Search Results (3,357)

Accurate classification of spindle rotational errors is critical for ensuring machining precision and operational reliability of CNC machine tools. However, existing methods face challenges in extracting discriminative feature information from vibration signals due to small inter-class differences and complex electromechanical interference. This paper proposes a novel deep learning model, MFAFENet, based on multi-sensor collaboration and multi-scale feature information adaptive fusion. Vibration signals from three mounting positions are transformed into time-frequency information representations via Short-time Fourier Transform. The proposed network adaptively fuses multi-scale feature information from parallel branches with different kernel sizes through a branch attention mechanism. An efficient channel attention module is then incorporated to recalibrate channel-wise feature responses. The cross-entropy loss function is employed to optimize the network parameters during training. Experiments on a spindle reliability test bench demonstrate that MFAFENet achieves 93.37% average test accuracy, outperforming other comparative methods. Ablation and comparative studies confirm the effectiveness of each module and the clear advantage of adaptive fusion over fixed-weight multi-scale methods. Multi-sensor fusion further improves accuracy by 7.23% over the best single-sensor setup. The proposed method establishes an effective end-to-end mapping between vibration signals and rotational errors, providing a promising solution for high-precision spindle condition monitoring. Full article

Accurately identifying urban functional zones and revealing their spatial interaction characteristics is crucial for understanding urban operational mechanisms and optimizing spatial layouts. Addressing the limitations of traditional research in simultaneously capturing static functional attributes and dynamic resident travel behaviors, this study takes the central urban area of Lhasa as the research object, integrating ride-hailing trajectory data with Point of Interest (POI) data to conduct research on urban functional zone identification and spatial interaction characteristics. First, Thiessen polygons were used to quantify the spatial influence range of POIs, and an address matching algorithm was employed to associate ride-hailing origins and destinations (ODs) with POIs. A weighted land use intensity index was constructed, and functional zones were precisely identified using information entropy and K-Means clustering. Secondly, with basic research units as nodes and OD flows as edges, a directed weighted spatial interaction network was constructed. Complex-network indicators and the Infomap community detection algorithm were utilized to analyze network characteristics, node importance, and community interaction patterns. The results show that: (1) The functional mixing degree in the study area exhibits a pattern of “highly composite core, relatively differentiated periphery.” Eight functional zone types, including commercial–residential mixed, science–education–culture, and transportation service zones, were ultimately identified. Residential areas form the base, while the core area features multi-functional agglomeration. (2) The spatial interaction network exhibits typical small-world effects, while its degree distribution is better characterized by a lognormal distribution rather than a power law. Node importance is dominated by betweenness centrality, with Lhasa Station, the Potala Palace, and core commercial areas constituting key hubs. (3) The network can be divided into four functionally coupled communities: the core multi-functional area, the western industry–residence integrated area, the eastern science–education-dominated area, and the southern transportation hub area, forming a “core leading, two wings supporting” center–subcenter spatial organization pattern. This study verifies the effectiveness of integrating trajectory and POI data for identifying urban functional zones and provides a new perspective for understanding the spatial structure and planning of plateau cities. Full article

To meet the high-fidelity testing environment requirements for autonomous driving system development, driving simulators are gradually evolving from tools that “only provide scenes and interaction interfaces” into integrated verification platforms for autonomous driving capabilities. These simulators, in particular, need to feature testable and scalable decision-making modules. However, the autonomous driving functions in existing driving simulators mostly rely on rule-based or simplified model approaches, which are inadequate for depicting the complex interactions in real-world traffic and fail to meet the personalized decision-making needs under various driving styles. To address these challenges, this paper designs and implements a trajectory data-driven personalized autonomous driving decision system, using drone aerial imagery as the core data source to provide realistic background traffic flow and human-like decision-making capabilities. The proposed system can be interpreted as an integrated decision–planning–control framework deployed within a high-fidelity driving simulation platform. It consists of a driving style classification module based on drone trajectory data, a personalized decision module integrating inverse reinforcement learning and dynamic game theory, and a planning and control module. First, a natural driving database is built using 4997 real vehicle trajectories, and prior features of different driving styles are extracted through trajectory feature engineering and an improved K-means++ method. Based on this, a personalized decision-making framework that combines dynamic game theory and maximum entropy inverse reinforcement learning is proposed, aiming to learn the preference weights of different driving styles in terms of safety, comfort, and efficiency. Furthermore, the Dueling Network Architecture (DuDQN) is used to generate human-like lane-changing strategies. Subsequently, a real-time closed-loop execution of personalized decisions in the simulation platform is achieved through fifth-order polynomial trajectory planning, lateral Linear Quadratic Regulator (LQR) control, and longitudinal cascade Proportional–Integral–Derivative (PID) control. Experimental results show that the personalized decision model trained with drone data can realistically reproduce vehicle decision-making behaviors in natural traffic flows within the simulation environment and generate autonomous driving strategies that are highly consistent with different driving styles. This significantly enhances the humanization and personalization capabilities of the autonomous driving module in the driving simulator. Full article

During long-term operation, power electronic converters are jointly affected by component degradation and operational disturbances, leading to pronounced nonstationary and multi-scale characteristics in output-voltage signals, which pose challenges for fault prediction. To address the degradation forecasting problem of Boost converter output voltage, this paper proposes a multi-scale temporal modeling method that integrates multivariate variational mode decomposition, distribution entropy-based complexity features, and a temporal convolutional network. Multivariate variational mode decomposition is employed to achieve frequency-aligned decomposition of the voltage signal, enabling effective separation of dynamic components at different scales. Distribution entropy is then introduced to characterize the evolution of local structural complexity in each mode, and multi-channel complexity feature sequences are constructed accordingly. Based on these features, a temporal convolutional network is used to perform unified modeling of short-term fluctuations and long-term degradation trends. Experimental results demonstrate that the proposed approach achieves consistently high accuracy across multiple independent runs, with average RMSE ranging from 0.0111 to 0.0179 and average MAPE from 1.15% to 1.84%. The low standard deviations further confirm its robustness for degradation trend prediction under varying operating conditions. Full article

We investigated bryophyte communities in mature beech forests (Fagus sylvatica L.) and Austrian pine plantations (Pinus nigra J.F. Arnold) on Fruška Gora Mountain (northern Serbia) to examine how stand structure and edaphic conditions influence trait composition and functional diversity. Environmental predictors included soil pH, soil temperature, herbaceous cover, and shrub density, while collinear structural variables were summarized using principal component analysis into a composite structural–moisture gradient. Community–environment relationships were analyzed using redundancy analysis (RDA) with restricted permutations, trait–environment coupling using RLQ and fourth-corner analysis, and functional diversity using Rao’s quadratic entropy (RaoQ). The RDA indicated significant effects of all predictors. RLQ revealed a structured multivariate coupling between bryophyte traits and environmental gradients. Functional diversity was higher in beech forests than in pine plantations, increasing with shrub density and decreasing along the structural–moisture gradient. Overall, plantation stands supported functionally more homogeneous bryophyte assemblages, highlighting the importance of stand structural complexity for maintaining forest-floor bryophytes’ functional diversity. Full article

In air jet looms, relay nozzles are critical components in governing airflow velocity and air consumption during the weft insertion process. Although computational fluid dynamics (CFD) offers high-fidelity simulation for aerodynamic analysis, its computational burden hinders its practicality in iterative aerodynamic design of relay nozzles. To address the challenge, this study proposes a data-driven framework integrating a Chebyshev polynomial Kolmogorov–Arnold Network (Chebyshev KAN) surrogate model with an Improved Multi-objective Red-billed Blue Magpie Optimizer (IMORBMO). The accuracy of the Chebyshev KAN model was benchmarked against conventional multilayer perceptrons (MLP), convolutional neural networks (CNN), and the standard Kolmogorov–Arnold Network (KAN). Experimental results demonstrate that the Chebyshev KAN model achieves the lowest mean absolute error (MAE) of 0.103 for airflow velocity and 0.115 for air consumption. Building upon the non-dominated sorting and crowding distance strategies, IMORBMO was developed, incorporating an adaptive mutation mechanism by information entropy for improvement of convergence, diversity, and uniformity of the Pareto-optimal solutions. Comprehensive evaluations on the ZDT and WFG benchmark suites confirm that the IMORBMO consistently attains the best and highly competitive performance, yielding the lowest generation distance (GD), inverted generational distance (IGD) values and the highest hypervolume (HV). Applied to the aerodynamic optimization of a relay nozzle, the proposed framework delivers an optimal aerodynamic design that increases airflow velocity by 10.5% while reducing air consumption by 15.4%, as verified by CFD simulation. The steady-state flow field was simulated by solving the Reynolds-Average NavierStokes equations with the k−ω turbulent model, utilizing Fluent 2025.R2. No-slip wall, inlet pressure and outlet pressures are boundary conditions to the relay nozzle surfaces. This work establishes a computationally efficient and accurate optimization paradigm that holds significant promise for aerodynamic design and other complex real-world engineering applications. Full article

Nonlinear analysis provides a framework for understanding the complexity and stability of human locomotion by capturing dynamic patterns beyond linear methods. This study examined the effect of data length on seven nonlinear measures: Sample Entropy (SpEn), Approximate Entropy (ApEn), Lyapunov Exponents using Wolf’s (LyE_W) and Rosenstein’s (LyE_R) algorithms, Detrended Fluctuation Analysis (DFA), Correlation Dimension (CD), and the Hurst–Kolmogorov process (HK). A 3500-frame kinematic dataset from a healthy adult performing motor-assisted elliptical training and treadmill walking was segmented from 100 to 3500 frames in 10-frame increments. Data from treadmill and elliptical conditions were analyzed and presented in a combined manner to highlight general stabilization trends across locomotor tasks. Results revealed that increasing data length significantly affected all nonlinear metrics (p ≤ 0.0005). Stabilization occurred at varying minimum lengths: SpEn at ~4.5–8.8 s (540–1060 frames), ApEn at ~5.4–7.7 s (650–920 frames), LyE_W at ~19.1–29.2 s (2290–3500 frames), LyE_R at ~1.3–1.5 s (150–180 frames), DFA at ~29.2 s (3500 frames), CD at ~1.7–15.9 s (200–1910 frames), and HK at ~9.1–9.8 s (1090–1180 frames). Notably, HK achieved stable estimates in approximately one-third of the time required for DFA and substantially less than LyE_W, supporting its suitability for time-constrained or clinical settings. These findings suggest the need to tailor data collection to each nonlinear metric and to report data length explicitly to improve accuracy, reproducibility, and methodological rigor in gait variability research. However, these findings should be interpreted within the limitations of a single-participant, exploratory design. Full article

In this paper, based on the Caputo-like delta fractional difference operator, we will present a fractional discrete model of a 4D Power System. We present an extension of the popular integer-order single-machine infinite-bus formulation to two fractional cases, one with commensurate (equal) fractional orders and another incommensurate (not equal). This extension captures long-memory effects in dynamics and thus offers a consistent mathematical description of the nonlinear behavior of power systems. The orders of the fractional models are analyzed numerically. Using time series evolution, phase-space plots, bifurcation maps, Lyapunov spectra, and the 0–1 chaos test, spectral entropy and $C_0$ complexity metrics, we identify chaotic regimes. Additionally, techniques for controlling chaos are explored to stabilize and regulate the dynamics of the system. Both the fractional formulations exhibit richer dynamical features than their integer counterparts, and for the incommensurate case, the sensitivity to the fractional variations is larger, generating complex nonlinear oscillations. The fractional discrete power system framework provides a new perspective for studying instability, the voltage collapse phenomenon, and chaotic oscillations in power engineering applications. Full article

Large Language Models (LLMs) have witnessed significant adoption across numerous domains since 2020, but their proclivity to hallucinate creates unacceptable dangers in high-risk environments like healthcare, where wrong outputs can directly jeopardize human safety. While present systems focus on pre-generation mitigation strategies, they cannot ensure the safety of individual outputs during inference. We provide a post hoc Hallucination Risk Scoring (HRS) methodology that intercepts questionable outputs before they reach patients via an agentic pipeline. Given a medical question, a domain-specific LLM generates an initial response from which five complimentary uncertainty signals are computed, which are then separated into a decision layer that governs escalation and a guidance layer that directs clinical knowledge injection by a GPT. The framework is tested using three biological question-answering datasets of various complexity: PubMedQA-Labeled, PubMedQA-Artificial, and BioASQ Task B. The results show an up to 38% safety increase at the most sensitive threshold configuration, zero deterioration across all experimental configurations enforced by the Revert Baseline method, and complexity-aware escalation rates that scale organically with dataset difficulty. Tunable thresholds allow physicians to calibrate system behavior based on deployment requirements, providing a practical safety–accuracy trade-off. Statistical research finds entropy as the primary uncertainty signal separating escalated from non-escalated situations across all datasets. These findings provide a deployable, interpretable, and configurable post hoc safety paradigm for reliable medical AI implementation. Full article

Efficient joining of hard metals to steels is crucial for supporting sustainable manufacturing under emissions strategies to minimize CO₂. CoNiCrFeCu high-entropy alloy containing scandium (Sc) was designed as a filler for laser braze-welding of WC-Co and steel. The designed compositions with different Sc levels were melted and cast in a high-vacuum non-consumable arc furnace. The results showed that the as-cast microstructure was a complex mixture of a networked Ni₂Si, elongated Cr-Fe-Co solid-solution phase, and Fe-Ni-Co-Cu solid-solution phase. Scandium was shown to have formed compounds with nickel/cobalt and copper. The TG-DSC analysis confirmed that the melting points of the designed compositions were between 973.7 °C and 981.5 °C. The maximum spreading area of the CoNiCrFeCu-0.9Sc composition on AISI 1045 steel was 64.83 mm², and on the WC-Co cermet it was 78.63 mm². The interface between the fusion zone and AISI 1045 steel exhibited an epitaxial growth of dendrites from the steel base metal. The interface between WC-Co and the fusion zone exhibited a partial penetration of brazing filler into the Co matrix, forming a metallurgical bonding between the dissimilar materials. Sc, as an alloying element in the filler metal, enhanced the bond formation because it decreased the solidus temperature and increased wetting. Full article

Diagnosis of colorectal cancer (CRC) primarily relies on histopathological examination of hematoxylin and eosin-stained tissue sections; however, manual interpretation is time-consuming, subjective, and increasingly impractical given the rapid growth of digital pathology data. We introduced a hybrid loss-based learning framework for multi-class colorectal histopathology image classification that improves class-balanced performance without increasing model complexity. Various EfficientNet versions were checked as the first step to establishing a strong baseline, and EfficientNet-B3 was chosen based on validation Matthews Correlation Coefficient (MCC). Extending this backbone, we propose a hybrid loss function that mixes weighted cross-entropy and focal loss to achieve the combined effect of dealing with the global class imbalance while also focusing on hard-to-classify samples. The results of experiments on a large-scale colorectal histopathology dataset show that the Hybrid-B3 model introduced significantly improves the baseline settings. Hybrid-B3 registers a test accuracy of 99.83%, a very high class-balanced performance with a balanced accuracy and G-Mean of 99.85%. The changes are verified and non-random by the statistical validation using bootstrap confidence intervals and paired significance tests. The offered solution emphasizes the efficiency of loss-function optimization solely to provide improvements in robustness and reliability in computational pathology and, correspondingly, yields a practical and scalable solution for colorectal cancer diagnostic support in the real ‍‌world. Full article

The development of accident-tolerant fuels has significantly enhanced the safety of fission reactors. The TiNbZrO alloy system has garnered considerable attention due to its excellent mechanical properties and outstanding irradiation resistance. Its unique compositional design enables effective suppression of irradiation-induced defect formation. In this study, TiNbZrO thin films are fabricated via radio-frequency magnetron sputtering and irradiated with 50 keV He ions to fluences of 5 × 10¹⁶, 1 × 10¹⁷, and 2 × 10¹⁷ ions/cm². The microstructural evolution before and after irradiation is characterized by Transmission Electron Microscopy (TEM) and Grazing Incidence X-ray Diffraction (GIXRD), and the changes in mechanical properties are evaluated by nanoindentation. With increasing irradiation fluence, the average size of He bubbles increases from 1.10 nm to 2.06 nm, the number density decreases from 5.27 × 10²⁴ m⁻³ to 1.39 × 10²⁴ m⁻³, and the swelling rate rises from 0.37% to 0.64%. Although significant irradiation hardening is observed in all samples, the maximum hardening rate reaches only 31.91%, a value substantially lower than that reported for many conventional nuclear materials. This demonstrates the superior irradiation resistance of TiNbZrO thin films. The superior irradiation resistance of TiNbZrO thin films stems from two synergistic effects: high-entropy lattice distortion suppresses atomic diffusion, while oxygen complexes pin defects. 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

In the fault diagnosis of complex industrial systems, labeled samples are expensive to obtain, which leads to insufficient training data for the belief rule base (BRB) model. Although unlabeled samples are abundant, the uncertainty of their pseudo-labels may undermine semi-supervised learning and hinder accurate parameter optimization of the BRB model. To address these issues, a dual-source evidence-driven semi-supervised BRB method (SS-BRB) is proposed for fault diagnosis. The proposed method makes effective use of unlabeled samples while preserving the interpretability and inference transparency of the BRB model. To improve the reliability of pseudo-labels in semi-supervised learning, a dual-source evidence-driven pseudo-labeling mechanism is designed. In this mechanism, local similarity information is combined with the global inference results of the BRB model. An entropy factor and a feature distance factor are introduced to adaptively adjust the confidence of pseudo-labels. In this way, the quality of pseudo-labels is improved, and the influence of noisy samples is reduced. Based on this mechanism, high-confidence pseudo-labeled samples are incorporated into the training set to further optimize the model. Experimental results show that the proposed method achieves good diagnostic performance on both the gearbox dataset and the WD615 diesel engine dataset. Even with limited labeled data, the proposed method still achieves high accuracy, robustness, and good generalization performance. Full article

Understanding pressure-induced isosymmetric phase transitions in molecular crystals requires consideration of both structural and thermodynamic factors, particularly in hydrogen-bonded systems. In this work, periodic density functional theory (DFT) calculations were employed to investigate the pressure-dependent behavior of L-serine and to elucidate the origin of its experimentally observed phase transition between Phase I and Phase IV. Geometry optimizations performed at ambient pressure and 8.8 GPa reproduce the compression of the crystal lattice and the pressure-driven stabilization of Phase IV. However, no spontaneous reorientation of the hydroxyl groups is observed, indicating that the transition is not accessible within a purely static framework. To further explore the stability of the system, a series of modified crystal structures with different hydroxyl group orientations was generated and analyzed, revealing a complex energy landscape at ambient conditions that becomes significantly simplified under compression. Phonon calculations within the quasi-harmonic approximation demonstrate that the experimentally observed Phase I structure is not stabilized by enthalpy but by vibrational entropy, whose contribution increases with temperature. These results show that the phase transition in L-serine is governed by an interplay between lattice energy, hydrogen-bond rearrangement, and vibrational effects, and highlight that an accurate description of polymorphic stability in such systems requires inclusion of both static and dynamic contributions. Full article