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

6,721 篇 会议
329 册 图书
116 篇 期刊文献

馆藏范围

7,165 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

4,791 篇 工学
- 3,971 篇 计算机科学与技术...
- 2,033 篇 软件工程
- 805 篇 电气工程
- 771 篇 信息与通信工程
- 592 篇 控制科学与工程
- 395 篇 生物工程
- 381 篇 生物医学工程（可授...
- 297 篇 光学工程
- 296 篇 机械工程
- 212 篇 仪器科学与技术
- 182 篇 电子科学与技术（可...
- 138 篇 化学工程与技术
- 126 篇 材料科学与工程（可...
- 120 篇 网络空间安全
- 108 篇 安全科学与工程
- 91 篇 动力工程及工程热...
1,626 篇 理学
- 809 篇 数学
- 492 篇 物理学
- 489 篇 生物学
- 273 篇 统计学（可授理学、...
- 189 篇 化学
- 141 篇 系统科学
842 篇 管理学
- 461 篇 管理科学与工程(可...
- 425 篇 图书情报与档案管...
- 181 篇 工商管理
679 篇 医学
- 604 篇 临床医学
- 254 篇 基础医学(可授医学...
- 145 篇 药学(可授医学、理...
- 100 篇 公共卫生与预防医...
122 篇 法学
- 115 篇 社会学
92 篇 教育学
58 篇 农学
52 篇 经济学
43 篇 艺术学
12 篇 文学
4 篇 军事学
1 篇 哲学

主题

927 篇 pattern recognit...
800 篇 artificial intel...
449 篇 machine learning
293 篇 feature extracti...
243 篇 deep learning
202 篇 accuracy
185 篇 support vector m...
134 篇 data mining
126 篇 neural networks
126 篇 face recognition
125 篇 training
103 篇 local binary pat...
99 篇 computer vision
99 篇 computer imaging...
89 篇 convolutional ne...
88 篇 real-time system...
85 篇 information syst...
83 篇 pattern matching
83 篇 computational mo...
83 篇 image processing...

机构

39 篇 chitkara univers...
33 篇 maharishi school...
27 篇 school of comput...
27 篇 indian stat inst...
25 篇 centre of interd...
25 篇 the islamic univ...
23 篇 department of ar...
23 篇 concordia univ c...
22 篇 national univers...
20 篇 school of comput...
19 篇 univ chinese aca...
18 篇 school of comput...
18 篇 univ waterloo de...
17 篇 vishwakarma inst...
16 篇 national laborat...
15 篇 school of artifi...
15 篇 institute of aut...
14 篇 lovely professio...
14 篇 uttaranchal inst...
13 篇 uttaranchal univ...

作者

55 篇 suen ching y.
24 篇 suen cy
22 篇 kamel mohamed s.
18 篇 lu bao-liang
17 篇 de-shuang huang
16 篇 karray fakhri
16 篇 abraham ajith
14 篇 maji pradipta
13 篇 dash yajnaseni
12 篇 c.y. suen
10 篇 liu cheng-lin
10 篇 venkatesh svetha
10 篇 wong alexander
10 篇 chauhan rahul
10 篇 zheng wei-long
10 篇 liu wei
9 篇 zhang lei
9 篇 gill kanwarparta...
9 篇 ma songde
9 篇 coenen frans

语言

6,316 篇 英文
822 篇 其他
72 篇 中文
1 篇 土耳其文

检索条件"任意字段=3rd International Conference on Pattern Recognition and Machine Intelligence"

共 7166 条记录，以下是1221-1230 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：

Review of Cybercrime Detection Approaches using machine Learning and Deep Learning Techniques

Review of Cybercrime Detection Approaches using Machine Lear...

引用

Applied Artificial intelligence and Computing (ICAAIC), international conference on

作者： Yalamandeswara Rao Gumma Subbarao Peram Department of Computer Science and Engineering Vignan Foundation For Science Technology and Research Guntur - Tenali Rd Vadlamudi Andhra Pradesh Department of Information Technology Vignan Foundation For Science Technology and Research (VFSTR) Guntur -Tenali Rd Vadlamudi Andhra Pradesh

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

This research explores the use of deep learning and machine Learning techniques in cybersecurity to detect and mitigate cyber threats. Specifically, this study focuses on Long Short-Term Memory (LSTM) and Graph Neural Networks (GNN) to analyse network traffic and system logs for patterns, anomalies, and malicious activities. The goal of the proposed research work is to enhance cyber-defining mechanisms and network security by leveraging Artificial intelligence (AI) to combat the evolving cyber threats.

关键词： Deep learning Recurrent neural networks machine learning algorithms Reviews Telecommunication traffic Learning (artificial intelligence) Network security

来源：评论

学校读者我要写书评

暂无评论

SegXAL: Explainable Active Learning for Semantic Segmentation in Driving Scene Scenarios 27th

SegXAL: Explainable Active Learning for Semantic Segmentati...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Mandalika, Sriram Nambiar, Athira Department of Computational Intelligence Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9783031781063

Most of the sophisticated AI models utilize huge amounts of annotated data and heavy training to achieve high-end performance. However, there are certain challenges that hinders the deployment of AI models "in-the-wild" scenarios i.e. inefficient use of unlabeled data, lack of incorporation of human expertise and lack of interpretation of the results. To mitigate these challenges, we propose a novel Explainable Active Learning (XAL) model viz. ‘XAL-based semantic segmentation model "SegXAL" , that can (i) effectively utilize the unlabeled data, (ii) facilitate the "Human-in-the-loop" paradigm and (iii) augment the model decisions in an interpretable way. In particular, we investigate the application of the SegXAL model for semantic segmentation in driving scene scenarios. The SegXAL model proposes the image regions that require labelling assistance from Oracle by dint of explainable AI (XAI) and uncertainty measures in a weakly-supervised manner. Specifically, we propose a novel Proximity-aware Explainable-AI (PAE) module and Entropy-based Uncertainty (EBU) module to get an Explainable Error Mask, which enables the machine teachers/human experts to provide intuitive reasoning behind the results and to solicit feedback to the AI system, via an active learning strategy. Such a mechanism bridges the semantic gap between man and machine through collaborative intelligence, where humans and AI actively enhance each other’s complementary strengths. A novel high-confidence sample selection technique based on the DICE similarity coefficient is also presented within the SegXAL framework. Extensive quantitative and qualitative analyses are carried out in the benchmarking Cityscape dataset. Results show the outperformance of our proposed SegXAL against other state-of-the-art models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

3D Reconstruction of Medical Image Based on Improved Ray Casting Algorithm 3rd

3D Reconstruction of Medical Image Based on Improved Ray Cas...

引用

3rd international conference on pattern recognition and Artificial intelligence, ICPRAI 2022

作者： Yu, Wang Ning, Gong School of Artificial Intelligence Beijing Technology and Business University Beijing100048 China

ISBN: (纸本)9783031090363

Although the traditional volume rendering ray casting algorithm has become one of the mainstream methods of medical image three-dimensional (3D) reconstruction, the 3D image quality and rendering speed still can not meet the requirements of high-definition and real-time in clinical medical diagnosis. In this paper, a fusion ray casting algorithm is proposed, which uses the improved resampling interpolation algorithm and the improved bounding box algorithm to improve the image rendering speed, and the improved data synthesis of sampling points is used to improve image quality in ray casting algorithm. The experimental results show that the method proposed in this paper can not only improve the speed of reconstruction, but also greatly improve the image quality of 3D reconstruction. © 2022, Springer Nature Switzerland AG.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Coal gangue detection method based on improved YOLOv5 3

Coal gangue detection method based on improved YOLOv5

引用

3rd international conference on Big Data, Artificial intelligence and Internet of Things Engineering, ICBAIE 2022

作者： Song, Qingjun Liu, Zhijiang Jiang, Haiyan Shandong University of Science and Technology College of Intelligence Equipment Taian271000 China

ISBN: (数字)9781665451604

ISBN: (纸本)9781665451604

Accurate identification of coal and gangue is helpful to improve the quality of raw coal. Based on the YOLOv5 algorithm, a new model yoloV5-SEDE with high precision and fast convergence is proposed. First, Mosaic data enhancement method is used to randomly crop and scale images to form new images to expand the data set. Nine anchor frames are generated by k-means clustering. After that, SENet attention module was added to enhance the identification ability of coal gangue targets, suppress invalid features and improve the utilization rate of feature information. SPPF structure is used instead of SPP structure to enrich the expression ability of feature mapping. In the feature fusion stage, the original feature pyramid fusion method is replaced by BiFPN weighted feature pyramid fusion method to make the semantic features obtained from the network have stronger robustness. Compared with the original target recognition algorithm, the average accuracy of this algorithm is improved by 1.59% (MAP_0.5) and 2.57% (MAP_0.5:0.95) respectively. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Memetic Algorithm Small Survey For 2019 Published Papers 3

Memetic Algorithm Small Survey For 2019 Published Papers

引用

3rd international conference on Creative Communication and Innovative Technology, ICCIT 2024

作者： Hendric Spits Warnars, Harco Leslie Spits Warnars, Laurens Utomo, Wiranto Herry Doucet, Antoine Ramadhan, Arief Siswanto, Teddy Bina Nusantara University Computer Science Department of Computer Science Jakarta11480 Indonesia Bina Nusantara University School of Information Systems Department of Information Systems Jakarta11480 Indonesia President University Master of Science and Technology West Java17530 Indonesia Université de La Rochelle Laboratoire L3i La Rochelle France Telkom University School of Computing Bandung40257 Indonesia Trisakti University Department of Information Systems Jakarta11440 Indonesia

ISBN: (纸本)9798350367492

The Memetic Algorithm (MA), introduced by Pablo Moscato in 1989, integrates Evolutionary Algorithms with local search methods, enhancing its effectiveness in solving complex optimization problems. This paper provides a comprehensive survey of MA research published in 2019, reviewing 75 selected papers from an initial pool of 112 identified through Google Scholar. The selected papers were categorized into five types: optimization problems (40 papers), image processing (10 papers), parallel processing (5 papers), gene/DNA datasets (4 papers), and other applications (16 papers). The survey highlights MA's versatility and effectiveness across various domains, particularly its potential for solving complex optimization problems. Key findings include the adaptability of MA for diverse applications, its ongoing relevance in addressing challenging issues, and promising opportunities for combining MA with other algorithms to enhance performance. The paper also emphasizes the significance of MA in fields such as image processing, where it improves pattern recognition and image enhancement, and in bioinformatics, where it optimizes gene selection and genetic algorithms. Despite the extensive study of MA, there remains a significant research gap in non-English literature, particularly in Bahasa, limiting accessibility for Indonesian researchers. This survey aims to bridge this gap by providing valuable insights and encouraging further exploration and application of MA to solve increasingly complex problems. It offers a comprehensive overview that underscores the importance of MA and its potential for future research and innovation. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Long-Term Sustainability of Healthcare Data Optimization Through Deep Federated Learning 3

Enhancing the Long-Term Sustainability of Healthcare Data Op...

引用

3rd IEEE international conference on Intelligent Techniques in Control, Optimization and Signal Processing, INCOS 2024

作者： Kumar, Balraj Evin, Munni Byeon, Haewon Sivaprakash, M. Sheeba, P. Maria Sunil, J. School of Computer Application Lovely Professional University Punjab Phagwara India School of Engineering and Computing American International University Kuwait College of Ai Convergence Inje University Department of AI-Big Data Gimhae50834 Korea Republic of Stella Mary's College of Engineering Department of Mechanical Engineering Tamil Nadu 629202 India St. Mother Theresa Engineering College Department of Electronics and Communication Engineering Thoothukudi India Annai Vailankanni College of Engineering Tamil Nadu Kanyakumari India

ISBN: (纸本)9798350361186

The medical industry regards the prevention and detection of skin diseases as a top priority. The number of people suffering from skin diseases is increasing faster than ever before due to increased levels of pollution and poor diet. Although it's not the major priority, having bad skin makes us less certain. Regularly inspecting your skin is an important step in identifying any degenerative or early changes in your skin that could lead to skin disease. machine learning algorithms can be utilized to create robust models that can categorize a wide range of skin conditions. First, the skin and non-skin must be distinguished in order to identify skin conditions. In order to determine the unambiguous a group of skin conditions A selection of five distinct machine learning algorithms has been employed to compile a dataset of skin infections. These algorithms include Kernel Self- pattern, Random Forest, Naive Bayes, Logistic Regression, and CNN, among others. A comparable investigation based on training accuracy and skepticism matrix criterion has been carried out and illustrated with graphs. It has been determined that, of all the applicants, CNN offers the highest level of training accuracy for the appropriate assumption of skin disorders. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Application of pattern recognition in Airport Target Conflict Alert 3rd

Application of Pattern Recognition in Airport Target Conflic...

引用

3rd international conference on Artificial intelligence, 2022

作者： Liu, Yan State Key Laboratory of Air Traffic Management System and Technology Nanjing210007 China

ISBN: (纸本)9789811694226

The operational safety of aircraft and vehicles at the airport currently mainly relies on the ATC and drivers, and there is a risk of collision caused by negligence of personnel. At present, control voice and video surveillance are important information that can be obtained from mode information, but they are not fully integrated into the control automation system application. Through the intelligent pattern recognition technology, the control voice and video monitoring information are recognized and processed, and the control system is integrated into the control system to accurately determine the operation trend of the airport target, and promptly give warnings, which has important practical significance. In response to this need, this paper studies structured command generation based on control voice, three-dimensional relationship calculation based on target semantics, future trajectory prediction and target conflict warning methods, to achieve knowledge-incorporated flight conflict detection between airport targets, and automate air traffic control System application method is designed to provide support for airport operation safety guarantee. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

EFEIR: Enhanced Feature Expression for Instance-Level Hierarchical Relation Learning in Few-Shot Wildlife Object Detection 3

EFEIR: Enhanced Feature Expression for Instance-Level Hierar...

引用

3rd international conference on Environmental Remote Sensing and Geographic Information Technology, ERSGIT 2024

作者： Li, Xingwu Yang, Hui Cheng, Fan School of Artificial Intelligence Anhui University Anhui Hefei230601 China Institutes of Physical Science and Information Technology Anhui University Anhui Hefei230601 China

ISBN: (纸本)9781510690219

Image-based wildlife recognition is an essential approach for wildlife monitoring. However, due to the scarcity of wildlife image data, particularly the difficulty in collecting rare species images, deep learning-based wildlife recognition faces challenges such as data scarcity and difficulty in model convergence. To address these challenges, this paper proposes a novel few-shot wildlife object detection method based on Enhanced Feature Expression with Instance-level Hierarchical Relation (EFEIR). Our contributions are twofold: first, we propose a feature-enhanced instance-level hierarchical relation learning approach that encodes contrastive-level, salient-level, and attention-level relations to enhance the query-relevant feature representation. Second, we introduce a new triplet-based loss in the regression stage, which aims to minimize the distance between anchor and positive samples while maximizing the distance between anchor and negative samples, thereby improving the model's discriminative capability in embedding space and enhancing its performance in few-shot object detection tasks. Experimental results show that under different shot conditions (5, 15, 20 reference images), our method achieves superior mAP50 accuracy compared to baseline models for five animal species: Eurasian Spoonbill, Male Elliot's Pheasant, Red Fox, Tufted Deer, and Macaque. These results validate the effectiveness and generalization capability of the proposed method under few-shot conditions, demonstrating its potential practical value. © 2025 SPIE.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

Comparison of Large-Scale Pre-Trained Models based ViT, Swin Transformer and ConvNeXt 3

Comparison of Large-Scale Pre-Trained Models based ViT, Swin...

引用

3rd international conference on Artificial intelligence and Computer Engineering, ICAICE 2022

作者： Yu, Jiapeng Faculty of Science and Technology Department of Data Science Beijing Normal University-Hong Kong Baptist University United International College 2000 Jintong Road Tangjiawan Guangdong Province Zhuhai China

ISBN: (纸本)9781510663473

In the field of computer vision, deep learning has developed tremendously, large-scale preforming has received increasing attention from experts and researchers. Different training models often have large performance gaps in training speed and accuracy when performing large-scale pre-training. In this case, choosing the appropriate model for large-scale pre-training is particularly important. This experiment uses the same image data set and the same hardware conditions to construct the image classification model respectively in the three mainstream image recognition large-scale pre-training models, Vision Transformer (VIT), Swin-Transformer and ConvNeXt, try to analyze the advantages and disadvantages of each model by experimental results. It is observed that Vision Transformer has the fastest running speed in computer vision classification experiments, but its accuracy is not as good as the other two models, Swin-Transformer has the slowest speed and average accuracy, ConvNeXt has the highest accuracy, but its speed is mediocre. The results of this experiment have some reference significance for future model selection for large-scale pre-training tasks in computer vision, this can decrease training time and improve training accuracy to some extent. © 2023 SPIE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Application of artificial intelligence technology in depression and suicide management 3

Application of artificial intelligence technology in depress...

引用

2022 3rd international conference on Computer Information and Big Data Applications, CIBDA 2022

作者： Li, Huinan Hu, Maorong Jiangxi University of Traditional Chinese Medicine Nanchang China The First Affiliated Hospital of Nanchang University China

ISBN: (纸本)9783800758760

Research significance: Depression is a common mental disorder with the characteristics of high morbidity, high disability rate, and high suicide rate. Depression is relatively difficult to diagnose, treat, monitor and manage. In recent years, with the emergence of artificial intelligence technology, it has provided new means for depression and suicide management. Based on the current situation of depression and suicide, this paper discusses the current application results of artificial intelligence in depression diagnosis, depression and suicide monitoring and management, and treatment intervention, so as to provide reference for related research on depression and suicide management based on artificial intelligence technology. Research methods: Search the literature on the application of artificial intelligence technology in depression intervention in recent years through literature navigation. Depression diagnosis, depression monitoring, depression intervention and other aspects were analyzed. The actual technology was compared in the children's motor skills, social interaction, daily life and casual attention. Research conclusion: Artificial intelligence technology is developing rapidly, and it has great advantages over traditional technology in the treatment of depression, but AI still has a lot of room for development, and it also has shortcomings at this stage, because machine learning algorithms are easier to Affected by biases such as racist and sexist rhetoric, key industry players need to ensure the robustness of their AI systems before bringing them to market. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Learning algorithms

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 << < 119 120 121 122 123 124 125 126 127 128 > >>

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：