检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第3期6卷 533-548页

作者： Le, Siqi Lai, Yingxu Wang, Yipeng He, Huijie Beijing University of Technology Faculty of Information Technology Beijing100124 China Ministry of Education Engineering Research Center of Intelligent Perception and Autonomous Control Beijing100124 China

Real open network environments include the traffic generated by known applications or protocols, which have been previously identified and labeled, and unknown network traffic that cannot be identified based on existing knowledge. Accurately identifying unknown traffic is critical to network management and security, not only to help managers allocate bandwidth appropriately for all types of applications and ensure quality of service but also to prevent security breaches that may result from unknown applications or protocols. Notably, the unknown network traffic has been increasing with the emergence of new applications or protocols, which further increases the difficulty in identifying them. Existing unknown traffic classification methods based on Softmax output confidence values cause bias in the prediction probability due to overconfidence of the model during the training process, thus decreasing the identification accuracy. Thus, for unknown traffic identification, this study proposes a deep-learning-based uncertainty-estimation (EUE) approach. EUE introduces the theory of evidence to the task of identifying unknown traffic by inferring traffic uncertainty directly from traffic evidence without the need for a Softmax layer, thus avoiding overconfidence in the model. Thus, the EUE can accurately identify unknown traffic while classifying known traffic at the application level. We construct two experimental scenarios simulating the real network environments with different proportions of unknown traffic to evaluate EUE. The experimental results show that the proposed approach EUE exhibits excellent classification accuracy. © 2024 IEEE. All rights reserved.

关键词： Internet protocols

来源：评论

学校读者我要写书评

暂无评论

Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning

引用

Research in Astronomy and Astrophysics 2025年第3期25卷 236-248页

作者： Zhen-Hong Shang Long Chen Zhen-Ping Qiang Yi Bi Run-Xin Li Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology College of Big Data and Intelligent Engineering Southwest Forestry University Yunnan Observatories Chinese Academy of Sciences

Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar *** paper introduces an innovative unsupervised deep learning optical flow model designed to calculate the transverse velocity field,addressing the challenges of missing optical flow labels and the limited accuracy of velocity field measurements in high-resolution solar *** proposed method converts the transverse velocity field computation problem into an optical flow computation problem,using two forward propagations of features to get rid of the reliance on optical flow ***,it reduces the impact of the“Brightness Consistency”constraint on optical flow accuracy by identifying and handling optical flow *** apply this method to compute the transverse velocity fields of high-resolution solar image sequences from the Hαand TiO bands,observed by the New Vacuum Solar *** experiments with several wellestablished optical flow methods,including those based on supervised deep learning models,show that our approach outperforms the comparison methods according to key evaluation metrics such as Residual Map Mean,Residual Map Variance,Cross Correlation,and Structural Similarity Index ***,since optical flow captures the fundamental motion information in image sequences,the proposed method can be applied to a variety of research areas,including solar image registration,sequence alignment,image super-resolution,magnetic field calibration,and solar activity *** code is available at https://***/jackie-willianm/Transverse-Velocity-Field-Measurement-of-Solar-High-Resolution-Images.

关键词： methods: data analysis Sun: fundamental parameters techniques: image processing

来源：评论

学校读者我要写书评

暂无评论

Optimal Adaptive Parameter Estimation With Online Varying Learning Gain

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 3518-3525页

作者： Chen, Siyu Na, Jing Huang, Yingbo Xing, Yashan Zhao, Jing Wong, Pak Kin Kunming University of Science and Technology Faculty of Mechanical and Electrical Engineering Yunnan Key Laboratory of Intelligent Control and Application Kunming650500 China University of Macau Department of Electromechanical Engineering 999078 China

It has been well known that the learning gain plays a crucial role in the adaptive parameter estimation (APE) for guaranteeing fast convergence and robustness. However, the tuning of learning gains in the existing methods is generally empirical and time-consuming. To address this issue, this article presents a novel APE approach to explore the optimality principle in the design of adaptive laws to obtain an online updated optimal learning gain, which is derived to minimize a cost function of estimation error with two weighting matrices. For this purpose, the estimation error is first reconstructed by using filter operations on the system and introducing several auxiliary variables. Then, two constructive APE algorithms driven by the extracted estimation error are developed. Finally, inspired by the duality of control and estimation, the estimation error dynamics are reformulated as a closed-loop system with an analogous control action to minimize the cost function. By using the Hamiltonian function, a differential Riccati equation is derived to find an optimal solution of learning gain to construct an optimal adaptive law. The robustness of the proposed adaptive laws subjected to disturbances is also analyzed. Comparative numerical simulations are given to illustrate the superiority of the proposed method. © 1963-2012 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Influence of Undercooling on the Solidification Behaviour and Microstructure of Non-equilibrium Solidification of Cu-based Alloys

引用

Journal of Wuhan University of technology(Materials Science) 2025年第2期40卷 610-618页

作者： LI Hejun AN Hongen Willey Liew Yun Hsien Ismal Saad Bih Lii Chuab Nancy Julius Siambun CAO Shichao WANG Hongfu YAO Wei College of Mechanical and Electronic Engineering Huanghe Jiaotong UniversityJiaozuo 454950China Henan Engineering Technology Research Center on Intelligent Manufacturing Technology and Equipment Jiaozuo 454950China Faculty of Engineering University Malaysia SabahKota Kinabalu 88400Malaysia School of Mechanical Engineering North University of ChinaTaiyuan 030051China Jiaozuo Robot Engineering Technology Center Jiaozuo 454950China

The evolution of the microstructure and morphology of Cu55Ni45 and Cu60Ni40 alloys under varying degrees of undercooling was investigated through molten glass purification and cyclic superheating *** increasing the Cu content,the effect of Cu on the evolution of the microstructure and morphology of the Cu-Ni alloy during undercooling was *** mechanism of grain refinement at different degrees of undercooling and the effect of Cu content on its solidification behaviour were *** solidification behaviour of Cu55Ni45 and Cu60Ni40 alloys was investigated using infrared thermometry and high-speed *** results indicate that both Cu55Ni45 and Cu60Ni40 alloy melts undergo only one recalescence during rapid *** degree of recalescence increases approximately linearly with increasing *** solidification front of the alloy melts undergoes a transition process from a small-angle plane to a sharp front and then to a smooth ***,the growth of the subcooled melt is constrained to a narrow range,facilitating the formation of a coarse dendritic crystal morphology in the Cu-Ni *** large undercooling,the stress breakdown of the directionally growing dendrites is primarily caused by thermal *** strain remaining in the dendritic fragments provides the driving force for recrystallisation of the tissue to occur,which in turn refines the tissue.

关键词： undercooling microstructure grain refinement solidification rate

来源：评论

学校读者我要写书评

暂无评论

Influence of Gravel Soil Gradation Characteristics on Permeability Coefficient Based on Neural Network

引用

Journal of engineering Science and technology Review 2025年第1期18卷 120-126页

作者： Ma, Hao Jin, Dandan Wang, Tao Ahmad, Mirza Iftikhar Faculty of Civil Engineering and Mechanics Jiangsu University Zhenjiang212000 China School of Intelligent Construction Wuchang University of Technology Wuhan430223 China School of Mechanical Engineering Hefei University of Technology Hefei230009 China School of Civil Engineering and Architecture Wuhan University of Technology Wuhan430070 China

The permeability coefficient of gravel soil is closely related to gradation characteristics and plays a key role in engineering safety and stability. Among the studies on the correlation between gravel soil gradation characteristics and permeability coefficient, traditional empirical formulas and theoretical models are subjected to specific limitations, failing to accurately capture the complex nonlinear relations. In this study, considerable test data on gravel soil were collected. The model establishment, training, and optimization were performed using a backpropagation (BP) neural network. The complex relations between gravel soil gradation characteristics and permeability coefficient were explored. Moreover, the influence of each particle size on permeability coefficient was demonstrated. The prediction results of full gradation and common gradation were comparatively analyzed. Results show that, the prediction results on permeability coefficient by neural network are more accurate. In this study, the sample size is enlarged to 138 groups, which significantly improves the prediction accuracy. d60 is the boundary particle size. The permeability coefficient increases with the increase in the fine particles with a size of d60 or below, whereas it decreases as the coarse particles with a size above d60 increase. The influence degree of different particle gradations on permeability coefficient is heterogeneous. d10 is a high-sensitivity particle size, which exerts the greatest influence on permeability coefficient, followed by d20 and d40, which are medium-sensitivity particle sizes. The relative weights of other particle sizes are small, being low-sensitivity particle sizes. The influence of fine particles on permeability coefficient is greater than that of coarse particles, and full gradation achieves a better prediction result for permeability coefficient compared with common gradation. p5 is also a key factor affecting permeability coefficient. © (2025), (Interna

关键词： Gravel

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithm for Person Re-Identification Based on Dual Network Architecture

引用

Computers, Materials & Continua 2025年第5期83卷 2889-2905页

作者： Meng Zhu Xingyue Wang Honge Ren Abeer Hakeem Linda Mohaisen College of Information Engineering Harbin UniversityHarbin150086China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin UniversityHarbin150086China College of Computer and Control Engineering Northeast Forestry UniversityHarbin150040China Heilongjiang Forestry Intelligent Equipment Engineering Research Center Northeast Forestry UniversityHarbin150040China Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

Changing a person’s posture and low resolution are the key challenges for person re-identification(ReID)in various deep learning *** this paper,we introduce an innovative architecture using a dual attention network that includes an attentionmodule and a joint measurement module of spatial-temporal *** proposed approach can be classified into two main ***,the spatial attention feature map is formed by aggregating features in the spatial ***,the same operation is carried out on the channel dimension to formchannel attention ***,the receptive field size is adjusted adaptively tomitigate the changing person posture ***,we use a joint measurement method for the spatial-temporal information to fully harness the data,and it can also naturally integrate the information into the visual features of supervised ReID and hence overcome the low resolution *** experimental results indicate that our proposed algorithm markedly improves the accuracy in addressing changing human postures and low-resolution issues compared with contemporary leading *** proposed method shows superior outcomes on widely recognized benchmarks,which are the Market-1501,MSMT17,and DukeMTMC-reID ***,the proposed algorithmattains a Rank-1 accuracy of 97.4% and 94.9% mAP(mean Average Precision)on the Market-1501 ***,it achieves a 94.2% Rank-1 accuracy and 91.8% mAP on the DukeMTMC-reID dataset.

关键词： Person reidentification ReID computer vision self-attention spatial-temporal information

来源：评论

学校读者我要写书评

暂无评论

DDT-Net:Deep Detail Tracking Network for Image Tampering Detection

引用

Computers, Materials & Continua 2025年第5期83卷 3451-3469页

作者： Jim Wong Zhaoxiang Zang Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang443002China College of Computer and Information Technology ChinaThree Gorges UniversityYichang443002China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650504China

In the field of image forensics,image tampering detection is a critical and challenging *** methods based on manually designed feature extraction typically focus on a specific type of tampering operation,which limits their effectiveness in complex scenarios involving multiple forms of *** deep learningbasedmethods offer the advantage of automatic feature learning,current approaches still require further improvements in terms of detection accuracy and computational *** address these challenges,this study applies the UNet 3+model to image tampering detection and proposes a hybrid framework,referred to as DDT-Net(Deep Detail Tracking Network),which integrates deep learning with traditional detection *** contrast to traditional additive methods,this approach innovatively applies amultiplicative fusion technique during downsampling,effectively combining the deep learning feature maps at each layer with those generated by the Bayar noise *** design enables noise residual features to guide the learning of semantic features more precisely and efficiently,thus facilitating comprehensive feature-level ***,by leveraging the complementary strengths of deep networks in capturing large-scale semantic manipulations and traditional algorithms’proficiency in detecting fine-grained local traces,the method significantly enhances the accuracy and robustness of tampered region *** with other approaches,the proposed method achieves an F1 score improvement exceeding 30% on the DEFACTO and DIS25k *** addition,it has been extensively validated on other datasets,including CASIA and *** results demonstrate that this method achieves outstanding performance across various types of image tampering detection tasks.

关键词： Image forensics image tampering detection image manipulation detection noise flow Bayar

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Techniques in Non-orthogonal Multiple Access (NOMA) in 5G Network: An Overview and Outlook

引用

Wireless Personal Communications 2025年第3期140卷 971-1013页

作者： Abuajwa, Osama Muhammad, Surajo Ambak, Zulkifli Mitani, Sufian Tiang, Jun-Jiat TM Innovation Centre Cyberjaya63000 Malaysia Centre for Wireless Technology CoE for Intelligent Network Faculty of Artificial Intelligence & Engineering Multimedia University Persiaran Multimedia Selangor Cyberjaya63100 Malaysia

This review paper critically examines energy efficiency schemes in Non-Orthogonal Multiple Access (NOMA) systems, focusing on critical topics such as the integration of NOMA with cutting-edge technologies like Multi-Input Multi-Output (MIMO), beamforming, Mobile Edge Computing (MEC), and Reconfigurable intelligent Surface (RIS), and discusses the challenges in radio resource allocation and environmental sustainability. The review aims to summarise the current state-of-the-art techniques, evaluate their performance, and identify future research directions to enhance energy efficiency in NOMA systems. This paper addresses several key findings: power allocation methods can enhance energy efficiency by up to 30% in specific scenarios;relay-assisted and hybrid NOMA schemes can boost data rates by 20–25%;and energy harvesting shows potential for improving energy efficiency, reducing power consumption by up to 15% in certain cases. These challenges include system complexity, which can increase the computational overhead by 40% when optimising resource allocation, and user fairness, where trade-offs in power allocation can reduce the data rate up to 10% for edge users in certain scenarios, ultimately affecting overall energy efficiency. © The Author(s) 2025.

关键词： Queueing networks

来源：评论

学校读者我要写书评

暂无评论

Robust Fixed-time Composite Controller Design with the Unknown System Dynamics Estimator for Nonlinear Robotic Manipulator Systems 24

Robust Fixed-time Composite Controller Design with the Unkno...

引用

2nd International Conference on Frontiers of intelligent Manufacturing and Automation, CFIMA 2024

作者： Li, Siyan Xing, Yashan Na, Jing Li, Qi Faculty of Mechanical and Electrical Engineering Yunnan Key Laboratory of Intelligent Control and Application Kunming University of Science and Technology Yunnan China

ISBN: (纸本)9798400710681

In this paper, a robust fixed-time composite control scheme based on an Unknown System Dynamics Estimator (USDE) is proposed. The proposed control method guarantees the tracking error convergence in a fixed-time for nonlinear robotic manipulators with unknown dynamics and disturbance. To address the existence of uncertainties, first, a simple structure of USDE by a low-pass filtering operation is constructed without using acceleration signals, Which is adjusted for only one filter coefficient. Then, the USDE compensate the estimated value into the robust fixed-time composite controller. The composite controller contains a fixed time control term, a robust control term, and a computed torque control term. By the fixed-time control term, the upper bound on the convergence time is independent of the initial conditions of the system, which ensures fast-tracking tasks for the robot manipulator. And the robust control term is used to reduce the impact of USDE estimation errors. The stability of the closed-loop system is demonstrated through Lyapunov criteria. The validity of the proposed method is verified by simulation. © 2024 Copyright held by the owner/author(s).

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

Direct spot-welding of zirconia ceramic to Ti-6Al-4V alloy for ultrahigh strength joint using pulsed Nd: YAG laser

引用

Ceramics International 2025年第14期51卷 18762-18774页

作者： Zhao, Zhanyong Janasekaran, Shamini Fong, Go Tze Tayier, Walisijiang Zhang, Nan Centre for Advanced Materials and Intelligent Manufacturing Faculty of Engineering Built Environment & Information Technology SEGi University Selangor Petaling Jaya47810 Malaysia School of Electromechanics Handan University Handan056006 China

The reliable and efficient joining of ZrO2 ceramic to Ti-6Al-4V alloy is critical in aerospace and biomedical fields. However, conventional methods, such as brazing or diffusion bonding, face limitations in large-scale production due to cumbersome and time-intensive processing requirements. This work proposes an innovative method for fabricating ultrahigh-strength Ti-6Al-4V/ZrO2 lap-joint by direct spot-welding of metal-to-ceramic using a pulsed Nd: YAG laser at room temperature. Serrated-like features were formed between the Ti-6Al-4V and ZrO₂ interfaces. The effects of laser pulse duration and spot diameter on the microstructure and shear strength of the joint were investigated, and the mechanical properties were optimized by these parameters. Scanning Electron Microscope (SEM), Energy Dispersive Spectrometer (EDS), X-ray Diffraction (XRD) were studied to characterise the microstructure, composition and phases of the joints. The interfacial microstructure can be described as Ti-6Al-4V alloy/β-Ti + TiO2/α-Ti + TiO + TiO2/TiO + Al0.52Zr0.48O1.74+Y2[Zr0.3Ti0.7]2O7/ZrO2-x + TiO/ZrO2. The maximum shear strength of the joint was about 99.06 MPa under laser pulse duration of 1.6 ms and spot diameter of 1.1 mm. After the shear test, fractures mainly occurred at the ceramic edge or within the ceramic. Experimental results demonstrated that laser spot welding possesses significant advantages over brazing or diffusion welding, including superior reliability, higher efficiency and environmental sustainability. Furthermore, the findings provide a comprehensive understanding of the welding mechanism, emphasizing the role of non-linear laser absorption in Ti-6Al-4V/ZrO2 joints, thereby offering valuable insights into the emerging technology for advanced metal-ceramic joining. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Brazing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：