检索结果-内蒙古大学图书馆

12th International Conference on information Technology in Medicine and Education, ITME 2022

作者： Zhong, Yuning Hu, Rong Li, Zuoyong Cai, Yuanzheng Fujian University of Technology College of Computer Science and Mathematics Fuzhou350118 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou350121 China

ISBN: (纸本)9798350310153

Insulator exposed to a wild environment for long-term running usually suffers from the damage of natural calamities that makes them become one of the most fragile components in the whole power system. In this case, even a slight fault will seriously affect the power supply safety of the power grid. Therefore, it is critical to find and identify the faulty insulator efficiently and accurately. However, an insulator is quite a small component in comparison with a huge power system which makes it hard to visible with naked eyes. This characteristic leads to poor recognition accuracy for existing detection methods. In order to solve the above problems, we propose an insulator defect detection algorithm based on an improved YOLOv4-tiny model. It differs from existing insulator detection models, our algorithm applies the effective channel attention network to the feature extraction network of YOLOv4-tiny, which significantly enhances the feature extraction ability of the backbone network. These two-way features of the pyramid can be fully fused in the two-way feature fusion stages seamlessly. Experimental results show that compared with, our proposed algorithm outperforms Faster RCNN and YOLOv3 in average classification accuracy, missed detection, and false detection. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Causal Attention Transformer for Video Text Retrieval

引用

IET Image processing 2025年第1期19卷

作者： Lan, Hua Lv, Chaohui School of Information and Communication Engineering Communication University of China Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China

In the metaverse, video text retrieval is an urgent and challenging need for users in social entertainment. The current attention-based video text retrieval models have not fully explored the interaction between video and text, and only brute force feature embedding. Moreover, Due to the unsupervised nature of attention weight training, existing models have weak generalization performance for dataset bias. Essentially, the model learns that false relevant information in the data is caused by confounding factors. Therefore, this article proposes a video text retrieval method based on causal attention transformer. Assuming that the confounding factors affecting the performance of video text retrieval all come from the dataset, a structural causal model that conforms to the video text retrieval task is constructed, and the impact of confounding effects during data training is reduced by adjusting the front door. In addition, we use causal attention transformer to construct a causal inference network to extract causal features between video text pairs, and replace the similarity statistical probability with causal probability in the video text retrieval framework. Experiments are conducted on the MSR-VTT, MSVD, and LSMDC datasets, which proves the effectiveness of the retrieval model proposed in this paper. © 2025 The Author(s). IET Image processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

关键词： Interactive computer graphics

来源：评论

学校读者我要写书评

暂无评论

Optimal control Synthesis of Markov Decision Processes for Efficiency with Surveillance Tasks

arXiv

引用

arXiv 2024年

作者： Chen, Yu Yin, Xuanyuan Li, Shaoyuan Yin, Xiang Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China School of Chemistry Chemical Engineering and Biotechnology Nanyang Technological University 62 Nanyang Drive Singapore

We investigate the problem of optimal control synthesis for Markov Decision Processes (MDPs), addressing both qualitative and quantitative objectives. Specifically, we require the system to fulfill a qualitative surveillance task in the sense that a specific region of interest can be visited infinitely often with probability one. Furthermore, to quantify the performance of the system, we consider the concept of efficiency, which is defined as the ratio between rewards and costs. This measure is more general than the standard long-run average reward metric as it aims to maximize the reward obtained per unit cost. Our objective is to synthesize a control policy that ensures the surveillance task while maximizes the efficiency. We provide an effective approach to synthesize a stationary control policy achieving ϵ-optimality by integrating state classifications of MDPs and perturbation analysis in a novel manner. Our results generalize existing works on efficiency-optimal control synthesis for MDP by incorporating qualitative surveillance tasks. A robot motion planning case study is provided to illustrate the proposed algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

A High-precision Time Synchronization Algorithm for Aviation Swarm Task Cooperation 2

A High-precision Time Synchronization Algorithm for Aviation...

引用

2nd IEEE International Conference on Electronic Technology, Communication and information, ICETCI 2022

作者： Yaobo, Shang Dongwei, Zhang Lei, Wang Zhe, Li Shujing, Li Air Traffic Control and Navigation College Air Force Engineering University Xi'an China Shaanxi Key Laboratory of Meta-Synthesis for Electronic and Information System Xi'an China

ISBN: (数字)9781728181158

ISBN: (纸本)9781728181158

Aiming at the high-precision time synchronization problem of aviation swarm task cooperation, a high-precision time synchronization algorithm suitable for this working environment is proposed. Based on RTT-REP principle, firstly, the influence of node mobility on synchronization accuracy under the condition of system maneuvering is analyzed, and it is proved that synchronization accuracy is closely related to relative distance and relative movement speed. Then, a method of eliminating maneuver error based on state sharing is put forward. This method shares position information through communication system, and then uses coordinate transformation to measure relative movement speed and relative distance to eliminate displacement error. Finally, the test methods are designed under static conditions in the laboratory and dynamic conditions in the field, and the performance of the system is tested. The experimental results show that the synchronization accuracy error of this system is less than 20ns, which proves that this method has high synchronization accuracy and strong practicability. © 2022 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

An Insulator Missing Defect Detection Method Based on Unmanned Aerial Vehicles

An Insulator Missing Defect Detection Method Based on Unmann...

引用

International Conference on control and Automation (ICCA)

作者： Yulong Zhang Zhongxian Zhou Lingxia Mu Xianghong Xue Jing Xin Youmin Zhang School of Automation and Information Engineering Xi'an University of Technology Xi'an Shaanxi China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China Department of Mechanical Industrial and Aerospace Engineering Concordia University Montreal Quebec Canada

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

In this paper, an insulator missing defect detection method is proposed based on unmanned aerial vehicles to solve the problem of glass insulator burst fault detection in high-voltage transmission lines. Firstly, the proposed method utilizes the improved Mask R-CNN (region-based convolutional neural network) algorithm to segment insulator strings in aerial images. Then, the constructed encoder-decoder network is used to extract and reconstruct features of the insulators, resulting in residual images. Finally, the residual images preserve the location information of the fault and obtains the result of missing insulators. The experiment shows that the proposed algorithm has high segmentation accuracy for insulators and high recognition accuracy for insulator missing faults.

关键词： Image segmentation Accuracy Power transmission lines Fault detection High-voltage techniques Insulators Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Core Real- Time Scheduling Based on Reinforcement Learning

Adaptive Multi-Core Real- Time Scheduling Based on Reinforce...

引用

International Conference on control and Automation (ICCA)

作者： Yonghui Liang Hui Li Fei Shen Qimin Xu Shuna Hua Shanying Zhu Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Re-search Center of Intelligent Control and Management Shanghai China Key Laboratory of Wireless Sensor Network and Communications Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China North Information Control Research Academy Group Company Ltd. Nanjing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

With the transformation towards industrial intel-ligence, multi-core processors are increasingly being applied in real-time networked control systems to ensure secure exe-cution of sensing, computing and actuating tasks under time constraints. However, existing scheduling methods result in either low CPU utilization or many missed task deadlines in dynamic systems. In this paper, we propose a two-layer scheduling architecture to address this issue by fully exploring the complex dependency between real-time tasks. To be specific, the local layer determines task execution priorities considering both dependency between tasks and deadline constraints by utilizing a reinforcement learning approach. Moreover, to better utilize the parallel capabilities of multi-core processors and reduce temporal collisions, this paper minimizes the requested core count for the task set based on a greedy strategy. The global layer designs a scheduling algorithm based on the pre-empt method and provides schedulability analysis of multiple task sets. Experimental results validate the correctness of the proposed scheduling approach, and efficiency is demonstrated through comparisons with baseline method.

关键词： Job shop scheduling Multicore processing Scheduling algorithms Networked control systems Reinforcement learning Real-time systems Sensors

来源：评论

学校读者我要写书评

暂无评论

Bearing-based Formation Tracking of Nonholonomic Agents in the Leader's Local Frame

Bearing-based Formation Tracking of Nonholonomic Agents in t...

引用

2021 China Automation Congress, CAC 2021

作者： Lv, Ke Yang, Ziwen Zhu, Shanying Wang, Lin Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (纸本)9781665426473

This paper investigates the formation tracking control problem of nonholonomic agents in the leader's local frame, based on bearing measurements. Most of existing works on formation tracking are aimed at tracking a given formation in the global frame, which cannot meet the needs of many applications such as a fleet of cars driving on the highway. In this case, if the cars cannot keep a fixed formation in the leader's local frame, they may drive off the highway. Thus we propose an integrated approach consisting of a bearing-based estimator and a tracking controller, to track a given formation in the leader's local frame. In order to eliminate the estimation error in formation tracking, a persistently exciting leader is characterized by conditions. The stability of the integrated method is proved rigorously. Simulation results prove the effectiveness of the proposed approach. © 2021 IEEE

关键词： Integrated control

来源：评论

学校读者我要写书评

暂无评论

Balanced Training for the End-to-End Autonomous Driving Model Based on Kernel Density Estimation

Balanced Training for the End-to-End Autonomous Driving Mode...

引用

IEEE Symposium on Intelligent Vehicle

作者： Tong Yao Wei Yuan Songan Zhang Chunxiang Wang Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China Global Institute of Future Technology Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

End-to-end autonomous driving models are widely used currently to avoid error transmission. The training of these models is affected by the imbalance of the training labels, such as imbalanced distributions of trajectory waypoint, steering, throttle, and brake labels. Therefore, the models cannot be trained enough on low-frequency labels. To mitigate this problem, a balanced training method is proposed in this paper. First, a general kernel density estimation method is used to estimate the probability function of labels. Then, to conduct balanced training, we design a cost-sensitive loss function that assigns different weights to each training data according to the probability of the labels. Comparative experiments on the Longest6 Benchmark show that the balanced training method proposed in this article improves the baseline significantly. We also conduct ablation studies to discuss the balanced training among different tasks in multi-task learning, as well as between two output forms: waypoint and action. Due to the generalization of kernel density estimation, the balanced training method proposed in this paper can be extended to any label distribution of two output forms in the end-to-end autonomous driving models.

关键词： Training Computational modeling Estimation Training data Benchmark testing Data models Trajectory

来源：评论

学校读者我要写书评

暂无评论

Bearing-only Formation control of Nonholonomic Agents with Unknown Dynamic Leaders

Bearing-only Formation Control of Nonholonomic Agents with U...

引用

2021 China Automation Congress, CAC 2021

作者： Su, Haifan Yang, Ziwen Zhu, Shanying Chen, Cailian Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (纸本)9781665426473

In this paper, the problem of bearing-only formation tracking control of multiple nonholonomic agents is studied. A leader-follower structure is adopted, where the leaders are moving at an unknown constant linear velocity and time-varying orientation. To solve the problem using bearing-only measurements, a finite-time estimator is firstly proposed to estimate the leaders' orientation information. Then, an adaptation law for estimating the leaders' linear velocity is proposed, based on which control inputs for tracking the leaders in a predefined bearing-based formation are designed, so that formation tracking can be achieved asymptotically. Rigorous theoretical analysis of the closed-loop system is given. It is proved that both the estimation errors and formation errors converge to zero under the connectivity of the communication graph and conditions for bearing rigidity. Numerical simulations are presented to testify the effectiveness of the proposed method. © 2021 IEEE

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Immovable Cultural Relics Preservation Through 3D Reconstruction Using NeRF 5

Immovable Cultural Relics Preservation Through 3D Reconstruc...

引用

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Lai, Zhiqing Lian, Mingchang Chen, Songhang Chen, Guoqing Lai, Xiaoling Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China Jingwei Space Information Technology Co. Ltd Longyan364030 China

ISBN: (纸本)9781643684840

Urban and rural development poses significant threats to immovable cultural relics, leading to their degradation and potential extinction. To address this issue, 3D reconstruction has emerged as an effective preservation method. However, traditional radar-based techniques require close scanning and extensive manual intervention, limiting their efficiency. This paper explores the application of neural radiance fields (NeRF) for visually reconstructing immovable cultural relics. NeRF employs a fully connected non-convolutional neural network to generate high-quality 3D models from 2D images. The study discusses NeRF's sampling strategy, positional encoding, field architecture, and rendering process. Experimental investigations evaluate the impact of Fourier parameters on reconstruction quality. A case study reconstructing Tianhou Temple using NeRF is presented, comparing it with ContextCapture software. All results demonstrate that NeRF offers an efficient, and cost-saving solution for reconstructing and preserving immovable cultural relics, providing accurate and realistic models with superior structural integrity. © 2024 The Authors.

关键词： Image reconstruction

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：