检索结果-内蒙古大学图书馆

5th International Conference on Machine Learning and computer Application, ICMLCA 2024

作者： Chen, Hao Ji, Yuan Zhu, Lankang Yang, Shu Cui, Li Feng, Changhui Wang, Penghao Tan, Yuxing Ma, Hanhan Jiaxing Hengchuang Electric Power Design and Research Institute Co. Ltd Jiaxing Hengchuang Jiaxing China National Research Center for Information Science and Technology Tsinghua University Department of Electronic Engineering and Beijing Beijing China School of Computer Science and Technology Xinjiang University Urumqi China

ISBN: (纸本)9798331530334

The conventional training of summarization models using maximum likelihood loss faces a challenge: the discrepancy between training and evaluation objectives. Training minimizes token-level loss, while evaluation focuses on sentence or document quality, leading to less effective results. To address this, we propose the Hybrid Loss Abstractive Summarization (HLAS) framework, which combines maximum likelihood loss with global sequence prediction metrics, aligning training with evaluation. Experiments on the BillSum and GovReport datasets show that HLAS significantly outperforms baseline models, achieving higher ROUGE scores and better summarization quality. © 2024 IEEE.

关键词： Abstractive Document Summarization Enhanced Evaluation Metric Hybrid Loss Optimization

来源：评论

学校读者我要写书评

暂无评论

Data-driven Power Flow Method Based on Exact Linear Regression Equations

引用

Journal of Modern Power systems and Clean Energy 2022年第3期10卷 800-804页

作者： Yanbo Chen Chao Wu Junjian Qi State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Electrical&Electronic EngineeringNorth China Electric Power UniversityBeijing 102206China Department of Electrical and Computer Engineering Stevens Institute of TechnologyHobokenNJ 07030USA

Power flow(PF)is one of the most important calculations in power *** widely-used PF methods are the Newton-Raphson PF(NRPF)method and the fast-decoupled PF(FDPF)*** smart grids,power generations and loads become intermittent and much more uncertain,and the topology also changes more frequently,which may result in significant state shifts and further make NRPF or FDPF difficult to *** address this problem,we propose a data-driven PF(DDPF)method based on historical/simulated data that includes an offline learning stage and an online computing *** the offline learning stage,a learning model is constructed based on the proposed exact linear regression equations,and then the proposed learning model is solved by the ridge regression(RR)method to suppress the effect of data *** online computing stage,the nonlinear iterative calculation is not *** results demonstrate that the proposed DDPF method has no convergence problem and has much higher calculation efficiency than NRPF or FDPF while ensuring similar calculation accuracy.

关键词： Data driven exact linear regression equation Fast-decoupled power flow Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Data Poisoning: Issues, Challenges, and Needs 7

Data Poisoning: Issues, Challenges, and Needs

引用

7th IET Smart Cities Symposium, SCS 2023

作者： Aljanabi, Mohammad Omran, Alaa Hamza Mijwil, Maad M. Abotaleb, Mostafa El-Kenawy, El-Sayed M. Mohammed, Sahar Yousif Ibrahim, Abdelhameed Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science &Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

ISBN: (纸本)9781839539831

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence. © The Institution of engineering & technology 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Source Leak Monitoring Device and Experimental Research for Urban Gas Pipeline Network

SSRN

引用

SSRN 2024年

作者： Zhanga, Jixin Li, Zhonghao Zhuo, Jincan Youb, Qiuju Qiaoa, Jianyu Wei, Jiahui Department of Safety Engineering Beijing Institute of Petrochemical Technology Beijing102617 China Urban System Engineering Research Institute of Beijing Academy of Science and Technology Beijing100195 China

As urbanization accelerates, the safety issues of urban gas pipeline networks, as crucial components of urban infrastructure, are becoming increasingly prominent. This paper addresses the issue of gas pipeline leaks in urban areas by designing and constructing an experimental platform aimed at simulating the safe operation of urban gas networks and monitoring pipeline data in real-time through a data acquisition system. The platform simulates the variations in key parameters under different leakage hole sizes and numbers. Static and dynamic leakage experiments were conducted to investigate the effects of different leakage hole sizes and initial pressures on the pressure variations inside the pipelines. The experimental results demonstrate that the initial pressure is directly proportional to the rate of pressure change inside the pipes, and the size of the leakage hole is approximately exponentially related to the rate of pressure change. Furthermore, dynamic leakage experiments reveal that the initial pressure inside the pipes has a significant impact on the final pressure when the leakage hole size is less than 15mm. Under the same initial pressure conditions, the number of leakage holes has a more pronounced effect on the final pressure inside the pipes when the leakage hole diameter is 15mm. This study provides experimental evidence for understanding the leakage patterns of urban gas pipelines, which holds important theoretical and practical significance for enhancing the safety of urban gas networks. © 2024, The Authors. All rights reserved.

关键词： Gases

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning for Wafer Surface Defect Pattern Recognition

Unsupervised Learning for Wafer Surface Defect Pattern Recog...

引用

Chinese Intelligent Automation Conference, CIAC 2021

作者： Geng, Sheng Liu, Huaping Wang, Feng Zhao, Shimin Liu, Hu Department of Control Science and Engineering Shanghai Institute of Technology Shanghai201418 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9789811663710

With the development of the semiconductor industry, the demand for wafer production has gradually increased. Wafer manufacturing is a very complicated process, and any abnormal fluctuations in each process in this process may cause surface defects on the wafer. Accurate and rapid identification of wafer defect patterns can promptly reflect abnormal problems in the production process. Aiming at such tasks, this paper proposes a pattern recognition method for wafer surface defects based on unsupervised learning. The method is divided into two parts: unsupervised pre-training and classification fine-tuning. In the unsupervised pre-training stage, in order to improve the model’s surface defect feature extraction capability, we propose a new wafer-oriented unsupervised sampling method (WaUSM). Our wafer surface defect pattern recognition method uses an unsupervised pre-training model as the initialization to set up a classification model downstream, and fine-tune the classification model through a small number of label images with wafer defect patterns, so that the classification model can more accurately identify various types of defects pattern. The method we proposed was successfully verified by wafer defect pattern recognition on the public dataset WM-811K, and the experimental results fully proved the effectiveness and industrial applicability of the method we proposed. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Wearable Master Manipulator for the Remote Vascular Interventional Surgery 20

A Novel Wearable Master Manipulator for the Remote Vascular ...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Lin, Zhijun Guo, Shuxiang Yan, Yonggan Li, Chenzhihang Zhao, Duohao Lyu, Chuqiao Beijing Institute of Technology Key Laboratory of Convergence Biomedical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology School of Life Science No.5 Zhongguancun South Street Haidian District Beijing100081 China Southern University of Science and Technology The Department of Electronic and Electrical Engineering Guangdong Shenzhen518055 China

ISBN: (纸本)9798350320831

Vascular interventional surgery (VIS) mainly relies on the surgeon's clinical experience and the image assistance of digital subtraction angiography (DSA). However, DSA will damage the surgeon's health. A master-slave vascular interventional surgical robotic system averts the threat of the X-ray, whereas most master manipulators of the system still have some problems, such as the different operating modes compared to the convention and the large inertia of the device itself. Therefore, a wearable device with precise measurement function, SurGlove, is developed in this study. The surgeon can wear SurGolve as the common medical glove and handle the catheter and guidewire directly. The film pressure sensor on the glove can judge the grasping signal and enable the optical tracking system to measure the markers on the device. The spatial rotation angle and displacement distance of the SurGolve are calculated in real-time. By wearing SurGlove, the surgeon can manipulate the guidewire and the catheter cooperatively. Furthermore, the evaluation experiments showed that the proposed device had a mean absolute error of 1.88° and a maximum error of less than 3° in rotation angle measurement. The maximum displacement error was less than 5 mm and the mean absolute error was 1.53 mm. This study preliminarily verified the feasibility of the proposed wearable SurGlove for the VIS robotic system. © 2023 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Development of a single-frequency fiber–solid hybrid laser operated at the Fraunhofer line of 527.039 nm

引用

Applied Optics 2025年第15期64卷 4341-4345页

作者： Zhang, Junxuan Ma, Jian Lu, Tingting Zhu, Xiaolei He, Yan Chen, Weibiao Aerospace Laser Technology and System Department Shanghai Institute of Optics and Fine Mechanics Chinese Academy of Sciences Shanghai201800 China Wangzhijiang Innovation Center for Laser Shanghai201800 China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences Beijing100049 China

A single-frequency laser operated at the Fraunhofer line of 527.039 nm has been demonstrated. Utilizing multi-stage fiber–bulk amplifiers seeded by a distributed feedback laser diode, a fundamental laser emitting at 1054.078 nm was carefully designed to boost the pulse energy to 0.64 mJ at 20 Hz. The 1054.078 nm laser was subsequently frequency-doubled to 527.039 nm. This green laser generated a pulse energy of 0.29 mJ, with a spectrum linewidth of less than 0.4 pm (a resolution limit of the wavelength meter) and a pulse duration of approximately 24 ns. The beam profile was a high-quality TEM00 mode with an M2 factor of less than 1.19. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Distributed feedback lasers Green lasers High power lasers Hybrid lasers Nd:YAG lasers Nd:YLF lasers

来源：评论

学校读者我要写书评

暂无评论

Design of Clutch Units of the Propulsion system for the Three-Dimension Triphibian Robot 20

Design of Clutch Units of the Propulsion System for the Thre...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Chen, Yingduo Guo, Shuxiang Yin, He Li, Ao Liu, Meng Beijing Institute of Technology The Key Laboratory of Convergence Biomedical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology School of Life Science No.5 Zhongguancun South Street Haidian District Beijing100081 China Southern University of Science and Technology The Department of Electronic and Electrical Engineering Guangdong Shenzhen518055 China

ISBN: (纸本)9798350320831

Robots capable of traversing various environments have stringent design requirements for their drive structures. To add flight capabilities to the existing amphibious spherical quadruped robot, enhance its mobility space, and optimize its propulsion strategies, this paper designs a clutch units for the propulsion system of the three-dimension triphibian robot (3DTR). The article first introduces the concept of the 3DTR and its significant importance, and explains the critical role of the clutch units for the propulsion system of the 3DTR. Then, according to the design requirements for functionality upgrade, the types of clutches and motors are selected, and the mechanical model of the clutch units is designed. Subsequently, performance tests and function verification of the clutch units were conducted, demonstrating the effectiveness of the clutch units design, laying the foundation for the subsequent overall design and experiment of the 3DTR propulsion system. © 2023 IEEE.

关键词： Clutches

来源：评论

学校读者我要写书评

暂无评论

Design and Characteristic Evaluation of a Novel Clamping Mechanism for Amphibious Spherical Bionic Robots 20

Design and Characteristic Evaluation of a Novel Clamping Mec...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Gu, Chengchao Guo, Shuxiang Liu, Meng Yin, He Li, Ao Beijing Institute of Technology Key Laboratory of Convergence Medical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology School of Life Science No.5 Zhongguancun South Street Haidian District Beijing100081 China Southern University of Science and Technology The Department of Electronic and Electrical Engineering Guangdong Shenzhen518055 China

ISBN: (纸本)9798350320831

The motion function and control of amphibious robots is a hot topic at present. The multi-function of robot is the development trend of robot. In this paper, based on the existing prototype bionic robot in the laboratory, the structure of the robot's mechanical leg is updated, and the underwater grasping function is successfully added. The new mechanical leg integrates a mechanical claw device, which makes use of the geometric characteristics of the parallelogram to shrink the mechanical claw, maximizes the use of the limited space below the robot, and greatly extends the effective length of the grasping end of the mechanical claw. At the same time, through static stress analysis and motion simulation, the designed structure was evaluated and analyzed, and the appropriate servo specifications and structure size were obtained, which verified that the current designed structure can complete the grasping task of 3kg objects. Finally, 3D printing technology was used to complete the production of the first version of the new mechanical leg, and the functional verification experiment of grasping objects of two different sizes was completed by using the steering gear control. © 2023 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Text Recognition on Curved Metal Surface: An Enhanced Approach using EasyOCR and OpenCV

Text Recognition on Curved Metal Surface: An Enhanced Approa...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Vijayalakshmi. R A.T.N Charany S. Niresh Kumar Somu C. S Sajan. D Deepika. N Department of Computer Science and Business System Rajalakshmi Institute of Technology Chennai India Department of Information Technology Chennai Institute of Technology Chennai India Department of Computer Science and Engineering St. Joseph’s College of Engineering Chennai India Department of Computer Science and Engineering Sri Sairam Institute of Technology Chennai India Department of Computer Science and Engineering Sri Venkateswara College of Engineering Chennai India

ISBN: (数字)9798331535193

ISBN: (纸本)9798331535209

Text is a fundamental system of symbolic representation, and it plays a major role in human culture and communication. Its ability to convey the rich semantic information has become very essential in vision-based applications. With the advancement of deep learning, computer vision techniques particularly in text detection and recognition has undergone significant evolution. This paper investigates the transformative impact of deep learning on scene text detection and recognition, specifically on curved metal surfaces. By leveraging Easy Optical Character Recognition (EasyOCR) and OpenCV, the proposed approach achieves an impressive accuracy of 90% for text recognition in challenging curved surfaces. Additionally, this study explores to optimization techniques designed to enhance detection precision and examines the scalability of deep learning models in real-world applications.

关键词： Deep learning Codes Accuracy Text recognition Social networking (online) Scalability Computational modeling Text detection Metals Containers

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：