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

6,437 篇 会议
961 篇 期刊文献
4 篇 学位论文
1 册 图书

馆藏范围

7,403 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,187 篇 工学
- 1,125 篇 电气工程
- 924 篇 计算机科学与技术...
- 665 篇 信息与通信工程
- 272 篇 控制科学与工程
- 203 篇 仪器科学与技术
- 165 篇 机械工程
- 164 篇 软件工程
- 128 篇 电子科学与技术（可...
- 101 篇 交通运输工程
- 101 篇 生物医学工程（可授...
- 88 篇 测绘科学与技术
- 72 篇 航空宇航科学与技...
- 34 篇 土木工程
- 29 篇 生物工程
- 24 篇 环境科学与工程（可...
- 19 篇 网络空间安全
- 17 篇 船舶与海洋工程
- 16 篇 光学工程
284 篇 理学
- 80 篇 系统科学
- 62 篇 物理学
- 50 篇 地球物理学
- 34 篇 数学
- 34 篇 生物学
- 22 篇 地理学
180 篇 医学
- 120 篇 临床医学
- 29 篇 基础医学(可授医学...
164 篇 管理学
- 155 篇 管理科学与工程(可...
49 篇 农学
- 26 篇 作物学
- 22 篇 农业资源与环境
35 篇 文学
- 35 篇 新闻传播学
14 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

7,403 篇 detection algori...
757 篇 detectors
754 篇 feature extracti...
621 篇 algorithm design...
576 篇 object detection
531 篇 image edge detec...
383 篇 testing
364 篇 robustness
330 篇 cameras
307 篇 computer science
283 篇 monitoring
277 篇 accuracy
274 篇 data mining
265 篇 computational mo...
255 篇 image segmentati...
234 篇 signal to noise ...
233 篇 clustering algor...
199 篇 change detection...
195 篇 pixel
191 篇 electrocardiogra...

机构

17 篇 school of electr...
15 篇 beijing universi...
13 篇 department of el...
13 篇 department of el...
11 篇 institute for in...
11 篇 department of el...
10 篇 national mobile ...
9 篇 department of el...
9 篇 wireless theorie...
8 篇 department of el...
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 mit lincoln labo...
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

7,323 篇 英文
39 篇 其他
36 篇 中文
4 篇 西班牙文
1 篇 土耳其文

检索条件"主题词=detection algorithms"

共 7403 条记录，以下是1181-1190 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：

Compression Robustness of Digital Image Forensics Evaluating Demosaicing Consistency

Compression Robustness of Digital Image Forensics Evaluating...

引用

International Workshop on Biometrics and Forensics (IWBF)

作者： Felix Kurth Thomas Wulz Andreas Uhl Dept. of Artificial Intelligence and Human Interfaces University of Salzburg Salzburg Austria

ISBN: (数字)9798350354478

ISBN: (纸本)9798350354485

Image tampering detection techniques based on the analysis of CFA-demosaicing traces excel by their detection accuracy, however, they are very sensitive against slightest changes in an image. Therefore, their robustness against lossy compression schemes is a crucial issue with respect to their applicability. The robustness of seven different tampering detection techniques of this type is experimentally assessed considering eight distinct lossy compression schemes, including four ISO/IEC JPEG standards as well as four algorithms originating from video intra-frame coding schemes. Overall, we find that the accuracy of the forensic analysis is reduced for increasing compression strength as expected, however, the relative performance of the compression schemes is different for the two considered test data sets and the tampering detection algorithms, respectively. In any case, distinct compression algorithms change the ranking of the forensic algorithms in terms of tampering detection accuracy in different manner across varying compression strengths and thus, it is almost impossible to provide general guidelines for compression algorithm deployment. With respect to compression robustness, a recent neural network-based technique predicting the relative positions of CFA blocks in the image turns out to be most robust against any type of compression, but is already best performing on uncompressed data.

关键词： Image coding Accuracy Forensics Transform coding Prediction algorithms Robustness detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of Insider Threat detection Methods Based on Temporal Representation

Experimental Evaluation of Insider Threat Detection Methods ...

引用

International Conference on Information, Communication and Networks (ICICN)

作者： Gaole Lu Huixiang Zhang Tianluo Liu Kaihua Liao Chun Feng School of Cyberspace Security Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9781665490832

At present, insider threat detection faces many challenges, such as imbalanced data sets, the complexity of malicious behavior, high data dimension, and difficulty for manual analysis to keep up with the data growth rate. An experimental evaluation of insider threat detection methods is carried in this paper. Firstly, the open data set is divided by day and week. Then, various temporal representations including percentile, mean difference, median difference, and concatenation of instances representations, are used to extract potential information. Four unsupervised machine learning algorithms and a supervised algorithm are comprehensively compared to explore the best detection schemes under different temporal representations. To comprehensively evaluate the detection performance of the algorithms, four commonly used performance metrics (i.e. detection rate (DR), Precision (PR), F1-score (F1), Area Under the Curve (AUC)) are introduced. The experimental results show that the random forest algorithm can achieve the best detection results using day granularity data combined with median differential representation-meddiff30, and the DR, PR, F1, and AUC are 75.43%, 99.59%, 85.84%, and 87.71 % respectively. For the four unsupervised detection algorithms, under the 20% investigation budget, the autoencoder combined with percentile representation-percentile30 in day granularity achieved DR of 95.83%, and AUC of 94.93%, with higher PR and F1 values under the same conditions. The local outlier factor algorithm combined with concatenation representation-c3 under week granularity achieved the highest DR, but the scheme of the autoencoder combined with percentile30 still achieved the highest PR, F1, and AUC.

关键词： Measurement Radio frequency Machine learning algorithms Manuals Behavioral sciences Data mining detection algorithms

来源：评论

学校读者我要写书评

暂无评论

A detection And Tracking System For Fisheye Videos From Traffic Intersections

A Detection And Tracking System For Fisheye Videos From Traf...

引用

IEEE Southeastcon

作者： Yizheng Wang Hala ElAarag Stetson University DeLand USA

Traditional pinhole camera models use rectilinear lenses and yield a smaller field of view (FOV). In order to survey wide areas in traffic intersections, multiple Closed-Circuit TeleVision (CCTV) cameras are needed. A fisheye camera lens can provide a larger FOV than a traditional camera without blind spots, but the images are often distorted. It is a valuable tool in both vehicle detection and tracking systems. In this research we propose a system for detecting and tracking vehicles in fisheye videos obtained from a traffic intersection. We first calibrated the fisheye videos into perspective views, then we trained several detection models on the collected image datasets. After training, we applied tracking algorithms on the video combined with detection results. We tested the performance of our system using mean average precision, center location error and processing time. Our experiments have shown that the different combinations of detection and tracking algorithms have tradeoffs in accuracy and processing time.

关键词： Training TV Vehicle detection Object detection Cameras Safety detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Cascaded Fuzzy Logic Controller for DVR Based Power Quality Improvement Voltage Sag/Swell Mitigation

Cascaded Fuzzy Logic Controller for DVR Based Power Quality ...

引用

Recent Innovation in Smart and Sustainable Technology (ICRISST), International Conference on

作者： D. Ravi Kishore Sivaprasad Kollati Garikina Jagadeesh Anapu Gowtham Ranga Doma Chandravamsi Department of Electrical and Electronics Engineering Godavari Institute of Engineering and Technology(Autonomous) Affiliated to JNTU Kakinada Rajahmundry A.P India

ISBN: (数字)9798350309140

ISBN: (纸本)9798350309157

Customers' demands for excellent power quality have greatly grown recently. Conventional electrical gadgets, sometimes referred to as D-FACTS devices, that guards sensitive loads against voltage fluctuations in distribution networks includes D-STATCOM, DVR, and UPQC. Two types of manufacturing procedure repercussions may be distinguished: increased sensitivity to intermittent failures (such voltage sag in distribution systems) and nonlinear and unbalanced loads. The DVR is a piece of equipment that was linked in series and controls the loading voltage by supplying the system with voltage. DVRs are typically placed in networks of distribution between sources and feeders of sensitive loads. The primary responsibility is to prevent any disconnections during disturbances by quickly supporting the load voltage (using a fast detection algorithm). The cascaded fuzzy logic controller techniques presented in this study are widely employed in voltage transmission and distribution systems to compensate for voltage sag and swell. This project describes a dynamic voltage restorer based on the average identifying methodology for single-phase power systems, in addition to discussing the usage of DVR to restore voltage sag and swell in distribution infrastructure using an alternative per-unit value approach (average detection). The results of the three-phase voltage sag and swell simulation have been given by SIMULINK/MATLAB. The Settling time obtained using Cascaded FLC controller is 0.15s and overall efficiency of the paper is 91.9%.

关键词： Fuzzy logic Technological innovation Voltage fluctuations Sensitivity Prevention and mitigation Power quality Power system dynamics Manufacturing Voltage control detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Human Action Recognition Using Dual-Stream Neural Networks with FMCW Radar

Human Action Recognition Using Dual-Stream Neural Networks w...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Yuqing Wu Yong Li Wei Cheng Guangyu Lei School of Electronics and Information Northwestern Polytechnical University Xi’an China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

This paper presents a approach to human action recognition utilizing FMCW radar. We propose a method that extracts range-time and velocity-time features from radar echoes and processes them using a dual-stream neural network for action classification. The improved Constant False Alarm Rate (CFAR) detection algorithm, combined with a Shape Profile Constraint - Feature Map (SPC-FM) generation method, significantly enhances feature extraction by removing noise. Experimental results demonstrate an average classification accuracy of 96.4% across six common actions, showcasing the method’s robustness for applications in various domains, including medical monitoring and autonomous vehicle systems.

关键词： Accuracy Shape Neural networks Noise Radar detection Radar Feature extraction Radar signal processing Human activity recognition detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence Techniques to Detect Water Stress

Application of Artificial Intelligence Techniques to Detect ...

引用

ACS/IEEE International Conference on Computer Systems and Applications

作者： Marwa Dorai Mehrez Abdellaoui Bouthaina Douh Ali Douik NOCCS Laboratory National Engineering School of Sousse University of Sousse Higher Institute of Computer Science and Communication Technologies University of Sousse Higher Institute of Agronomic Sciences of Chott Mariem University of Sousse

ISBN: (数字)9798331518240

ISBN: (纸本)9798331518257

Water stress is a critical issue that significantly affects agricultural productivity worldwide, particularly in the context of climate change and diminishing water resources. Conventional methods for detecting water stress, such as visual inspections and ground sensors, often lack the precision, costeffectiveness, and scalability needed for modern agricultural demands. Recent advances in artificial intelligence (AI) offer innovative solutions by leveraging complex data from multiple sources. This research aims to develop a multimodal AI model that integrates satellite imagery, drone data, and ground IoT sensors to improve the accuracy and timeliness of water stress detection. By combining Convolutional Neural Networks (CNNs) for image analysis, machine learning algorithms for sensor data interpretation, and advanced data fusion techniques, the proposed model captures water stress indicators from various perspectives, enhancing sensitivity and specificity. The expected outcomes include significant improvements in precision and responsiveness compared to traditional single-source methods. This approach aims to optimize irrigation, minimize crop losses, and support sustainable water management, providing a valuable tool for precision agriculture.

关键词： Artificial intelligence Multimodal sensors Machine learning Water monitoring Water resources Agriculture detection algorithms Climate change Stress measurement Intelligent sensors Data models Sensor fusion Sensitivity and specificity Scalability Convergence of numerical methods Irrigation Machine learning Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

YOLOX Algorithm Driven by Software and Hardware Collaboration Domestic Waste Intelligent Identification and Accurate Sorting Robot System Design

YOLOX Algorithm Driven by Software and Hardware Collaboratio...

引用

Service Robotics (ICoSR), International Conference on

作者： Chunxiang Zhu Yuanbin Mu Hong Shu Yinglian Jin College of Engineering Training Centre China Jiliang University Hangzhou China School of Internet of Things Technology Hangzhou Polytechnic Hangzhou China College of Mechanical and Electrical Engineering China Jiliang University Hangzhou China

ISBN: (数字)9798350367119

ISBN: (纸本)9798350367126

Based on the artificial intelligence computing platform Jetson NANO and YOLOX algorithm, an intelligent and efficient domestic waste sorting system based on YOLOX-NANO is designed. The lightweight YOLOX multi-target detection algorithm is used to achieve accurate identification of four types of domestic waste under occlusion, and based on the CoreXY coordinate transformation algorithm to achieve the best angle judgment and accurate grasping of the mechanical claw; it is implemented using TensorRT optimization technology The lightweight YOLOX multi-target detection algorithm was deployed on the artificial intelligence computing platform Jetson Nano, and the overall construction of an intelligent and efficient sorting system for four types of garbage based on YOLOX-NANO was completed. This system uses a self-made data set for training. The data set includes 4 categories of garbage and a total of 13 subcategories. After testing, it can effectively achieve multi-target detection. The detection mAP0.5:0.95 value is 97.37%, and the target detection speed reaches 30.60FPS, the garbage sorting speed can reach up to 6 pieces/minute. Can be used for clean, environmentally friendly smart garbage cans.

关键词： Training Accuracy Service robots Software algorithms Software detection algorithms Artificial intelligence System analysis and design Sorting Testing

来源：评论

学校读者我要写书评

暂无评论

Research on Pupil Center Localization Method Based on Fitting Elliptical Contours with Arc-support Line Segments

Research on Pupil Center Localization Method Based on Fittin...

引用

Image Processing (ASIP), Asia Symposium on

作者： Zhen Wang Jiaxuan Wei Lei Zhang Shunqi Gao Zhan Wang School of Science and Technology Tianjin University of Finance and Economics Tianjin China

ISBN: (数字)9798350376159

ISBN: (纸本)9798350376166

In head-mounted eye tracking system, detecting pupil center efficiently and precisely is the prime assignment. A pupil center localization method based on fitting elliptical contours with arc-support line segments is proposed to solve the problems of low detection rates of existing pupil detection algorithms in real-world scenarios caused by factors such as lighting variations, occlusions, and off-axis effects. First, use the Haar feature detector to locate the approximate position of the pupil in the eye diagram. Secondly, combine the Canny algorithm with the arc-support segment detection algorithm to extract the elliptical arc that may belong to the pupil contour, and eliminate a large number of redundant points. Then according to the distance, polarity and direction between the arc segments, the arc segments are combined into different groups, and ellipse fitting is performed by the Least Squares Method to generate the initial ellipse set. Based on the physiological characteristics of the pupil, filter out the ellipse with positive polarity, and determine the support inlier of the ellipse. Finally, the support inlier is fitted for a second time to obtain more accurate ellipse parameters, and the best ellipse is selected as the pupil contour according to the ellipse confidence level. Through comparative experiments on the public eye image dataset (LPW), the average detection rate has increased by 12.5% compared with the highest of the existing six algorithms, Even if the acquiring of eye image is affected by some shadows and light spots, the proposed method still can accurately identify the pupil, can be applied to various head-mounted eye tracking systems to provide more accurate pupil position information for line-of-sight estimation.

关键词： Location awareness Accuracy Image edge detection Fitting Gaze tracking Interference Feature extraction Physiology Pupils detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Community Deception Based on Genetic Algorithm Using Graph Local Structure

Community Deception Based on Genetic Algorithm Using Graph L...

引用

International Conference on Advanced Information Technologies (ICAIT)

作者： Cing Gel Vung Yi Yi Hlaing Faculty of Computer Science University of Computer Studies (Kalay) Kalay Myanmar Faculty of Computer Science University of Computer Studies Mandalay Mandalay Myanmar

ISBN: (数字)9798331510046

ISBN: (纸本)9798331510053

Many researchers have studied community detection attacks in different ways but there is no best method to fool all community detection algorithms. In this study, to concern privacy protection, we aim to generate the perturbation network using genetic algorithm based on heuristic approach from community disclosure by community detection algorithms. Clustering coefficient and randomization of initialization population are applied to ensure the diversity of the solution spaces and to remove the repetition of same chromosomes in population. This system proposes a local features-based mutation approach for generating the adversarial network effective in community deception. The experimental exhibits the optimal strategy with normalizing mutual information (NMI) and Modularity (Q) by running on difference datasets with variety community detection algorithms.

关键词： Privacy Social networking (online) Network topology Perturbation methods Topology Reliability detection algorithms Time complexity Protection Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Context Aware Cyberbullying Classification Using Network Science

Context Aware Cyberbullying Classification Using Network Sci...

引用

International Conference on Soft Computing and Machine Intelligence (ISCMI)

作者： Grace Milverton Arathi Arakala Sona Taheri Discipline of Mathematical Sciences RMIT University Melbourne Australia

ISBN: (数字)9798331518127

ISBN: (纸本)9798331518134

This research investigates the use of network science measures to enhance cyberbullying detection. Traditional detection algorithms rely on machine learning to classify content as ‘bullying’ based solely on textual analysis. However, these approaches often miss context, leading to incorrect classifications. Limited research has been done on incorporating network measures based on connections, to provide social context on platforms. This study integrates network features with textbased features, following a cyberbullying definition from the literature that includes aggression, repetition, harmful intent, power imbalance, and peer visibility. The results demonstrate that combining network context features and text features leads to higher accuracy in cyberbullying classification than methods relying only on text.

关键词： Context-aware services Accuracy Cyberbullying Machine learning detection algorithms Machine intelligence

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 << < 115 116 117 118 119 120 121 122 123 124 > >>

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：