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

6,133 篇 会议
65 篇 期刊文献
51 册 图书
1 篇 学位论文

馆藏范围

6,250 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,641 篇 工学
- 2,559 篇 计算机科学与技术...
- 1,814 篇 软件工程
- 1,429 篇 信息与通信工程
- 993 篇 电气工程
- 436 篇 控制科学与工程
- 404 篇 电子科学与技术（可...
- 371 篇 光学工程
- 349 篇 生物工程
- 289 篇 生物医学工程（可授...
- 287 篇 仪器科学与技术
- 235 篇 机械工程
- 149 篇 安全科学与工程
- 139 篇 交通运输工程
- 117 篇 化学工程与技术
- 107 篇 材料科学与工程（可...
- 104 篇 网络空间安全
- 101 篇 动力工程及工程热...
- 84 篇 建筑学
1,499 篇 理学
- 697 篇 数学
- 545 篇 物理学
- 375 篇 生物学
- 232 篇 系统科学
- 218 篇 统计学（可授理学、...
- 118 篇 化学
542 篇 管理学
- 327 篇 管理科学与工程(可...
- 259 篇 图书情报与档案管...
- 129 篇 工商管理
348 篇 医学
- 327 篇 临床医学
- 164 篇 基础医学(可授医学...
- 110 篇 药学(可授医学、理...
99 篇 法学
62 篇 农学
49 篇 经济学
40 篇 教育学
27 篇 军事学
16 篇 文学
5 篇 艺术学

主题

328 篇 feature extracti...
310 篇 internet of thin...
267 篇 real-time system...
196 篇 internet
189 篇 image segmentati...
172 篇 signal processin...
167 篇 image processing
159 篇 accuracy
151 篇 deep learning
146 篇 image edge detec...
140 篇 signal processin...
130 篇 cameras
128 篇 image coding
128 篇 training
117 篇 image color anal...
112 篇 visualization
106 篇 image retrieval
102 篇 computational mo...
99 篇 robustness
91 篇 psnr

机构

11 篇 school of comput...
9 篇 faculty of infor...
8 篇 school of cyber ...
8 篇 school of electr...
8 篇 beijing universi...
8 篇 state key labora...
7 篇 school of inform...
7 篇 school of inform...
7 篇 college of elect...
7 篇 institute of sig...
7 篇 harbin institute...
7 篇 college of infor...
7 篇 school of electr...
6 篇 university of sc...
6 篇 school of inform...
6 篇 school of electr...
6 篇 chaoyang univ te...
6 篇 university of el...
6 篇 wuhan university...
6 篇 department of in...

作者

13 篇 yoshitaka sakura...
13 篇 tsuruta setsuo
13 篇 sakurai yoshitak...
13 篇 fan zhun
12 篇 setsuo tsuruta
11 篇 li li
11 篇 wang wei
10 篇 yetongnon kokou
9 篇 dipanda albert
9 篇 zhang yan
9 篇 lee chin-feng
8 篇 zhang lei
8 篇 jing wang
8 篇 wang hao
7 篇 zhu guijie
7 篇 kinshuk
7 篇 jeon gwanggil
7 篇 ahmad tohari
7 篇 shen jau-ji
7 篇 wang xin

语言

5,527 篇 英文
703 篇 其他
41 篇 中文
1 篇 土耳其文

检索条件"任意字段=International Conference on Signal-Image Technology and Internet-Based Systems"

共 6250 条记录，以下是911-920 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：

Research on Fish Body Color Recognition based on Multi-object Segmentation 7

Research on Fish Body Color Recognition Based on Multi-objec...

引用

7th international conference on Vision, image and signal Processing, ICVISP 2023

作者： Li, Beibei Liu, Yiran Li, Wensheng Duan, Qingling National Innovation Center for Digital Fishery China Agricultural University Beijing100083 China Key Laboratory of Agricultural Information Acquisition Ministry of Agriculture China Agricultural University Beijing100083 China Beijing Engineering and Technology Research Center for Internet of Things in Agriculture China Agricultural University Beijing100083 China College of Information and Electrical Engineering China Agricultural University Beijing100083 China Laizhou Mingbo Aquatic Products Co. Ltd Shandong261418 China College of Information and Electrical Engineering Yantai Research Institute of China Agricultural University Shandong264670 China

ISBN: (纸本)9781839539848

The recognition of fish body color is of important research significance for the realization of healthy breeding, coloring breeding, and quality grading of aquatic products. The accurate multi-object segmentation is the basis of fish body color recognition, but this is challenging because the fish and background are so similar. To solve the above problems, we propose a fish body color recognition method based on multi-object segmentation. Firstly, convert the collected fish image into color space, separate saturation components and extract mixed-saturation components. Secondly, the central cross(CC) filter and the high-low-double-filter algorithm(HL-DF) are used to realize multi-object segmentation. Finally, the body color recognition matrix is constructed based on the mapping relationship between the fish body color and the color threshold in the HSV color space to recognize the fish body color. We applied Cyprinidae fishes as the experimental object and conducted experiments on real datasets. The results show that the recognition accuracy is 99.78%, the recall is 99.56%, the Fl-score is 99.56% and the precision is 99.57%. The performance of fish body color recognition is better compared with methods such as AlexNet, ShuffleNet V2, and KNN, with significant advantages. © The Institution of Engineering & technology 2023.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Low-Latency Channel Estimation for mmWave Massive MIMO-OFDM systems based on Beam-Delay Domain Pattern 23

Low-Latency Channel Estimation for mmWave Massive MIMO-OFDM ...

引用

23rd IEEE international conference on Communication technology, ICCT 2023

作者： Qiu, Zhikai Zhu, Pengcheng Li, Jiamin Jiang, Yanxiang Wang, Yan Southeast University National Mobile Communications Research Laboratory Nanjing210096 China

ISBN: (纸本)9798350325959

The sixth-generation (6G) wireless network aims to facilitate multi-connectivity, ultra-reliable and low-latency communications, while millimeter-wave (mmWave) massive multiple-input multiple-output (massive MIMO) communication is a promising technology as it exploits vast available mm Wave bandwidth. Most of the existing mm Wave channel estimation schemes are designed for narrowband systems or exhibit limited performance as they independently estimate the channel at different frequencies. This paper investigated a low-latency scheme for channel estimation in mmWave massive MIMO-OFDM systems, utilizing the beam-delay domain pattern. We first explore the sparse 2-Dimensional (2D) pattern of mmWave beam-delay domain channel and formulate the problem as 2 phases: spatial-frequency domain channel observation and sparse channel recovery. The latest sparse signal recovery method is referenced and we adapt it to the Beam-Delay Channel Estimation (BDCE) algorithm in the beam-delay domain for sparse channel estimation. Simulation results demonstrate that the proposed BDCE algorithm achieves superior accuracy and reduces channel estimation latency compared with traditional estimation algorithms. © 2023 IEEE.

关键词： beam-delay domain pattern channel estimation low-latency massive MIMO-OFDM mmWave

来源：评论

学校读者我要写书评

暂无评论

Research of Gesture Recognition Algorithm based on Acceleration Trajectory image 2

Research of Gesture Recognition Algorithm Based on Accelerat...

引用

2nd international conference on Networking systems of AI, INSAI 2022

作者： Zhu, Yaling Zheng, Gang Li, Xiangwei College of Software Engineering Lanzhou Institute of Technology GanSu Lanzhou China

ISBN: (纸本)9781665491785

According to the characteristics of neural network computing, this paper designs a neural network based on acceleration for gesture detection. First, the acceleration information is collected by using the acceleration sensor to extract the key point information, and convert the effective data into the acceleration track image data. Two neural networks with depth distribution of 50 and 101 are built and trained by ResNet algorithm. Matching image data features to obtain models with accuracy rates of 85% and 91% respectively, so as to achieve higher gesture recognition accuracy with less computational time and storage space complexity. © 2022 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

A Lightweight image Dehazing Algorithm based on Deep Learning 2

A Lightweight Image Dehazing Algorithm Based on Deep Learnin...

引用

2nd international conference on Robotics, Artificial Intelligence and Intelligent Control, RAIIC 2023

作者： Zhang, Jiashuo Chen, Chunmei Liu, Guihua Pang, Zhongxiang Xiang, Pingping Pu, Wei Swust School of Information Engineering Mianyang China

ISBN: (纸本)9798350328004

The dehazing algorithm based on deep learning has good performance. However, this way has some problems such as high computational complexity and long latency time still exist, making it difficult to apply in real-time systems. To address this issue, this paper proposes a lightweight network called zUNet based on UNet. Firstly, a lightweight convolution module is designed to obtain redundant feature maps through low-cost computation. Then, the channel attention mechanism is used to extract global features. Replace The convolution modules in UNet are replaced with gate mechanism residual blocks to dynamically fuse feature maps. Finally, the proposed zUNet algorithm is compared with mainstream algorithms such as FFA-Net on the SOTS-IN and SOTS-OUT datasets. The results show that the peak signal-to-noise ratio (PSNR) of zUNet reaches an average of 37.38 dB, which is the best among all the evaluated algorithms. The number of parameters (Param) are 0.552M, the multiply- accumulate operations (MACs) are 1.933G, and the latency time is 6.031ms, at least 42%, 90%, and 39% lower, respectively. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

An Online Approach to Balancing the Energy Consumption for IoT Sensors in UAV-based MEC systems 16

An Online Approach to Balancing the Energy Consumption for I...

引用

16th international conference on Wireless Communications and signal Processing, WCSP 2024

作者： Li, Yang Lin, Xiaohui Bi, Suzhi Dai, Mingjun Su, Gongchao College of Electronics and Information Engineering Shenzhen University Shenzhen China School of Computer Science Kashi University Kashi China

ISBN: (纸本)9798350390643

In this paper, we consider an unmanned aerial vehicle-enabled (UAV-enabled) Mobile Edge Computing (MEC) internet of Things (IoT) system consisting of multiple energy harvesting devices. In the system, the UAV acts as the edge computing platform providing computation service to the devices. We assume that the energy and sensing data arrive at the devices stochastically. As the amount of energy harvested by devices can differ significantly, we attempt to balance the energy consumption among devices thus avoiding the loss of devices due to the depletion of the battery energy. To ensure energy fairness, we employ an a-utility function, which incorporates the device's remaining energy and energy expenditure. Without any future knowledge of the data and energy arrivals, our objective is to design an online algorithm to jointly optimize the long-term system throughput and utility, while satisfying the stability requirement of the data queue. We formulate the problem as multi-stage stochastic programming that involves functions of time averages and propose an online algorithm based on the perturbed Lyapunov optimization technique. Due to the time-coupling of different variables, we first transform the original problem into a multi-stage stochastic optimization problem involving only time averages. Then, we utilize the Lyapunov optimization method to decouple the transformed problem into a series of per-slot deterministic subproblems. In each slot, we alternatively optimize the auxiliary variables, the data sensing rate, the computation offloading, the communication resource allocation, and the trajectory of the UAV. Simulation results show that the online algorithm can maintain the stability of the data queue. Additionally, we observe a tradeoff between the system's lifetime and throughput when adjusting the parameter α, as well as a tradeoff between throughput and delay for the Lyapunov method. © 2024 IEEE.

关键词： Stochastic programming

来源：评论

学校读者我要写书评

暂无评论

Achieving Effective Artifact Subspace Reconstruction in EEG Using Real-Time Video-based Artifact Identification

Achieving Effective Artifact Subspace Reconstruction in EEG ...

引用

2023 IEEE international conference on systems, Man, and Cybernetics, SMC 2023

作者： Kang, Sunghyun Won, Kyungho Kim, Heegyu Baek, Jihoon Ahn, Minkyu Jun, Sung Chan Gwangju Korea Republic of School of Computer Science and Electrical Engineering Handong Global University Pohang Korea Republic of Gwangju Korea Republic of

ISBN: (纸本)9798350337020

Identifying and minimizing physiological artifacts in EEG is challenging because these artifacts may corrupt the underlying brain activity severely. In this work, we proposed a hybrid approach to detect/reduce EEG artifacts by combining the MediaPipe face mesh model and artifact subspace reconstruction (ASR). Four types of artifacts, eye blinking, horizontal/vertical eye movements, and jaw movement during EEG measurement were generated to test our approach. We observed that real-time video-based artifact identification achieved over 95% accuracy in detecting eye blinking, horizontal eye movement, and jaw movement. Moreover, the targeted noise reduction was effective in analyzing the signal-to-noise ratio (SNR) for each specific artifact. This work may contribute to improving the reliability and accuracy of EEG data analysis in the real-world and online scenarios by providing a practical and effective approach to identifying and reducing physiological artifacts in real-time. © 2023 IEEE.

关键词： artifact detection artifacts electroencephalography (EEG) image processing

来源：评论

学校读者我要写书评

暂无评论

SAMRec: Self-Attention based Multimodal Recommendation 8

SAMRec: Self-Attention Based Multimodal Recommendation

引用

8th IEEE international conference on Vision, image and signal Processing, ICVISP 2024

作者： Zhao, Yiming Mei, Jia Wang, Mingjie Zhang, Chuanzhi Gu, Yajie Wang, Jun School of information Science and Technology Yunnan Normal University Kunming China Ministry of Education Yunnan Normal University Key Laboratory of Educational Informatization for Nationalities Kunming China Yunnan Normal University Faculty of Education Key Laboratory of Educational Informatization for Nationalities Ministry of Education Kunming China

ISBN: (纸本)9798331541460

With the development of multimedia platforms, traditional recommendation systems that rely on historical user-item interactions are no longer sufficient for most platforms' demand for precise recommendations, as they fail to leverage item modality information. Multimodal recommendation is a method that combines historical user-item interaction data with multimodal item information to better capture user preferences. Existing multimodal recommendation methods often treat item modality information in a simplistic manner, typically using pretrained models to extract features, without deeply exploring the relationships between various modality information. To address this issue, we propose a multimodal recommendation model based on the self-attention mechanism, which effectively captures the global relationships among the multiple item modality features that users have interacted with, thereby more accurately modeling user preferences. Additionally, to prevent the loss of relatively important information when using the self-attention mechanism, we incorporate skip connect to linearly combine the original modality features, ensuring that all critical information is retained while improving the global feature representation. The experimental results show that the self-attention mechanism greatly improves the model's capacity to better capture user preferences, resulting in increased recommendation accuracy. We evaluate the suggested model on three publicly available datasets. © 2024 IEEE.

关键词： multimodal recommendation systems self-attention

来源：评论

学校读者我要写书评

暂无评论

Sports Training 3D Human Motion Simulation and Video Analysis based on Fish Swarm Algorithm

Sports Training 3D Human Motion Simulation and Video Analysi...

引用

2023 international conference on Networking, Informatics and Computing, ICNETIC 2023

作者： Zhang, Mengjie Xi'an Academy of Fine Arts Sports Ministry Xi'an710065 China

ISBN: (纸本)9798350313314

Computer vision is an important branch of computer science and artificial intelligence. The main content of its research is how to use a variety of imaging systems instead of visual organs as signal input means, by the computer to complete the processing and interpretation of information instead of the brain. That is, from the traditional method mainly based on human eye observation to the human motion measurement method based on high precision video capture and analysis, from the experience-based training analysis method to the human motion analysis method based on human motion simulation change. With the maturity and popularization of motion capture technology, it has become a reality to acquire a large number of 3d motion data sets efficiently and quickly. Digital graphics and image technology are introduced into sports training, and a 3d human motion simulation and video analysis system for sports training is developed. It has become an important development direction of sports teaching to conduct standardized guidance and scientific teaching for sports participants through sports video. The ultimate research goal of computer vision is to enable computers to observe and understand the world through vision as humans do. Among them, the realization of key frame extraction, automatic recognition and classification of 3D human motion data is an important research content of human motion analysis, and an important premise and basis for the effective management and reuse of motion capture data. © 2023 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

An image-based Fall Detection System for the Elderly using YOLOv5 2

An Image-based Fall Detection System for the Elderly using Y...

引用

2nd international conference on Automation, Computing and Renewable systems, ICACRS 2023

作者： Marshal, S. Raj, Samson Arun Jebaseeli, T. Jemima Niranjan, S. CSE Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798350340235

A system's capacity to identify whether a person has fallen is known as fall detection. People who fall have difficulty moving their muscles. Even without injuries, the elderly people are too exhausted to stand up. Currently, there is an increasing amount of focus on the protection of old people living alone. The fall detection system using wearable gadgets and environmental monitoring devices has been introduced. Yet, there are certain problems, such as high invasion, poor accuracy, and weak resilience, due to the usage of the internet of Things and early fall detection warnings. Elderly people frequently need assistance getting up after falling, and if that assistance is delayed, the consequences of falling could be highly serious. Despite extensive studies on the subject conducted over the past few years, creating non-invasive technologies for automatic fall detection that are trustworthy and acceptable to the people being monitored remains difficult. The geriatric population has continued to increase as a result of medical technological advancements. Because falls can result in fractures and have catastrophic repercussions have received a lot of attention. Therefore, it is crucial for both older individuals and those who care for them to identify fall accidents quickly. Some of the fall detection scenarios are people who are irresponsible and stumble, those who are afflicted with ailments like heart attacks or strokes, children playing on the ground, and senior citizens. © 2023 IEEE.

关键词： Convolutional Neural Network deep learning elderly fall detection image processing

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based IoT Device Authentication and Cost-Effective Key Management Framework 2

Blockchain-Based IoT Device Authentication and Cost-Effectiv...

引用

2nd IEEE international conference on Innovations in High-Speed Communication and signal Processing, IHCSP 2024

作者： Manoharan, Geetha Venugopal, B. Kunnathully, Kannan Suribabu, Potnuri Tiwari, Mohit Roy, Vandana Sr University School of Business Telangana Warangal India Indian Institute of Plantation Management Bengaluru Jnana Bharathi Campus Malathalli Bengaluru India Veltech School of law India Jntua University Kmm Engineering College AP Tirupati India Bharati Vidyapeeth's College of Engineering Cse Department Delhi A-4 Rohtak Road Delhi Paschim Vihar India Gyan Ganga Institue of Technology and Sciences Department of Electronics Communication M.P. Jabalpur India

ISBN: (纸本)9798350368949

IoT is seen as an exciting innovation that might start an entirely novel industrial revolution. A collection of internet-connected devices. An unavoidable and pervasive framework is still an open problem in IoT research for embedded devices, neural networks, machine learning, and other widespread and universal systems. IoT systems rely on sensors and controllers. IoT uses millions of sensors to gather and share outside information with the public internet. Many applications analyze and evaluate diverse data collected from devices. Those compact devices for sensors have limited processing power. Security is crucial for precise data flow between verified users, which becomes more complicated in a network of IoT devices. IoT's decentralized architecture design faces security concerns include privacy, reliability, security, anonymity, and device-user trust. Due to limited resources in sensor devices, typical cryptographic techniques for identification and organizational management of keys are not suitable for IoT systems. Effective protection against electronic card theft, session data publication, external attack, passwords guessing, user sensing simulation, and anonymity for users is provided by the suggested technique. Because it meets all security criteria, the updated protocol offers better security. The simplest protocol that can survive all known attacks and provide the essential security is the suggested one. With a 99% success rate and superior performance across all measures, the findings show that the suggested blockchain technology IoT identification framework is the way to go. © 2024 IEEE.

关键词： cryptographic internet of Things networks privacy protocol security sensors

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 << < 88 89 90 91 92 93 94 95 96 97 > >>

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：