检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Gu, Yan Liu, Zhaoze Dai, Shuhong Liu, Cong Wang, Ying Wang, Shen Theodoropoulos, Georgios Cheng, Long The School of Control and Computer Engineering North China Electric Power University Beijing China The School of Computer Science and Technology Shandong University of Technology China The Institute of Computing Technology Chinese Academy of Sciences Beijing China The School of Computer Science University College Dublin Ireland Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

Cloud computing has revolutionized the provisioning of computing resources, offering scalable, flexible, and on-demand services to meet the diverse requirements of modern applications. At the heart of efficient cloud operations are job scheduling and resource management, which are critical for optimizing system performance and ensuring timely and cost-effective service delivery. However, the dynamic and heterogeneous nature of cloud environments presents significant challenges for these tasks, as workloads and resource availability can fluctuate unpredictably. Traditional approaches, including heuristic and meta-heuristic algorithms, often struggle to adapt to these real-time changes due to their reliance on static models or predefined rules. Deep Reinforcement Learning (DRL) has emerged as a promising solution to these challenges by enabling systems to learn and adapt policies based on continuous observations of the environment, facilitating intelligent and responsive decision-making. This survey provides a comprehensive review of DRL-based algorithms for job scheduling and resource management in cloud computing, analyzing their methodologies, performance metrics, and practical applications. We also highlight emerging trends and future research directions, offering valuable insights into leveraging DRL to advance both job scheduling and resource management in cloud computing. © 2025, CC BY.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Geometry Problem Solving Based on Counter-Factual Evolutionary Reasoning 19

Geometry Problem Solving Based on Counter-Factual Evolutiona...

引用

19th IEEE International Conference on Automation Science and engineering, CASE 2023

作者： Song, Bing Xiong, Gang Shen, Zhen Zhu, Fenghua Lv, Yisheng Ye, Peijun Institute of Automation Chinese Academy of Sciences The State Key Laboratory of Management and Control for Complex Systems Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences The Beijing Engineering Research Center of Intelligent Systems and Technology China Chinese Academy of Sciences The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Dongguan523808 China Qingdao Academy of Intelligent Industries Intelligent Manufacturing Center Qingdao266000 China

ISBN: (纸本)9798350320695

As a representative topic in natural language processing and automated theorem proving, geometry problem solving requires an abstract problem understanding and symbolic reasoning. A major challenge here is to find a feasible reasoning sequence that is consistent with given axioms and the theorems already proved. Most recent methods have exploited neural network-based techniques to automatically discover eligible solving steps. Such a kind of methods, however, is greatly impacted by the expert solutions for training. To improve the accuracy, this paper proposes a new method called counterfactual evolutionary reasoning, which uses a generative adversarial network to generate initial reasoning sequences and then introduces counterfactual reasoning to explore potential solutions. By directly exploring theorem candidates rather than the neural network selection, the new method can sufficiently extend the searching space to get a more appropriate reasoning step. Through comparative experiments on the recent proposed Geometry3k, the largest geometry problem solving dataset, our method generally achieves a higher accuracy than most previous methods, bringing an overall improvement about 4.4% compared with the transformer models. © 2023 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

High-Performance Convolutional Neural Network Emulation Via Fpga-Integrated Memristive Circuitry

SSRN

引用

SSRN 2024年

作者： Yang, Yucheng Tan, Aolong Duan, Shukai Wang, Lidan State Key Laboratory of Intelligent Vehicle Safety Technology China College of Artificial Intelligence Southwest University China National & Local Joint Engineering Research Center of Intelligent Transmission and Control Technology China Chongqing Key Laboratory of Brain-inspired Computing and Intelligent Chips China

In this study, to tackle the challenges of high cost, insufficient reliability, and short lifespan associated with physical memristors, a FPGA-based memristor simulation circuit is proposed. This circuit is deployed on the Xilinx ZYNQ-7000 FPGA XC7Z020, with a resource utilization rate of less than 1%, and has been successfully integrated and validated. Moreover, the paper leverages a memristor model to build a convolutional neural network for MNIST image recognition, which achieves an accuracy of 90.22% with a parameter count of 512. © 2024, The Authors. All rights reserved.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Real-time Semantic Segmentation of Solar Photovoltaic Arrays for Autonomous UAV Flights

Real-time Semantic Segmentation of Solar Photovoltaic Arrays...

引用

第43届中国控制会议

作者： Nanyan Li Hao Chen Zhigang Sun Jing Gao Dewei Yi Cunjia Liu Jinya Su School of Automation Southeast University Key Laboratory of Measurement and Control of CSE Ministry of Education Southeast University State Grid Jiangsu Integrated Energy Service Co. Ltd. Department of Computing Science University of Aberdeen Department of Aeronautical and Automotive Engineering Loughborough University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper considers the real-time semantic segmentation of solar PhotoVoltaic(PV) arrays using down-facing cameras onboard Unmanned Aerial Vehicles(UAVs) to support autonomous navigation for ultra-low altitude industrial inspection. Various semantic segmentation algorithms, including SegNet, UNet, Deeplabv3+, and their respective variants, are compared to identify the most suitable one that strikes a balance between segmentation and real-time performance. Subsequently, each video frame is processed by the selected segmentation network to create a solar array mask. This mask is then optimally fitted to diverse solar array shapes to determine angular and horizontal deviations between the image center and the solar array center-line. The algorithms are validated on a self-constructed dataset of 594 solar PV array UAV images, encompassing varied environmental conditions and solar farm layouts. The top-performing network, lightweight vgg16bn-Unet, achieves 99.4% overall accuracy and 98.2% Intersection over Union(IoU), while the most balanced network, mobilev3-Deeplabv3+, attains 98.9% accuracy and96.5% IoU, with a 27.59 fps(using an NVIDIA GeForce MX150 GPU) suitable for real-time UAV flights.

关键词： CNN Machine Vision Solar Inspection UAV Navigation Real-time and Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Key technologies for electric vehicles

引用

Green Energy and Intelligent Transportation 2022年第2期1卷 135-137页

作者： Rui Xiong Jonghoon Kim Weixiang Shen Chen Lv Hailong Li Xiaoyong Zhu Wanzhong Zhao Bingzhao Gao Hongyan Guo Chengming Zhang Fengchun Sun Department of Vehicle Engineering School of Mechanical EngineeringBeijing Institute of TechnologyNo.5 South Zhongguancun StreetHaidian DistrictBeijing 100081China Energy Storage and Conversion Laboratory Department of Electrical EngineeringCollege of EngineeringChungnam National UniversityDaejeon34134South Korea School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyHawthornVictoria 3122Australia School of Mechanical and Aerospace Engineering Nanyang Technological University639798Singapore School of Business Society and Engineering Mälardalen UniversitySE 72123VäteråsSweden School of Electrical and Information Engineering Jiangsu UniversityZhenjiangChina Department of Vehicle Engineering Nanjing University of Aeronautics and AstronauticsNanjingChina Clean Energy Automotive Engineering Center Tongji UniversityShanghai 201804China State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchun 130022China Department of Electrical Engineering Harbin Institute of TechnologyHarbinChina

*** Electric vehicles(EVs)are playing an increasingly important role in decarbonizing the transportation *** constitute a promising solution to a set of global challenges such as climate change and air *** are an integration of a wide spectrum of techniques,such as battery monitoring,battery safety and vehicle energy *** this regard,the EV development still faces significant challenges,which necessitate innovations in EV *** this,Green Energy and Intelligent Transportation(GEITS)organizes a special issue of“Key Technologies for Electric Vehicles”that attempts to advance knowledge in the area of EVs and provides a platform for researchers and engineers to share recent research results and discuss critical challenges in this field.A wide spectrum of topics are discussed,including but not limited to the following.

关键词： battery Key challenges

来源：评论

学校读者我要写书评

暂无评论

A Neurobehavioral Evaluation of the Efficacy of 1mA Longitudinal, Anodal TDCS on Multitasking and Transfer Performance

A Neurobehavioral Evaluation of the Efficacy of 1mA Longitud...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Akash K Rao Shashank Uttrani Darshil Shah Vishnu K Menon Arnav Bhavsar Shubhajit Roy Chowdhury Ramsingh Negi Varun Dutt Manipal Academy of Higher Education Applied Cognitive Science Laboratory Indian Institute of Technology Mandi School of Computing and Electrical Engineering Indian Institute of Technology Mandi Cognitive Control and Machine Learning Group at the Institute of Nuclear Medicine and Allied Sciences Defence Research and Development Organization

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Multitasking requires rapid switching of attention and cognitive resources between different tasks in a dynamic environment, relying on cognitive processes, such as working memory, executive control, and selective attention. Although studies have investigated the efficacy of various neurobehavioral interventions in improving multitasking capabilities, the effects of longitudinal anodal transcranial direct current stimulation (tDCS) in enhancing multitasking performance have not been investigated. This research investigated the efficacy of 1mA anodal tDCS administered longitudinally on multitasking performance. 42 participants were randomly and equally divided into the experimental and placebo control conditions in this study conducted for 10 days. All participants executed two multitasking tasks on day 1 and received 1mA anodal/placebo tDCS during task training from day 2 to day 8. Various behavioral and neurophysiological measures have been measured. The findings revealed that tDCS had the propensity to augment multitasking capabilities in the trained task but had limited transfer capabilities. EEG-based brain connectivity analysis also revealed the formation of network hubs in the prefrontal and frontal regions, indicating enhanced cortical activation in the beta band. We intend to use these findings to design interventional frameworks to enhance multitasking performance using tDCS.

关键词： Training Atmospheric measurements Memory management Switches Multitasking Particle measurements Dynamic scheduling control systems Transcranial direct current stimulation Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Are Deep Neural Networks Robust to Named Entities? An Adversarial Attack and Defense Perspective

SSRN

引用

SSRN 2022年

作者： Li, Ang Leng, Xinlin Li, Shuangjiao Zhang, Fangyuan Xu, Weifeng Wang, Hongtao School of Control and Computer Engineering North China Electric Power University Baoding071051 China Engineering Research Center of Intelligent Computing for Complex Energy Systems Ministry of Education Baoding071051 China

Following the pervasive applications of deep neural networks across natural language tasks, adversarial attacks against these models have proven to be a serious threat. By adding small perturbations via word substitution, word-level adversarial attacks can fool deep classifiers making incorrect decisions. Previous word-level attacks mainly focus on substituting verbs and adjectives by their synonyms. In this paper, we ask whether a deep textual classifier is robust to the replacement of Named Entities (NEs) of the same category. We propose an effective NE adversarial attack method, which proves that NEs are very sensitive to such substitutions for deep textual classifiers. To enhance the robustness of classifiers, we also propose three novel defense approaches: 1) mask replacement, 2) concept replacement, and 3) data augmentation based on NE sampling. We evaluate these approaches on text classification tasks under different victim and attack models,using a variety of standard datasets including IMDB, AGNEWS and SST2. Experimental results illustrate the performance improvements of our defense approaches against NE adversarial attacks. © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research and Exploration on Innovation and Entrepreneurship Practice Education System for Railway Transportation Specialists

Research and Exploration on Innovation and Entrepreneurship ...

引用

作者： Jiu Yong Jianwu Dang Yangping Wang Jianguo Wei Yan Lu The National Virtual Simulation Experiment Teaching Center of Railway Traffic Information and Control Lanzhou Jiaotong University College of Intelligence and Computing Tianjin University The School of Electronic and Information Engineering Lanzhou Jiaotong University Key Laboratory of Four Electric BIM Engineering and Intelligent Application Railway Industry

With the background of concept of rail transit major engineering,guided by industry demand, and based on the cultivation of practical abilities for outstanding engineering and technology talents in rail transit characteristic majors,we are committed to creating a national strategic innovation and entrepreneurship practical education system for rail transit characteristic professionals, continuously improving the practical teaching mode. We will carry out the construction of a "matrix style" practical teaching system that integrates the four modernizations,the construction of a virtual simulation practical teaching platform that integrates expertise and innovation, and open sharing, as well as the reform and exploration of the entire chain of integrated practical education. The scheme focuses on improving students' ability to solve complex engineering problems and their ability to apply composite knowledge and innovate and start businesses, cultivating a large number of outstanding rail transit engineering talents with solid professional foundations, outstanding practical abilities, and innovative and entrepreneurial qualities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Linear Bandit Learning via Over-the-air Computation

arXiv

引用

arXiv 2023年

作者： Wang, Jiali Jiang, Yuning Liu, Xin Wang, Ting Shi, Yuanming MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China Automatic Control Laboratory EPFL Switzerland ShanghaiTech University China

In this paper, we investigate federated contextual linear bandit learning within a wireless system that comprises a server and multiple devices. Each device interacts with the environment, selects an action based on the received reward, and sends model updates to the server. The primary objective is to minimize cumulative regret across all devices within a finite time horizon. To reduce the communication overhead, devices communicate with the server via over-the-air computation (AirComp) over noisy fading channels, where the channel noise may distort the signals. In this context, we propose a customized federated linear bandits scheme, where each device transmits an analog signal, and the server receives a superposition of these signals distorted by channel noise. A rigorous mathematical analysis is conducted to determine the regret bound of the proposed scheme. Both theoretical analysis and numerical experiments demonstrate the competitive performance of our proposed scheme in terms of regret bounds in various settings. © 2023, CC BY-NC-SA.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

Rational Modulation of Redox Equilibrium Over Mn Modified Ce-Sn Catalyst for Low-Temperature Elimination of No and Hg0

SSRN

引用

SSRN 2024年

作者： Shi, Qiqi Lu, Litong Kang, Dongrui Shen, Boxiong Bian, Yao Zhang, Xiao Lyu, Honghong Li, Shuhao Tianjin Key Laboratory of Clean Energy and Pollution Control School of Energy and Environmental Engineering Hebei University of Technology Tianjin300401 China Department of Chemistry and Biotechnology School of Science Computing and Engineering Technologies Swinburne University of Technology MelbourneVIC3122 Australia CSIRO Manufacturing Private Bag 10 Clayton SouthVIC3169 Australia

The synergistic catalytic removal of NO and Hg0 under low temperatures is still a great challenge. Here, we report a Mn-modified Ce-Sn catalyst for simultaneous removal of NO and Hg0 at low temperature. The optimum Mn0.2/Ce0.33Sn0.67 exhibited more than 95% NO conversion and N2 selectivity above 86% at 150-250 °C as well as Hg0 removal of nearly 100% within 150-300 °C. SnO2-promoted Ce-Sn solid solution enhanced the surface proportion of Ce3+, the number of surface chemisorbed oxygen and the electronic interaction within Ce-Sn linkage. Mn modification further reasonably promoted redox cycling at low temperatures and improved acidic distribution of catalyst. Under the cooperation of Ce-Sn and Mn sites, the presence of Hg0 could substantially facilitate the reduction of NO at 250-300 °C and the SCR atmosphere had a weak inhibitory effect on Hg0 removal. During the SCR process, the NH4+ and NH2 species that directly reacted with gaseous NO following the Eley−Rideal mechanism and the improved reactivity of NH2 with nitrates following the Langmuir−Hinshelwood mechanism enhanced the NO conversion efficiency at low temperature. Meanwhile, Mn modification could alleviate competitive adsorption of NH3 on Hg0 and promote the formation of more chemically adsorbed mercury species. This work will provide guidance for the design of low-temperature catalysts for the simultaneous removal of NO and Hg0 in flue gas. © 2024, The Authors. All rights reserved.

关键词： Temperature

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：