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

7,609 篇 会议
317 篇 期刊文献
4 册 图书
2 篇 学位论文

馆藏范围

7,932 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,293 篇 工学
- 2,970 篇 计算机科学与技术...
- 1,616 篇 软件工程
- 1,522 篇 电气工程
- 851 篇 信息与通信工程
- 664 篇 控制科学与工程
- 597 篇 电子科学与技术（可...
- 323 篇 仪器科学与技术
- 302 篇 机械工程
- 178 篇 动力工程及工程热...
- 170 篇 生物医学工程（可授...
- 166 篇 交通运输工程
- 154 篇 生物工程
- 151 篇 光学工程
- 139 篇 安全科学与工程
- 100 篇 材料科学与工程（可...
- 83 篇 建筑学
- 79 篇 土木工程
- 78 篇 测绘科学与技术
- 77 篇 化学工程与技术
1,079 篇 理学
- 423 篇 数学
- 392 篇 物理学
- 169 篇 生物学
- 133 篇 系统科学
- 96 篇 统计学（可授理学、...
- 81 篇 化学
627 篇 管理学
- 554 篇 管理科学与工程(可...
- 258 篇 工商管理
- 103 篇 图书情报与档案管...
173 篇 医学
- 149 篇 临床医学
- 93 篇 基础医学(可授医学...
72 篇 法学
65 篇 经济学
51 篇 农学
27 篇 军事学
21 篇 教育学
5 篇 文学
4 篇 艺术学

主题

868 篇 real time system...
769 篇 real-time system...
513 篇 embedded systems
490 篇 hardware
444 篇 embedded system
398 篇 application soft...
391 篇 computer archite...
258 篇 computational mo...
240 篇 timing
225 篇 processor schedu...
205 篇 monitoring
180 篇 resource managem...
177 篇 quality of servi...
165 篇 wireless sensor ...
164 篇 energy consumpti...
164 篇 costs
160 篇 control systems
159 篇 operating system...
148 篇 bandwidth
144 篇 computer science

机构

28 篇 eindhoven univer...
22 篇 beijing key labo...
21 篇 eindhoven univer...
20 篇 beijing key labo...
18 篇 university of te...
17 篇 beijing inst tec...
17 篇 karlsruhe instit...
15 篇 school of electr...
14 篇 karlsruhe instit...
14 篇 college of compu...
13 篇 department of co...
11 篇 department of co...
11 篇 delft university...
11 篇 university of ch...
10 篇 school of comput...
10 篇 computer enginee...
10 篇 department of co...
10 篇 hong kong univer...
9 篇 department of el...
9 篇 tsinghua univers...

作者

24 篇 jian-jia chen
24 篇 tei-wei kuo
17 篇 kees goossens
15 篇 zhuang yin
14 篇 benny akesson
13 篇 saniie jafar
13 篇 jafar saniie
12 篇 obermaisser roma...
12 篇 benini luca
12 篇 chen liang
11 篇 sikora axel
10 篇 twan basten
10 篇 chao wang
10 篇 dip goswami
10 篇 shangping ren
10 篇 jörg henkel
10 篇 kuo tei-wei
10 篇 roman obermaisse...
10 篇 zonghua gu
10 篇 zebo peng

语言

7,720 篇 英文
156 篇 其他
55 篇 中文
1 篇 德文
1 篇 葡萄牙文

检索条件"任意字段=IEEE Symposium on Real-Time and Embedded Technology and Applications"

共 7932 条记录，以下是561-570 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 Robust and real-time Hyper-Spectral Sensor-Fusion Model for Concrete Crack Segmentation

A Robust and Real-Time Hyper-Spectral Sensor-Fusion Model fo...

引用

ieee Sensors applications symposium, SAS

作者： Matthias Steiner Nicolas Baumann Luzian Lebovitz Michele Magno Department of Information Technology and Electrical Engineering ETH Zurich Zürich Switzerland

Structural defects in civil infrastructure, such as highways, roads, bridges, and dams, can severely impact their reliability and safety. Manual inspection of such infrastructure is labor-intensive and costly, creating the demand for automated damage-tracking systems. Data-driven techniques, such as machine learning, and statistical methods have been utilized in a remarkable number of Structural Health Monitoring (SHM) applications. However, real-time and high-accuracy concrete crack detection poses severe challenges for deployment on embedded systems and mobile robotic platforms, due to their computational constraints, low-latency requirements, and the robustness of model predictions in field deployments. This work proposes a robust and low-latency transformer-based deep-crack segmentation model that leverages both Red Green Blue (RGB) and Hyper Spectral (HYP) data for crack detection. The model is optimized for deployment on resource-constrained embedded systems, enabling structural health monitoring on robotic platforms, and studies the aleatoric and epistemic uncertainties of the estimated crack maps. The final model is deployed on one of the most popular robotic embedded computation platforms such as the NVIDIA Jetson Xavier NX, achieving state-of-the-art performance with an accuracy of 99.54% at an inference time of only 7.41ms using the RGB camera only. The proposed approach provides a promising solution for automating laborious SHM applications such as inspecting critical infrastructure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QAVIS technology: MEASURING WAVE PROCESSES IN COASTAL ZONES BASED ON THE ANALYSIS OF INTERNET VIDEO BROADCAST

QAVIS TECHNOLOGY: MEASURING WAVE PROCESSES IN COASTAL ZONES ...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Fischenko, V. Mitnik, L. Dolgikh, G. Goncharova, A. Zimin, P. Klescheva, N. Golik, A. VI Ilichev Pacific Oceanol Inst FEB RAS Vladivostok Russia Far Eastern Fed Univ Vladivostok Russia

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

This paper discusses the possibility of the new QAVIS software technology to measure or estimate wind wave and swell signals in the coastal zones of the oceans. The developed technology is based on the analysis of video streams from coastal Internet cameras. QAVIS processes data from screen graphic memory. This allows processing streaming video in real-time indefinitely. The QAVIS accuracy of wave processes measurements inferior to that of professional oceanographic instruments, but is sufficient for many applications. A brief description of the technology is presented, and examples of the analysis of synchronous continuous 34-day observations of wind waves and swell in the United States, Mexico, and Costa Rica coastal zones are given. The QAVIS-derived results are compared with satellite SAR images and seismic data.

关键词： coastal video monitoring image and video processing wind waves swell SAR microseisms

来源：评论

学校读者我要写书评

暂无评论

real-time LiDAR module with 64x128-pixel CMOS SPAD array and 940-nm PCSEL 17

Real-time LiDAR module with 64x128-pixel CMOS SPAD array and...

引用

17th ieee Sensors applications symposium (SAS)

作者： Hsiao, An-Tai Liu, Chun-Hsien Chen, Po-Hsuan Liu, Yao-Lun Wang, Wei-Chi Sang, Tzu-Hsien Tsai, Chia-Ming Lin, Gray Guo, Jiun-In Lin, Sheng-Di Natl Yang Ming Chiao Tung Univ Inst Elect 1001 Univ Rd Hsinchu 30010 Taiwan

ISBN: (数字)9781665409810

ISBN: (纸本)9781665409810

High-performance light detection and ranging (LiDAR) modules are highly demanded for advanced driving assistance system and autonomous driving. The high power level of emitter required for long-distance ranging is one of the key issues to be addressed to realize commercially affordable vehicle LiDAR. In this work, for the first time, we demonstrate a low-cost real-time LiDAR module by using CMOS-fabricated 64x128-pixel single-photon avalanche diode (SPAD) array, a 940-nm photonic-crystal surface-emitting laser (PCSEL), and a FPGA card for control and signal processing. Thanks to the high-sensitivity of SPAD and small divergence angle of PCSEL, a 60-m 3-D imager has been realized with a low laser peak power of similar to 0.5 W. The ranging distance and frame rate are 60 m and 10 frames per second, respectively, for the target reflectivity of 10% - 90% and the sunlight condition of 0 - 50k lux. Our work reveals the great potential of these two intriguing devices for making low-cost high-performance vehicle LiDARs.

关键词： Single-photon avalanche diodes photonic-crystal surface-emitting laser LiDAR CMOS technology

来源：评论

学校读者我要写书评

暂无评论

CoVIO: Online Continual Learning for Visual-Inertial Odometry

CoVIO: Online Continual Learning for Visual-Inertial Odometr...

引用

2023 ieee/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Vödisch, Niclas Cattaneo, Daniele Burgard, Wolfram Valada, Abhinav University of Freiburg Germany University of Technology Nuremberg Germany

ISBN: (纸本)9798350302493

Visual odometry is a fundamental task for many applications on mobile devices and robotic platforms. Since such applications are oftentimes not limited to predefined target domains and learning-based vision systems are known to generalize poorly to unseen environments, methods for continual adaptation during inference time are of significant interest. In this work, we introduce CoVIO for online continual learning of visual-inertial odometry. CoVIO effectively adapts to new domains while mitigating catastrophic forgetting by exploiting experience replay. In particular, we propose a novel sampling strategy to maximize image diversity in a fixed-size replay buffer that targets the limited storage capacity of embedded devices. We further provide an asynchronous version that decouples the odometry estimation from the network weight update step enabling continuous inference in real time. We extensively evaluate CoVIO on various real-world datasets demonstrating that it successfully adapts to new domains while outperforming previous methods. The code of our work is publicly available at http://***. © 2023 ieee.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A novel fire monitoring system for electric bicycle shed based on YOLOv8

A novel fire monitoring system for electric bicycle shed bas...

引用

ieee International symposium on embedded Multicore Socs (MCSoC)

作者： Hongyang Zhong Ziwen Wang Zhiyi Chen Wenhao Chen Yujie Li Guilin University of Electronic Technology Guilin China School of Artificial Intelligence Guangxi Colleges and Universities Key Laboratory of AI Algorithm Engineering Guilin University of Electronic Technology Guilin China

With the increasing popularity of electric bicycles, safety concerns regarding electric bicycle sheds have garnered public attention. In order to protect people’s life and property safety, an accurate and real-time fire monitoring system for electric bicycle shed is crucial. We proposed a YOLOv8 based fire monitoring system for electric bicycle shed. The system can be conveniently deployed on various end devices, computers, and IoT terminals. The proposed system uses deep learning technology to offer round-the-clock real-time monitoring, early fire detection, and automatic alarm triggering capabilities. The experimental results demonstrated that the proposed system can successfully monitor fire for electric bicycle. It is highly practical and can be widely used for fire monitoring and other similar applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Significance of Edge AI towards real-time and Intelligent Enterprises

The Significance of Edge AI towards Real-time and Intelligen...

引用

2023 ieee International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2023

作者： Surianarayanan, Chellammal Raj, Pethuru Niranjan, S.K. Bharathidasan University Centre for Distance and Online Education Tamilnadu Tiruchirappalli India Reliance Jio Platforms Ltd. Bangalore560103 India JSS Science and Technology University Mysuru India

ISBN: (纸本)9781665462631

Edge AI is a next-generation paradigm for crafting and running scores of real-time and rewarding applications and services for businesses and people. Edge AI is the powerful combination of two hugely popular domains of edge computing and artificial intelligence. Edge AI represents advanced version of edge analytics. With the consistent surge in AI models being produced through the training of AI algorithms (machine and deep learning) on datasets (training, validation and testing) for automating and accelerating a variety of business and people-centric tasks, the AI domain is being seen as a paradigm shift by IT pundits and business executives across the world. With the accumulation of IoT edge devices in our everyday environments (homes, hotels, hospitals, etc.), the computing, which generally happens in nearby and faraway cloud server clusters, moves over to IoT edge devices, which are called as networked embedded systems. This fusion of AI and edge computing is being proclaimed as the most promising and potential venture in the ensuing knowledge era. In this paper, we are to discuss the power of edge AI in setting up and sustaining real-time and intelligent enterprises, which are capable of bringing delights to their customers, partners, suppliers, resellers, and employees. Especially worldwide enterprises can elegantly envisage and experiment a brew of fresh possibilities and opportunities. © 2023 ieee.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Federated Learning for real-time applications in Edge Networks 17

Communication-Efficient Federated Learning for Real-time App...

引用

17th ieee International Conference on Advanced Networks and Telecommunications Systems, ANTS 2023

作者： Singh, Neha Tripathi, Tanmay Adhikari, Mainak Iiit Lucknow Computer Science Lucknow226002 India Manipal University Jaipur Information Technology Jaipur303007 India

ISBN: (纸本)9798350307672

In recent times, Federated Learning (FL) has played a vital role in real-time applications by collaboratively learning a shared model across massive end devices without exchanging local data. However, most of the existing FL frameworks suffered from high transmission time and communication overhead due to the frequent exchange of the model parameters to the centralized cloud server. To overcome the communication overhead, in the paper, we propose a new hierarchical FL framework in edge networks, namely FedLocal by integrating synchronous edge-fog model aggregation and asynchronous fog-cloud model aggregation. Synchronous edge-fog model aggregation in distributed fog devices reduces transmission time. Further, we adopt a self-knowledge distillation technique for synchronous FL strategy by enabling edge devices to transfer knowledge from older local models to more recent personalized models. Additionally, the asynchronous fog-cloud model aggregation in the centralized cloud server improves the efficiency of the proposed FL frame-work by distributing the overall global parameters to the local edge devices for better decision-making. Extensive simulation results over the water irrigation testbed on the paddy field demonstrate the efficiency of the proposed FedLocal strategy over the existing ones. © 2023 ieee.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Augmented reality for Quality Inspection: A User-Centred Systematic Review of Use Cases, Trends and technology

Augmented Reality for Quality Inspection: A User-Centred Sys...

引用

2023 ieee International symposium on Mixed and Augmented reality Adjunct, ISMAR-Adjunct 2023

作者： Albers, Alexander Bohné, Thomas Tadeja, Slawomir Konrad University of Cambridge United Kingdom Karlsruhe Institute of Technology Germany

ISBN: (纸本)9798350328912

Augmented reality (AR)-based quality inspection (QI) has the potential to aid operators in industry by providing additional information and real-time feedback on their actions. To realise the full potential of AR, users must be considered in the design of applications because their perception and behaviour influence the effectiveness of an AR-based quality inspection system. However, how the design of AR experiences affects the performance of QI remains under-explored. To address this research gap, we conducted a systematic literature review, considered 27 use cases, and investigated how QI-related challenges have been addressed from the user's perspective. We identified six tasks that tend to benefit from AR and mapped common user interface (UI) elements and interaction modalities. Furthermore, we observed concepts that address design challenges, such as visibility and obstructions of physical and digital objects. However, we also found that current systems lack a focus on ergonomics and safety requirements. © 2023 ieee.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Efficient Skeleton-Based Action Recognition for real-time embedded Systems

Efficient Skeleton-Based Action Recognition for Real-Time Em...

引用

ieee Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Nadhira Noor Fabianaugie Jametoni Jinbeom Kim Hyunsu Hong In Kyu Park Dept. of Electrical and Computer Engineering Inha University Incheon Korea Finedigital Inc Korea

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Action recognition is vital for various real-world applications, yet its implementation on embedded systems or edge devices faces challenges due to limited computing and memory resources. Our goal is to facilitate lightweight action recognition on embedded systems by utilizing skeleton-based techniques, which naturally require less computing and memory resources. To achieve this, we propose innovative methodologies and optimizations tailored for embedded deployment, including post-training quantization, optimized model architectures, and efficient resource utilization. By enabling real-time and lightweight action recognition on resource-constrained embedded systems, our research opens up new possibilities for applications in areas like autonomous surveillance, driving, and indoor safety monitoring.

关键词： embedded systems Accuracy Quantization (signal) Surveillance Memory management Network architecture real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Distributed TSN time Synchronization Algorithm with Increased Tolerance for Failure Scenarios 9

A Distributed TSN Time Synchronization Algorithm with Increa...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Peng, Yifei Wu, Xinlin Tu, Xiaodong Jiang, Tigang Xu, Du Xie, Jun University of Electronic Science & Technology of China School of Information and Communication Engineering Chengdu China

ISBN: (纸本)9798350317251

The integration of Industrial Internet of Things (IIoT) and time-Sensitive Networking (TSN) enables efficient and reliable real-time communication and control. Currently, one of the current research hotspots in the field of TSN is the improvement of reliability in the use of ieee 802.1AS(ieee Standard for Local and metropolitan area networks - Timing and Synchronization for time-Sensitive applications). On one hand, ieee 802.1AS does not provide specific steps for constructing redundant clock trees, and on the other hand, it cannot detect error time values caused by the failure propagation of devices on the clock tree. To address these issues, this paper proposes a Distributed time synchronization strategy based on ieee 802.1AS(DAS). DAS utilizes a broadcast-based message exchange, and each endpoint device calculates its own synchronized time using fault-tolerant time synchronization methods. Furthermore, the time information is no longer embedded in data packets, avoiding the impact of erroneous time values on the time synchronization of other devices. Extensive simulations and on-board verifications are conducted on the DAS algorithm in this paper. The results show that the DAS algorithm can tolerate more failure scenarios while maintaining similar time synchronization accuracy compared to ieee 802.1AS. Although the DAS algorithm consumes more bandwidth, this overhead is acceptable in small-scale networks. As far as we know, our work is the first in the industry to simultaneously achieve compatibility with existing 802.1AS and distributed TSN time synchronization, and to physically implement it in switch. © 2023 ieee.

关键词： ieee Standards

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 << < 53 54 55 56 57 58 59 60 61 62 > >>

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：