Search Results (170)

Identifying urban functional areas increasingly relies on data-driven approaches that utilize multimodal spatial information. There is a growing focus on purpose-oriented functional area identification with greater policy relevance. This paper proposes a data-driven methodology to identify functional areas from the perspective of bicycle users. To achieve this, line-based road network units were defined around bicycle stations, and spatial–temporal data such as Origin–Destination flows and Point of Interest information were semantically integrated to delineate functional areas. An experiment was conducted on 2628 public bicycle stations in Seoul, Republic of Korea, for May 2022, and a total of five functional areas were identified via a Co-Matrix Factorization-based fusion approach. Additionally, the proposed method was validated through visual evaluation and comparison with actual bicycle usage data. The results demonstrate that by simultaneously incorporating spatial–temporal information and latent connectivity, this approach identifies bicycle-friendly areas, even with low observed usage, highlighting its potential for policy applications. Full article

The prediction of Remaining Useful Life (RUL) constitutes a vital aspect of Prognostics and Health Management (PHM), providing capabilities for the assessment of mechanical component health status and prediction of failure instances. Recent studies on feature extraction, time-series modeling, and multi-task learning have shown remarkable advancements. However, most deep learning (DL) techniques predominantly focus on unimodal data or static feature extraction techniques, resulting in a lack of RUL prediction methods that can effectively capture the individual differences among heterogeneous sensors and failure modes under complex operational conditions. To overcome these limitations, an adaptive RUL prediction framework named ADAPT-RULNet is proposed for mechanical components, integrating the feature extraction capabilities of attention-enhanced deep learning (DL) and the decision-making abilities of deep reinforcement learning (DRL) to achieve end-to-end optimization from raw data to accurate RUL prediction. Initially, Functional Alignment Resampling (FAR) is employed to generate high-quality functional signals; then, attention-enhanced Dynamic Time Warping (DTW) is leveraged to obtain individual degradation stages. Subsequently, an attention-enhanced of hybrid multi-scale RUL prediction network is constructed to extract both local and global features from multi-format data. Furthermore, the network achieves optimal feature representation by adaptively fusing multi-source features through Bayesian methods. Finally, we innovatively introduce a Deep Deterministic Policy Gradient (DDPG) strategy from DRL to adaptively optimize key parameters in the construction of individual degradation stages and achieve a global balance between model complexity and prediction accuracy. The proposed model was evaluated on aircraft engines and railway freight car wheels. The results indicate that it achieves a lower average Root Mean Square Error (RMSE) and higher accuracy in comparison with current approaches. Moreover, the method shows strong potential for improving prediction accuracy and robustness in varied industrial applications. Full article

Aluminum alloy surface microstructures possess functional characteristics such as hydrophilicity/hydrophobicity and anti-icing and have important applications in fields such as aerospace and power systems. In order to improve the filling quality of the microstructure and verify the anti-icing property of the microstructure, this work develops a scheme for achieving large-area hot embossing of anti-icing functional microstructures based on a multi-arc ion-plating mold. Compared with conventional steel, the hardness of the PVD-coated steel increases by 44.7%, the friction coefficient decreases by 66.2%, and the wear resistance is significantly enhanced. The PVD-coated punch-assisted embossing could significantly improve filling properties. While the embossing temperature is 300 °C, the PVD-coated punch-assisted embossing can ensure the complete filling of the micro-array channels. In contrast, under-filling defects occur in conventional hot embossing. Then, a large-area micro-channel specimen of 100 cm² was precisely formed without warping, and the average surface roughness Ra was better than 0.8 µm. The maximum freezing fraction of the micro-array channel was reduced by about 53.2% compared with the planar, and the complete freezing time was delayed by 193.3%. The main reason is that the air layer trapped by the hydrophobic structures hinders heat loss at the solid–liquid interface. Full article

This work presents a comprehensive study of weakly B-symmetric warped product manifolds ${\left(WBS\right)}_n$, a natural extension of several classical curvature-restricted geometries including B-flat, B-parallel, and B-recurrent manifolds. We begin by formulating the fundamental properties of the B-tensor $B(X,Y)=aS(X,Y)+brg(X,Y)$, where S is the Ricci tensor, r the scalar curvature, and $a,b$ are smooth non-vanishing functions. The warped product structure is then exploited to obtain explicit curvature identities for base and fiber manifolds under various geometric constraints. Detailed characterizations are established for Einstein conditions, Codazzi-type tensors, cyclic parallel tensors, and the behavior of geodesic vector fields. The weakly B-symmetric condition is analyzed through all possible projections of vector fields, leading to sharp criteria describing the interaction between the warping function and curvature. Several applications are discussed in the context of Lorentzian geometry, including perfect fluid and generalized Robertson–Walker spacetimes in general relativity. These results not only unify different curvature-restricted frameworks but also reveal new geometric and physical implications of warped product manifolds endowed with weak B-symmetry. Full article

As advancements in inertial measurement units (IMUs) for motion analysis progress, the inability to directly apply decades of research-based optical motion capture (OMC) methodologies presents a significant challenge. This study aims to bridge this gap by proposing an innovative deep learning approach to predict marker positions from IMU data, allowing traditional OMC-based calculations to estimate joint kinematics. Eighteen participants walked on a treadmill with seven IMUs and retroreflective markers. Trials were divided into normalized gait cycles (101 frames), and an autoencoder network with a custom Biomech loss function was used to predict 16 marker positions from IMU data. The model was validated using the leave-one-subject-out method and assessed using root mean squared error (RMSE). Joint angles in the sagittal plane were calculated using OMC methods, and RMSE was computed with and without alignment using dynamic time warping (DTW). The models were also tested on external datasets. Marker predictions achieved RMSE values of 2–4 cm, enabling joint angle predictions with 4–7° RMSE without alignment and 2–4° RMSE after DTW for sagittal plane joint angles (ankle, knee, hip). Validation using separate and open-source datasets confirmed the model’s generalizability, with similar RMSE values across datasets (4–7° RMSE without DTW and 2–4° with DTW). This study demonstrates the feasibility of applying conventional biomechanical models to IMUs, enabling accurate movement analysis and visualization outside controlled environments. This approach to predicting marker positions helps to bridge the gap between IMUs and OMC systems, enabling decades of research-based biomechanical methodologies to be applied to IMU data. Full article

With the advancement of new power system construction, thermostatically controlled loads represented by regional air conditioning systems are being extensively integrated into the grid, leading to a surge in the number of user nodes. This large-scale integration of new loads creates challenges for the grid, as the resulting load data exhibits strong periodicity and randomness over time. These characteristics are influenced by factors like temperature and user behavior. At the same time, spatially adjacent nodes show similarities and clustering in electricity usage. This creates complex spatiotemporal coupling features. These complex spatiotemporal characteristics challenge traditional forecasting methods. Their high model complexity and numerous parameters often lead to overfitting or the curse of dimensionality, which hinders both prediction accuracy and efficiency. To address this issue, this paper proposes a load forecasting method based on spatiotemporal partitioning and collaborative cross-regional attention. First, a spatiotemporal similarity matrix is constructed using the Shape Dynamic Time Warping (ShapeDTW) algorithm and an adaptive Gaussian kernel function based on the Haversine distance. Spectral clustering combined with the Gap Statistic criterion is then applied to adaptively determine the optimal number of partitions, dividing all load nodes in the power grid into several sub-regions with homogeneous spatiotemporal characteristics. Second, for each sub-region, a local Spatiotemporal Graph Convolutional Network (STGCN) model is built. By integrating gated temporal convolution with spatial feature extraction, the model accurately captures the spatiotemporal evolution patterns within each sub-region. On this basis, a cross-regional attention mechanism is designed to dynamically learn the correlation weights among sub-regions, enabling collaborative fusion of global features. Finally, the proposed method is evaluated on a multi-node load dataset. The effectiveness of the approach is validated through comparative experiments and ablation studies (that is, by removing key components of the model to evaluate their contribution to the overall performance). Experimental results demonstrate that the proposed method achieves excellent performance in short-term load forecasting tasks across multiple nodes. Full article

Residual stresses and internal strains in 3D printing can lead to issues such as cracking, warping, and delamination—challenges that are amplified when using functional composite materials like magnetic PLA filaments. This study investigates the thermo-mechanical strain evolution during fused filament fabrication (FFF) of magnetite-filled PLA using an integrated methodology combining strain gauge sensors, high-resolution infrared thermal imaging, and synchrotron X-ray microtomography. Printing parameters, including nozzle temperature (190–220 °C), build platform temperature (30–100 °C), printing speed (30–60 mm/s), and cooling strategy (fan on/off) were systematically varied to evaluate their influence. Results reveal steep thermal gradients along the build direction (up to −1 °C/µm), residual strain magnitudes reaching 0.1 µε, and enhanced viscoelastic creep at elevated platform temperatures. The addition of magnetic particles modifies heat distribution and strain evolution, leading to strong sensitivity to process conditions. These findings provide valuable insight into the complex thermo-mechanical interactions governing the structural integrity of magnetically functionalized PLA composites in additive manufacturing. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder that severely impacts motor function, necessitating early detection for effective management. However, current diagnostic methods are expensive and resource-intensive, limiting their accessibility. This study proposes a non-invasive, gait-based screening approach for PD using time-series analysis of video-derived motion data. Gait patterns indicative of PD are analyzed using videos containing walking sequences of PD subjects. The video data are processed via computer vision and human pose estimation techniques to extract key body points. Classification is performed using K-Nearest Neighbors (KNN) and Long Short-Term Memory (LSTM) networks in conjunction with time-series techniques, including Dynamic Time Warping (DTW), Bag of Patterns (BoP), and Symbolic Aggregate Approximation (SAX). KNN classifies based on similarity measures derived from these methods, while LSTM captures complex temporal dependencies. Additionally, Shapelet-based Classification is independently explored for its ability to serve as a self-contained classifier by extracting discriminative motion patterns. On a self-collected dataset (43 instances: 8 PD and 35 healthy), DTW-based classification achieved 88.89% accuracy for both KNN and LSTM. On an external dataset (294 instances: 150 healthy and 144 PD with varying severity), KNN and LSTM achieved 71.19% and 57.63% accuracy, respectively. The proposed approach enhances PD detection through a cost-effective, non-invasive methodology, supporting early diagnosis and disease monitoring. By integrating machine learning with clinical insights, this study demonstrates the potential of AI-driven solutions in advancing PD screening and management. Full article

In this study, a novel arbitrary order Virtual Element Method (p-VEM) for free torsional vibration analysis of beams with negligible warping is presented. This method can serve as an equivalent beam model for slender aerospace structural components. The proposed formulation utilizes a spatial discretization of the primary variable with implicit virtual functions that are approximated with polynomials of arbitrary order p by employing a suitably defined projection operator and degrees of freedom. From the spatial discretization of the weak form of the equations of motion, the semi-discrete equations of motion are obtained, from which stiffness and mass matrices are derived without the need for additional stabilization. The developed formulation is validated through several case studies, which demonstrate that the p-VEM offers higher accuracy and faster convergence rate compared to traditional modeling approaches. Full article

High-power microelectronic packaging faces critical thermomechanical failures under rapid thermal cycling, primarily due to interfacial stress concentration and warping in conventional homogeneous heat sinks. To address this challenge, this study proposes a novel functionally graded SiC/Al composite with a tailored thermal expansion coefficient (CTE) gradient, designed to achieve adaptive thermal expansion matching between the chip and heat sink. Through multiscale finite element analysis, the stress–strain behavior and warping characteristics of homogeneous (Cu and Al) and gradient materials were systematically investigated. The results show that the gradient SiC/Al design significantly reduces the peak thermal stress and maximum warping deformation. The progressive CTE transition effectively mitigates abrupt interfacial strain jumps and extends device lifespan under extreme thermal loads. This advancement positions gradient SiC/Al composites as a key enabler for next-generation high-density packaging and power electronics requiring cyclic thermal stability. The study provides both theoretical insights into thermomechanical coupling and practical guidelines for designing robust electronic packaging solutions. Full article

In this paper, we investigate the geometry and topology of compact warped product minimal submanifolds of arbitrary codimension immersed in a sphere. These submanifolds satisfy a specific pinching condition relating the length and Laplacian of the warping function to the dimensions of the warped product. Our results extend previous work on minimal immersions into the sphere. Full article

Distributed acoustic sensing shows great potential for pipeline monitoring. However, internally deployed and unfixed sensing cables are highly susceptible to disturbances from water flow noise, severely challenging impact source localization. This study proposes a novel two-step method to address this. The first step employs Variational Mode Decomposition (VMD) combined with Short-Time Energy Entropy (STEE) for the adaptive extraction of impact signal from noisy data. STEE is introduced as a stable metric to quantify signal impulsiveness and guides the selection of the relevant intrinsic mode function. The second step utilizes the Pruned Exact Linear Time (PELT) algorithm for accurate signal segmentation, followed by an unsupervised learning method combining Dynamic Time Warping (DTW) and clustering to identify the impact segment and precisely pick the arrival time based on shape similarity, overcoming the limitations of traditional pickers under conditions of complex noise. Field tests on an operational water pipeline validated the method, demonstrating the consistent localization of manual impacts with standard deviations typically between 1.4 m and 2.0 m, proving its efficacy under realistic noisy conditions. This approach offers a reliable framework for pipeline safety assessments under operational conditions. Full article

This study investigates the influence of weaving process parameters on the structural homogeneity of woven fabrics, with a focus on the structural autoregulation phenomenon. Two experimental fabric groups of 30 each, plain and twill weaves, were produced using varied loom settings: shed closure timing, lease rod position, backrest roller position, warp pre-tension, and yarn twist direction. Structural uniformity was assessed using a proprietary method and the MagFABRIC 2.1. image analysis system, which quantify intra-repeat, inter-repeat, and global inhomogeneity. This method uses the size, shape, and location of inter-thread pores as well as warp and weft pitches. The results indicate that autoregulation can reduce local structural disturbances, including warp yarn grouping. In plain weaves, loom parameters and humidity significantly contributed to structural autoregulation. In contrast, twill weaves demonstrated dominant internal feedback mechanisms, significantly influenced by yarn twist direction. Regression models at F = 10 revealed nonlinear interactions, confirming autoregulation and experimentally supporting Nosek’s quasi-dynamic theory for these types of fabrics. The results of these studies have practical relevance in high-performance textiles such as filtration, barrier fabrics, and composite reinforcements, where local structural deviations critically affect the functional properties of fabrics. Full article

This paper presents FWStab, a specialized video stabilization dataset tailored for flapping-wing platforms. The dataset encompasses five typical flight scenarios, featuring 48 video clips with intense dynamic jitter. The corresponding Inertial Measurement Unit (IMU) sensor data are synchronously collected, which jointly provide reliable support for multimodal modeling. Based on this, to address the issue of poor image acquisition quality due to severe vibrations in aerial vehicles, this paper proposes a multi-modal signal fusion video stabilization framework. This framework effectively integrates image features and inertial sensor features to predict smooth and stable camera poses. During the video stabilization process, the true camera motion originally estimated based on sensors is warped to the smooth trajectory predicted by the network, thereby optimizing the inter-frame stability. This approach maintains the global rigidity of scene motion, avoids visual artifacts caused by traditional dense optical flow-based spatiotemporal warping, and rectifies rolling shutter-induced distortions. Furthermore, the network is trained in an unsupervised manner by leveraging a joint loss function that integrates camera pose smoothness and optical flow residuals. When coupled with a multi-stage training strategy, this framework demonstrates remarkable stabilization adaptability across a wide range of scenarios. The entire framework employs Long Short-Term Memory (LSTM) to model the temporal characteristics of camera trajectories, enabling high-precision prediction of smooth trajectories. Full article

Kumite is a karate sparring competition in which two players fight each other using various techniques. In kumite matches, it is essential to reduce a preliminary action (hereinafter referred to as “pre-action”), such as pulling the arms and lowering the shoulders just before performing an attack technique. This is because pre-actions reveal the timing of the attack to the opponent. However, players often find it difficult to recognize their own pre-actions, and accurately estimating their presence or absence is challenging with conventional motion analysis methods, as pre-actions are subtle compared to major techniques like punching or kicking. Previously, we proposed a method for detecting pre-actions during single punches performed in a static state using inertial sensors. While this method was effective in controlled situations, it failed to detect pre-actions in punches during actual kumite matches. The main reason is that players generally perform footwork during matches, and this footwork is often misrecognized as pre-action via conventional detection methods. To address misrecognition caused by footwork, we propose a new method that combines preprocessing designed to detect and smooth footwork segments in the inertial data with the conventional pre-action detection method, thereby enabling pre-action detection during kumite matches. In the preprocessing, we apply an autocorrelation function to assess the constancy of footwork and accurately separate the footwork segment from the kumite technique segment. Only the footwork segment is then smoothed to suppress its influence on the detection process. Our experimental results show that the proposed method can estimate the presence or absence of pre-action in the punch of an actual kumite match with an accuracy of 0.875. Full article