Accurately recognizing driver distraction is critical for preventing traffic accidents,yet current detection models face two persistent challenges.First,distractions are often fine-grained,involving subtle cues such a...Accurately recognizing driver distraction is critical for preventing traffic accidents,yet current detection models face two persistent challenges.First,distractions are often fine-grained,involving subtle cues such as brief eye closures or partial yawns,which are easily missed by conventional detectors.Second,in real-world scenarios,drivers frequently exhibit overlapping behaviors,such as simultaneously holding a cup,closing their eyes,and yawning,leading tomultiple detection boxes and degradedmodel performance.Existing approaches fail to robustly address these complexities,resulting in limited reliability in safety critical applications.To overcome these pain points,we propose YOLO-Drive,a novel framework that enhances YOLO-based driver monitoring with EfficientViM and Polarized Spectral–Spatial Attention(PSSA)modules.Efficient ViMprovides lightweight yet powerful global–local feature extraction,enabling accurate recognition of subtle driver states.PSSA further amplifies discriminative features across spatial and spectral domains,ensuring robust separation of concurrent distraction cues.By explicitly modeling fine-grained and overlapping behaviors,our approach delivers significant improvements in both precision and robustness.Extensive experiments on benchmark driver distraction datasets demonstrate that YOLO-Drive consistently out-performs stateof-the-art models,achieving higher detection accuracy while maintaining real-time efficiency.These results validate YOLO-Drive as a practical and reliable solution for advanced driver monitoring systems,addressing long-standing challenges of subtle cue recognition and multi-cue distraction detection.展开更多
Focusing on the unclear mechanism of aerodynamic interference in overlapping rotors of heavy-load electric vertical take-off and landing(eVTOL)aircraft,this paper aims to reveal the aerodynamic interference characteri...Focusing on the unclear mechanism of aerodynamic interference in overlapping rotors of heavy-load electric vertical take-off and landing(eVTOL)aircraft,this paper aims to reveal the aerodynamic interference characteristics and flow field evolution laws of overlapping rotor configurations in hovering conditions through numerical simulation methods.The research method involves constructing a computational model for rotor flow fields and aerodynamic characteristics based on the Reynolds-averaged Navier-Stokes(RANS)equations and the Spalart-Allmaras(S-A)turbulence model.The dynamic simulation of rotor rotational motion was achieved by using the moving nested grid technology.The reliability of the computational method was ensured through the grid independence verification and the comparison with experimental data.The research results indicate that in overlapping rotor systems,rotorⅡexperiences a decrease in thrust,significant power fluctuations,and reduced hovering efficiency due to continuous interference from the adjacent rotor’s wake and blade-vortex interactions.Blade-tip vortices undergo breakage,fusion,and secondary rolling in the overlapping region,forming large-scale turbulent structures that lead to attenuation of the induced velocity field and aerodynamic efficiency losses.Additionally,the interaction between the rotor downwash and the fuselage triggers a“fountain effect”and a sudden increase in surface pressure on the fuselage,exacerbating flow field distortion.Based on the aforementioned mechanisms,the safe flight of overlapping rotor configurations can be achieved by optimizing the configuration strategy of the rotational speed phase difference between adjacent blades.This study provides a theoretical basis for the rotor layout design and the aerodynamic performance enhancement of heavy-load eVTOL aircraft.展开更多
In order to solve the problem of poor formability caused by different materials and properties in the process of tailor-welded sheets forming,a forming method was proposed to change the stress state of tailor-welded s...In order to solve the problem of poor formability caused by different materials and properties in the process of tailor-welded sheets forming,a forming method was proposed to change the stress state of tailor-welded sheets by covering the tailor-welded sheets with better plastic properties overlapping sheets.At the same time,the interface friction effect between the overlapping and tailor-welded sheets was utilized to control the stress magnitude and further improve the formability and quality of the tailor-welded sheets.In this work,the bulging process of the tailor-welded overlapping sheets was taken as the research object.Aluminum alloy tailor-welded overlapping sheets bulging specimens were studied by a combination of finite element analysis and experimental verification.The results show that the appropriate use of interface friction between tailor-welded and overlapping sheets can improve the formability of tailor-welded sheets and control the flow of weld seam to improve the forming quality.When increasing the interface friction coefficient on the side of tailor-welded sheets with higher strength and decreasing that on the side of tailor-welded sheets with lower strength,the deformation of the tailor-welded sheets are more uniform,the offset of the weld seam is minimal,the limit bulging height is maximal,and the forming quality is optimal.展开更多
To meet the intelligent detection needs of underwater defects in large hydropower stations,the hydrodynamic performance of a bionic streamlined remotely operated vehicle containing a thruster protective net structure ...To meet the intelligent detection needs of underwater defects in large hydropower stations,the hydrodynamic performance of a bionic streamlined remotely operated vehicle containing a thruster protective net structure is numerically simulated via computational fluid dynamics and overlapping mesh technology.The results show that the entity model generates greater hydrodynamic force during steady motion,whereas the square net model experiences greater force and moment during unsteady motion.The lateral and vertical force coefficients of the entity model are 4.32 and 3.13 times greater than those of the square net model in the oblique towing test simulation.The square net model also offers better static and dynamic stability,with a 24.5%increase in dynamic stability,achieving the highest lift-to-drag ratio at attack angles of 6°∼8°.This research provides valuable insights for designing and controlling underwater defect detection vehicles for large hydropower stations.展开更多
Detecting overlapping communities in attributed networks remains a significant challenge due to the complexity of jointly modeling topological structure and node attributes,the unknown number of communities,and the ne...Detecting overlapping communities in attributed networks remains a significant challenge due to the complexity of jointly modeling topological structure and node attributes,the unknown number of communities,and the need to capture nodes with multiple memberships.To address these issues,we propose a novel framework named density peaks clustering with neutrosophic C-means.First,we construct a consensus embedding by aligning structure-based and attribute-based representations using spectral decomposition and canonical correlation analysis.Then,an improved density peaks algorithm automatically estimates the number of communities and selects initial cluster centers based on a newly designed cluster strength metric.Finally,a neutrosophic C-means algorithm refines the community assignments,modeling uncertainty and overlap explicitly.Experimental results on synthetic and real-world networks demonstrate that the proposed method achieves superior performance in terms of detection accuracy,stability,and its ability to identify overlapping structures.展开更多
Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional...Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional oversampling methods often generate synthetic samples without considering density variations,leading to redundant or misleading instances that exacerbate class overlap in high-density regions.To address these limitations,we propose Wasserstein Generative Adversarial Network Variational Density Estimation WGAN-VDE,a computationally efficient density-aware adversarial resampling framework that enhances minority class representation while strategically reducing class overlap.The originality of WGAN-VDE lies in its density-aware sample refinement,ensuring that synthetic samples are positioned in underrepresented regions,thereby improving class distinctiveness.By applying structured feature representation,targeted sample generation,and density-based selection mechanisms strategies,the proposed framework ensures the generation of well-separated and diverse synthetic samples,improving class separability and reducing redundancy.The experimental evaluation on 20 benchmark datasets demonstrates that this approach outperforms 11 state-of-the-art rebalancing techniques,achieving superior results in F1-score,Accuracy,G-Mean,and AUC metrics.These results establish the proposed method as an effective and robust computational approach,suitable for diverse engineering and scientific applications involving imbalanced data classification and computational modeling.展开更多
The influences of strength coefficient K, work hardening exponent n and thickness t of the overlapping sheet on bulging process are analyzed based on hardening material model. Also, bulging experiments are carried out...The influences of strength coefficient K, work hardening exponent n and thickness t of the overlapping sheet on bulging process are analyzed based on hardening material model. Also, bulging experiments are carried out by taking the aluminum alloy LF21 as formed sheet metal, and selecting overlapping sheet with different thicknesses and material properties, by which accuracy of the above analysis result is verified in the aspects of geometric shape, thickness distribution and limit bulging height. The results show that higher strength coefficient K, larger work hardening exponent n and proper thickness of the overlapping sheet are helpful to improve the formability and forming uniformity of formed sheet metal.展开更多
基金funded by the Guangzhou Development Zone Science and Technology Project(2023GH02)the University of Macao(MYRG2022-00271-FST)research grants by the Science and Technology Development Fund of Macao(0032/2022/A)and(0019/2025/RIB1).
文摘Accurately recognizing driver distraction is critical for preventing traffic accidents,yet current detection models face two persistent challenges.First,distractions are often fine-grained,involving subtle cues such as brief eye closures or partial yawns,which are easily missed by conventional detectors.Second,in real-world scenarios,drivers frequently exhibit overlapping behaviors,such as simultaneously holding a cup,closing their eyes,and yawning,leading tomultiple detection boxes and degradedmodel performance.Existing approaches fail to robustly address these complexities,resulting in limited reliability in safety critical applications.To overcome these pain points,we propose YOLO-Drive,a novel framework that enhances YOLO-based driver monitoring with EfficientViM and Polarized Spectral–Spatial Attention(PSSA)modules.Efficient ViMprovides lightweight yet powerful global–local feature extraction,enabling accurate recognition of subtle driver states.PSSA further amplifies discriminative features across spatial and spectral domains,ensuring robust separation of concurrent distraction cues.By explicitly modeling fine-grained and overlapping behaviors,our approach delivers significant improvements in both precision and robustness.Extensive experiments on benchmark driver distraction datasets demonstrate that YOLO-Drive consistently out-performs stateof-the-art models,achieving higher detection accuracy while maintaining real-time efficiency.These results validate YOLO-Drive as a practical and reliable solution for advanced driver monitoring systems,addressing long-standing challenges of subtle cue recognition and multi-cue distraction detection.
基金supported by the National Natural Science Foundation of China(No.11872211)。
文摘Focusing on the unclear mechanism of aerodynamic interference in overlapping rotors of heavy-load electric vertical take-off and landing(eVTOL)aircraft,this paper aims to reveal the aerodynamic interference characteristics and flow field evolution laws of overlapping rotor configurations in hovering conditions through numerical simulation methods.The research method involves constructing a computational model for rotor flow fields and aerodynamic characteristics based on the Reynolds-averaged Navier-Stokes(RANS)equations and the Spalart-Allmaras(S-A)turbulence model.The dynamic simulation of rotor rotational motion was achieved by using the moving nested grid technology.The reliability of the computational method was ensured through the grid independence verification and the comparison with experimental data.The research results indicate that in overlapping rotor systems,rotorⅡexperiences a decrease in thrust,significant power fluctuations,and reduced hovering efficiency due to continuous interference from the adjacent rotor’s wake and blade-vortex interactions.Blade-tip vortices undergo breakage,fusion,and secondary rolling in the overlapping region,forming large-scale turbulent structures that lead to attenuation of the induced velocity field and aerodynamic efficiency losses.Additionally,the interaction between the rotor downwash and the fuselage triggers a“fountain effect”and a sudden increase in surface pressure on the fuselage,exacerbating flow field distortion.Based on the aforementioned mechanisms,the safe flight of overlapping rotor configurations can be achieved by optimizing the configuration strategy of the rotational speed phase difference between adjacent blades.This study provides a theoretical basis for the rotor layout design and the aerodynamic performance enhancement of heavy-load eVTOL aircraft.
基金Funded by the National Natural Science Foundation of China(Nos.52075347,51575364)and the Natural Science Foundation of Liaoning Provincial(No.2022-MS-295)。
文摘In order to solve the problem of poor formability caused by different materials and properties in the process of tailor-welded sheets forming,a forming method was proposed to change the stress state of tailor-welded sheets by covering the tailor-welded sheets with better plastic properties overlapping sheets.At the same time,the interface friction effect between the overlapping and tailor-welded sheets was utilized to control the stress magnitude and further improve the formability and quality of the tailor-welded sheets.In this work,the bulging process of the tailor-welded overlapping sheets was taken as the research object.Aluminum alloy tailor-welded overlapping sheets bulging specimens were studied by a combination of finite element analysis and experimental verification.The results show that the appropriate use of interface friction between tailor-welded and overlapping sheets can improve the formability of tailor-welded sheets and control the flow of weld seam to improve the forming quality.When increasing the interface friction coefficient on the side of tailor-welded sheets with higher strength and decreasing that on the side of tailor-welded sheets with lower strength,the deformation of the tailor-welded sheets are more uniform,the offset of the weld seam is minimal,the limit bulging height is maximal,and the forming quality is optimal.
基金supported by the National Key R&D Program of China(Grant No.2022YFB4703401).
文摘To meet the intelligent detection needs of underwater defects in large hydropower stations,the hydrodynamic performance of a bionic streamlined remotely operated vehicle containing a thruster protective net structure is numerically simulated via computational fluid dynamics and overlapping mesh technology.The results show that the entity model generates greater hydrodynamic force during steady motion,whereas the square net model experiences greater force and moment during unsteady motion.The lateral and vertical force coefficients of the entity model are 4.32 and 3.13 times greater than those of the square net model in the oblique towing test simulation.The square net model also offers better static and dynamic stability,with a 24.5%increase in dynamic stability,achieving the highest lift-to-drag ratio at attack angles of 6°∼8°.This research provides valuable insights for designing and controlling underwater defect detection vehicles for large hydropower stations.
基金supported by the Natural Science Foundation of China(Grant No.72571150)。
文摘Detecting overlapping communities in attributed networks remains a significant challenge due to the complexity of jointly modeling topological structure and node attributes,the unknown number of communities,and the need to capture nodes with multiple memberships.To address these issues,we propose a novel framework named density peaks clustering with neutrosophic C-means.First,we construct a consensus embedding by aligning structure-based and attribute-based representations using spectral decomposition and canonical correlation analysis.Then,an improved density peaks algorithm automatically estimates the number of communities and selects initial cluster centers based on a newly designed cluster strength metric.Finally,a neutrosophic C-means algorithm refines the community assignments,modeling uncertainty and overlap explicitly.Experimental results on synthetic and real-world networks demonstrate that the proposed method achieves superior performance in terms of detection accuracy,stability,and its ability to identify overlapping structures.
基金supported by Ongoing Research Funding Program(ORF-2025-488)King Saud University,Riyadh,Saudi Arabia.
文摘Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional oversampling methods often generate synthetic samples without considering density variations,leading to redundant or misleading instances that exacerbate class overlap in high-density regions.To address these limitations,we propose Wasserstein Generative Adversarial Network Variational Density Estimation WGAN-VDE,a computationally efficient density-aware adversarial resampling framework that enhances minority class representation while strategically reducing class overlap.The originality of WGAN-VDE lies in its density-aware sample refinement,ensuring that synthetic samples are positioned in underrepresented regions,thereby improving class distinctiveness.By applying structured feature representation,targeted sample generation,and density-based selection mechanisms strategies,the proposed framework ensures the generation of well-separated and diverse synthetic samples,improving class separability and reducing redundancy.The experimental evaluation on 20 benchmark datasets demonstrates that this approach outperforms 11 state-of-the-art rebalancing techniques,achieving superior results in F1-score,Accuracy,G-Mean,and AUC metrics.These results establish the proposed method as an effective and robust computational approach,suitable for diverse engineering and scientific applications involving imbalanced data classification and computational modeling.
基金Project(51205260)supported by the National Natural Science Foundation of ChinaProject(L2012046)supported by the Liaoning Provincial Committee of Education,China
文摘The influences of strength coefficient K, work hardening exponent n and thickness t of the overlapping sheet on bulging process are analyzed based on hardening material model. Also, bulging experiments are carried out by taking the aluminum alloy LF21 as formed sheet metal, and selecting overlapping sheet with different thicknesses and material properties, by which accuracy of the above analysis result is verified in the aspects of geometric shape, thickness distribution and limit bulging height. The results show that higher strength coefficient K, larger work hardening exponent n and proper thickness of the overlapping sheet are helpful to improve the formability and forming uniformity of formed sheet metal.
