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

5,586 篇 会议
259 册 图书
112 篇 期刊文献

馆藏范围

5,957 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

4,087 篇 工学
- 3,152 篇 计算机科学与技术...
- 2,598 篇 软件工程
- 661 篇 信息与通信工程
- 487 篇 控制科学与工程
- 410 篇 生物工程
- 380 篇 电气工程
- 322 篇 机械工程
- 285 篇 光学工程
- 281 篇 生物医学工程（可授...
- 230 篇 电子科学与技术（可...
- 182 篇 材料科学与工程（可...
- 180 篇 化学工程与技术
- 156 篇 动力工程及工程热...
- 152 篇 交通运输工程
- 150 篇 安全科学与工程
- 143 篇 土木工程
1,797 篇 理学
- 1,057 篇 数学
- 447 篇 生物学
- 415 篇 物理学
- 222 篇 统计学（可授理学、...
- 189 篇 系统科学
- 156 篇 化学
984 篇 管理学
- 676 篇 管理科学与工程(可...
- 342 篇 图书情报与档案管...
- 340 篇 工商管理
238 篇 教育学
- 233 篇 教育学
218 篇 医学
- 191 篇 临床医学
- 176 篇 基础医学(可授医学...
186 篇 法学
- 153 篇 社会学
149 篇 经济学
- 148 篇 应用经济学
119 篇 艺术学
76 篇 农学
38 篇 文学
9 篇 军事学
8 篇 历史学
4 篇 哲学

主题

197 篇 software enginee...
159 篇 programming
131 篇 software enginee...
127 篇 linear programmi...
123 篇 artificial intel...
116 篇 accuracy
105 篇 deep learning
101 篇 feature extracti...
101 篇 dynamic programm...
90 篇 computational mo...
88 篇 semantics
85 篇 optimization
79 篇 machine learning
79 篇 training
77 篇 computer science
77 篇 programming tech...
76 篇 computer communi...
73 篇 convolutional ne...
71 篇 integer programm...
70 篇 programming lang...

机构

20 篇 chitkara univers...
15 篇 school of inform...
11 篇 school of comput...
11 篇 university of ch...
11 篇 school of comput...
10 篇 college of compu...
10 篇 school of inform...
10 篇 univ potsdam has...
10 篇 univ sumatera ut...
9 篇 school of comput...
9 篇 department of co...
9 篇 school of cyber ...
9 篇 school of comput...
9 篇 univ calgary dep...
8 篇 university of sc...
8 篇 college of infor...
8 篇 school of transp...
8 篇 school of data s...
8 篇 school of comput...
8 篇 college of compu...

作者

11 篇 hirschfeld rober...
11 篇 maurer frank
11 篇 yang li
10 篇 li yang
10 篇 mawengkang herma...
8 篇 stuckey peter j.
8 篇 holcombe mike
7 篇 wang jing
7 篇 kukreja vinay
7 篇 hoos holger h.
7 篇 beck j. christop...
7 篇 zhang wei
6 篇 liu bo
6 篇 yan jun
6 篇 huang min
6 篇 liu bing
6 篇 lo david
6 篇 michael r. lyu
6 篇 liu yu
6 篇 wang jun

语言

5,783 篇 英文
161 篇 其他
35 篇 中文
1 篇 西班牙文

检索条件"任意字段=4th International Conference on the Art Science and Engineering of Programming"

共 5957 条记录，以下是111-120 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：

Advanced Facial Emotion Classification with 135 Classes for Enhanced Cybersecurity Applications

Advanced Facial Emotion Classification with 135 Classes for ...

引用

AI in Cybersecurity (ICAIC), international conference on

作者： Gregory Powers Aobo Jin Abdul Basit Tonmoy Haowei Cao Hardik Gohel Qixin Deng Mathematics and Computer Science Wabash College Crawfordsville U.S Computer Science University of Houston Victoria Victoria U.S Electrical and Computer Engineering Johns Hopkins University Baltimore U.S

ISBN: (数字)9798331518882

ISBN: (纸本)9798331518899

A key component of behavior analysis and human-computer interaction (HCI) is facial expression detection, which helps systems understand and react to human emotions more effectively and nuancedly. While previous research predominantly focuses on classifying seven or eight primary emotions, there has been limited exploration into more detailed and varied emotional expressions. In this paper, we address this gap by utilizing a recently published dataset that includes $\mathbf{1 3 5}$ distinct emotional classes, significantly increasing the complexity and granularity of emotion recognition tasks. To tackle this challenge, we propose a novel framework that combines U-Net and ResNet architectures, leveraging the strengths of each to capture intricate emotional cues and spatial features. Our approach achieves higher accuracy than current state-of-the-art (SOTA) methods, demonstrating its effectiveness for high-dimensional emotion classification in complex, real-world applications.

关键词： Human computer interaction Emotion recognition Accuracy Face recognition Complexity theory Behavioral sciences Computer security artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Forefront System for Sugarcane Leaf Disease Classification Using Deep Learning

A Forefront System for Sugarcane Leaf Disease Classification...

引用

international conference on Robotics,Electrical and Signal Processing Techniques (ICREST)

作者： Abu Noman Md Sakib Sajal Basak Partha Mohammad Anik Islam Shojib MD Mahamudul Hasan Badiuzzaman Shuvo Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh Computer Science and Engineering Chittagong University of Engineering & Technology Chittagong Bangladesh Computer Science and Engineering East West University Dhaka Bangladesh

ISBN: (数字)9798331530952

ISBN: (纸本)9798331530969

the agriculture sector has already seen a favorable advancement because of the involvement of machine learning (ML) methods. Sugarcane industry faces a gruesome drawback because of several types of leaf diseases. Nowadays, ML methods have come handy also to detect the diseases at the very early stage. Our work represents a cutting-edge deep learning method with a goal to classify five popular sugarcane leaf diseases: Bacterial Blight, Mosaic, RedRot, Rust, Yellow, and can also identify which one is Healthy. this study also conducts a comparative analysis of various state-of-the-art models, evaluating their training time, parameters, accuracy and model size using the same dataset. Based on this evaluation, the optimal model was selected for final evaluation. Several pre-trained models were modified to enhance speed and reduce storage requirements. the system can identify the disease category for every given sugarcane leaf image using the EfficientNetB0 model, which demonstrated the best performance, and also provides the probability of correct identification. Several preprocessing steps are involved such as removing noise, addressing missing data, and standardizing images to ensure maximum accuracy. the models were trained, validated, and tested on a dataset of 4,800 sugarcane leaf images from the Sugarcane Leaf Disease Dataset. Among all the models, EfficienNetB0, InceptionV3 and ResNet50 achieved high accuracy (98.75%, 98.54% and 98.54%, respectively). However, EfficienNetB0 was ultimately chosen due to its faster training, smaller size, and fewer parameters, making it ideal for this study.

关键词： Training Deep learning Analytical models Accuracy Computational modeling Transfer learning Signal processing algorithms Agriculture Diseases Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrating Machine Learning and Deep Learning Techniques for Enhanced Historical Script Classification 4th

Integrating Machine Learning and Deep Learning Techniques fo...

引用

4th international conference on Intelligent Systems and Pattern Recognition, ISPR 2024

作者： Boudraa, Merouane Bennour, Akram Al-Sarem, Mohammed Shukla, Piyush Kumar LAMIS Laboratory Echahid Cheikh Larbi Tebessi University Tebessa Algeria College of Computer Science and Engineering Taibah University Medina Saudi Arabia Technological University of Madhya Pradesh Madhya Pradesh Bhopal India

ISBN: (纸本)9783031821554

the accurate identification of script styles in historical manuscripts is crucial for gaining insights into their historical context and significance. this study proposes an integrated system that combines manual and machine learning features to effectively identify script styles within manuscripts, utilizing the ClAMM dataset. the system comprises three primary steps: preprocessing the dataset using denoising and binarization techniques, extracting manual features using the Harris detector, and performing script classification using pretrained CNN models. By merging manual feature engineering with advanced deep learning techniques, our system showcases its ability to accurately recognize script styles competing with state-of-the-art methods with accuracy of 89.2%. these results not only validate the effectiveness of our approach but also contribute significantly to the broader advancement of script classification in historical manuscript analysis. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing MRP Adoption in SMEs: A Python-Based Algorithmic Approach 6

Enhancing MRP Adoption in SMEs: A Python-Based Algorithmic A...

引用

6th international conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Vitti, M. Coletta, R. Reis, J. Pinto, F.S. Facchini, F. Polytechnic University of Bari Via E. Orabona 4 Bari70126 Italy Industrial Engineering and Management Faculty of Engineering Lusófona University and RCM2+ Campo Grande Lisbon1749-024 Portugal

Implementing Enterprise Resource Planning (ERP) and Material Requirements Planning (MRP) systems enables companies to gain a competitive advantage in current dynamic and uncertain markets. Although implementing these systems offers several benefits, it encounters major barriers, especially in Small and Medium Enterprises (SMEs). they constitute a significant share of the industrial sector globally but often face challenges such as limited access to finance, technology, and markets, which can hinder their growth and sustainability. Addressing these barriers is vital for leveraging the full potential of SMEs and fostering a more dynamic and resilient global economy. In this context, adopting Python-based solutions could be a promising solution. Python's open-source nature indeed empowers users with unrestricted application development, distribution, and commercialization. this flexibility fosters platform-independent development and eliminates vendor lock-in. Furthermore, its clear syntax, powerful interpreter, and extensibility enable efficient and versatile programming across various paradigms, making it a very useful language for resource-limited contexts such as SMEs. To this concern, the objective of the present work was to investigate the benefits offered by implementing a Python-based algorithm to facilitate the adoption of an MRP system in SMEs. To this end, a Python algorithm has been developed based on a sequence of four logical steps: exploding, netting, lot sizing, and offsetting, and was numerically applied. the results obtained provided a clear perspective on the usefulness of Python and the benefits derived from its use due to its ease of use, flexibility, and reduced costs. © 2024 the Authors. Published by Elsevier B.V.

关键词： Enterprise resource planning

来源：评论

学校读者我要写书评

暂无评论

Development of an Automation Module for Planning Trajectories for Painting Aircraft Fuselage Elements 1

引用

7th international Russian Automation conference, RusAutoCon 2024

作者： Voroshchenko, V.D. Gorkavyy, M.A. Gudim, A.S. Komsomolsk-Na-Amure State University 27 Lenina St Komsomolsk-On-Amure681013 Russia

ISBN: (数字)9783031824944

ISBN: (纸本)9783031824937

the article is devoted to the development of a module for automating the planning of trajectories for painting aircraft fuselage elements. the scientific problem of the lack of modern control methods and technologies at aviation assembly plants, namely, in robotic areas for painting parts, is posed. And the applied problem of the inappropriate use of robotic painting due to lengthy readjustment due to the lack of automated adjustment of the robot’s control program is posed. the stages of development and implementation of module calculations are presented: the stage of processing a 3D model of a part to identify key vertices, generating points for the painting trajectory of one face, generating a complex of painting trajectories for the entire part, corrective transformation of the trajectory into the coordinate system of the central point of the robot manipulator tool. Based on the obtained trajectory, an automated synthesis of the robot's control program was implemented. the use of a control program was demonstrated and conclusions were drawn about the performance of the painting path planning module: it was empirically established that the robot performs the path according to the requirements. In the future, the module will be integrated into a hardware and software complex for managing and correcting control programs for painting aircraft parts. the use of a software and hardware complex will allow for robotic painting, improve the quality of the applied paint layer, reduce the production time of products and the paint consumption, and this will reduce the cost of products. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

artificial Intelligence for Cybersecurity: A State of the art

Artificial Intelligence for Cybersecurity: A State of the Ar...

引用

AI in Cybersecurity (ICAIC), international conference on

作者： Abdullah Al Siam Md Maruf Hassan Touhid Bhuiyan Department of Software Engineering Daffodil International University Dhaka Bangladesh Department of CSE Southeast University Bangladesh School of IT Washington University of Science and Technology VA USA

ISBN: (数字)9798331518882

ISBN: (纸本)9798331518899

the goal of this study is to analyze the role of artificial intelligence (AI) in cybersecurity by analyzing the strengths of many key AI techniques, including machine learning (ML), deep learning (DL), natural language processing (NLP), and anomaly detection algorithms. We conducted a detailed literature assessment on current research to assess the applicability of AI approaches in cybersecurity. Principal methodologies examined include machine learning for behavioral analytics, deep learning for malware detection, natural language processing for phishing identification, and anomaly detection for intrusion detection. artificial intelligence approaches significantly enhance cybersecurity, with each strategy providing distinct functionalities. this study’s distinctive contributions are its comparative assessment of approaches, emphasizing their strengths and practical applications in cybersecurity while addressing present issues and future avenues for improvement. the research suggests that a combination of AI in cybersecurity that merges these strategies could provide a significant increase in digital security. these findings bring substantial value by identifying the best scenarios for using each AI approach in cybersecurity.

关键词： Deep learning Quantum computing Phishing Natural language processing Robustness Resource management Computer security Computer crime Anomaly detection Faces

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Forecasting Using Deep Learning and Time Series Ensemble Techniques 44th

Bitcoin Forecasting Using Deep Learning and Time Series Ense...

引用

44th SGAI international conference on Innovative Techniques and Applications of artificial Intelligence, SGAI 2024

作者： Zafar, Huma Kapetanakis, Stylianos Middlesex University LondonNW4 1DY United Kingdom Distributed Analytics Solutions LondonE14 5RE United Kingdom

ISBN: (纸本)9783031779145

this research investigates Bitcoin price prediction by reviewing the current state of the art, comparing Time Series and Deep Learning models, evaluating their performance on a range of metrics, and assessing the selected model’s real-world applicability. It reviewed existing studies on Deep Learning, Time Series, and Bitcoin, and utilised 44,419 hourly Bitcoin data points for data visualization and mining. the findings showed that ensemble models, particularly stacked ensemble, outperformed other models in predictive accuracy, with the lowest error metrics and highest R2 value. Deep learning models also performed well, but with slightly higher errors. Time Series models were inadequate for Bitcoin price prediction, as evidenced by their negative R2 values. these results contribute to our understanding of effective modelling approaches for Bitcoin price prediction. the study also suggests promising avenues for future research, such as fine-tuning ensemble models, incorporating advanced feature engineering techniques, and exploring volatility forecasting. thus, the study offers a valuable contribution to the field of cryptocurrency research, advancing knowledge on Bitcoin price prediction and fostering a deeper comprehension of the intricacies underlying cryptocurrency markets. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Breaking Information Silos: Global Guided Task Prediction for Class-Incremental Learning 27th

Breaking Information Silos: Global Guided Task Prediction fo...

引用

27th international conference on Pattern Recognition, ICPR 2024

作者： Hu, Chaoshun Ye, Biaohua Chen, Zixuan Lai, Jian-Huang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangzhou510555 China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou China

ISBN: (纸本)9783031781889

Class-incremental learning (CIL) aims to learn a series of tasks sequentially, each introducing several new categories. Because providing the task labels during inference can significantly increase accuracy, many approaches attempt to predict task labels in CIL. However, existing works focus on learning local information and overlook the importance of global information. the absence of global guidance leads to the formation of information silos across disparate tasks, resulting in potential inter-task interference. To break information silos, we propose a method called Global Guided Task Prediction (GGTP) to introduce global information. Our method consists of two modules. the local de-redundant module aims to reduce information redundancy across different tasks from a global perspective. We combine dual encoders and feature decorrelation loss to effectively reduce redundancy while minimizing catastrophic forgetting. the global information module explicitly extracts global information to serve as auxiliary information guiding task prediction. We extract the most important information from all local information through a global encoder and then aggregate them to form global information. Extensive experiments validate the effectiveness of our method, which achieves state-of-the-art results. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Confidence-Guided Feature Alignment for Cloth-Changing Person Re-identification 27th

Confidence-Guided Feature Alignment for Cloth-Changing Pers...

引用

27th international conference on Pattern Recognition, ICPR 2024

作者： Huang, Sirong Zheng, Huicheng School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9783031781094

Much progress has been made in the field of person re-identification, but changes in clothing have hindered the practical application of long-term person re-identification. Cloth-changing person re-identification (CC-ReID) aims to address this problem, with the main challenge being the extraction of discriminative features unrelated to clothing. Existing methods, which mainly focus on introducing clothing-irrelevant cues such as key points, contours, and 3D shapes, require additional modules for feature extraction, resulting in increased complexity and potential inaccuracies due to dependence on the performance of external models. Few studies directly use the original RGB images to make the model constantly focus on clothing-independent information. In this paper, we propose a Confidence-Guided Feature Alignment Network (CGFA) for CC-ReID. Specifically, we design a confidence module that automatically learns to make confidence adjustments to fine-grained information, prompting the model to mine clothing-independent discriminative features without introducing other modal cues. By transferring knowledge, we encourage the model to learn discriminative identity features that are independent of clothing bias. As a result, the confidence module can be removed during the inference phase. the proposed simple but efficient method uses only RGB modality without additional cues, and can serve as a powerful baseline for CC-ReID to drive future research. Extensive experiments on the CC-ReID datasets demonstrate the effectiveness of the proposed method, which achieves state-of-the-art performance. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and High-Fidelity Model for Generalized Audio-Driven 3D Talking Face Synthesis 27th

A Lightweight and High-Fidelity Model for Generalized Audi...

引用

27th international conference on Pattern Recognition, ICPR 2024

作者： Liu, Shunce Zhong, Yuwei Wang, Huixuan Peng, Jingliang Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China School of Information Science and Engineering University of Jinan Jinan China School of Software and Microelectronics Peking University Beijing China School of Software Shandong University Jinan China

ISBN: (纸本)9783031781247

We present LW-GeneFace, a lightweight and high-fidelity model for generalized audio-driven facial animation, in this paper. We develop this model by reducing the size while maintaining the synthetic quality of GeneFace, an audio-driven facial animation model known for its high fidelity and generalization capabilities. Specifically, we compress the first and the third stages of GeneFace as they dominate the model size. In the first stage, we propose a lightweight version of the WaveNet-based network inspired by MobileNetV3 and DP-block. It utilizes depthwise separable convolution and dual-path feature extraction to compress the network while maintaining effective feature extraction. the shared network structure in the dual-path feature extraction further reduces model complexity and improves training efficiency. In the third stage, we generate realistic 3D renderings at reduced model size by introducing novelties in RAD-NeRF. Technically, we reduce the hash table sizes in the grid-based encoding modules, as well as present a lightweight bottleneck MLP architecture to increase the non-linearity of the model. Experimental results demonstrate that LW-GeneFace achieves state-of-the-art performance with both model size and synthetic quality considered. the source code of LW-GeneFace will be released after acceptance of this paper. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Animation

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 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：