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

24,537 篇 会议
162 篇 期刊文献
56 册 图书
1 篇 学位论文
1 篇 科技报告

馆藏范围

24,757 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,118 篇 工学
- 6,328 篇 控制科学与工程
- 4,098 篇 计算机科学与技术...
- 2,652 篇 软件工程
- 2,145 篇 电气工程
- 1,863 篇 机械工程
- 1,144 篇 仪器科学与技术
- 735 篇 信息与通信工程
- 587 篇 生物工程
- 473 篇 生物医学工程（可授...
- 426 篇 光学工程
- 402 篇 力学（可授工学、理...
- 388 篇 电子科学与技术（可...
- 262 篇 化学工程与技术
- 250 篇 材料科学与工程（可...
- 250 篇 交通运输工程
- 244 篇 动力工程及工程热...
- 214 篇 土木工程
- 202 篇 建筑学
- 181 篇 安全科学与工程
3,068 篇 理学
- 1,763 篇 数学
- 903 篇 物理学
- 643 篇 生物学
- 582 篇 统计学（可授理学、...
- 482 篇 系统科学
- 229 篇 化学
1,223 篇 管理学
- 958 篇 管理科学与工程(可...
- 310 篇 工商管理
- 306 篇 图书情报与档案管...
328 篇 医学
- 287 篇 临床医学
- 205 篇 基础医学(可授医学...
122 篇 经济学
106 篇 法学
87 篇 农学
53 篇 教育学
27 篇 文学
16 篇 军事学
13 篇 艺术学
1 篇 哲学

主题

2,475 篇 predictive model...
1,994 篇 robots
1,825 篇 robotics and aut...
1,735 篇 computational mo...
1,713 篇 automation
1,645 篇 data models
1,581 篇 robot sensing sy...
1,488 篇 analytical model...
1,401 篇 adaptation model...
1,379 篇 training
1,164 篇 accuracy
1,141 篇 mathematical mod...
1,099 篇 trajectory
1,046 篇 mobile robots
914 篇 feature extracti...
840 篇 robustness
838 篇 robot kinematics
793 篇 control systems
718 篇 solid modeling
700 篇 uncertainty

机构

179 篇 university of ch...
143 篇 school of artifi...
111 篇 robotics institu...
87 篇 school of automa...
84 篇 institute of aut...
72 篇 shenyang institu...
70 篇 institutes for r...
68 篇 the robotics ins...
68 篇 school of electr...
63 篇 state key labora...
61 篇 school of mechat...
49 篇 department of au...
49 篇 department of au...
48 篇 state key labora...
46 篇 school of automa...
44 篇 school of mechan...
42 篇 robotics institu...
39 篇 school of automa...
32 篇 school of automa...
29 篇 carnegie mellon ...

作者

37 篇 secchi cristian
34 篇 yuechao wang
32 篇 yun-hui liu
31 篇 cristian secchi
29 篇 shugen ma
28 篇 lining sun
24 篇 xiang li
22 篇 jian wang
22 篇 jianda han
22 篇 fabio ramos
20 篇 xinyu wu
20 篇 wu xinyu
20 篇 daniela rus
19 篇 tomizuka masayos...
19 篇 wei li
19 篇 levine sergey
18 篇 c. laugier
18 篇 jie zhao
18 篇 chen chen
18 篇 dinesh manocha

语言

24,428 篇 英文
245 篇 其他
92 篇 中文
2 篇 西班牙文
1 篇 俄文

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

共 24757 条记录，以下是4701-4710 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：

Residual Denoising Diffusion models

Residual Denoising Diffusion Models

引用

conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jiawei Liu Qiang Wang Huijie Fan Yinong Wang Yandong Tang Liangqiong Qu State Key Laboratory of Robotics Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Science Institutes for Robotics and Intelligent Manufacturing University of Chinese Academy of Sciences Shenyang University The University of Hong Kong

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

We propose residual denoising diffusion models (RDDM), a novel dual diffusion process that decouples the traditional single denoising diffusion process into residual diffusion and noise diffusion. This dual diffusion framework expands the denoising-based diffusion models, initially uninterpretable for image restoration, into a unified and interpretable model for both image generation and restoration by introducing residuals. Specifically, our residual diffusion represents directional diffusion from the target image to the degraded input image and explicitly guides the reverse generation process for image restoration, while noise diffusion represents random perturbations in the diffusion process. The residual prioritizes certainty, while the noise emphasizes diversity, enabling RDDM to effectively unify tasks with varying certainty or diversity requirements, such as image generation and restoration. We demonstrate that our sampling process is consistent with that of DDPM and DDIM through coefficient transformation, and propose a partially path-independent generation process to better understand the reverse process. Notably, our RDDM enables a generic UNet, trained with only an L1 loss and a batch size of 1, to compete with state-of-the-art image restoration methods. We provide code and pre-trained models to encourage further exploration, application, and development of our innovative framework (https://***/nachifurlRDDM).

关键词： Schedules Computer vision Image synthesis Perturbation methods Noise reduction Noise Diffusion processes

来源：评论

学校读者我要写书评

暂无评论

A simple data augmentation method for automatic modulation recognition via mixing signals

A simple data augmentation method for automatic modulation r...

引用

robotics, Intelligent Control and Artificial Intelligence (RICAI), international conference on

作者： Weiguo Shen Dongwei Xu Xinjie Xu Zhuangzhi Chen Qi Xuan Wei Wang Yun Lin Xiaoniu Yang The National Key Laboratory of Electromagnetic Space Security Jiaxing China The Binjiang Artificial Intelligence Institute of ZJUT Zhejiang University of Technology Hangzhou China The Binjiang Artificial Intelligence Institute of ZJUT Harbin Engineering University Harbin China The National Key Laboratory of Electromagnetic Space Security Zhejiang University of Technology Hangzhou China

ISBN: (数字)9798331541699

ISBN: (纸本)9798331541705

Automatic Modulation Recognition(AMR) is crucial in cognitive radio, transitioning from traditional methods to deep learning-based classification. However, deep learning requires large datasets for effective training, making data augmentation vital for enhancing model generalization and accuracy. It helps to expand the dataset, thereby improving the models’ generalization ability and accuracy. We proposes a novel data augmentation approach for AMR task based on signal mixing, with four specific methods designed to improve the performance of Mixed Signals. The experimental results demonstrate that the proposed methods lead to a notable improvement in the classification accuracy of deep learning-based AMR models in diverse scenarios. Notably, experiments conducted with datasets at a single signal-to-noise ratio show a significant increase in classification accuracy, confirming the effectiveness of the signal mixing method.

关键词： Deep learning Training Solid modeling Accuracy Modulation Data augmentation Data models Robustness Robots Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Sim2Real Bilevel Adaptation for Object Surface Classification using Vision-Based Tactile Sensors

Sim2Real Bilevel Adaptation for Object Surface Classificatio...

引用

IEEE international conference on robotics and automation (ICRA)

作者： Gabriele M. Caddeo Andrea Maracani Paolo Didier Alfano Nicola A. Piga Lorenzo Rosasco Lorenzo Natale Humanoid Sensing and Perception Istituto Italiano di Tecnologia Genoa Italy DIBRIS Universitá di Genova Genoa Italy MaLGa Center DIBRIS Universitá di Genova Genoa Italy IIT@MIT Istituto Italiano di Tecnologia Genoa Italy

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In this paper, we address the Sim2Real gap in the field of vision-based tactile sensors for classifying object surfaces. We train a Diffusion Model to bridge this gap using a relatively small dataset of real-world images randomly collected from unlabeled everyday objects via the DIGIT sensor. Subsequently, we employ a simulator to generate images by uniformly sampling the surface of objects from the YCB Model Set. These simulated images are then translated into the real domain using the Diffusion Model and automatically labeled to train a classifier. During this training, we further align features of the two domains using an adversarial procedure. Our evaluation is conducted on a dataset of tactile images obtained from a set of ten 3D-printed YCB objects. The results reveal a total accuracy of 81.9%, a significant improvement compared to the 34.7% achieved by the classifier trained solely on simulated images. This demonstrates the effectiveness of our approach. We further validate our approach using the classifier on a 6D object pose estimation task from tactile data.

关键词： Training Bridges Accuracy Pose estimation Tactile sensors Manuals Diffusion models

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Control for a Flexible Joint Manipulator and Its Verification

Reinforcement Learning Control for a Flexible Joint Manipula...

引用

IEEE international conference on Mechatronics, robotics and automation (ICMRA)

作者： HeJia Gao ChuanFeng He JuQi Hu Yi Tong Wu School of Artificial Intelligence Anhui University Hefei China

ISBN: (数字)9798350307535

ISBN: (纸本)9798350307542

1 Flexible Joint Manipulator (FJM) is a system that can control its joints with high precision. This paper proposes a reinforcement learning (RL) method to control the FJM and achieve output constraint. The RL method can learn from the feedback of the system and adjust the control parameters accordingly. The paper also proves the stability of the system by using Lyapunov stability analysis. Finally, we verify the superiority of RL control method by comparative simulation.

关键词： Uncertainty Mechatronics Trajectory tracking Collaboration Reinforcement learning Manipulators Control systems Stability analysis Robustness Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Proposed Technique for Data Security with the AES Algorithm in Robot Operating System (ROS) 27

Proposed Technique for Data Security with the AES Algorithm ...

引用

27th international Computer Science and Engineering conference, ICSEC 2023

作者： Tanadechopon, Teerapong Kasemsontitum, Boontariga Institute of Field Robotics King Mongkut's Institute of Technology Thonburi Bangkok Thailand

ISBN: (纸本)9798350342109

Currently, the Robot Operating System (ROS), is extensively used in various fields such as education, research, commercial and industry. This is due to the fact that ROS offers a range of packages that handle communication and hardware operation. However, it is widely known that ROS's security is still not robust. Transitioning from ROS to ROS2, which has enhanced security, might be somewhat challenging because some tasks might be in actual use in the industry or ongoing research projects. The issue of data security is also of paramount importance. There are currently various methods to hack into systems or intercept data in computer networks. After studying numerous related research works, we propose an encryption method for transmitted and received data using the AES algorithm, known as Layer-2. This method has been experimented with streaming images of four resolutions: 320× 240, 640× 480, 1280× 720, and 1920× 1080. By comparing the frame rate and CPU usage during both unencrypted and encrypted streaming, it was found that the software developed according to the concept of this research can stream in an encrypted format at the same frame rate as unencrypted streaming, with an average maximum increase in CPU usage of 19.98% on the publishing side. The encryption concept in this research is designed based on a text-based protocol combined with the function overloading feature of object-oriented programming. This allows for a quick add-on to operating ROS software with minimal modifications. Furthermore, it can be adapted for use with other data transmission methods, such as Publish/Subscribe models like NATS, MQTT, etc. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Deflection Correction and End-Point Control of Heavy-Duty Vertical Single-Link Flexible Manipulators

Deep Learning-Based Deflection Correction and End-Point Cont...

引用

IEEE international conference on robotics and Biomimetics

作者： Amir Hossein Barjini Sadeq Yaqubi S. Mohammad Tahamipour-Z Jouni Mattila Department of Automation Technology and Mechanical Engineering Tampere University Finland

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Flexible link manipulators (FLM) have gained significant importance due to their applications in lightweight robots, energy-efficient systems, and humanoid robots. In this paper, we propose a novel approach to modeling and controlling a single-link flexible manipulator (SLFM). First, a Vertical Single-Link Manipulator (VSLFM) is modeled, taking gravity effects into account, using the Hamilton principle. Data on the link's properties, payload mass, and target angle are used as features to predict the deflection as output, based on numerical analysis of partial differential equation model. For the first time, a Deep Neural Network (DNN) is proposed and trained offline to predict the static deflection of the payload in a set of VSLFMs, using the data obtained from the numerical analysis. Utilizing the predicted deflection, a modified PID controller is developed to control the arc position of the payload. This controller does not require deflection feedback, making it ideal for industrial applications with limited sensors. The method is experimentally validated using an SLFM, which is validated based on a ground truth system consisting of inertial measurement unit-based sensor network.

关键词： Technological innovation Numerical analysis Artificial neural networks Mathematical models Energy efficiency Sensors Numerical models Manipulator dynamics Payloads Gravity

来源：评论

学校读者我要写书评

暂无评论

Galaxy Morphology Semantic Segmentation Based on K-Net

Galaxy Morphology Semantic Segmentation Based on K-Net

引用

robotics, Intelligent Control and Artificial Intelligence (RICAI), international conference on

作者： Tengyu Li Tao Hu Dashu Zhang Songtian Yu Wentao Li School of Mechatronic Engineering and Automation Shanghai University Shanghai China

ISBN: (数字)9798331541699

ISBN: (纸本)9798331541705

At present, modern large-scale astronomical observation equipment can collect a large number of high-resolution images. Astronomy has entered the era of big data. Deep learning has shown great potential in astronomical image analysis due to its powerful feature extraction and segmentation capabilities. In the study of galaxy evolution, image segmentation can separate different parts of galaxies, help identify the types of galaxies and analyze structural details, which is crucial to understanding the formation and evolution of galaxies. Therefore, this paper proposes a galaxy morphology segmentation method based on K-Net. The experimental data comes from the Galaxy Zoo project, and the model is trained using strategies such as transfer learning. The trained model can be used to segment four common galaxy images. The experimental results show that the overall accuracy reaches 97.11%, and the mean intersection over union is also 80.87%, indicating that the model performs well in the segmentation of astronomical images. The mean accuracy and the mean dice coefficient are both higher than 87%, indicating that the model is stable in distinguishing different categories. Therefore, K-Net has great application potential in astronomical image segmentation tasks.

关键词： Training Adaptation models Accuracy Spirals Semantic segmentation Transfer learning Morphology Stars Training data Data models

来源：评论

学校读者我要写书评

暂无评论

Automated Production Allocation & Deferment Calculation Using Integrated Digital Oil Field Realtime Surveillance Data and Physics Based Well-models

Automated Production Allocation & Deferment Calculation Usin...

引用

2024 Abu Dhabi international Petroleum Exhibition and conference, ADIPEC 2024

作者： Al Jabri, Kawthe Al Hinai, Ahme More, Anand Raosahe Kumar, Nitis Kumar, Suresh ARA EP Petroleum Oman Weatherford International United States

ISBN: (纸本)9781959025498

Objectives/Scope: Automate Production Allocation and Deferment calculation workflow using Integrated Digital Oil Field (DOF) realtime surveillance data and physics based well models benefitting ARA Petroleum's Production Optimization team by improving Field Allocation factor, improving DOF system performance, reduce production losses caused due to delayed & errored manual calculations processes and integration of this data with Business Intelligence (BI) and cross domain applications. Achieve complete digital transformation of the process. methods, Procedures, Process: DOF team developed physics-based models for all wells (ESP, PCP and Naturally flowing types) using PVT, Completion, Artificial lift system data and integrated these models with DOF Real time data (RTD) for automatic estimation of Well rates. Using Well Management System (WMS) and Real time data of custody transfer meter, calculation of Field factors was automated to generate Allocated rates automatically. The process was coupled with daily well flowing hours to estimate deferment production due to well downtime, trips. This daily automatic workflow task is scheduled on Production server for faster and accurate data generation of daily and average allocated rates. This paper describes in detail the workflow used for implementation of the process. Results, Observations, Conclusions: Since implementation of the Automatic Allocation and Deferment workflow, it has maintained daily and average allocated rates for 80+ ESP, PCP and Naturally flowing wells in the field. Application of the workflow has resulted in improved ability to track production with targets. Corrected Allocated rates w.r.t optimized well parameters is an added advantage of this workflow rather than using constant rates between two valid well-tests which was an outdated traditional approach. This allocated rates data has helped ARA petroleum engineers to accurately;compare production with target plan, optimize well/reservoir performance, p

关键词： Proven reserves

来源：评论

学校读者我要写书评

暂无评论

A Deterministic Path Planning Algorithm with Greedy Heuristics for Mobile Robots

A Deterministic Path Planning Algorithm with Greedy Heuristi...

引用

international conference on Autonomous Robots and Agents, ICARA

作者： Liu Zhenqi Su Rong Yao Jiarong School of Electrical and Electronic Engineering Nanyang Technological University Singapore

ISBN: (数字)9798350394245

ISBN: (纸本)9798350394252

This paper proposes a novel global path planning algorithm for mobile robots. The path extends with samples taken under a greedy heuristic strategy so that samples close to the goal are prioritized. Inspired by graph-searching algorithms, it employs a vertex evaluation scheme to navigate around the obstacles. To remove redundant paths, a rewiring mechanism is proposed to fine-tune the planned path. Numerical simulation is conducted in $\mathbb{R}^{2}$ with different obstacle distributions. The proposed algorithm finds better paths with less computation cost than reference sampling-based planners. Compared with the optimality-guaranteed graph-search methods, the proposed algorithm is more robust against obstacle density while ensuring a solution quality close to the global optimum.

关键词： Costs automation Navigation Heuristic algorithms Numerical simulation Path planning Robustness

来源：评论

学校读者我要写书评

暂无评论

Improving Hazy Image Recognition by Unsupervised Domain Adaptation

Improving Hazy Image Recognition by Unsupervised Domain Adap...

引用

international conference on Control, automation, robotics and Vision (ICARCV)

作者： Zhiyu Yuan Yuhang Li Jianfei Yang Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor School of Electrical and Electronic Engineering Nanyang Technological University

ISBN: (纸本)9781665476881

Deep learning has achieved excellent performance in computer vision tasks, like image recognition, natural language processing, etc. However, in real-world applications, special circumstances brought about by the external world may create domain bias caused by distribution discrepancy between training and testing data, leading to degrading model performance. For example, when auto-driving meets hazy weather, the model performance will drop significantly. In this paper, we explore to solve this problem by utilizing modern Domain Adaptation (DA) methods, which generalizes from the source domain to the target domain by minimizing the distribution difference caused by dataset bias. We firstly propose the cross-domain haze image datasets and benchmark the five classic DA methods. The experiments show that DA methods can mitigate the negative effect of haze and significantly improves the model performance for visual recognition.

关键词： Training Deep learning Adaptation models Visualization Image recognition Computational modeling Benchmark testing

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500页 << < 467 468 469 470 471 472 473 474 475 476 > >>

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：