined effects of a persistently increasing sediment supply and episodic relative sea-level fall, with the transition mechanism primarily governed by tectonic-eustatic coupling. In the lowstand systems tract of the middle-upper section, a “high-supply, high-progradation” fluvial-dominated delta developed in the Kongbei fault-step zone, whereas a “low-supply, low-progradation” minor fluvial system formed in the Kongnan fault-step zone. Here, tidal reworking was weak, and tidal flats developed only locally. In contrast, the highstand systems tract in the middle-lower section was dominated by a tide-dominated delta in the Kongnan fault-step zone, while the Kongbei fault-step zone remained a “low-supply, low-progradation” minor fluvial system. The established depositional models provide a geological basis for reservoir prediction and hydrocarbon exploration in the Pinghu Formation of Block K. Full article

DBSCAN is widely used to identify structured regions in unlabeled data, but its performance depends critically on the selection of the neighborhood parameter $\epsilon$. Traditional heuristics for estimating $\epsilon$ often become unreliable in high-dimensional or varying-density settings because they rely heavily on local geometric criteria and may fail under smooth transitions or topological ambiguity. This work presents a three-level perspective on DBSCAN hyperparameter selection. At the algorithmic level, $\epsilon$ controls neighborhood connectivity and structural transitions in clustering. At the modeling level, the ordered k-distance signal is approximated through a surrogate dynamical estimation framework inspired by a mass–spring–damper system. At the causal level, the resulting estimator is interpreted through interventions on its internal threshold-selection mechanism. The proposed method models the variation of $\epsilon$ using ordinary differential equations defined on the ordered k-distance signal, enabling analysis of structural transitions in density organization via a surrogate dynamical representation. System identification is performed using L-BFGS-B optimization on the smoothed k-distance curve, while the system dynamics are solved with the fourth-order Runge–Kutta method. The resulting estimator identifies transition regions that are structurally informative for $\epsilon$ selection in DBSCAN. To analyze the estimator at the intervention level, Pearl’s do-calculus is used to compute the Average Causal Effect (ACE). The method was evaluated on synthetic benchmarks and on the Covtype dataset, including scenarios with multi-density overlap and dimensionality up to ${\mathbb{R}}^{10}$. The resulting ACE values, $+0.9352$, $+0.5148$, and $+0.9246$, indicate that the proposed estimator improves intervention-based $\epsilon$ selection relative to the geometric baseline across the evaluated datasets. Its practical computational cost is dominated by nearest-neighbor search, behaving approximately as $O(NlogN)$ under favorable indexing conditions and degrading toward $O\left(N^2\right)$ in high-dimensional or weak-pruning regimes. Full article

We develop a categorical framework for modeling recursive uncertainty over preferences in decision theory. Classical models of ambiguity allow for uncertainty over outcomes or beliefs but usually rely on finite or exogenously truncated representations when agents face uncertainty about their own evaluative criteria. Given that such recursive preference formation generates an infinite hierarchy that may not stabilize at any finite level, we introduce a contractive von Neumann–Morgenstern utility functor on a category of compact metric spaces enriched over complete metric spaces, and establish the existence and uniqueness of its canonical fixed point. This fixed point is interpreted as a universal preference space that contains all levels of recursive ambiguity in a consistent and metrically stable form. We further extend the construction to multi-utility representations and discuss its relation to existing models of ambiguity and universal choice spaces. This framework offers a minimal unified representation of recursive preference structures. Full article

Human activity recognition (HAR) using inertial sensors is essential for health monitoring and wellness applications, yet robust classification in real-world adult scenarios remains challenging due to subject variability and activity transitions in smartphone sensing environments. This study investigated smartphone-based physical activity recognition using accelerometer and gyroscope signals under a cross-subject evaluation protocol. To reduce label ambiguity and improve generalization, the original activity set was grouped into a reduced 6-class taxonomy. We evaluated lightweight deep learning models, including a smartphone-only convolutional neural network (CNN) and a multimodal fusion model combining smartphone and smartwatch signals. Using GroupKFold cross-subject validation, the smartphone-only CNN achieved competitive performance with Macro-F1 ≈ 0.46, while multimodal fusion did not provide consistent improvements. We also examined temporal segmentation and showed that shorter windows (2.0 s) yield better results than longer windows. Sensor ablation confirmed the importance of gyroscope information, and per-class analysis indicated that dynamic activities could be recognized reliably, whereas stairs and static categories remained difficult. Overall, the results demonstrate the practicality of smartphone-based activity recognition using built-in smartphone sensors without external wearable devices for adult activity monitoring and provide recommendations for window length and sensor selection in cross-subject HAR. Full article

To improve the safety and reliability of tidal stream turbines (TSTs) under harsh marine environments, a novel probabilistic approach is proposed for blades fault detection in TSTs subject to stochastic disturbances of unknown probability distribution. On the basis of analytically analyzing the influence of blade imbalance fault on stator current signals, stationary wavelet transform (SWT) is first performed to extract multiscale time–frequency characteristics of blade faults from stator current data corrupted by non-stationary stochastic disturbances. Then an enhanced feature space is established by further computing the energy, standard deviation and kurtosis of SWT decomposition coefficients. By introducing the mean-covariance-based ambiguity set to characterize the probability distribution of feature vector in both fault-free and faulty cases, an optimal separating hyperplane for fault detection is learned using a distributionally robust optimization technique. It can achieve an optimal trade-off between the false alarm rate and the missed detection rate in a probabilistic setting, without requiring any specific distribution assumption. In this way, the proposed fault detection system is robust not only against disturbances but also against distributional uncertainties of disturbances. Finally, an experimental study based on a 0.23 kW tidal stream turbine platform is carried out to validate the effectiveness of the proposed method. Full article

Chagas disease, caused by Trypanosoma cruzi, affects 7 million people. Studying the ecology of triatomine vectors through midgut content analysis allows for infection diagnosis and the identification of blood meal sources (BMSs). Current BMS methodologies are limited by the accuracy of genetic data for local fauna, limiting species identification of hosts involved in parasite transmission. Here, we performed a systematic review on BMSs of T. cruzi vectors and showed the geographical distribution by T. cruzi lineages and vertebrate orders. We propose a decision tree system combining ecological and taxonomic approaches (EcoTaxDT) to discriminate ambiguous BMS results. The EcoTaxDT was validated using published and new BMS results. The review highlights the growing number of BMS studies and the awareness of host species potentially involved in transmission cycles. In Brazilian studies, EcoTaxDT allowed for taxonomic assignments when genetic identity was insufficient or when identified taxa had no geographical occurrence. New BMS results, validated by EcoTaxDT, showed triatomines feeding on Natalus macrourus, Echimyidae, Tettigoniidae, and Tropidurus itambere. Reliable BMS data and T. cruzi diagnosis are crucial for understanding transmission dynamics and human infection risk. EcoTaxDT is functional in correcting inconsistent BMS outputs, ensuring robust and consistent results by integrating genetic, taxonomy, and species geographical distribution. Full article

This paper draws on Michel Foucault’s analysis of disciplinary power to examine the history of penal punishment and Buddhist chaplaincy at Lüshun Prison in Dalian during Japan’s colonial rule (1905–1945). The goal is to call into question the dominant understanding of Japanese prison system as simply an apparatus of naked colonial oppression by exploring the contradictions and limitations in the penitentiary system of Japan as an empire and a modern nation-state. The research is based on official prison documents, True Pure Land Buddhist Honganji sect archival sources, local Chinese publications, oral testimonies from the 2000s, interviews with descendants, and fieldwork at Lüshun Prison. The first part introduces the history of Lüshun Prison and the second explains the prison as a modern criminal justice institution embodying the Benthamian panopticon principle and modern disciplinary power. The third part examines the brutal corporeal punishment at Lüshun Prison and explores how the prison combined deliberate strategies of disciplining manipulation with bodily punishment to (re)create disciplined and subjected individuals. The fourth and fifth parts focus on Buddhist chaplaincy at Lüshun Prison as a disciplining practice. The fourth considers the limits of Buddhist chaplaincy by showing the depoliticized Buddhist doctrine deployed by chaplains was unable to discipline prisoners as it failed to make them repent and be loyal subjects of imperial Japan. The notion of public good used to justify Buddhist chaplaincy in Japan loses its political meaning when applied to the colonial penitentiary setting of Lüshun Prison. The fifth part further explores this ambiguity in Buddhist chaplaincy by focusing on examining the case of Ahn Jung-geun, the Korean independence activist who assassinated the Japanese statesman Ito Hirobumi and was imprisoned and executed at Lüshun Prison in 1910. Rather than transforming Ahn, prison chaplains ended up being transformed by him. This reversion betrays not just a tension between the private and the public, or the individual and the social, but at the same time a tension between the supposedly homogenized nation-state and the multi-ethnic empire. Full article

For the calibration of surface plate, the classical Moody method is still commonly used. In this method the straightness of a number of lines over a surface plate in a union-jack configuration is measured and combined into a flatness measurement. The measurement of the two center lines is used to determine so-called closure errors. A shortcoming of this method is that it gives an ambiguous value for the central height and that the measurements of the central lines are not involved in the evaluation. This research shows how the lines can be incorporated in the measurement evaluation in a least-squares sense. This gives a measurement redundancy leading to an 18% reduction in the uncertainty. Also, it is shown that a further reduction in the uncertainty is possible when using the gravity vector as a common reference, as can be done when using electronic levels. A least-squares evaluation of measurements taken in this way gives an even further redundancy, leading to a reduction in the uncertainty of 29% relative to the traditional evaluation according to the Moody method. This is illustrated with an actual measurement example and additional Monte Carlo simulations. Full article

In the era of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) architectures are gaining significant attention for their ability to ground language generation in reliable knowledge sources. Despite their effectiveness, RAG systems based solely on semantic similarity often fail to ensure factual accuracy in specialized domains, where terminological ambiguity can affect retrieval relevance. This study proposes Entity Linking Enhanced RAG (ELERAG), an enhanced RAG architecture that integrates a factual signal derived from Entity Linking to improve the accuracy of educational question-answering systems in Italian. The system includes a Wikidata-based Entity Linking module and implements a hybrid re-ranking strategy based on Reciprocal Rank Fusion (RRF). To validate our approach, we compared it against standard baselines and state-of-the-art methods, including a Weighted-Score Re-ranking, a standalone Cross-Encoder and a combined RRF + Cross-Encoder pipeline. Experiments were conducted on two benchmarks: a custom academic dataset and the standard SQuAD-it dataset. Results show that, in domain-specific contexts, ELERAG significantly outperforms both the baseline and the Cross-Encoder configurations. Conversely, the Cross-Encoder approaches achieve the best results on the general-domain dataset. These findings provide strong experimental evidence of the domain mismatch effect, highlighting the importance of domain-adapted hybrid strategies to enhance factual precision in educational RAG systems without relying on computationally expensive models trained on disparate data distributions. They also demonstrate the potential of entity-aware RAG systems in educational environments, fostering adaptive and reliable AI-based tutoring tools. Full article