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

6,452 篇 会议
925 篇 期刊文献
2 篇 学位论文
1 册 图书

馆藏范围

7,380 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,162 篇 工学
- 1,138 篇 电气工程
- 909 篇 计算机科学与技术...
- 678 篇 信息与通信工程
- 263 篇 控制科学与工程
- 193 篇 仪器科学与技术
- 160 篇 机械工程
- 160 篇 软件工程
- 119 篇 电子科学与技术（可...
- 107 篇 生物医学工程（可授...
- 98 篇 交通运输工程
- 83 篇 测绘科学与技术
- 81 篇 航空宇航科学与技...
- 30 篇 土木工程
- 28 篇 生物工程
- 19 篇 环境科学与工程（可...
- 19 篇 网络空间安全
- 15 篇 水利工程
- 14 篇 光学工程
265 篇 理学
- 80 篇 系统科学
- 50 篇 地球物理学
- 49 篇 物理学
- 34 篇 数学
- 32 篇 生物学
- 24 篇 地理学
169 篇 医学
- 110 篇 临床医学
- 27 篇 基础医学(可授医学...
160 篇 管理学
- 151 篇 管理科学与工程(可...
44 篇 农学
- 26 篇 作物学
- 17 篇 农业资源与环境
35 篇 文学
- 35 篇 新闻传播学
12 篇 艺术学
6 篇 军事学
5 篇 经济学
4 篇 教育学
3 篇 法学

主题

7,380 篇 detection algori...
773 篇 detectors
766 篇 feature extracti...
632 篇 algorithm design...
585 篇 object detection
532 篇 image edge detec...
397 篇 testing
372 篇 robustness
333 篇 cameras
307 篇 computer science
292 篇 accuracy
286 篇 monitoring
280 篇 data mining
273 篇 computational mo...
254 篇 image segmentati...
235 篇 signal to noise ...
235 篇 clustering algor...
200 篇 change detection...
196 篇 pixel
195 篇 electrocardiogra...

机构

17 篇 school of electr...
15 篇 beijing universi...
13 篇 department of el...
13 篇 department of el...
12 篇 department of el...
11 篇 institute for in...
10 篇 national mobile ...
9 篇 department of el...
9 篇 wireless theorie...
8 篇 department of el...
8 篇 mit lincoln labo...
8 篇 graduate school ...
8 篇 department of au...
8 篇 institute of com...
7 篇 beijing key labo...
7 篇 school of electr...
7 篇 department of el...
7 篇 department of el...
7 篇 department of el...
7 篇 southeast univ n...

作者

13 篇 wei li
13 篇 bin wu
9 篇 dacheng yang
9 篇 ming chen
9 篇 h. wang
9 篇 r. raheli
8 篇 xin liu
8 篇 jaeseok kim
8 篇 shixin cheng
8 篇 keiichi tamura
8 篇 v.k. garg
8 篇 j. mcnames
8 篇 xin zhang
7 篇 lei wang
7 篇 a. schaum
7 篇 hajime kitakami
7 篇 hui zhao
7 篇 giulio colavolpe
7 篇 hui li
7 篇 yong li

语言

7,309 篇 英文
36 篇 中文
30 篇 其他
4 篇 西班牙文
1 篇 土耳其文

检索条件"主题词=Detection Algorithms"

共 7380 条记录，以下是871-880 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：

YOLOv5s-FSDA: Fire and Smoke detection Algorithm Based on Improved YOLOv5s

YOLOv5s-FSDA: Fire and Smoke Detection Algorithm Based on Im...

引用

International Conference on Digital Home (ICDH)

作者： Yuhua Li Yanru Xu Mengyue Zhang Jianqiang Sheng Software Engineering College Zhengzhou University of Light Industry Zhengzhou China Shenzhen Institute of Information Technology Shenzhen China

ISBN: (数字)9798331509873

ISBN: (纸本)9798331509880

Fire and smoke detection are critical to reducing fire losses. Edge devices with limited resources require a model that is more lightweight while still maintaining the detection accuracy necessary for fire and smoke detection tasks. To solve these problems, this paper proposes a fire and smoke detection algorithm based on YOLOvSs, named YOLOvSsFSDA. Firstly, we incorporate the Cross-scale Feature Fusion (CFF) structure, enhancing the recognition and representation capabilities of features across different scales. Secondly, to further reduce the model burden, we adopt Ghost Convolution (GhostConv) technology to reduce model parameter count and computational load. Thirdly, to enhance the model's overall grasp of fire and smoke areas, we integrate the Content-Aware ReAssembly of Features (CARAFE) upsampling method. In addition, we introduce the Similarity Intersection over Union (SIoU) loss function to reduce the positioning error between the prediction and actual boxes, ensuring that fire and smoke targets of different scales can be located more accurately. Experimental results show that the YOLOvSs-FSDA algorithm, while maintaining the high detection accuracy of YOLOvSs, reduces model complexity by 30% and computational costs by 18%.

关键词： YOLO Accuracy Convolution Computational modeling Image edge detection Prediction algorithms Computational efficiency Complexity theory detection algorithms Load modeling

来源：评论

学校读者我要写书评

暂无评论

Vehicle detection Based on Improved YOLOv8

Vehicle Detection Based on Improved YOLOv8

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Chin Hong Lim Tee Connie Kah Ong Michael Goh Faculty of Information Science & Technology Multimedia University Melaka Melaka Malaysia

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Vehicle detection is a crucial component of Intelligent Transportation System (ITS). With the advancement of deep learning and computer vision, state-of-the-art algorithms such as You Only Look Once version 8 (YOLOv8) have been developed to address the real-time detection challenges. However, during the experimentation process, we observed a class imbalance problem in the self-collected Malaysian traffic dataset. In this paper, we analyse this problem in detail and propose a Simplified Variant of Oversampling (SVO) method to mitigate it. By applying the proposed method, we can ensure that the detection algorithm performs consistently across all classes, thereby improving the overall accuracy and dependability of the system. The measurements used in this paper are mean Average Precision (mAP), precision and recall. The oversampling approach improved mAP50 and mAP50-95 by 16.91 % and 29.43%, respectively. Additionally, different attention mechanisms for instance Triplet Attention, Squeeze and Excitation Networks (SE) and Large Selective Kernel Network (LSKNet), were integrated into the backbone of the detection network to further enhance performance. Among these, the LSKNet attention mechanism achieved the best performance, further improving the mAP50 and mAP50-95 by 2.46% and 2.70%, respectively.

关键词： YOLO Deep learning Attention mechanisms Vehicle detection Lighting Real-time systems Recording Kernel detection algorithms Intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Lightweight Road Vehicle detection Algorithm Based on Improved YOLOv8

Lightweight Road Vehicle Detection Algorithm Based on Improv...

引用

Computer Information Science and Application Technology (CISAT), International Conference on

作者： Xin Zhang

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

This paper addresses the problems of large model size, many parameters, high equipment requirements, and low recall rate in traditional vehicle detection models, and proposes a lightweight road vehicle detection algorithm based on the improved YOLOv8 (You Only Look Once). The improved detection algorithm reduces the number of parameters and the size of the model, which can effectively improve the detection speed and shorten the training time. This paper proposes a lightweight Shared Parameter detection head (SPDH), which can greatly reduce the number of model parameters while ensuring the detection accuracy. in the meantime SimAM attention mechanism, a lightweight and parameterless attention mechanism of convolutional neural networks, is added to the network to enhance the detection performance. Finally, the Star Block in StarNet proposed by Microsoft in 2024 is used to replace the Bottleneck in C2f for further lightening and guarantee performance. Experiments on BIT-Vehicle dataset demonstrate that the superior performance of the algorithm compared to the original model. Under the premise that The parameter count has been decreased by approximately 35% and the model’s size has been reduced by around 34%, resulting in a 1.2% increase in precision and a 1.8% increase in recall, and other evaluation indicators are roughly consistent with the benchmark model. The excellence of the improved algorithm is proved.

关键词： Training YOLO Information science Attention mechanisms Vehicle detection Road vehicles Stars Approximation algorithms Convolutional neural networks detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent detection Algorithm of Small Foreign Objects in Images Based on Deep Learning

Research on Intelligent Detection Algorithm of Small Foreign...

引用

Electronics and Devices, Computational Science (ICEDCS), International Conference on

作者： Feng Jiliang Ye Wangping Guo Cheng Wang Qiong Lou Hongna Xi’an XK Electric Power Equipment Intelligent Service Co. Ltd Xi’an China Jiangxi Communication Terminal Industry Technology Research Institute Co. Ltd Ji’an China

ISBN: (数字)9798331527624

ISBN: (纸本)9798331527631

To address the challenge of identifying small foreign objects in images, this study introduces an advanced algorithm integrating deep learning with multi-scale detection methodologies. The algorithm constructs a sophisticated multilayer convolutional neural network (CNN) architecture, which thoroughly explores the multi-scale attributes of the image. This is then combined with an anomaly detection framework to achieve precise identification of small foreign objects within images. The model leverages the robust feature extraction capabilities of the CNN to capture fine details across various scales, enabling the effective detection and localization of anomalous regions within the image. To evaluate the algorithm's effectiveness and applicability, a series of simulations were conducted across multiple scenarios. The results from these simulations indicate that the algorithm consistently achieves a detection accuracy rate exceeding 95% in diverse environments, while maintaining a false detection rate below 5%, thereby demonstrating the algorithm's stability and efficiency in handling complex backgrounds. Furthermore, the simulation outcomes reveal that the system exhibits strong real-time performance and resilience when applied to intricate industrial settings, further underscoring the algorithm's significant potential for widespread use in industrial inspection and quality control processes.

关键词： Deep learning Accuracy Computational modeling Quality control Feature extraction Real-time systems Data models Convolutional neural networks Object recognition detection algorithms

来源：评论

学校读者我要写书评

暂无评论

An End-to-end Campus Fire detection Algorithm Incorporating Priori Features

An End-to-end Campus Fire Detection Algorithm Incorporating ...

引用

Robotics, Intelligent Control and Artificial Intelligence (RICAI), International Conference on

作者： Yu Liang Xinlin Xie Xuan Liu Jie Wang Shanxi Key Laboratory of Advanced Control and Industrial Intelligence Intelligence School of Electronic Information Engineering Taiyuan University of Science and Technology Taiyuan China

ISBN: (数字)9798331541699

ISBN: (纸本)9798331541705

To address the imbalance in detection speed and accuracy caused by smoke, flame, and background confusion in campus video surveillance scenarios, an end-to-end campus fire detection algorithm incorporating priori features is proposed. First, a feature pyramid fusion module guided by priori features is constructed to cascade the multi-scale feature fusion module. The priori features are individually pre-trained by Convolutional Neural Network (CNN) classification network. The feature complementarity between the two is utilized to improve the feature representation of the detection network. Second, a lightweight set prediction detection head is designed. The head does not require manually designed anchors and post-processing strategies, enabling end-to-end detection while balancing speed and accuracy. Finally, a joint loss function that integrates the losses of categorical and bipartite matching is proposed. Focus on the drawbacks of the slow convergence associated with bipartite matching, both classification information and bipartite bit matching are considered in the detection results. Experimental results on the fire detection dataset demonstrate that the proposed algorithm improved average accuracy by 7.8% while maintaining detection speed, effectively balancing speed and accuracy in fire detection.

关键词： YOLO Training Visualization Accuracy Feature extraction Transformers Video surveillance Convolutional neural networks detection algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

Research on Complex Street View detection Algorithm Based on YOLOv8

Research on Complex Street View Detection Algorithm Based on...

引用

Signal Processing and Intelligent Computing (SPIC), International Conference on

作者： Haiyang Du Jun Liu School of Automation and Electrical Engineering Shenyang Ligong University Shenyang China

ISBN: (数字)9798350368888

ISBN: (纸本)9798350368895

The current street scene is becoming more and more complex, with high pedestrian and vehicular traffic and a large number of targets. Aiming at the problems that the accuracy of the current complex street scene-oriented detection algorithms is not satisfactory and the leakage rate of small targets is unstable, the intelligent detection algorithm YOLOv8s- for complex street scenes is proposed, aiming at the intelligent detection of multi-targets in daily street scenes. This study is based on the target detection model of YOLOv8s, proposing a C2f-DCNv2 module that can sample features flexibly; adding a small target detection layer in the head; and using the Shape IoU loss function. The improved algorithm improves the precision, recall, and average accuracy by 2.2%, 3.6%, and 5.0%, respectively, compared with the initial algorithm, and these experimental data validate that this study can have a good performance when targeting the detection task of complex street scenes.

关键词： Performance evaluation Accuracy Pedestrians Shape Urban areas Signal processing algorithms Object detection Real-time systems Mobile handsets detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Focused: An Approach to Framework-Oriented Cross-Language Link Specification and detection

Focused: An Approach to Framework-Oriented Cross-Language Li...

引用

International Conference on Software Maintenance (ICSM)

作者： Ailun Yu Yifan Shi Bo Shen Wei Zhang Haiyan Zhao Guangtai Ling Tianyong Wu Zhi Jin Key Laboratory of High Confidence Software Technologies (Peking University) MoE China School of Computer Science Peking University Beijing China Huawei Technologies Co. Ltd. Beijing China

ISBN: (数字)9798350395686

ISBN: (纸本)9798350395693

Framework-based multilingual software development (MLSD) is becoming prevalent in software engineering practice. Despite the advantages, framework-based MLSD also leads to reduced understandability and changeability of multilingual software, due to the introduced cross-language links (XLLs). To help alleviate this problem, there are existing practice and research crafting rules to specify and detect XLLs, but only focusing on specific frameworks. With the intention of coping with the diversity of XLL conventions across different multi-lingual frameworks, this paper proposes Focused, an extensible approach to framework-oriented cross-language link specification and detection. The basic idea is to decouple the two activities of XLL specification and detection as much as possible by mediating between them with a set of DSL-enabled XLL rules, making Focused configurable to different multilingual frameworks. We evaluated Focused on 3 widely-used multilingual frameworks and 15 high-starred open-source projects using these frameworks, showing the expressiveness, effectiveness, and efficiency of Focused.

关键词： Software maintenance Focusing Programming Real-time systems Multilingual DSL detection algorithms Software engineering Software development management

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion detection in Cloud Computing Environments

Network Intrusion Detection in Cloud Computing Environments

引用

Applied Intelligence and Computing (AIC), IEEE World Conference on

作者： Madhusudhan Dasari Sreeramulu K. Suganyadevi Anuteja Reddy Neravetla Abdul Sajid Mohammed Dept of Cyber Security American Express USA Department of ECE Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Information Technology University of The Cumberlands Kentucky USA Dept of School of Computer and Information Sciences University of the Cumberlands Kentucky USA

ISBN: (数字)9798350384598

ISBN: (纸本)9798350384604

The increasing use of cloud computing has also resulted in a higher vulnerability to cyber attacks. Network Intrusion detection Systems (NIDS) play a vital role in protecting cloud computing environments from these attacks. However, the unique characteristics of cloud computing, such as its dynamic and distributed nature, pose challenges for traditional NIDS. This paper provides an overview of the current state of NIDS in cloud computing environments, including their limitations and potential solutions. It also discusses the use of machine learning and artificial intelligence techniques in improving NIDS performance. The effectiveness of NIDS in detecting both known and unknown attacks is crucial for the security of cloud computing environments and requires continuous research and development.

关键词： Cloud computing Network intrusion detection Organizations Machine learning Network security Data breach detection algorithms Cyberattack Research and development Monitoring

来源：评论

学校读者我要写书评

暂无评论

GCSAR: Small-Object-Enhanced detection Algorithm Based on Gradient Aggregation and Channel Enhancement for SAR Ship detection

GCSAR: Small-Object-Enhanced Detection Algorithm Based on Gr...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Kefu Lin Yujuan Han School of Computer Science Shanghai Maritime University Shanghai China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

High-resolution Synthetic Aperture Radar (SAR) utilizes pulse compression technology to accurately resolve the distance between targets and enable imaging,the application of detection algorithm in ship identification task is promoted. However, the current CNN architecture does not perform well for tasks such as low-resolution images and small objects. The features of small targets may be lost during the training process, is one of the factors that makes ship detection missions perform poorly in SAR *** study presents GCSAR, an enhanced detection algorithm tailored for detecting small objects in SAR imagery, focusing specifically on maritime ship detection. The model improves upon the YOLOv8 architecture by incorporating SPDconv in the backbone and Gradient-Aggregation-and-Channel-Enhancement-Module (GACEM) in the neck, allowing for better detection performance in SAR images dataset containing sea vessels images.

关键词： Training Image resolution Object detection Network architecture Feature extraction Radar polarimetry Neck Marine vehicles detection algorithms Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Measuring Video QoE from Encrypted Traffic: A Collaborative Approach Using Machine Learning and Stalling detection

Measuring Video QoE from Encrypted Traffic: A Collaborative ...

引用

International Conference on Network Protocols

作者： Longjie Wang Wenyong Wang Wei Jiang Bin Zhang Qixun Zhu Jun Deng Junrui Wu School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China China Telecom Sichuan Branch Chengdu China Sichuan Communication Surveying & Design Institute Co. Ltd Chengdu China NSFOCUS Information Chengdu Technology Co. LTD Chengdu China

ISBN: (数字)9798350351712

ISBN: (纸本)9798350351729

Video stream has become the largest part of the Internet traffic, and video Quality of Experience (QoE) is an important factor affecting the overall QoE of Internet users. Accurate measurement of video $\mathbf{Q o E}$ from the perspective of traffic can help network operators to better plan network resources and improve user retention. To accurately measure video QoE through traffic, multiple factors need to be considered, with stalling being a significant one. Mean Opinion Score (MOS) is an indicator that quantifies video QoE. Traditionally, labeling MOS for videos requires subjective quality assessment experiments, which is time-consuming and labor-intensive. Second, the statistical features used by traditional machine learning methods are difficult to represent the stalling events in video steams, leading to inaccurate MOS measurements. Therefore, a number of past studies only estimate the indirect metrics that affect MOS, such as resolution and bitrate. In this paper, we use the parametric model ITU-T P. 1203 to automatically label MOS for videos. And we propose a two-stage approach to accurately measure MOS from video traffic. First, we introduce a stalling detection algorithm to identify stalling events from HTTP Adaptive Streaming (HAS) traffic. Then, we use these stalling events to produce secondary features and combine them with other statistical video stream features to establish a machine learning model for direct MOS measuring. Experiments show that our proposed method reduces the Root Mean Squared Error (RMSE) of MOS estimation from 0.455 to 0.406 compared to the conventional method.

关键词： Estimation Machine learning Streaming media Feature extraction Quality assessment Internet Quality of experience detection algorithms Usability Video recording

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 << < 84 85 86 87 88 89 90 91 92 93 > >>

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：