检索结果-内蒙古大学图书馆

2023 International Conference on computer Application and Information Security, ICCAIS 2023

作者： Liu, Yuxiang Wang, Han Liu, Minghao School of Computer and Information Security Guilin University of Electronic Technology Guangxi Guilin541004 China School of Electronic Engineering and Automation Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9781510675032

The purpose of this study is to improve the performance and efficiency of online learning recommendation systems. The performance and efficiency of recommendation systems depend on multiple factors, including distributed computing, data storage, collaborative filtering algorithms, and optimization of recommendation accuracy. To address these issues, this study built a distributed computing system and HDFS data storage on the Spark platform, and implemented multiple recommendation algorithms to improve the performance and efficiency of the recommendation system. Through analysis of the Mooper dataset, this study conducted feature modeling and proposed a learning resource recommendation system based on Java, Scala, and web technologies, which can provide users with a better learning resource recommendation experience. In addition, this study also developed an anomaly learning behavior detection algorithm, which can detect anomalies in user behavior. Experimental results show that the accuracy and recall rate of the recommendation system have been improved, and the anomaly detection algorithm has high accuracy and robustness, thereby improving the reliability and stability of the recommendation system. In summary, the innovation of this study lies in proposing a recommendation system based on distributed computing and collaborative filtering algorithm, and making new progress in anomaly learning behavior detection. This study provides a new method for the field of recommendation systems, which can provide better solutions for the performance and efficiency of recommendation systems. © 2024 SPIE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Deep Security Detection Framework Based on ATT&CK

引用

International Journal of Network Security 2023年第1期25卷 161-170页

作者： Qiu, Rixuan Fu, Yu Le, Jian Zheng, Fuyong Qi, Gan Peng, Chao Zhang, Yi Li, Yuancheng Liu, Yan Dispatch Monitoring Center State Grid Jiangxi Information & Telecommunication Company Nanchang China School of Electrical Engineering and Automation Wuhan University Wuhan430072 China School of Control and Computer Engineering & North China Electric Power University Beijing102206 China

It is urgent to establish an efficient and comprehensive security system architecture facing the increasingly severe network threat. Aiming at the security problems in information systems, a deep security detection framework based on ATT&CK is proposed. There are three modules: information collection, analysis engine, and security response. The anomaly detection results of the technical layer based on ATT&CK knowledge base association analysis are mapped to the attack links of the tactical layer, thus realizing the bottom-up system security detection. An improved transformer anomaly detection method based on FLOATER positional coding is applied in the security detection framework to realize the early detection of network threats. Based on the continuous dynamic system, the positional coding function is learned to capture the temporal features of the sequence. Then multi-head attention is used to encode the input sequence. Moreover, the model training is optimized by the adversarial method. The experimental results demonstrated that the method applied in this work outperforms traditional deep learning models in terms of detection accuracy and F1 score. © 2022,International Journal of Network Security. All Rights Reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

BOOSTED CURRICULUM REINFORCEMENT LEARNING 10

BOOSTED CURRICULUM REINFORCEMENT LEARNING

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Klink, Pascal D'Eramo, Carlo Peters, Jan Pajarinen, Joni Department of Computer Science TU Darmstadt Germany Department of Electrical Engineering and Automation Aalto University Finland

Curriculum value-based reinforcement learning (RL) solves a complex target task by reusing action-values across a tailored sequence of related tasks of increasing difficulty. However, finding an exact way of reusing action-values in this setting is still a poorly understood problem. In this paper, we introduce the concept of boosting to curriculum value-based RL, by approximating the action-value function as a sum of residuals trained on each task. This approach, which we refer to as boosted curriculum reinforcement learning (BCRL), has the benefit of naturally increasing the representativeness of the functional space by adding a new residual each time a new task is presented. This procedure allows reusing previous action-values while promoting expressiveness of the action-value function. We theoretically study BCRL as an approximate value iteration algorithm, discussing advantages over regular curriculum RL in terms of approximation accuracy and convergence to the optimal action-value function. Finally, we provide detailed empirical evidence of the benefits of BCRL in problems requiring curricula for accurate action-value estimation and targeted exploration. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Working on the Structural Components of Evolutionary Approaches 16th

Working on the Structural Components of Evolutionary Approac...

引用

16th International Joint Conference on Computational Intelligence, IJCCI 2024

作者： Tzanetos, Alexandros Kůdela, Jakub Jönköping University Gjuterigatan 5 Jönköping553 18 Sweden Institute of Automation and Computer Science Faculty of Mechanical Engineering Brno University of Technology Czech Republic

ISBN: (纸本)9789897587214

Several researchers have turned their attention to the structural components of Evolutionary Computation and Swarm Intelligence-oriented approaches. This direction offers various opportunities, such as developing automatic design and configuration frameworks and integrating operators and mechanisms addressing known limitations. This work lists recent operators and discusses promising mechanisms found in existing natureinspired approaches. It also discusses how these algorithmic components can be integrated into modular frameworks and how they can be assessed and benchmarked. The work aims to emphasize the importance of the research direction about nature-inspired mechanisms and operators in the Evolutionary Computation field. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Computing Performance Analysis of IEC 61499 Distributed automation Systems

Computing Performance Analysis of IEC 61499 Distributed Auto...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Tuojian Lyu Valeriy Vyatkin Department of Electrical Engineering and Automation Aalto University Espoo Finland Department of Computer Science Computer and Space Engineering Luleå Tekniska Universitet Sweden

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

This work analyzes the computing performance of distributed control systems in IEC 61499 on two hardware devices, Dell XPS workstation and Raspi 4B. Based on the test IEC 61499 application, three different system configurations are tested to simulate the distribution options of singleprocess and single-thread, multi-threading, and multi-process on both hardware platforms. Experimental results show that multiprocess configurations yield more consistent execution time due to dedicated resource allocation, while multi-threading, though resource-efficient, can lead to latency variability. These results aim at help in choosing optimal configurations and selecting hardware for performance in distributed automation systems.

关键词： Performance evaluation automation Decentralized control Hardware Performance analysis Workstations Resource management IEC Standards

来源：评论

学校读者我要写书评

暂无评论

Research on the Structural Design and Basin Characteristics of Pilot Electromagnetic Valves for New Energy Wastewater Treatment Systems 5

Research on the Structural Design and Basin Characteristics ...

引用

5th IEEE International Conference on Advanced Electrical and Energy Systems, AEES 2024

作者： Wang, Na Dong, Yueyang Zhen, Xiaofei Jiao, Ruonan Fu, Haoran Chen, Yuying Lanzhou Jiaotong University School of Mechatronic Engineering Lanzhou China Lanzhou Jiaotong University School of New Energy and Power Engineering Lanzhou China The University of Adelaide Faculty of Engineering Computer and Mathematical Sciences Adelaide Australia Shandong University of Science and Technology Academy of Electrical and Automation Engineering Qingdao China

ISBN: (纸本)9798331517724

Pilot-operated solenoid valves have the advantage of fast response times and can meet high pressure and large diameter requirements through their structural characteristics, making them widely used in various fields. The pilot-operated solenoid valve discussed in this article is applied in a new energy system a sewage treatment system based on solar photovoltaic and solar thermal technology. The pilot-operated solenoid valve designed in this paper controls the flow rate and velocity of the sewage. This article uses Fluent to calculate the flow coefficient of pilot-type solenoid valves at various openings, exploring the flow characteristics of these valves. Based on computational fluid dynamics, simulations of the cavitation flow field were performed for pilot-type solenoid valve models at different openings, resulting in pressure contour plots and liquid velocity vector diagrams within the pilot valve. The study investigated the effects of the valve opening and the pressure difference at the inlet and outlet on the cavitation conditions within the valve. This provides a foundation for subsequent analysis of the vibration characteristics and structural optimization of solenoid pilot valves. The results indicate that negative pressure occurs within the solenoid pilot valve at all openings, leading to cavitation phenomena. When the opening is greater than or equal to 0.5, significant negative pressure appears near the valve port of the valve sleeve, with more pronounced cavitation phenomena, which can easily lead to cavitation bubbles and deformation. © 2024 IEEE.

关键词： Solenoid valves

来源：评论

学校读者我要写书评

暂无评论

Formation Control Optimization via Virtual Leader Exploration with Deep Reinforcement Learning for Unmanned Aerial Vehicles 29

Formation Control Optimization via Virtual Leader Exploratio...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zhao, Kangwei Zhai, Xiangping Bryce Zhu, Jing Tan, Chee Wei Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing China Nanjing University of Aeronautics and Astronautics College of Automation Nanjing China Nanyang Technological University Collage of Computer Science and Engineering Singapore

ISBN: (纸本)9798350330717

Compared to single unmanned aerial vehicle (UAV), multi-UAVs formation has garnered significant attention due to their advantages in collaborative task execution, task allocation, as well as heightened redundancy and reliability. This paper investigates a UAV rendezvous system comprising multiple UAVs with random positions and velocities. We introduce the concept of a virtual leader, with the objective of transforming the formation control problem of UAVs into tracking the positional movements of the virtual leader. We model the exploration of the optimal position for the virtual leader as a Markov decision process and propose a variablestep exploration algorithm combined with deep reinforcement learning techniques, guiding the virtual leader towards its optimal position from its initial location. The experimental simulation results ultimately demonstrate the effectiveness of our approach. © 2023 IEEE.

关键词： deep reinforcement learning Multi-UAVs formation variable-step exploration algorithm virtual leader

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Moving Object Segmentation:Recent Progress and Research Prospects

引用

Machine Intelligence Research 2023年第3期20卷 335-369页

作者： Rui Jiang Ruixiang Zhu Hu Su Yinlin Li Yuan Xie Wei Zou College of Information Engineering Shanghai Maritime UniversityShanghai201306China School of Computer Science and Technology East China Normal UniversityShanghai200062China Research Center of Precision Sensing and Control Institute of AutomationChinese Academy of SciencesBeijing100190China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing100190China

Moving object segmentation(MOS),aiming at segmenting moving objects from video frames,is an important and challenging task in computer vision and with various *** the development of deep learning(DL),MOS has also entered the era of deep models toward spatiotemporal feature *** paper aims to provide the latest review of recent DL-based MOS methods proposed during the past three ***,we present a more up-to-date categorization based on model characteristics,then compare and discuss each category from feature learning(FL),and model training and evaluation *** FL,the methods reviewed are divided into three types:spatial FL,temporal FL,and spatiotemporal FL,then analyzed from input and model architectures aspects,three input types,and four typical preprocessing subnetworks are *** terms of training,we discuss ideas for enhancing model *** terms of evaluation,based on a previous categorization of scene dependent evaluation and scene independent evaluation,and combined with whether used videos are recorded with static or moving cameras,we further provide four subdivided evaluation setups and analyze that of reviewed *** also show performance comparisons of some reviewed MOS methods and analyze the advantages and disadvantages of reviewed MOS methods in terms of ***,based on the above comparisons and discussions,we present research prospects and future directions.

关键词： Moving object segmentation(MOS) change detection background subtraction deep learning(DL) video understanding

来源：评论

学校读者我要写书评

暂无评论

Channel Controlled ARQ Protocol Design for OCDM-Based Data Transmissions 13

Channel Controlled ARQ Protocol Design for OCDM-Based Data T...

引用

13th IEEE International Conference on CYBER Technology in automation, Control, and Intelligent Systems, CYBER 2023

作者： Qin, Wenxuan Zhang, Yechu Yan, Lei Zhang, Rongxin Wang, Yiyin School of Computer and Communication Engineering Northeastern University Qinhuangdao China School of Electronic Science and Engineering Xiamen University Xiamen China Shanghai Jiao Tong University Department of Automation Shanghai China

ISBN: (纸本)9798350315196

Channel controlled automatic retransmission request (CC-ARQ) has shown potential in reducing complexity and bit error rate (BER) in wireless links. In this paper, we design an ARQ protocol transmission scheme for OCDM-based data transmissions. By employing retransmission threshold design based on orthogonality deficiency (od) of the channel matrix, the data transmissions receiver can enjoy the enough diversity offered by the wireless OCDM links with linear equalizers, which is essential for low-complexity communication environments, e.g., sensor cyber systems. © 2023 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Designed Steering Law for the Hybrid Actuators of Single Gimbal Control Moment Gyroscopes and Reaction Wheels Array 41

Designed Steering Law for the Hybrid Actuators of Single Gim...

引用

第41届中国控制会议

作者： Feng Liu Dongping Wang Kedong LYU School of electrical information engineering North Minzu University College of Computer and Information Engineering Tianjin Agricultural University Department of Automation Engineering Tianjin Electronic Information Technician College

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Single Gimbal Control Momentum Gyroscopes(SGCMG) are widely used with the ability of large torque output and high accuracy control of a *** singularity problem(especially the internal elliptical singularity) of SGCMG becoming a major obstacle in successful implementing the task of the attitude *** singularity can be effectively avoided by additional reaction wheel(RW) array in the field of the actual ***,the saturation problem is existed in the *** this paper,the hybrid actuators of the SGCMG with pyramid configuration and RW array with orthogonal configuration is *** new steering law is ***,the internal elliptical singularity and the saturation problem of the RW can be effectively avoided by the new steering law at the same time.

关键词： singularity avoidance new designed steering law hybrid actuators of SGCMG and RW array

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：