Search Results (2,855)

Human pose estimation (HPE) has advanced rapidly with deep learning, enabling a transition from specialized sensing and multi-view systems toward monocular RGB-based approaches. These developments have expanded applications in healthcare, robotics, sports analytics, and human–computer interaction. However, the growing diversity of deep learning paradigms, ranging from convolutional and recurrent models to graph-based and Transformer-based approaches, has resulted in a fragmented literature, making it difficult to systematically compare methods and guide system design. This paper addresses this challenge by providing a comprehensive survey of deep learning-based monocular HPE methods published over the past decade and introducing a unified modular framework. The proposed framework organizes HPE systems into six modular estimation paradigms, including single-image-based estimation, multi-frame-based estimation, Top-Down and Bottom-Up pose estimation strategies, 2D-to-3D pose reconstruction, and direct 3D estimation. Each module is analyzed in terms of representative approaches, design trade-offs, and practical considerations, supported by algorithmic formulations that outline the computational pipeline at each stage. Unlike prior surveys that primarily catalog methods or report benchmark results in isolation, this work emphasizes how component-level design choices relate to overall system performance. The paper summarizes performance trends on benchmarks including Human3.6M, COCO, and MPII, highlighting persistent challenges such as occlusion and viewpoint variation, and outlines future research directions including interaction-aware modeling, efficient deployment, and improved robustness under real-world conditions. Full article

This study presents an intelligent framework for the analysis of multidimensional geomechanical states in underground mining systems based on numerical simulation and machine learning methods. A three-dimensional geomechanical model of the Zholymbet deposit was developed in the RS3 environment using the generalized Hoek–Brown failure criterion. Numerical simulations were performed for representative mining scenarios characterized by complex excavation interaction and stress redistribution. The modelling results were transformed into a multidimensional geomechanical dataset containing stress, deformation, displacement, and yielding parameters. Principal component analysis (PCA) was applied to investigate the internal structure of the geomechanical state space and identify dominant patterns controlling the rock mass behavior. Clustering analysis revealed several geomechanical regimes corresponding to stable, transitional, and instability-prone conditions. Isolation Forest anomaly detection demonstrated that atypical geomechanical states are not randomly distributed but spatially localized near excavation systems and mining horizons. The obtained results indicate that hazardous geomechanical conditions are governed by complex interactions between stress concentration, deformation intensity, yielding processes, and excavation geometry. The proposed approach provides a basis for intelligent interpretation of large-scale numerical modelling results and may support geomechanical risk assessment in underground mining operations. Full article

Natural microbial pigments offer important advantages and are widely studied for food applications. We investigated the biosynthetic pathways, characteristics, and bioactivities of the orange–red pigment produced by Bacillus velezensis YM–3, a strain isolated from the traditional Pixian Douban condiment. Whole-genome sequencing revealed complete pathways for melanin, phytoene, and heme biosynthesis. The purified extracellular pigment was characterized using ultraviolet–visible spectroscopy, Fourier-transform infrared spectroscopy, nuclear magnetic resonance spectroscopy, and ultra-performance liquid chromatography–high-resolution mass spectrometry; it was preliminarily characterized as melanin-like pigment. The pigment was highly soluble in alkaline solutions, moderately soluble in water, and insoluble in common organic solvents. It exhibited strong photostability and remained stable at low temperature, precipitated under acidic conditions, and showed high stability under alkaline environments. Furthermore, the pigment demonstrated in vitro free radical scavenging activity. Hence, this study provides a scientific foundation for exploring the potential utility of B. velezensis YM–3 and its pigment metabolites as functional agents. Full article

With the widespread adoption of intelligent terminals, edge devices, and distributed information systems in the financial domain, financial security sensing data exhibit multisource heterogeneity, dynamic temporal patterns, and high privacy sensitivity. Traditional centralized anomaly detection methods are no longer able to simultaneously satisfy the requirements of cross-institutional or cross-node collaborative modeling, client data privacy protection, and robust monitoring of transaction and system anomalies. To address this challenge, a data-local federated deep anomaly detection framework has been proposed for distributed financial security sensing systems. Initially, a local deep financial security sensing representation module is constructed to perform temporal encoding and attention-based modeling on multisource financial signals, including terminal operation status, network transaction communication, backend server operation, identity authentication, and anomaly alerts, thereby extracting representations relevant to anomalous behaviors. Subsequently, a data-local federated optimization and personalized aggregation mechanism is developed to enable cross-node knowledge sharing without transmitting raw transaction or client data, while local personalized detection heads are employed to adapt to non-independent and identically distributed (non-IID) financial institution data. Furthermore, an adversarially robust security detection and trust-aware aggregation strategy is introduced to enhance model stability under input noise, feature masking, anomaly camouflage, and potential malicious client updates. Experimental results demonstrate that the proposed method achieves an Accuracy of $92.37\%$, a Precision of $89.41\%$, a Recall of $88.26\%$, an F1-score of $88.83\%$, an AUC of $93.06\%$, and a PR-AUC of $89.15\%$ in the primary financial anomaly detection task, significantly outperforming baseline methods such as Isolation Forest, Autoencoder, LSTM, Transformer, FedAvg, FedProx, SCAFFOLD, and MOON. In robustness experiments, the method attains F1-scores of $87.95\%$, $86.42\%$, $86.88\%$, $84.57\%$, $86.73\%$, and $83.91\%$ under Gaussian noise, feature masking, temporal shift, adversarial perturbation, and $20\%$ and $30\%$ malicious client scenarios, respectively. Ablation studies further confirm the effectiveness of local representation learning, personalized federated optimization, adversarial training, and trust-aware aggregation mechanisms. Overall, the proposed approach provides an efficient intelligent anomaly detection solution for financial AI security monitoring scenarios characterized by data localization requirements, node heterogeneity, and attack perturbations. Full article

The trend in the power electronics industry toward higher power density and efficiency has brought high-frequency transformers (HFTs) to the forefront of critical applications, including isolated DC–DC converters, electric vehicle chargers, and solid-state transformers. This paper focuses on the leakage inductance of HFTs and presents a systematic comparative framework that evaluates five surrogate modeling and hybrid optimization approaches for the rapid and accurate estimation of leakage inductance. A comprehensive parametric dataset was constructed, comprising 1210 finite element analysis simulations conducted via finite element analysis in the ANSYS Maxwell 2024 R1 environment, varying the number of winding turns, primary winding thickness, and secondary winding thickness of the HFT. All five methods were trained and evaluated on the same dataset under identical conditions. The comparative evaluation demonstrates that the proposed hybrid Gray Wolf optimizer–artificial neural network (GWO-ANN) framework achieved the highest prediction accuracy (R² = 0.9832, MSE = 0.01780, MAE = 0.0935 µH) and the fastest convergence among all tested approaches. The generalization capability of the proposed model was confirmed through blind validation tests across six geometric configurations spanning the full range of the design space, yielding a maximum prediction error of 8.15% and an average error of 2.14%. The functional validity of the proposed parameters was further tested in a third validation layer using MATLAB/Simulink R2024b transformer circuit studies, demonstrating a theoretical efficiency of 96.06%. This three-layer validation approach proves both the parametric and functional reliability of the proposed framework for HFT designs. Full article

This article explores the structural paradox of the byeong-gut (Korean shamanic healing ritual): why it adheres to the rigid and canonical format of the jaesu-gut (shamanic blessing ritual) instead of adopting a specialized clinical procedure. Critiquing the instrumental trap of previous scholarship that reduces shamanic healing to psychological comfort or social liberation, this study proposes a relational displacement model by integrating Roy Rappaport’s theory of ritual invariance with the relational ontologies of Bruno Latour and Tim Ingold. The article demonstrates that shamanic healing operates through a dual mechanism. First, at the non-discursive (material) level, the ritual functions as an ontological technology that objectifies and displaces individual suffering onto external surrogates. Second, at the discursive (linguistic) level, a meticulous analysis of the manse-baji (invocation chant) illustrates how the patient’s fragmented life is re-assembled into a meshwork of human and non-human agencies. Ultimately, this article argues that the byeong-gut transcends mere functional curing; it serves as a sophisticated knowledge system that re-maps the isolated ego onto a relational cosmology, transforming the Geertzian bafflement of suffering into an intelligible event within a shared and sacred cosmic order. Full article

Historic urban districts are increasingly exposed to rapid urban transformation, resulting in the deterioration of heritage fabric, weakening of spatial identity, and disruption of everyday patterns of use. Although participatory approaches are increasingly recognised in heritage-led regeneration, many applications remain limited by the lack of analytical mechanisms capable of connecting community perspectives with spatial and behavioural evidence in a structured and practical manner. This study develops and applies a participatory decision-support approach based on the People–Place–Behaviour (PPB) framework within the historic district of El-Mokhtalat in Mansoura, Egypt. The study combines spatial documentation, behavioural observation, and stakeholder consultation to examine how everyday urban practices, adaptive reuse, informal interventions, and local perceptions collectively influence regeneration priorities within the historic environment. The findings indicate that regeneration priorities emerge through the interaction between spatial conditions, community perceptions, and behavioural patterns rather than through isolated physical conditions alone. Based on stakeholder consultations (n = 30), the analysis identifies a prioritisation gradient in which architectural conservation and environmental enhancement represent the most immediate intervention priorities, while adaptive reuse and public-space improvements remain dependent on contextual compatibility and local acceptance. The study also demonstrates the analytical value of behavioural evidence in revealing recurring spatial pressures, identity-related transformations, and everyday interaction patterns affecting the continuity of the historic urban fabric. By integrating participatory, spatial, and behavioural evidence within a unified evaluation process, the study proposes a context-sensitive analytical approach capable of supporting more informed and locally responsive heritage-led regeneration strategies. Full article

The Vortex Ring State (VRS) poses a catastrophic aerodynamic threat to coaxial dual-rotor unmanned aerial vehicles (UAVs). Traditional reactive detection mechanisms provide insufficient altitude for recovery, while existing data-driven diagnostics are severely bottlenecked by data leakage, extreme class imbalance, and a lack of physical interpretability. To bridge these gaps, this paper proposes a physics-informed multimodal deep learning framework that transitions from post-occurrence detection to proactive early warning. We establish a 1.5 s precursor window—creating a three-class ordinal state space—to provide the flight control system with critical intervention time for differential rotor recovery. We developed a novel ViT-LSTM architecture (MTSF-Net) to fuse continuous seven-channel onboard-recorded data (comprising three-axis acceleration, three-axis angular velocity, and barometric vertical velocity), which are subsequently transformed into Continuous Wavelet Transform (CWT) spectrograms. To ensure real-time unidirectional inference while preserving absolute physical vibration scales across heterogeneous sensors, a Calibrated Benchmark Normalization (CBN) strategy is introduced. Furthermore, a Hybrid Ordinal Loss is proposed to mitigate the extreme sample imbalance (<0.5%) of the precursor state by penalizing asymmetric aerodynamic degradation. Evaluated under a strict sortie-based isolation protocol, the proposed system achieves an exceptional test accuracy of 98.26% and an unprecedented precursor recall of 100%. Notably, it completely eliminates fatal missed detections (VRS predicted as Normal) and false-positive VRS predictions triggered by precursor states. Finally, Gradient-weighted Class Activation Mapping (Grad-CAM) is utilized to verify that the multimodal sensor processing pipeline successfully anchors onto authentic physical vibration frequencies rather than artifactual noise, laying a rigorous, interpretable foundation for intelligent aviation safety systems. Full article

The Gaizi River Basin, an alpine region in China crossed by the Karakoram Highway, is highly prone to glacier-related debris flows (GDF). Accurate debris flow susceptibility assessment in this high-altitude area remains challenging due to complex terrain, active tectonics, and dynamic glacial processes. This study develops a hybrid model integrating statistical methods and machine learning-based anomaly detection for debris flow susceptibility mapping. To address data noise, certainty factor (CF) distributions of debris flow predisposing factors (DFPFs) were derived via Locally Weighted Scatterplot Smoothing (LOWESS). The strength of the association between DFPFs and GDF susceptibility was evaluated using the mean residual between the raw and LOWESS-smoothed CF values. Multiple anomaly detection algorithms, including distance-based (L2 Norm), density-based (One-Class SVM), ensemble (Isolation Forest, RandNet), and GAN-based (WBiGAN-GP) methods, were tested on raw and CF-transformed data, using only the GDF inventory as the label. The CF-WBiGAN-GP model delivers the most balanced performance, excelling at identifying both high- and low-susceptibility zones. Results show that distance to stream, slope, and the topographic roughness and wetness indices are strongly associated with GDF susceptibility. Distance to glacier and precipitation appear less informative for direct susceptibility inference under our specific dataset and analytical setup. Full article

This paper introduces and investigates a novel two-parameter sequence, termed the biparametric Appell extension (B-App-Ex) and denoted by ${\mathcal{B}}_n(x;\lambda ,\alpha )$. Standard classical Appell sequences often lack sufficient structural parameters, which can limit their operational flexibility in certain advanced spectral schemes. To address this limitation, we construct an enhanced operational framework by integrating a binomial structural kernel ${(1+w)}^{\lambda }$ with a linear exponential scaling $e^{\alpha xw}$ entirely within the Appell class. We provide a rigorous logical deduction of the fundamental properties of this sequence, including its explicit power series representation, a characteristic three-term recurrence relation, and a governing second-order differential equation (DEq.). A significant contribution of this work is the establishment of analytically exact connection and inverse connection formulas between the B-App-Ex basis and various classical orthogonal polynomial (COP) families. Numerical verification via a collocation-based projection framework demonstrates that these algebraic kernels achieve near-machine epsilon precision (≈${10}^{-15}$), remaining stable even for high-order approximations. Furthermore, by isolating the dilation factor $\alpha$, we establish an $O\left(N\right)$ computational complexity that offers a reduction in latency by approximately two orders of magnitude compared to classical matrix-based transformations. The results demonstrate that the proposed biparametric (Bip.) extension offers a versatile and highly optimized analytical template for modeling complex dynamic systems where structural shifting and spatial scaling must be tuned simultaneously. Full article

The evaluation of biomass boilers using partial approaches limits system understanding, because energy, exergy, dynamic, and emergy analyses describe complementary, but not equivalent, dimensions of thermo-industrial performance. In response to this gap, an integrated methodological framework is proposed to analyze two representative steam generator technologies in the sugar industry, fueled with ternary mixtures of sugarcane bagasse, Agricultural Crop Residues (ACR), and Dichrostachys cinerea, with the aim of identifying robust operating windows from a simultaneously thermal, exergetic, transient, and sustainability perspective. The methodology combines: (i) a direct and indirect steady-state model to quantify thermal losses and efficiency; (ii) an exergy model to assess conversion quality; (iii) a two-node coupled transient dynamic model capable of representing the differentiated response of the combustion zone and the water/steam system to moisture perturbations; and (iv) an emergy model to estimate the overall sustainability of the process. The results show that the effective moisture content of the mixture is the dominant control variable, since it determines the lower heating value on a wet basis, the specific fuel consumption, the main thermal loss, and the dynamic stability of the system. In the transient domain, a +5% step perturbation in moisture generates drops of 11.14–12.20 °C and 17.76–19.39 °C in furnace temperature for G1 and G2, respectively, while the steam response is damped to 1.03–1.14 °C and 2.39–2.65 °C. Likewise, moisture explains the magnitude of the response with coefficients of determination above 0.99, and the sensitivity analysis identifies the controller time constant, the thermal mass of the water/steam system, and the emissivity as the most influential parameters. Overall, the proposed framework makes it possible to go beyond isolated efficiency assessment and move toward a holistic characterization of biomass boiler performance under technically plausible ternary mixtures. Although the proposed methodological framework is transferable to other biomass combustion contexts, the numerical results—including optimal compositional zones, emergy indicators, and dynamic sensitivity coefficients—are specific to the Cuban sugar industry conditions, adopted transformities, and the biomass types evaluated herein. Full article

Potato starch (Solanum spp.) undergoes structural and functional modifications during traditional Andean chuño production; however, the integrated effects of processing history, cultivar-associated characteristics, and field-based environmental conditions remain insufficiently characterised. This study investigated the effects of chuño processing on the compositional, pasting, morphological, molecular, and crystalline properties of starches isolated from three potato cultivars (Condor Imilla, Luk’i Turno, and Dutch Désirée). Native and chuño starches were characterised by amylose quantification, viscoamylography, scanning electron microscopy (SEM), Fourier-transform infrared spectroscopy (FT-IR), and X-ray diffraction (XRD), together with severe thermal treatment to evaluate structural stability. Chuño processing was associated with a reduction in amylose content across all cultivars (6.9–23.4%) and an increase in gelatinisation onset temperature of approximately 21.5% (from ~65 °C to ~79 °C). Peak viscosity decreased substantially after processing (457.5–1110 BU to 194.5–442.5 BU), while breakdown values remained close to zero, indicating increased resistance to viscosity loss during heating. SEM analysis revealed changes in granule morphology and size distribution associated with chuño processing and subsequent thermal treatment, with more pronounced reductions in granule size observed in Condor Imilla and Luk’i Turno than in Dutch Désirée. FT-IR analysis demonstrated modifications in short-range molecular organisation without the appearance of new functional groups, indicating structural reorganisation rather than chemical transformation. XRD analysis confirmed that all starches retained the native B-type crystalline polymorph after chuño processing, although reductions in diffraction intensity and peak definition indicated decreased long-range structural order. Severe thermal treatment eliminated detectable crystalline order in all samples, producing predominantly amorphous diffraction profiles. Overall, chuño processing was associated with reduced swelling capacity, lower paste viscosity, enhanced thermal stability, and multiscale structural reorganisation while preserving the fundamental B-type polymorph. Given that the plant material originated from distinct agroecological environments and that traditional chuño production involved a variable number of processing cycles, the observed differences should be interpreted as integrated responses of starch systems to processing history and material characteristics rather than strictly genotype-driven effects. These findings highlight the potential of chuño as a naturally modified starch system with distinctive technological properties. Full article

Ferrocenium-catalyzed transformations provide a practical and sustainable approach to propargylic substitution reactions. Herein, we investigate the ring-opening of cyclopropyl-substituted propargylic alcohols with alcohol nucleophiles, catalyzed by ferrocenium tetrafluoroborate ([FeCp₂][BF₄]) to afford synthetically valuable enyne ethers. Mechanistic studies using GC and NMR spectroscopy reveal that the reaction proceeds via initial formation of a ring-closed propargylic ether intermediate, which subsequently undergoes ring opening to the enyne ether. Experimental evidence supports a carbocationic pathway in which the ferrocenium cation promotes ionization to a stabilized cyclopropyl ether intermediate, followed by intramolecular, ferrocenium-assisted cyclopropyl ring opening to the enyne product. Reaction rates and product distributions are strongly influenced by temperature and solvent polarity, with polar solvents and elevated temperatures favoring ring opening. At room temperature, the ring-closed substitution product predominates, whereas efficient formation of enynes occurs at 65 °C. The reaction progresses faster in a polar solvent, indicating an ionic mechanism. Studies employing substrates containing substituted cyclopropyl rings demonstrated pronounced regioselectivity during nucleophilic ring opening with alcohols, with preferential cleavage of the bond between the two substituted carbon atoms. This selectivity is consistent with partial positive-charge stabilization in the transition state. The corresponding enyne ether products were isolated in 98–31% isolated yields, in most cases as a single regio- and E/Z stereoisomer (5 h at 45 °C, 5 mol% [FeCp₂][BF₄] catalyst load, six equivalents alcohol nucleophile). The ferrocenium-catalyzed cyclopropyl ring opening establishes a convenient method for accessing enyne motifs, which are important structural units in organic synthesis and medicinal chemistry. Full article

The objective of this study was to examine the physicochemical properties of maltodextrins derived from starch isolated from red- and purple-fleshed potatoes, in comparison to those obtained from light-fleshed potatoes. The investigation focused on several parameters, including dextrose equivalent (DE), non-carbohydrate components, maltooligosaccharide profile, particle size, surface morphology, water-binding capacity, solubility, rheological properties, structural composition as determined by Fourier transform infrared spectroscopy (FT-IR), and molecular weights. Maltodextrins sourced from the starch of colored potato varieties exhibit superior functional properties, notably nearly 100% solubility and enhanced water absorption capacity. This is attributed to their fine microstructure, which promotes hydration and facilitates the diffusion of water into the interior of the particles, in contrast to maltodextrins derived from the starch of yellow potato varieties. This phenomenon is also influenced by the maltooligosaccharide profile, characterized by a high proportion of low-molecular-weight sugars, lower molecular weights, and polydispersity (Pd), as well as the low SPAN of these maltodextrins. Additionally, maltodextrins derived from the starch of yellow potato varieties (Tajfun and Lord) formed soft gels, whereas those from colored potatoes resulted in hard gels. Full article

Deep neural networks have been widely applied in architectural analysis and design research, supporting tasks such as facade recognition, floor-plan analysis, and architectural visual classification. However, although existing models possess strong predictive capabilities, their decision-making processes remain characterized by a pronounced black-box nature, making it difficult to provide architects with understandable and traceable grounds for judgment. This limits their practical value in the architectural field, as designers require not only accurate outputs but also interpretable explanatory evidence regarding the basis of decision-making. This issue is particularly critical in architectural interpretation, where judgments are rarely made solely on the basis of isolated visual features, but are instead often formed through comparison and negotiation with precedents, spatial logic, and domain knowledge. To address this challenge, this paper proposes ArchiExplain, a multi-level interpretability framework for architectural image understanding, aiming to enable a deeper understanding of architectural images. The main contributions of this study are threefold: (1) We construct two architectural datasets for interpretability evaluation: a facade dataset composed of streetscape images from Harbin, China, and Greece, and a floor-plan dataset consisting of Real-plan drawings from real design cases and standardized generated R-plan drawings. Unlike existing datasets that primarily serve style recognition, semantic parsing, or image generation tasks, the datasets in this paper focus on evaluating the correspondence among model explanations, precedent associations, visual evidence, and predictive judgments. (2) Based on the above datasets, we propose the ArchiExplain framework. Unlike attribution methods such as Grad-CAM, Saliency Maps, and Integrated Gradients, which mainly reveal local discriminative regions, or influence-based methods that only trace the influence of training samples, this framework integrates training-sample influence tracing, Saliency Maps, and Integrated Gradients. It establishes a unified evidential chain among precedent samples, discriminative image regions, and final predictions, thereby transforming neural network decisions into an interpretable reasoning process with architectural significance. (3) Experimental results show that ArchiExplain performs stably on 100 randomly selected test samples, achieving an accuracy of 98.41% in the facade classification task and 98.34% in the floor-plan classification task. Further deletion/occlusion faithfulness analysis shows that the main attribution methods outperform the random baseline. Meanwhile, a questionnaire study involving 28 architects further verifies the consistency between model explanations and human architectural cognition. These findings indicate that ArchiExplain can enhance the transparency of architectural deep learning models and has practical application potential in architectural design analysis, model diagnosis, and precedent-based learning. Full article