检索结果-内蒙古大学图书馆

VRAR: Video-Radar Automatic Registration Method Based on Trajectory Spatiotemporal Features and Bidirectional Mapping

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Li, Kong Dai, Zhe Cui, Hua Wang, Xuan Song, Huansheng Changan University School of Information Engineering Xian China Changan University School of Transportation Engineering Xian China Chang’an University School of Future Transportation Xi’an China Yantai University School of Computer and Control Engineering Yantai China School of Information Engineering Chang’ an University Xi’an China

Automating video and radar spatial registration without sensor layout constraints is crucial for enhancing the flexibility of perception systems. However, this remains challenging due to the lack of effective approaches for constructing and utilizing matching information between heterogeneous sensors. Existing methods rely on human intervention or prior knowledge, making it difficult to achieve true automation. Consequently, establishing a registration model that automatically extracts matching information from heterogeneous sensor data remains a key challenge. To address these issues, we propose a novel Video- Radar Automatic Registration (VRAR) method based on vehicle trajectory spatiotemporal feature encoding and a bidirectional mapping network. We first establish a unified representation for heterogeneous sensor data by encoding spatiotemporal features of vehicle trajectories. Based on this, we automatically extract a large number of high-quality matching points from synchronized trajectory pairs using a frame synchronization strategy. Subsequently, we utilize the proposed Video-Radar Bidirectional Mapping Network to process these matching points. This network learns the bidirectional mapping between the two sensor modalities, extending the alignment from discrete local observation points to the entire observable space. Experimental results demonstrate that the VRAR method exhibits significant performance advantages in various traffic scenarios, verifying its effectiveness and generalizability. This capability of automated and adaptive registration highlights the method’s potential for broader applications in heterogeneous sensor integration. © 1991-2012 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Switching event-triggered self-adjusting prescribed performance force control of electrohydraulic load simulator

引用

ISA Transactions 2025年

作者： Li, Jiafeng Ji, Ruihang Yan, Hao Shan, Jiefeng Chen, Zanwei School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China Department of Electrical and Computer Engineering National University of Singapore 117576 Singapore

This paper addresses the problem of switching event-triggered self-adjusting prescribed performance force control of electro-hydraulic load simulator (EHLS). A reduced-order fuzzy speed state observer for speed estimation is designed and a self-adjusting performance boundary is devised to mitigate the commutation jitter problem. The switching event-triggered mechanism dynamically adjusts the triggering conditions to optimize resource utilization. To reduce the complexity of the traditional inverse stepping control, the dynamic surface technique is adopted. The results demonstrate that the proposed control method guarantees the boundedness of the closed-loop system states and confines the tracking error to a small range near the equilibrium point within a finite time horizon. Finally, the effectiveness of the proposed method is demonstrated through experimentation. © 2025 International Society of Automation

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

H-STEP: Heuristic Stable Edge Service Entity Placement for Mobile Virtual Reality Systems

引用

IEEE Transactions on Mobile Computing 2025年

作者： Chi, Xuejian Chen, Honglong Ni, Zhichen Sun, Haiyang Sun, Peng Yu, Dongxiao Shandong Provincial Engineering Research Center of Intelligent Sensing and Measurement and Control Technology College of Control Science and Engineering Qingdao266580 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Shandong University School of Computer Science and Technology Qingdao266237 China

Virtual reality (VR) technology, as a latency-sensitive application, can achieve real-time response to enhance the user's quality of experience (QoE) on edge devices. However, edge servers, unlike internally managed cloud servers, are prone to hardware failures, software abnormalities, and network attacks. Most prior studies have focused on reducing service delay and improving user coverage through service entity (SE) placement, often neglecting the critical impact of edge server malfunctions on user QoE. In this work, we design a stable service entity placement framework that connects users on faulty servers to collaborative edge servers, ensuring seamless task completion. This framework presents two primary challenges: determining the grouping of collaborative edge services and the placement of SEs. To address these challenges, we introduce a heuristic stable service entity placement (H-STEP) scheme. This scheme first determines the grouping of collaborative edge servers using an iterative search algorithm and then places SEs on suitable edge servers via a fast non-dominated sorting genetic placement algorithm. This approach balances stability benefits with total cost, enhancing the system's economic benefits. We theoretically analyze the performance of H-STEP and derive the performance gap between H-STEP and the optimal scheme. Extensive real-data-driven simulations demonstrate that H-STEP's performance closely approximates that of the optimal scheme and surpasses existing schemes. © 2002-2012 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Robustness and Scalability of Consensus Networks: The Role of Memory Information

引用

IEEE Transactions on Automatic control 2025年

作者： Wang, Jiamin Liu, Jian Xiao, Feng Zheng, Yuanshi Xidian University Center for Multi-Agent School of Mechano-electronic Engineering Xi'an710071 China North China Electric Power University School of Control and Computer Engineering Beijing102206 China

It has been reported that local memory information could enhance certain consensus performance of multi-agent networks, such as protecting privacy and accelerating consensus. This article aims to investigate whether memory information can improve the robustness and scalability of consensus networks. The robustness is measured by the 2 gains from disturbances to consensus errors, and the scalability means that consensus can be preserved without re-tuning control parameters as the network scale increases. Using the linear combination of previous and current iteration states of agents and their neighbors, a memory-based consensus protocol is developed and we provide a necessary and sufficient condition for achieving consensus. Then, we establish the analytic expression of the 2 gain, which is exclusively determined by control parameters and non-zero minimum and maximum Laplacian eigenvalues. Furthermore, we show how tuning the memory coefficient can improve both robustness and scalability, and the optimal control parameters are further derived. Interestingly, we observe a positive correlation between robustness and scalability. © 1963-2012 IEEE.

关键词： Consensus networks graph laplacian memory information robustness scalability

来源：评论

学校读者我要写书评

暂无评论

Conditional Feature Generative Adversarial Network for Fault Diagnosis of Axial Piston Pump

引用

IEEE Sensors Journal 2025年第11期25卷 20907-20919页

作者： Chen, Dong-Ning Hu, Dong-Bo Wang, Hao-Wen Xian, Qing-Gui Yao, Cheng-Yu Deng, Ran-Yang Yanshan University School of Mechanical Engineering Qinhuangdao066004 China Yanshan University Hebei Key Laboratory of Industrial Computer Control Engineering Qinhuangdao066004 China

A conditional feature generative adversarial network (CFGAN) for small sample data augmentation was proposed in this paper to address the issue of the scarcity of fault samples in axial piston pump fault diagnosis. With one-dimensional data as input, a feature extractor was constructed in this method to extract features, bringing about an original deep feature dataset. Subsequently, this dataset was employed to train the generation model for enhancing the training efficiency. Additionally, the Wasserstein distance was introduced to improve the stability of the model training. Conditional labels were added to the inputs of the generator and discriminator to guide the model's training and generate high-quality feature datasets. Afterward, the effectiveness of the proposed data generation method was verified through the data obtained from the Paderborn Bearing Dataset and an axial piston pump fault simulation testbed. The fault diagnosis accuracy of the augmented dataset was significantly improved compared to the non-augmented dataset. Furthermore, a multi-scale convolutional neural network was established and utilized different-sized convolutional kernels to extract and fuse multi-scale information from the samples. This approach enabled the capture of more comprehensive fault state features, contributing to enhanced diagnostic accuracy. The experimental data of the axial piston pump validate that the diagnostic accuracy with fused multi-sensor signals was higher compared to a single sensor. © 2001-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Approach for Software Just-in-Time Defects Prediction

引用

International Journal of Network Security 2025年第3期27卷 476-486页

作者： Yu, Yingting Chen, Mingliang Zeng, Chuanhan Xie, Guoqiang Pan, Benren Cui, Liu Sun, Heyang Li, Yuancheng State Grid Jiangxi Electric Power Co. Ltd. Research Institute Jiangxi Province Nanchang330096 China Xi'an Jiaotong University Shaanxi Province Xi'an710049 China School of Control and Computer Engineering North China Electric Power University Changping District Beijing102206 China

To address the challenges of high maintenance costs, time-consuming processes, and delayed defect repairs in software projects, we introduce a Just-In-Time (JIT) Defect Prediction method tailored for software. Initially, we established an enriched code change metrics system. Building upon existing change metrics, we incorporated two novel dimensions—time and review—to mitigate errors and reduce data deviations during feature extraction. Recognizing the prevalent imbalance where defect-free samples in open-source software outweigh defective ones, we innovatively utilize the Boundary Equilibrium Generative Adversarial Networks (BEGAN) model. This strategy aims to produce synthetic defect data, rectifying the dataset imbalance. Concluding our methodology, we present the CBGRU model for JIT defect prediction. This model synergistically integrates the Convolutional Neural Network (CNN) for data properties and the Bidirectional Gated Recurrent Unit (BGRU) to capture temporal correlations within diverse data sets. Empirical evaluations across three open-source software platforms reveal that BEGAN surpasses conventional imbalance-handling techniques. Remarkably, our proposed CBGRU model enhances Precision by 17% and F-measure by 9.6% compared to prior methodologies. © (2025), (Femto Technique Co., Ltd.). All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

DISTANCE BETWEEN SPECIES BY CONFUSION OPERATORS OF MULTI-CLASS CLASSIFIERS

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2025年第1期2025卷 171-182页

作者： Tarbă, Nicolae Irimescu, Ionela N. Pleavă, Ana M. Scarlat, Eugen N. Mihăilescu, Mona Doctoral School Computer Science and Engineering Department Faculty of Automatic Control and Computers National University of Science and Technology POLITEHNICA Bucharest Romania Applied Sciences Doctoral School National University of Science and Technology POLITEHNICA Bucharest Romania CAMPUS Research Center National University of Science and Technology POLITEHNICA Bucharest Romania Physics Dept National University of Science and Technology POLITEHNICA Bucharest Romania Physics Dept Research Center for Applied Sciences in Engineering National University of Science and Technology POLITEHNICA Bucharest Romania

We introduce a method to evaluate the similarities between classes of objects based on the confusion matrices coming from the multi-class machine learning (ML) predictors that operate in the vector space generated by the classes. Operation in the confusion domain allows us to use the distance as evaluation metric of the closeness of the relevant properties carried by the classes. We applied the method to semiquantitatively evaluate the effects of X-ray and carbon ion radiation on cultured SW1353 chondrosarcoma cells with respect to the non-irradiated reference. We prove that it is possible to draw useful information on the strength of cells nuclei changes. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Radiation effects

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based framework for weakly-supervised temporal action localization

引用

Pattern Recognition 2025年 160卷

作者： Zou, Yuanbing Zhao, Qingjie Sarker, Prodip Kumar Li, Shanshan Wang, Lei Liu, Wangwang School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Institute of Control Engineering Beijing100190 China

Weakly supervised temporal action localization aims to localize action instances with only video-level supervision. Due to the absence of frame-level annotation supervision, how effectively separate action snippets and backgrounds from semantically ambiguous features becomes an arduous challenge for this task. To address this issue from a generative modeling perspective, we propose a novel diffusion-based network with two stages. Firstly, we design a local masking mechanism module to learn the local semantic information and generate binary masks at the early stage, which (1) are used to perform action-background separation and (2) serve as pseudo-ground truth required by the diffusion module. Then, we propose a diffusion module to generate high-quality action predictions under the pseudo-ground truth supervision in the second stage. In addition, we further optimize the new-refining operation in the local masking module to improve the operation efficiency. The experimental results demonstrate that the proposed method achieves a promising performance on the publicly available mainstream datasets THUMOS14 and ActivityNet. The code is available at https://***/Rlab123/action_diff. © 2024

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Study of orography–MJO interaction and its impact on rainfall variability in West Sumatra

引用

Journal of Earth System Science 2025年第2期134卷 1-27页

作者： Satiadi, Didi Purwaningsih, Anis Harjupa, Wendi Saufina, Elfira Fathrio, Ibnu Trismidianto Rahmatia, Fahmi Pratama, Ridho Hashiguchi, Hiroyuki Shimomai, Toyoshi Research Center for Climate and Atmosphere National Research and Innovation Agency (BRIN) Bandung Indonesia Department of Computer Engineering School of Electrical Engineering Telkom University Bandung Indonesia Disaster Prevention Research Institute Kyoto University Kyoto Japan Research Institute for Sustainable Humanosphere Kyoto University Kyoto Japan Department of Electronic and Control Systems Engineering Shimane University Shimane Japan

Abstract: This study examines the impact of orography and the Madden–Julian Oscillation (MJO) on rainfall patterns in West Sumatra, Indonesia, using ERA5 reanalysis data. We analyzed variables such as precipitation, zonal and vertical winds, vertically integrated moisture convergence (VIMC), Froude number, lifting condensation level (LCL), level of free convection (LFC), level of non-buoyancy (LNB), convective available potential energy (CAPE), and convective inhibition (CINH), focusing on MJO phases 3 (MJO-3) and 4 (MJO-4). The ERA5 data was validated with observations from the Agam Observation Station, including data from the equatorial atmosphere radar, X-band Doppler Radar, optical rain gauge, microwave radiometer, and radiosonde. Our analysis, covering 22 years (2001–2022) of hourly data from five locations at varying elevations, reveals that topography significantly influences rainfall distribution, with windward slopes and mountain peaks receiving the most rainfall. This pattern closely aligns with VIMC, indicating that moisture convergence is a key driver of rainfall variability. MJO-3 significantly enhances rainfall by reducing zonal wind speeds, thereby increasing moisture convergence, while MJO-4 has a minimal impact, with increased zonal wind speeds limiting moisture convergence. The study concludes that VIMC patterns, influenced by wind dynamics, are central to understanding rainfall variability in West Sumatra’s mountainous terrain under different MJO phases. Research highlights: Orography strongly influences rainfall in West Sumatra, with the most precipitation on windward slopes and peaks, linked to vertically integrated moisture convergence (VIMC). MJO-3 boosts rainfall by reducing zonal wind speeds, which enhances moisture convergence and emphasizes wind dynamics in rainfall variability. MJO-4 has minimal impact on rainfall, as increased zonal winds restrict moisture convergence, leading to slight changes in precipitation. VIMC is crucial for under

关键词： MJO Orography rainfall topography West Sumatra

来源：评论

学校读者我要写书评

暂无评论

An Entropy-Integrated Adaptive Coding and Scheduling Framework for Optimized Data Transmission in Fog-Cloud IoT Architectures

引用

IEEE Internet of Things Journal 2025年

作者： Lu, Yang Zang, Yuting Bian, Ziyi Zhao, Shuai Zheng, Yan Northeast Forestry University College of Computer and Control Engineering Harbin China Harbin Normal University College of Computer and Information Engineering Harbin China La Trobe University School of Computing Engineering and Mathematical Sciences MelbourneVIC Australia

Entropy-driven network coding has been used as a basis for optimizing data transmission and enhancing resource utilization in Fog-Cloud IoT architectures, including applications in smart cities, industrial automation, environmental monitoring, and healthcare. In Fog-Cloud IoT architectures, conventional data transmission protocols are inefficient because they cannot adapt to dynamic entropy levels, resulting in underutilized bandwidth, increased latency, and higher energy consumption. In this paper, we propose an Enhanced Entropy-Driven Network Coding (E-EDNC) framework to address these problems. Our framework integrates real-time entropy estimation with adaptive coding strategies and employs a hybrid evolutionary-reinforcement learning (HE-RL) algorithm to dynamically optimize coding parameters and scheduling decisions. Experimental results demonstrate that E-EDNC improves bandwidth utilization by 25%, reduces latency by 25%, and decreases energy consumption by 12%, thereby enhancing overall data transmission efficiency and reliability in Fog-Cloud IoT environments. © 2014 IEEE.

关键词： Network coding

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：