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

2,963 篇 会议
163 篇 期刊文献
64 册 图书
6 篇 学位论文

馆藏范围

3,196 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,849 篇 工学
- 998 篇 计算机科学与技术...
- 543 篇 电气工程
- 543 篇 软件工程
- 454 篇 信息与通信工程
- 264 篇 光学工程
- 232 篇 电子科学与技术（可...
- 194 篇 仪器科学与技术
- 157 篇 生物医学工程（可授...
- 154 篇 控制科学与工程
- 145 篇 材料科学与工程（可...
- 109 篇 机械工程
- 92 篇 生物工程
- 49 篇 化学工程与技术
- 40 篇 测绘科学与技术
- 38 篇 动力工程及工程热...
- 38 篇 航空宇航科学与技...
- 31 篇 交通运输工程
- 30 篇 安全科学与工程
1,307 篇 理学
- 1,072 篇 物理学
- 242 篇 数学
- 107 篇 生物学
- 59 篇 化学
- 48 篇 系统科学
- 48 篇 统计学（可授理学、...
310 篇 医学
- 236 篇 临床医学
- 78 篇 特种医学
- 49 篇 基础医学(可授医学...
226 篇 管理学
- 150 篇 管理科学与工程(可...
- 88 篇 图书情报与档案管...
- 55 篇 工商管理
21 篇 法学
19 篇 经济学
16 篇 农学
11 篇 教育学
10 篇 军事学
3 篇 文学

主题

263 篇 image processing
257 篇 signal processin...
130 篇 signal processin...
107 篇 image segmentati...
106 篇 optical sensors
105 篇 real-time system...
94 篇 optical devices
94 篇 cameras
86 篇 sensors
76 篇 optical imaging
71 篇 data processing
71 篇 feature extracti...
70 篇 field programmab...
68 篇 accuracy
67 篇 internet of thin...
67 篇 detection and tr...
65 篇 optical signal p...
64 篇 digital signal p...
62 篇 neural networks
60 篇 optical filters

机构

11 篇 yonsei univ ctr ...
10 篇 yonsei univ dept...
7 篇 school of electr...
5 篇 yonsei univ cisd
5 篇 school of electr...
5 篇 univ calif san d...
5 篇 school of inform...
5 篇 state key labora...
5 篇 college of physi...
4 篇 school of inform...
4 篇 department of in...
4 篇 school of optica...
4 篇 state key labora...
4 篇 maharishi school...
4 篇 key laboratory o...
4 篇 stanford univ gi...
4 篇 samara national ...
4 篇 canadian space a...
4 篇 school of inform...
4 篇 mpb communicatio...

作者

16 篇 park no-cheol
14 篇 park young-pil
12 篇 park kyoung-su
11 篇 javidi b
8 篇 n.a. riza
7 篇 beyette fr
7 篇 song myeong-gyu
6 篇 kim choong
6 篇 zhaohui li
6 篇 fainman y.
5 篇 li peng
5 篇 nelson bn
5 篇 shastri bhavin j...
5 篇 li zheng yuan
5 篇 koo ja choon
5 篇 prucnal paul r.
5 篇 yang hyunseok
5 篇 nomura t
5 篇 huang hk
4 篇 minho lee

语言

3,118 篇 英文
39 篇 其他
38 篇 中文
2 篇 俄文
2 篇 土耳其文

检索条件"任意字段=Conference on Algorithms, Devices, and Systems for Optical Information Processing"

共 3196 条记录，以下是71-80 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：

Estimating the Feasibility of Images Simulation in Unity 3D for Sub-Pixel processing algorithms

Estimating the Feasibility of Images Simulation in Unity 3D ...

引用

2023 Wave Electronics and its Application in information and Telecommunication systems, WECONF 2023

作者： Sivov, N. Yu. Shmatko, E.V. Poroykov, A. Yu. National Research University MPEI Department of Physics Named after V.A. Fabrikant Moscow Russia

ISBN: (纸本)9798350348293

Computer image simulation is used in the development of optical measurement systems and processing algorithms. It allows the performance of a system or algorithm to be verified and its measurement uncertainty to be assessed. Modern algorithms make it possible to achieve sub-pixel accuracy in digital image processing. An example of such algorithms is the cross-correlation processing in Particle Image Velocimetry. Often, standard graphics engines such as Unity 3D and Unreal Engine are used to simulate the images. The purpose of this work is to evaluate the possibility of using these tools to generate images for further processing by subpixel resolution algorithms. This paper presents the results of a computational experiment to estimate the maximum spatial resolution for simulations in Unity 3D. A qualitative and quantitative analysis of the results confirms the possibility of using the tested graphics engine for the analysis of subpixel resolution algorithms for digital image processing. © 2023 IEEE.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Speech Command Recognition Algorithm Based on Improved MFCC Features

Speech Command Recognition Algorithm Based on Improved MFCC...

引用

International conference on Communications, Signal processing, and systems, CSPS 2023

作者： Song, Ziyi Ma, Lin School of Electronics and Information Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819975396

In recent years, deploying low-power speech recognition algorithms on resource-constrained hardware devices has become a research focus. However, traditional algorithms rely on extensive data and complex models, which pose challenges for low-power devices with limited resources. This paper proposes an improved MFCC feature extraction method combined with the DTW algorithm, which enhances computational speed and reduces resource consumption in speech recognition. Experimental results validate the effectiveness and feasibility of the proposed method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense 37

Fed-FA: Theoretically Modeling Client Data Divergence for Fe...

引用

37th conference on Neural information processing systems (NeurIPS)

作者： Zhang, Zhiyuan Chen, Deli Zhou, Hao Meng, Fandong Zhou, Jie Sun, Xu Peking Univ Sch Comp Sci Natl Key Lab Multimedia Informat Proc Beijing Peoples R China Tencent Inc WeChat AI Pattern Recognit Ctr Beijing Peoples R China

ISBN: (纸本)9781713899921

Federated learning algorithms enable neural network models to be trained across multiple decentralized edge devices without sharing private data. However, they are susceptible to backdoor attacks launched by malicious clients. Existing robust federated aggregation algorithms heuristically detect and exclude suspicious clients based on their parameter distances, but they are ineffective on Natural Language processing (NLP) tasks. The main reason is that, although text backdoor patterns are obvious at the underlying dataset level, they are usually hidden at the parameter level, since injecting backdoors into texts with discrete feature space has less impact on the statistics of the model parameters. To settle this issue, we propose to identify backdoor clients by explicitly modeling the data divergence among clients in federated NLP systems. Through theoretical analysis, we derive the f-divergence indicator to estimate the client data divergence with aggregation updates and Hessians. Furthermore, we devise a dataset synthesization method with a Hessian reassignment mechanism guided by the diffusion theory to address the key challenge of inaccessible datasets in calculating clients' data Hessians. We then present the novel Federated F-Divergence-Based Aggregation (Fed-FA) algorithm, which leverages the f-divergence indicator to detect and discard suspicious clients. Extensive empirical results show that Fed-FA outperforms all the parameter distance-based methods in defending against backdoor attacks among various natural language backdoor attack scenarios.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Morphological processing Algorithm of Blood Image 25

Fuzzy Morphological Processing Algorithm of Blood Image

引用

25th IEEE International conference of Young Professionals in Electron devices and Materials, EDM 2024

作者： Turgunov, Abrorjon M. Narzullaev, Temur N. Matyakubov, Marks Ya. Payzieva, Munira T. Kamolova, Sevara J. Rakhmonova, Nilufar N. Department of Algorithms and Mathematical Modeling Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Tashkent Uzbekistan Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Tashkent Uzbekistan

ISBN: (纸本)9798350389234

This article, a morphological image processing algorithm is developed for early detection of viral hepatitis from microscopic blood images. It is mentioned that it can be used to accurately determine each boundary detail in the fuzzy morphological processing of the gray image of the blood image. Boundary detection leads to higher recognition results in neural network training. Compared to the work of a number of scholars, our method offers such performance, but it offers improved dynamics and flexibility in the formulation of linguistic boundary criteria, which can be a leading factor in the design of image processing systems with dynamic and flexible rules, such as Type 2 allows fuzzy rules, which offers an interesting alternative to currently common deep learning applications. The validated experimental results show the reliability of the modified method compared to the Chaira method. Mean, entropy and standard deviation were calculated. It turned out to be higher than the values of the Chaira method. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of Application-Level Load Balancing algorithms

Analysis of Application-Level Load Balancing Algorithms

引用

2023 systems of Signals Generating and processing in the Field of on Board Communications, SOSG 2023

作者： Sukhoplyuev, D.I. Nazarov, A.N. Mirea Russian Technology University Institute of Information Technology Moscow Russia

ISBN: (纸本)9798350397727

The present article examines the application-level load balancing strategies employed in the microservice architecture of IoT servers, which use wireless communication protocols like Wi-Fi to exchange radio signals among IoT devices. Load balancing at the application level is a crucial task, add to address it, a hypothesis is proposed. To evaluate the effectiveness of various load balancing algorithms, mathematical models based on queuing theory are developed for four algorithms: Round Robin, Weighted Round Robin, Least Connection, and search of the optimal vector. A numerical analysis is conducted to compare the performance of these algorithms. The results confirm the aforementioned hypothesis, and highlight the need to develop a load balancing algorithm that can account for error coefficients arising from distinct services. © 2023 IEEE.

关键词： Numerical analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Improved TDOA Algorithm for Shallow Water Underwater Positioning 16

Research on Improved TDOA Algorithm for Shallow Water Underw...

引用

16th International conference on Signal processing systems, ICSPS 2024

作者： Shen, Biyue Rong, Shaowei Ji, Lingxian Wu, Kaiyuan Li, Jiaju Deng, Xiangyu Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Faculty of Artificial Intelligence Industry Kunming University of Science and Technology Kunming650500 China

ISBN: (纸本)9781510689251

Accurate positioning in shallow water regions is crucial for various underwater applications. TDOA algorithms estimate the signal source location by measuring the time differences of signal arrival at multiple receivers. However, these methods often suffer from Non-Line-of-Sight (NLOS) errors and noise, leading to reduced positioning accuracy in shallow water environments. This research proposes an improved TDOA estimation algorithm that utilizes cross-correlation techniques to mitigate NLOS errors and combines the strengths of the Chan and Taylor algorithms to enhance positioning precision. The proposed algorithm addresses challenges such as time ambiguity and alpha-stable noise, offering advantages in TDOA modeling for underwater positioning. Implementation details are provided, including the design of matching basis functions, time delay matching procedures, algorithm flow, and computational steps. Simulation tests validate the effectiveness of the algorithm, demonstrating significant improvements in positioning accuracy. The computational complexity is also analyzed to assess the algorithm's practicality. Finally, the research findings are summarized, and directions for future work are discussed. © 2025 SPIE.

关键词： Time difference of arrival

来源：评论

学校读者我要写书评

暂无评论

Learning Optimal Edge processing with Offloading and Energy Harvesting 23

Learning Optimal Edge Processing with Offloading and Energy ...

引用

26th ACM International conference on Modelling, Analysis, and Simulation of Wireless and Mobile systems (MSWiM)

作者： Fox, Andrea De Pellegrini, Francesco Altman, Eitan Univ Avignon Lab Informat Avignon LIA Avignon France Univ Cote Azur INRIA Ctr Inria Sophia Antipolis France

ISBN: (纸本)9798400703669

Modern portable devices can execute increasingly sophisticated AI models on sensed data. The complexity of such processing tasks is data-dependent and has relevant energy cost. This work develops an Age of information markovian model for a system where multiple battery-operated devices perform data processing and energy harvesting in parallel. Part of their computational burden is offloaded to an edge server which polls devices at given rate. The structural properties of an optimal policy for a single device-server system are derived. They permit to define a new model-free reinforcement learning method specialized for monotone policies, namely Ordered Q-Learning, providing a fast procedure to learn the optimal policy. The method is oblivious to the devices' battery capacities, the cost and the value of data batch processing and to the dynamics of the energy harvesting process. Finally, the polling strategy of the server is optimized by combining this policy improvement technique with stochastic approximation methods. Extensive numerical results provide insight into the system properties and demonstrate that the proposed learning algorithms outperform existing baselines.

关键词： AoI Energy-Harvesting Offloading MDP Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Microbial Growth Monitoring: A Parallel OD600 Detection System Based on Artificial Intelligence 2

Intelligent Microbial Growth Monitoring: A Parallel OD600 De...

引用

2nd International conference on Machine Vision, Image processing and Imaging Technology, MVIPIT 2024

作者： Xu, Libing Ren, Fei Doma, Bonifacio T. Nanjing SuperKong Electronics Co. Ltd. Nan Jing China School of Information Technology Mapua University Philippines School of Graduate Studies Manila Philippines

ISBN: (纸本)9798331543037

Microbial OD600 measurement is a crucial experimental technique in microbiological and molecular biological research, evaluating microbial growth by measuring optical density at 600 nm wavelength. While convenient, this method has limitations. For instance, different microbial species and growth stages may absorb light differently, potentially leading to biases when measuring multiple strains simultaneously. This paper presents an innovative parallel OD600 detection system capable of simultaneously monitoring growth curves of multiple microbial strains. Our research integrates advanced optical systems, precise mechanical control, and artificial intelligence algorithms, not only improving the accuracy and efficiency of bacterial growth measurements but also achieving parallel processing and analysis of multiple samples. We discuss in detail the hardware design, software architecture, and core algorithms, with particular emphasis on the application of machine learning in multi-strain data analysis and prediction. Experimental results demonstrate that this system significantly outperforms traditional methods in measurement accuracy, automation level, multi-sample processing capability, and data analysis. ©2024 IEEE.

关键词： Bacteria

来源：评论

学校读者我要写书评

暂无评论

Vehicle Number Plate Recognition And information Access System

Vehicle Number Plate Recognition And Information Access Syst...

引用

2024 International conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Mane, Pradeep B. Patil, Varsha Kiran Paithankar, Mayur R. Kotgire, Mallikarjun M. Shah, Samveg S. Dept. Electronics and Telecommunication AISSMS Institute of Information Technology Pune India

ISBN: (纸本)9798350355338

Addressing the growing challenges posed by increasing vehicles and stringent traffic violations, many vehicle number plates go undetected while passing through toll booths and traffic lights. Thus it creates the need for a vehicle number plate recognition system. Existing systems employing ANPR algorithms utilize MATLAB and K-Nearest neighbour algorithms for image processing. Drawbacks include limitations in adapting to dynamic environments, Real time recognition, handling multiple vehicles, slow processing speeds, incapability of multiple object detection in single frame. The paper focuses on Automatic Number Plate Recognition (ANPR), employing specialized cameras and advanced image processing and using YOLOv8 for object detection and extracting license plate information from video feeds using EasyOCR. The noisy data generated during character recognition is filtered out using Regex based algorithm. The system integrates with centralized databases for real-time vehicle information access for users. The same database is used to automate e-challan updation, contributing to traffic management by swiftly issuing fines for rule violations. The proposed video-based processing system achieves number plate detection using YOLOv8 and storage of vehicle number plates in a centralized MongoDB database with an accuracy achieved of 96% in license plate detection and reduces noisy data using algorithm. It also enables real-time data retrieval through a user interface using Reactjs as frontend and is also connected to the MongoDB database for precise and user-friendly access in modern traffic systems. © 2024 IEEE.

关键词： optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Memory in Motion: Exploring Leaky Integration of Time Surfaces for Event-based Eye-tracking

Memory in Motion: Exploring Leaky Integration of Time Surfac...

引用

2024 Biomedical Circuits and systems conference

作者： Boretti, Chiara Bich, Philippe Prono, Luciano Pareschi, Fabio Royatti, Riccardo Setti, Gianluca Politecn Torino DET Turin Italy Politecnico Torino PiC4SeR Turin Italy Univ Bologna DEI Bologna Italy Univ Bologna ARCiS Bologna Italy KAUST CEMSE Thuwal Saudi Arabia

ISBN: (纸本)9798350354966;9798350354959

Augmented and Virtual Reality (AR/VR) technologies are gaining popularity to improve healthcare professionals training, with precise eye tracking playing a crucial role in enhancing performance. However, these systems need to be both low-latency and low-power to operate in real-time scenarios on resource-constrained devices. Event-based cameras can be employed to address these requirements, as they offer energy-efficient, high temporal resolution data with minimal battery drain. However, their sparse data format necessitates specialized processing algorithms. In this work, we propose a data pre-processing technique that improves the performance of nonrecurrent Deep Neural Networks (DNNs) for pupil position estimation. With this approach, we integrate over time - with a leakage factor - multiple time surfaces of events, so that the input data is enriched with information from past events. Additionally, in order to better distinguish between recent and old information, we generate multiple memory channels characterized by different leakage/forgetting rates. These memory channels are fed to well-known non-recurrent neural estimators to predict the position of the pupil. As an example, by using time surfaces only and feeding them to a MobileNet-V3L model to track the pupil in DVS recordings, we achieve a P10 accuracy (Euclidean error lower than ten pixels) of 85.40%, whether by using memory channels we achieve a P10 accuracy of 94.37% with a negligible time overhead.

关键词： information leakage

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320页 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：