Search Results (28)

Driving style recognition plays a crucial role in improving the operational safety, fuel efficiency, and intelligent control of commercial vehicles. Under real-world driving conditions, Controller Area Network (CAN) bus data from commercial vehicles simultaneously contain rapid transient variations induced by pedal and braking operations, as well as long-term behavioral trends reflecting driving habits, exhibiting pronounced multi-temporal characteristics. In addition, such data are typically affected by high noise levels, high dimensionality, and highly variable operating conditions, which makes it difficult for methods relying on single-scale features or handcrafted rules difficult to maintain robust and stable performance in complex scenarios. To address these challenges, this paper proposes a driving style classification network, termed the Multi-Scale Convolution and Efficient Channel Attention Network (MSCA-Net). By employing parallel convolutional branches with different temporal receptive fields, the proposed network is able to capture fast driver responses, local temporal dependencies, and long-term behavioral evolution, enabling unified modeling of cross-scale temporal patterns in driving behavior. Meanwhile, the Efficient Channel Attention mechanism adaptively emphasizes CAN signal channels that are highly relevant to driving style discrimination, thereby enhancing the discriminative capability and robustness of the learned feature representations. Experiments conducted on real-world multi-dimensional CAN time-series data collected from commercial vehicles demonstrate that the proposed MSCA-Net achieves improved classification performance in driving style recognition. Furthermore, the potential application of the recognized driving styles in adaptive Automated Manual Transmission shift strategy adjustment is discussed, providing a feasible engineering pathway toward behavior-aware intelligent control of commercial vehicle powertrains. Full article

The deployment of 5G (Fifth-Generation) networks in industrial Internet of Things (IoT), intelligent transportation, and emergency communications introduces heterogeneous and dynamic network states, leading to frequent and diverse faults. Traditional fault detection methods typically emphasize either local temporal anomalies or global distributional characteristics, but rarely achieve an effective balance between the two. In this paper, we propose a parallel multi-branch convolutional neural network (CNN)–Transformer framework (MBCT) to improve fault diagnosis accuracy in 5G networks. Specifically, MBCT takes time-series network key performance indicator (KPI) data as input for training and performs feature extraction through three parallel branches: a CNN branch for local patterns and short-term fluctuations, a Transformer encoder branch for cross-layer and long-term dependencies, and a statistical branch for global features describing quality-of-experience (QoE) metrics. A gating mechanism and feature-weighted fusion are applied outside the branches to adjust inter-branch weights and intra-branch feature sensitivity. The fused representation is then nonlinearly mapped and fed into a classifier to generate the fault category. This paper evaluates the performance of the proposed model on both the publicly available TelecomTS multi-modal 5G network observability dataset and a self-collected SDR5GFD dataset based on software-defined radio (SDR). Experimental results demonstrate that the proposed model achieves superior performance in fault classification, achieving 87.7% accuracy on the TelecomTS dataset and 86.3% on the SDR5GFD dataset, outperforming the baseline models CNN, Transformer, and Random Forest. Moreover, the model contains approximately 0.57M parameters and requires about 0.3 MFLOPs per sample for inference, making it suitable for large-scale online fault diagnosis. Full article

Accurate identification of the combustion state in municipal solid waste incineration (MSWI) processes is crucial for achieving efficient, low-emission, and safe operation. However, existing methods often struggle with stable and reliable recognition due to insufficient feature extraction capabilities when confronted with challenges such as complex flame morphology, blurred boundaries, and significant noise in flame images. To address this, this paper proposes a novel hybrid architecture model named PRTNet, which aims to enhance the accuracy and robustness of combustion state recognition through multi-scale feature enhancement and adaptive fusion mechanisms. First, a local-semantic enhanced residual network is constructed to establish spatial correlations between fine-grained textures and macroscopic combustion patterns. Subsequently, a feature-adaptive fusion Transformer is designed, which models long-range dependencies and high-frequency details in parallel via deformable attention and local convolutions, and achieves adaptive fusion of global and local features through a gating mechanism. Finally, a cross-scale feature guided aggregation module is proposed to fuse shallow detailed information with deep semantic features under dual-attention guidance. Experiments conducted on a flame image dataset from an MSWI plant in Beijing show that PRTNet achieves an accuracy of 96.29% in the combustion state classification task, with precision, recall, and F1-score all exceeding 96%, significantly outperforming numerous mainstream baseline models. Ablation studies further validate the effectiveness and synergistic effects of each module. The proposed method provides a reliable solution for intelligent flame state recognition in complex industrial scenarios, contributing to the advancement of intelligent and sustainable development in municipal solid waste incineration processes. Full article

Semantic change detection (SCD) effectively captures ground object transition information within change regions, delivering more comprehensive and detailed results than binary change detection (BCD) tasks. The existing multi-task SCD models enable parallel processing of segmentation and BCD of bi-temporal remote sensing images, but they still have shortcomings in feature mining, interaction, and cross-task transfer. To address these limitations, a multi-branch feature interaction network (MBFI-Net) is proposed. MBFI-Net designs parallel encoding branches with attention mechanisms that enhance semantic change perception by jointly modeling global contextual patterns and local details. In addition, MBFI-Net proposes bi-temporal feature interaction (BTFI) and cross-task feature transfer (CTFT) modules to improve feature diversity and representativeness, and combines with prior logical relationship constraints to improve SCD performance. Comparative and ablation studies on the SECOND and Landsat-SCD datasets highlight the superiority and robustness of MBFI-Net, which achieves SeKs of 0.2117 and 0.5543, respectively. Furthermore, MBFI-Net strikes a balance between SCD results and model complexity and has superior detection performance for semantic change categories with a small proportion. Full article

As power systems expand and grow smarter, the safe and steady operation of substation equipment has become a prerequisite for grid reliability. In cluttered substation scenes, however, existing deep learning detectors still struggle with small targets, multi-scale feature fusion, and precise localization. To overcome these limitations, we introduce PBZGNet, a defect-detection network that couples a gradual parallel-branch backbone, a zoom-fusion neck, and a global channel-recalibration module. First, BiCoreNet is embedded in the feature extractor: dual-core parallel paths, reversible residual links, and channel recalibration cooperate to mine fault-sensitive cues. Second, cross-scale ZFusion and Concat-CBFuse are dynamically merged so that no scale loses information; a hierarchical composite feature pyramid is then formed, strengthening the representation of both complex objects and tiny flaws. Third, an attention-guided decoupled detection head (ADHead) refines responses to obscured and minute defect patterns. Finally, within the Generalized Focal Loss framework, a quality rating scheme suppresses background interference while distribution regression sharpens the localization of small targets. Across all scales, PBZGNet clearly outperforms YOLOv11. Its lightweight variant, PBZGNet-n, attains 83.9% mAP@50 with only 2.91 M parameters and 7.7 GFLOPs—9.3% above YOLOv11-n. The full PBZGNet surpasses the current best substation model, YOLO-SD, by 7.3% mAP@50, setting a new state of the art (SOTA). Full article

Accurate and robust feature matching across multi-view urban imagery is fundamental for urban mapping, 3D reconstruction, and large-scale spatial alignment. Real-world urban scenes involve significant variations in viewpoint, illumination, and occlusion, as well as repetitive architectural patterns that make correspondence estimation challenging. To address these issues, we propose the Cross-Context Aggregation Matcher (CCAM), a detector-free framework that jointly leverages multi-scale local features, long-range contextual information, and geometric priors to produce spatially consistent matches. Specifically, CCAM integrates a multi-scale local enhancement branch with a parallel self- and cross-attention Transformer, enabling the model to preserve detailed local structures while maintaining a coherent global context. In addition, an independent positional encoding scheme is introduced to strengthen geometric reasoning in repetitive or low-texture regions. Extensive experiments demonstrate that CCAM outperforms state-of-the-art methods, achieving up to +31.8%, +19.1%, and +11.5% improvements in AUC@{5°, 10°, 20°} over detector-based approaches and up to 1.72% higher precision compared with detector-free counterparts. These results confirm that CCAM delivers reliable and spatially coherent matches, thereby facilitating downstream geospatial applications. Full article

This article presents the results of an experimental study on the hydrodynamics of the coolant at the inlet of the fuel assembly in the RITM reactor core. The importance of these studies stems from the significant impact that inlet flow conditions have on the flow structure within a fuel assembly. A significant variation in axial velocity and local flow rates can greatly affect the heat exchange processes within the fuel assembly, potentially compromising the safety of the core operation. The aim of this work was to investigate the effect of different designs of orifice inlet devices and integrated absorber grids on the flow pattern of the coolant in the rod bundle of the fuel assembly. To achieve this goal, experiments were conducted on a scaled model of the inlet section of the fuel assembly, which included all the structural components of the actual fuel assembly, from the orifice inlet device to the second spacer grids. The test model was scaled down by a factor of 5.8 from the original fuel assembly. Two methods were used to study the hydrodynamics: dynamic pressure probe measurements and the tracer injection technique. The studies were conducted in several sections along the length of the test model, covering its entire cross-section. The choice of measurement locations was determined by the design features of the test model. The loss coefficient (K) of the orifice inlet device in fully open and maximally closed positions was experimentally determined. The features of the coolant flow at the inlet of the fuel assembly were visualized using axial velocity plots in cross-sections, as well as concentration distribution plots for the injected tracer. The geometry of the inlet orifice device at the fuel assembly has a significant impact on the pattern of axial flow velocity up to the center of the fuel bundle, between the first and second spacing grids. Two zones of low axial velocity are created at the edges of the fuel element cover, parallel to the mounting plates, at the entrance to the fuel bundle. These unevennesses in the axial speed are evened out before reaching the second grid. The attachment plates of the fuel elements to the diffuser greatly influence the intensity and direction of flow mixing. A comparative analysis of the effectiveness of two types of integrated absorber grids was performed. The experimental results were used to justify design modifications of individual elements of the fuel assembly and to validate the hydraulic performance of new core designs. Additionally, the experimental data can be used to validate CFD codes. Full article

To address the challenge that MOSFET temperature in motor controllers is influenced by multiple factors, exhibits strong temporal dependence, and involves complex feature interactions, this study proposes a temperature prediction model that integrates Temporal Convolutional Networks (TCNs) and the Informer architecture in parallel, enhanced with a cross-attention mechanism. The model leverages TCNs to capture local temporal patterns, while the Informer extracts long-range dependencies, and cross-attention strengthens feature interactions across channels to improve predictive accuracy. A dataset was constructed based on measured MOSFET temperatures under various operating conditions, with input features including voltage, load current, switching frequency, and multiple ambient temperatures. Experimental evaluation shows that the proposed method achieves a mean absolute error of 0.2521 °C, a root mean square error of 0.3641 °C, and an R² of 0.9638 on the test set, outperforming benchmark models such as Times-Net, Informer, and LSTM. These results demonstrate the effectiveness of the proposed approach in reducing prediction errors and enhancing generalization, providing a reliable tool for real-time thermal monitoring of motor controllers. Full article

Short-term passenger flow prediction provides critical data-driven support for optimizing resource allocation, guiding passenger mobility, and enhancing risk response capabilities in urban rail transit systems. To further improve prediction accuracy, this study proposes a hybrid SMA-VMD-Informer-BiLSTM prediction model. Addressing the challenge of error propagation caused by non-stationary components (e.g., noise and abrupt fluctuations) in conventional passenger flow signals, the Variational Mode Decomposition (VMD) method is introduced to decompose raw flow data into multiple intrinsic mode functions (IMFs). A Slime Mould Algorithm (SMA)-based optimization mechanism is designed to adaptively tune VMD parameters, effectively mitigating mode redundancy and information loss. Furthermore, to circumvent error accumulation inherent in serial modeling frameworks, a parallel prediction architecture is developed: the Informer branch captures long-term dependencies through its ProbSparse self-attention mechanism, while the Bidirectional Long Short-Term Memory (BiLSTM) network extracts localized short-term temporal patterns. The outputs of both branches are fused via a fully connected layer, balancing global trend adherence and local fluctuation characterization. Experimental validation using historical entry flow data from Weihouzhuang Station on Xi’an Metro demonstrated the superior performance of the SMA-VMD-Informer-BiLSTM model. Compared to benchmark models (CNN-BiLSTM, CNN-BiGRU, Transformer-LSTM, ARIMA-LSTM), the proposed model achieved reductions of 7.14–53.33% in $f_{mse}$, 3.81–31.14% in $f_{rmse}$, and 8.87–38.08% in $f_{mae}$, alongside a 4.11–5.48% improvement in $R^2$. Cross-station validation across multiple Xi’an Metro hubs further confirmed robust spatial generalizability, with prediction errors bounded within $f_{mse}$: 0.0009–0.01, $f_{rmse}$: 0.0303–0.1, $f_{mae}$: 0.0196–0.0697, and $R^2$: 0.9011–0.9971. Furthermore, the model demonstrated favorable predictive performance when applied to forecasting passenger inflows at multiple stations in Nanjing and Zhengzhou, showcasing its excellent spatial transferability. By integrating multi-level, multi-scale data processing and adaptive feature extraction mechanisms, the proposed model significantly mitigates error accumulation observed in traditional approaches. These findings collectively indicate its potential as a scientific foundation for refined operational decision-making in urban rail transit management, thereby significantly promoting the sustainable development and long-term stable operation of urban rail transit systems. Full article

Background: The increasing popularity of fruit juices as part of perceived healthy dietary choices has raised concerns regarding their erosive effects on dental enamel. While prior in vitro studies have largely relied on commercial fruit drinks and non-human enamel samples, this study adopts a more ecologically valid approach by using fresh local fruit juices and extracted human teeth to evaluate enamel erosion. Objectives: This study aimed to assess the consumption patterns, oral hygiene behaviours, and awareness of the erosive potential of fruit juices among Malaysian adults and to evaluate the erosive effects of freshly squeezed local fruit juices on human dental enamel under simulated oral conditions. Methods: A questionnaire-based cross-sectional survey (n = 189) was conducted among dental clinic attendees to assess fruit juice intake habits, oral health practices, and awareness levels. In parallel, an in vitro study was performed using 40 extracted premolar teeth immersed in lime juice, pineapple juice, citric acid (positive control), or distilled water (negative control) over a 10-day period. Enamel volume loss, surface roughness, and microhardness were analysed pre- and post-immersion. Results: Fruit juice consumption was highly prevalent, with lime (57.7%) being the most commonly consumed, followed by watermelon (53.0%), star fruit (15.9%), and pineapple (15.4%). The majority of respondents preferred sweetened juices (75.7%) and demonstrated only moderate oral hygiene, with just 53.4% reporting brushing their teeth twice daily. Awareness of the dental effects of acidic beverages was limited. In vitro results confirmed that both lime and pineapple juices significantly reduced enamel microhardness and increased surface roughness (p < 0.0001), with lime juice causing the greatest enamel volume loss due to its higher acidity. Conclusions: These findings highlight the need for public health strategies that raise awareness on the implications of dietary acids and promote protective oral health behaviours. Dental practitioners should incorporate dietary counselling in routine care, particularly for populations at higher risk. Full article

In the study of dynamic systems, bifurcation diagrams are a very popular graphical tool for studying stability and nonlinear changes in behavior. They are instrumental in analyzing the system’s response to parameter changes. These diagrams show the system’s various dynamic patterns and phase transitions by plotting the relationship between the system response and the parameters. This paper presents a computational algorithm for studying bifurcations in dynamic systems, especially for systems with chaotic behavior that depends on parameter changes. Depending on the type of system to be analyzed, the following two strategies for computing bifurcation diagrams are described: (i) detecting crossing points through the Poincaré plane and (ii) the identification of local maxima (or minima) in one of the system solutions. In addition, this paper presents a method for implementing parallel computation in MATLAB using the Parallel Computing Toolbox from MathWorks, which significantly reduces the computational time required to generate bifurcation diagrams. This work contributes to the study of dynamic systems by providing the reader with accessible tools for studying any dynamic system under established standards and reducing the computational time required for these types of studies by implementing these algorithms utilizing the multi-core processors found in modern computers. Full article

The current work records for the first time the rare-metal pegmatites with mixed NYF-LCT located at Wadi Sikait, south Eastern Desert of the Egyptian Nubian Shield. Most of the Sikait pegmatites are associated with sheared granite and are surrounded by an alteration zone cross-cutting through greisen bodies. Sikait pegmatites show zoned and complex types, where the outer wall zones are highly mineralized (Nb, Ta, Y, Th, Hf, REE, U) than the barren cores. They consist essentially of K-feldspar, quartz, micas (muscovite, lepidolite, and zinnwaldite), and less albite. They contain a wide range of accessory minerals, including garnet, columbite, fergusonite-(Y), cassiterite, allanite, monazite, bastnaesite (Y, Ce, Nd), thorite, zircon, beryl, topaz, apatite, and Fe-Ti oxides. In the present work, the discovery of Li-bearing minerals for the first time in the Wadi Sikait pegmatite is highly significant. Sikait pegmatites are highly mineralized and yield higher maximum concentrations of several metals than the associated sheared granite. They are strongly enriched in Li (900–1791 ppm), Nb (1181–1771 ppm), Ta (138–191 ppm), Y (626–998 ppm), Hf (201–303 ppm), Th (413–685 ppm), Zr (2592–4429 ppm), U (224–699 ppm), and ∑REE (830–1711 ppm). The pegmatites and associated sheared granite represent highly differentiated peraluminous rocks that are typical of post-collisional rare-metal bearing granites. They show parallel chondrite-normalized REE patterns, enriched in HREE relative to LREE [(La/Lu)_n = 0.04–0.12] and strongly negative Eu anomalies [(Eu/Eu*) = 0.03–0.10]. The REE patterns show an M-type tetrad effect, usually observed in granites that are strongly differentiated and ascribed to hydrothermal fluid exchange. The pegmatite has mineralogical and geochemical characteristics of the mixed NYF-LCT family and shows non-CHARAC behavior due to a hydrothermal effect. Late-stage metasomatism processes caused redistribution, concentrated on the primary rare metals, and drove the development of greisen and quartz veins along the fracture systems. The genetic relationship between the Sikait pegmatite and the surrounding sheared granite was demonstrated by the similarities in their geochemical properties. The source magmas were mostly derived from the juvenile continental crust of the Nubian Shield through partial melting and subsequently subjected to a high fractional crystallization degree. During the late hydrothermal stage, the exsolution of F-rich fluids transported some elements and locally increased their concentrations to the economic grades. The investigated pegmatite and sheared granite should be considered as a potential resource to warrant exploration for REEs and other rare metals. Full article

Video emotion recognition faces significant challenges due to the strong spatiotemporal coupling of dynamic expressions and the substantial variations in cross-scale motion patterns (e.g., subtle facial micro-expressions versus large-scale body gestures). Traditional methods, constrained by limited receptive fields, often fail to effectively balance multi-scale correlations between local cues (e.g., transient facial muscle movements) and global semantic patterns (e.g., full-body gestures). To address this, we propose an enhanced attention module integrating multi-dilated convolution and dynamic feature weighting, aimed at improving spatiotemporal emotion feature extraction. Building upon conventional attention mechanisms, the module introduces a multi-branch parallel architecture. Convolutional kernels with varying dilation rates (1, 3, 5) are designed to hierarchically capture cross-scale the spatiotemporal features of low-scale facial micro-motion units (e.g., brief lip tightening), mid-scale composite expression patterns (e.g., furrowed brows combined with cheek raising), and high-scale limb motion trajectories (e.g., sustained arm-crossing). A dynamic feature adapter is further incorporated to enable context-aware adaptive fusion of multi-source heterogeneous features. We conducted extensive ablation studies and experiments on popular benchmark datasets such as the VideoEmotion-8 and Ekman-6 datasets. Experiments demonstrate that the proposed method enhances joint modeling of low-scale cues (e.g., fragmented facial muscle dynamics) and high-scale semantic patterns (e.g., emotion-coherent body language), achieving stronger cross-database generalization. Full article

Human motion recognition is crucial for applications like navigation, health monitoring, and smart healthcare, especially in weak GNSS scenarios. Current methods face challenges such as limited sensor diversity and inadequate feature extraction. This study proposes a CNN–Transformer–Attention framework with multimodal enhancement to address these challenges. We first designed a lightweight wearable system integrating synchronized accelerometer, gyroscope, and magnetometer modules at wrist, chest, and foot positions, enabling multi-dimensional biomechanical data acquisition. A hybrid preprocessing pipeline combining cubic spline interpolation, adaptive Kalman filtering, and spectral analysis was developed to extract discriminative spatiotemporal-frequency features. The core architecture employs parallel CNN pathways for local sensor feature extraction and Transformer-based attention layers to model global temporal dependencies across body positions. Experimental validation on 12 motion patterns demonstrated 98.21% classification accuracy, outperforming single-sensor configurations by 0.43–7.98% and surpassing conventional models (BP-Network, CNN, LSTM, Transformer, KNN) through effective cross-modal fusion. The framework also exhibits improved generalization with 3.2–8.7% better accuracy in cross-subject scenarios, providing a robust solution for human activity recognition and accurate positioning in challenging environments such as autonomous navigation and smart cities. Full article

The proliferation of multimodal misinformation on social media has become a critical concern. Although detection methods have advanced, feature representation and cross-modal semantic alignment challenges continue to hinder the effective use of multimodal data. Therefore, this paper proposes an IBWO-CASC detection model that integrates an improved Beluga Whale Optimization algorithm with cross-modal attention feature fusion. Firstly, the Beluga Whale Optimization algorithm is enhanced by combining adaptive search mechanisms with batch parallel strategies in the feature space. Secondly, a feature alignment method is designed based on supervised contrastive learning to establish semantic consistency. Then, the model incorporates a Cross-modal Attention Promotion mechanism and global–local interaction learning pattern. Finally, a multi-task learning framework is built based on classification and contrastive objectives. The empirical analysis shows that the proposed IBWO-CASC model achieves a detection accuracy of 97.41% on our self-constructed multimodal misinformation dataset. Compared with the average accuracy of the existing six baseline models, the accuracy of this model is improved by 4.09%. Additionally, it demonstrates enhanced robustness in handling complex multimodal scenarios. Full article