检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,216 篇 会议
9 篇 期刊文献

馆藏范围

1,225 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

499 篇 工学
- 387 篇 控制科学与工程
- 249 篇 计算机科学与技术...
- 147 篇 电气工程
- 86 篇 软件工程
- 61 篇 机械工程
- 39 篇 仪器科学与技术
- 18 篇 信息与通信工程
- 16 篇 力学（可授工学、理...
- 12 篇 生物工程
- 11 篇 材料科学与工程（可...
- 11 篇 交通运输工程
- 10 篇 生物医学工程（可授...
- 9 篇 光学工程
- 9 篇 土木工程
- 8 篇 石油与天然气工程
- 7 篇 建筑学
- 5 篇 动力工程及工程热...
- 5 篇 电子科学与技术（可...
- 5 篇 化学工程与技术
- 5 篇 安全科学与工程
102 篇 理学
- 67 篇 数学
- 21 篇 物理学
- 19 篇 统计学（可授理学、...
- 15 篇 生物学
- 13 篇 系统科学
- 6 篇 化学
35 篇 管理学
- 30 篇 管理科学与工程(可...
- 7 篇 工商管理
- 7 篇 图书情报与档案管...
7 篇 医学
- 6 篇 临床医学
3 篇 文学
2 篇 农学
1 篇 法学
1 篇 教育学
1 篇 军事学

主题

165 篇 mathematical mod...
104 篇 predictive model...
93 篇 automation
93 篇 adaptation model...
90 篇 robots
87 篇 computational mo...
82 篇 data models
81 篇 training
61 篇 trajectory
59 篇 analytical model...
58 篇 equations
57 篇 accuracy
55 篇 numerical models
51 篇 approximation me...
48 篇 stability analys...
46 篇 vectors
45 篇 feature extracti...
39 篇 robot sensing sy...
39 篇 control systems
39 篇 estimation

机构

10 篇 faculty of mecha...
9 篇 state key labora...
8 篇 institute of com...
8 篇 school of electr...
8 篇 institute of aut...
6 篇 department of el...
6 篇 silesian tech un...
6 篇 university of ch...
6 篇 univ rostock cha...
5 篇 faculty of elect...
5 篇 chair of mechatr...
5 篇 faculty of elect...
5 篇 institute of aut...
5 篇 institute of aut...
5 篇 systems research...
4 篇 school of automa...
4 篇 carleton univ de...
4 篇 department of au...
4 篇 department of au...
4 篇 department of au...

作者

13 篇 jerzy baranowski
12 篇 waldemar bauer
8 篇 janusz szpytko
8 篇 rafał stanisławs...
7 篇 aschemann harald
7 篇 marian łukaniszy...
7 篇 krzysztof j. lat...
6 篇 krzysztof gałkow...
6 篇 jarosław figwer
6 篇 wojciech p. hune...
6 篇 baranowski jerzy
6 篇 rauh andreas
6 篇 yang li
6 篇 harald aschemann
5 篇 andreas rauh
5 篇 ignacy duleba
5 篇 szulc katarzyna
5 篇 krzysztof arent
5 篇 krzysztof bartec...
4 篇 rydel marek

语言

1,202 篇 英文
17 篇 其他
7 篇 中文
1 篇 西班牙文

检索条件"任意字段=25th International Conference on Methods and Models in Automation and Robotics"

共 1225 条记录，以下是271-280 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

A Framework for Automatic Identification of Neural Network Structural Redundancy Based on Reinforcement Learning 5

A Framework for Automatic Identification of Neural Network S...

引用

5th international conference on Computer Information Science and Artificial Intelligence, CISAI 2022

作者： Wu, Tingting Song, Chunhe Zeng, Peng State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781510662520

the increasing structure of neural networks makes it difficult to deploy on edge devices with limited computing resources. Network pruning has become one of the most successful model compression methods in recent years. Existing works usually compress models by removing unimportant filters based on the importance. However, the importance-based algorithms tend to ignore the parameters that extract edge features with small criterion values. And recent studies have shown that the existing criteria rely on norm and lead to similar model compression structures. Aiming at the problems of ignoring edge features and manually specifying the pruning rate in current importance-based model pruning algorithms, this paper proposes an automatic recognition framework for neural network structure redundancy based on reinforcement learning. First, we perform cluster analysis on the filters of each layer, and map the filters into a multidimensional space to generate similar sets with different functions. We then propose a criterion for identifying redundant filters within similar sets. Finally, we use reinforcement learning to automatically optimize the cluster dimension, and then determine the optimal pruning rate for each layer to reduce the performance loss caused by pruning. Extensive experiments on various benchmark network architectures and datasets demonstrate the effectiveness of our proposed framework. © 2023 SPIE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of Iterative Learning Control for a subclass of robotic systems with an alternative reference signal setting

Design of Iterative Learning Control for a subclass of robot...

引用

international conference on methods and models in automation and robotics (MMAR)

作者： Łukasz Hładowski Bartłomiej Sulikowski Krzysztof Gałkowski Institute of Control and Computation Engineering University of Zielona Góra Zielona Góra Poland Institute of Automation Electronic and Electrical Engineering University of Zielona Góra Zielona Góra Poland

ISBN: (数字)9798350362343

ISBN: (纸本)9798350362350

In this paper new results on the application of the Iterative Learning Control (ILC) schemes applied to the Gantry robot are presented. the main result given refers to the situation where the reference signal pre-defined for ILC can be extended by some quantity that genuinely does not appear in the model but is important for the practical application of such system. In case of a considered system - the Gantry robot - its original state space model output refers to the robot position that in turn defines the robot’s movement trajectory. For many practically-relevant applications it is enough to define the reference signal for the ILC in terms of this trajectory. this is not always ideal, as for some tasks it is easier (at least in terms of wear of the robot parts) to include additional requirements for the reference signal. the results presented in this paper allow to extend it by an additional factor - which, in this case, is the robot velocity. In what follows the ILC scheme is designed and implemented for such a combined reference signal.

关键词： automation Instruction sets Stability criteria Trajectory Linear matrix inequalities Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

Electromechanical Design and Control Using a Large Language Model

Electromechanical Design and Control Using a Large Language ...

引用

international conference on Control, Mechatronics and automation (ICCMA)

作者： Klison Gashi Marco Chacin Gilbert Tang Centre for Robotics and Assembly Cranfield University UK

ISBN: (数字)9798331517519

ISBN: (纸本)9798331517526

Lately, artificial intelligence (AI) has seen a rapid increase in both adoption and capabilities, with one distinct area of interest being Large Language models (LLM). this article investigates the use of an LLM, OpenAI’s GPT–4o, as a tool for the speed control and design of a DC motor with benchmark results identified for comparison. A prompt engineering approach was used with a trial–and–error by adjusting the prompt to identify the knowledge areas and capabilities of the LLM. As a result, the LLM was able to solve and interpret mathematical equations, methods, symbols and terminologies relating to control engineering, and could design controllers analytically, while struggling with manual and graphical tuning processes.

关键词： Motor drives automation Large language models Frequency-domain analysis Process control Manuals Manipulators Software Iterative methods Tuning

来源：评论

学校读者我要写书评

暂无评论

Time series for rail passengers flow prediction: a survey

Time series for rail passengers flow prediction: a survey

引用

international conference on methods and models in automation and robotics (MMAR)

作者： Maciej Szymkowski Włodzimierz Woźniak Bartosz Jura Faculty of Computer Science Białystok University of Technology Białystok Poland Computer Science Research Group Artificial Intelligence Development division Łukasiewicz Research Network – Poznań Institute of Technology Poznań Poland

ISBN: (数字)9798350362343

ISBN: (纸本)9798350362350

Nowadays, rails are one of the most popular forms of transportation. It is related to the relatively lower costs of the tickets in comparison to airplanes or even costs connected with travelling by car. It needs to be pointed out that this type of transportation has also one important issue that must be addressed. It is connected to the selection of the appropriate train type for all interested passengers. It is extremely hard especially when passengers’ pileups are observed. In this work, we would like to propose an idea to consume time-series data for prediction of the passengers’ flow in one, selected train station that is Łόdź, Poland. Diversified algorithms that can be used directly in these data were presented and our own ideas are given. We would like to also propose our own pipeline built on the basis of all analyzed approaches.

关键词： Rails Surveys Costs Time series analysis Pipelines Transportation Predictive models

来源：评论

学校读者我要写书评

暂无评论

DgrCLR: Dual Gradient Reinforcement Contrastive Learning for Coal Gangue Classification 5

DgrCLR: Dual Gradient Reinforcement Contrastive Learning for...

引用

5th international conference on robotics, Intelligent Control and Artificial Intelligence, RICAI 2023

作者： Li, Hongxi Zhu, Wenbo Zhu, Zhen Yang, Juqing Chen, Jianwen Li, Haibing Zhang, Zhongbo School of Electronic Information Engineering Foshan University Foshan China School of Mechatronic Engineering and Automation Foshan University Foshan China Electronic Information School Foshan Polytechnic Foshan China

ISBN: (纸本)9798350357950

In the application of coal gangue visual classification, the influence of strong vibration and uneven illumination in an industrial environment causes the fuzzy boundary of the target and reduces the degree of discrimination of sample features. the existing contrastive learning methods cause apparent gradient degradation due to model and design limitations, leading to fuzzy sample classification failure. Getting rid of the samples with poor annotation effects and alleviating gradient degradation are critical issues in improving the accuracy of coal gangue classification. this paper proposes DgrCLR, a dual gradient reinforcement coal gangue classification algorithm based on improved contrastive learning. By designing the Hybrid reinforcement module and Multi-scale feature fusion module, the gradient degradation is alleviated, the dependence on labeled samples is reduced, and the detail representation ability of the model is improved. the experimental results show that the highest accuracy of the DgrCLR model for coal gangue classification is 85.4%, much higher than that of traditional supervised deep learning models. In addition, the gradient strength of DgrCLR is 20 times or higher than that of SimCLR in some model layers by gradient strength summation comparison. © 2023 IEEE.

关键词： Coal gangue Contrastive learning Gradient reinforcement Hybrid reconstruction Multi-scale

来源：评论

学校读者我要写书评

暂无评论

Model-Based Covert Cyber-Attack Detection for Cooling System in Data Center

Model-Based Covert Cyber-Attack Detection for Cooling System...

引用

robotics, Control and automation Engineering (RCAE), international conference on

作者： Siyu Huang Chen Ma Yinhao Wang Aibing Qiu Jingfeng Mao School of Electrical Engineering and Automation Nantong University Nantong China Department of Mathematical Sciences Durham University Durham UK

ISBN: (数字)9798350355642

ISBN: (纸本)9798350355659

this paper investigates a model-based covert cyber-attack detection scheme for cooling system in data center. Firstly, a state-space model of cooling system is established based on the operational principles. then, the existence conditions of covert cyber-attack are outlined, i.e., all attacks that satisfy these conditions cannot be detected using conventional schemes. Furthermore, a residual signal at the actuator side is proposed based on the structure of attacked system, which can detect covert cyber-attack effectively. Finally, a simulation of cooling system in data center is carried out to demonstrate the effectiveness and superiority of the proposed scheme.

关键词： Data centers Actuators automation Cooling Data models State-space methods Cyberattack Robots

来源：评论

学校读者我要写书评

暂无评论

Design of Hysteresis Control based Adaptive Sliding Mode Control and Cuckoo Search based PI Control for DC-DC Boost Converters

Design of Hysteresis Control based Adaptive Sliding Mode Con...

引用

international conference on methods and models in automation and robotics (MMAR)

作者： Tamen thapa Sarkar Ashruti Upadhyaya Chitralekha Mahanta Department of EEE IIT Guwahati Assam India

ISBN: (数字)9798350362343

ISBN: (纸本)9798350362350

Due to the underlying complexities and nonlinear behavior of the DC-DC boost converters, its control becomes a difficult operation. the non-minimum phase behavior of the DC-DC boost converters also makes it tough to control. this paper proposes two different techniques based on hysteresis based Adaptive SMC and Cuckoo Search (CS) based Proportional-Integral (PI) control methods for controlling DC-DC boost converters. the two techniques applied in this research are compared in terms of various performance indices such as Integral of Absolute Error (IAE), overshoot, rise time and settling time. the effectiveness of the two proposed controllers are evaluated in relation to changes in input voltage, reference voltage and load. the two proposed methods are also compared against a conventional PID tuned by Internal Model Controller (IMC). the hysteresis control based adaptive sliding mode controller performs better than CS based PI controller and IMC based PID controller with lesser IAE against fluctuations in terms of reference voltage, load, and input voltage.

关键词： Resistance Adaptation models PI control Fluctuations Pulse width modulation PD control Voltage control

来源：评论

学校读者我要写书评

暂无评论

Optimal control and optimum design of elasticity system: Topological derivative method for control problem

Optimal control and optimum design of elasticity system: Top...

引用

international conference on methods and models in automation and robotics (MMAR)

作者： Jan Sokolowski Yixin Tan Systems Research Institute Polish Academy of Sciences Warsaw Poland Institut Élie Cartan de Lorraine CNRS Université de Lorraine Nancy France School of Mathematical Sciences East China Normal University Shanghai China

ISBN: (数字)9798350362343

ISBN: (纸本)9798350362350

We consider a class of boundary dynamic optimal control problems for elasticity systems in the geometric domain. the class of control problems admits the so-called Turnpike Property. the relation of optimal controls for static problems and dynamic problems is investigated. thus, we consider the steady state problem in order to compute the optimal control. the cost is minimized with respect to boundary controls. Meanwhile, the optimal cost of control is minimized with respect to the shape and topology of its domain of integration. the topological optimum design problem is solved by the topological derivative method for the steady-state model. the level set function for the purposes of topology optimization is defined. Numerical results for topology optimization are presented.

关键词： Costs Shape Optimal control Elasticity Topology Steady-state Numerical models

来源：评论

学校读者我要写书评

暂无评论

An Overview of methods of Industrial Anomaly Detection

An Overview of Methods of Industrial Anomaly Detection

引用

robotics, Control and automation Engineering (RCAE), international conference on

作者： Siqi Yang Shu Liu Penghui Shang Hui Wang Zhiyuan Research Institute Hangzhou City China

ISBN: (数字)9798350355642

ISBN: (纸本)9798350355659

Industrial anomaly detection plays a crucial role in modern manufacturing and production processes. In order to help researchers and professionals in the manufacturing industry understand the developing research results in this field, this paper begins with an introduction of common methods of industrial anomaly detection such as neural networks, GAN, transformer with discussing the limitations in this domain. Subsequently, owing to the emergence of the fourth wave of artificial intelligence, Advanced anomaly detection techniques based on Large Language models (LLMs) and variants are explored, including AnomalyGPT, VisionGPT and LLMAD which have influenced a lot as the cutting-edge technologies. Additionally, based on the current developing trends of the LLMs-based method, this paper analyzes challenges and deficiencies existing in practice which have the potential to lead the way in future research. Conclusively, this overview exposes the bottleneck of traditional methods and emphasizes the revolutionary impact LLMs could have on multimodal scenes of anomaly detection while putting insight into the extend of methodical practicability.

关键词： Manufacturing industries Service robots Large language models Neural networks Production Transformers Market research Generative adversarial networks Manufacturing Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

ARSFineTune: On-the-Fly Tuning of Vision models for Unmanned Ground Vehicles 20

ARSFineTune: On-the-Fly Tuning of Vision Models for Unmanned...

引用

20th Annual international conference on Distributed Computing in Smart Sensor Systems and the Internet of things (DCOSS-IoT)

作者： Ahmed, Masud Hasan, Zahid Faridee, Abu Zaher Md Anwar, Mohammad Saeid Jayarajah, Kasthuri Purushotham, Sanjay You, Suya Roy, Nirmalya Univ Maryland Baltimore Cty Baltimore MD 21228 USA New Jersey Inst Technol Newark NJ USA DEVCOM Army Res Lab Adelphi MD USA

ISBN: (纸本)9798350369458;9798350369441

the performance of semantic segmentation (SS) can degrade when the data distribution in the deployed environment is different from what the model initially learned during their training. While domain adaptation (DA) and continual learning (CL) methods have been proposed to improve performance in new or unseen domains over time, the effort required for annotating large swathes of training data during deployment is non-trivial;acquiring new data for training incurs both significant network, device memory costs, and manual effort for labeling. To address this, we propose ARSFineTune, a novel framework that actively selects the most informative regions of visuals encountered by a mobile robot for the CL network to learn from, greatly minimizing the data transfer overhead related to annotations. We first propose a proficient entropy-driven ranking mechanism to identify candidate regions and rank challenging images at the edge node. We then facilitate a cyclical feedback loop between the server and edge, continuously refining the accuracy of semantic segmentation by fine-tuning the model with minimal transferred data to/from the field deployed device. We implement ARSFineTune in a real-time setting using the robotics Operating System (ROS), where a Jackal (an unmanned ground vehicle - UGV) collaborates with the central server. through extensive experiments, we found that ARSFineTune delivers competitive performance, closely aligning with existing state-of-the-art techniques, while requiring substantially less data for fine-tuning. Specifically, with only 5% of the total labeled regions (25% challenging regions of the most 20% problematic samples) of the entire dataset for fine-tuning, ARSFineTune reaches a performance level nearly identical (approximate to 97%) to the previous state-of-the-art model, boasting mIoU scores of 59.5% on the Cityscape dataset and 41% on the CAD-EdgeTune dataset, which is a challenging dataset due to varying lighting conditions over time. the r

关键词： Active learning continual learning semantic segmentation Robot Operating System (ROS)

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共123页 << < 24 25 26 27 28 29 30 31 32 33 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：