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

13,377 篇 会议
17 篇 期刊文献

馆藏范围

13,394 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,105 篇 工学
- 6,398 篇 计算机科学与技术...
- 5,095 篇 软件工程
- 1,730 篇 信息与通信工程
- 1,008 篇 控制科学与工程
- 735 篇 生物工程
- 721 篇 电气工程
- 667 篇 生物医学工程（可授...
- 582 篇 网络空间安全
- 511 篇 光学工程
- 451 篇 安全科学与工程
- 398 篇 电子科学与技术（可...
- 344 篇 交通运输工程
- 328 篇 动力工程及工程热...
- 288 篇 机械工程
- 267 篇 仪器科学与技术
2,667 篇 理学
- 1,298 篇 数学
- 879 篇 生物学
- 637 篇 统计学（可授理学、...
- 535 篇 物理学
- 328 篇 系统科学
- 242 篇 化学
1,877 篇 管理学
- 1,300 篇 管理科学与工程(可...
- 789 篇 图书情报与档案管...
- 573 篇 工商管理
947 篇 医学
- 687 篇 临床医学
- 681 篇 基础医学(可授医学...
- 659 篇 公共卫生与预防医...
- 264 篇 药学(可授医学、理...
508 篇 法学
- 471 篇 社会学
262 篇 经济学
- 262 篇 应用经济学
223 篇 农学
210 篇 教育学
198 篇 文学
9 篇 军事学
1 篇 艺术学

主题

2,085 篇 accuracy
1,690 篇 deep learning
1,198 篇 machine learning
1,188 篇 computational mo...
1,044 篇 training
1,026 篇 data models
968 篇 predictive model...
724 篇 real-time system...
687 篇 convolutional ne...
685 篇 feature extracti...
676 篇 machine learning...
585 篇 support vector m...
532 篇 federated learni...
485 篇 adversarial mach...
330 篇 contrastive lear...
311 篇 medical services
295 篇 random forests
289 篇 analytical model...
278 篇 prediction algor...
271 篇 neural networks

机构

105 篇 lovely professio...
101 篇 chitkara univers...
57 篇 department of co...
47 篇 school of comput...
45 篇 school of comput...
45 篇 department of co...
44 篇 department of co...
42 篇 the islamic univ...
40 篇 shandong provinc...
36 篇 college of compu...
32 篇 university of ch...
28 篇 department of co...
27 篇 department of co...
26 篇 computer science...
26 篇 graphic era deem...
25 篇 department of co...
25 篇 amrita vishwa vi...
25 篇 the islamic univ...
23 篇 department of co...
23 篇 college of intel...

作者

23 篇 satvik vats
18 篇 shiva mehta
18 篇 kukreja vinay
18 篇 vats satvik
17 篇 anjali t.
17 篇 rishabh sharma
17 篇 deepak upadhyay
16 篇 senthil kumar th...
15 篇 singh jagendra
15 篇 venugopalan manj...
13 篇 manjunatha
13 篇 rakesh kumar
12 篇 ramya maranan
11 篇 selvanayaki kola...
11 篇 s. kaliappan
10 篇 andersson karl
10 篇 muthukumaravel a...
10 篇 yang yang
10 篇 ayodeji olalekan...
10 篇 surendran r.

语言

12,124 篇 英文
1,269 篇 其他
306 篇 中文
1 篇 西班牙文

检索条件"任意字段=2024 International Conference on Computing, Machine Learning and Data Science, CMLDS 2024"

共 13394 条记录，以下是4851-4860 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：

ANOMALY-AWARE SEMANTIC SELF-ALIGNMENT FRAMEWORK FOR VIDEO-BASED PERSON RE-IDENTIFICATION 49

ANOMALY-AWARE SEMANTIC SELF-ALIGNMENT FRAMEWORK FOR VIDEO-BA...

引用

49th IEEE international conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ran, Zhidan Lu, Xiaobo Liu, Wei Southeast Univ Sch Automat Nanjing 210096 Peoples R China Minist Educ Key Lab Measurement & Control Complex Syst Engn Nanjing 210096 Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Video-based person re-identification (Re-ID) aims at matching the video snippets of the same person across multiple cameras. The ubiquitous appearance misalignment is a critical challenge in video person re-identification. Existing alignment-based methods rely on off-the-shelf human parsing models and cannot handle anomalous appearance information (e.g., obstacles and pedestrian interference) in video sequences. In this paper, we propose Anomaly-Aware Semantic Self-Alignment (ASSA), a novel video-based person Re-ID framework that seeks out body parts without prior human topology information and learns part-based feature representations against anomalous information. The proposed ASSA performs part classifier training and part-aligned representation learning alternately. For the classifier training, we design a Salient Region Extraction module to segment the entire foreground from the background in each input frame. Furthermore, a novel Anomaly-Aware Refinement module is proposed to suppress the influence of anomalous interference. Extensive experiments on three prevalent benchmarks demonstrate the effectiveness and superiority of the proposed framework.

关键词： Video person re-identification part-based representation learning feature alignment

来源：评论

学校读者我要写书评

暂无评论

Cyber Chronicles: Tracking Behavior Patterns for Detecting Threats in Large Networks 3

Cyber Chronicles: Tracking Behavior Patterns for Detecting T...

引用

3rd international conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Ramasubbu, Senthilnathan Thangavel, Senthil Kumar Jeyakumar, G. Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350372120

One of the primary challenges in cybersecurity is that even one un-detected, appropriately unanalyzed malicious security event can hide the attack vectors of a potential hacker. It is essential to detect the data breach at the earliest stage to reduce the impact on the business. The malicious actor's activities will have higher visibility during the initial attacks to compromises or exploitation at the beginning of the attack cycle. After the initial compromise, the attacker studies the environment and establishes the persistence and covert channel communication. At this successive phase of the attack cycle, the attacker camouflages with the production data flow, access, and noises in the network and application logs. It is essential to detect the attacks during the reconnaissance and initial attacks and should not miss any malicious activities. Most of our security tools focus on reducing false positives;however, reducing false negatives is critical to cyber security. Hence, this paper is focused on suitable deep learning to reduce the False Negatives (FNs) with minimal Type II error to detect the attacks well in advance. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Towards a New Hybrid Synthetic Minority Oversampling Technique for Imbalanced Problem in Software Defect Prediction 5

Towards a New Hybrid Synthetic Minority Oversampling Techniq...

引用

5th international conference on data Analytics for Business and Industry, ICDABI 2024

作者： Saheed, Yakub Kayode Abdulsalam, Sulaiman Olaniyi Ibrahim, Mohammed Babatunde Baba, Usman Ahmad American University of Nigeria School of ITand Computing Adamawa State Nigeria Kwara State University Dept. of Computer Science Malete Nigeria Nigerian Extractive Industries Transparency Initiative ICT Unit Abuja Nigeria North-Eastern University Dept. of Computer Science Gombe Nigeria

ISBN: (纸本)9798350368710

The software industry strives to improve software quality through continuous bug prediction, bug elimination, and module fault prediction. This issue has piqued researchers' interest because of its significant relevance in the software industry. Frequently, Software Defect Prediction (SDP) models contain significantly skewed data, making it difficult for classifiers to recognize defective occurrences. The machine learning (ML) community has put a lot of effort into solving the problem of learning from imbalanced SDP data, though less so in empirical software engineering. The over-sampling strategy is one of many recent solutions to this problem. This strategy balances the number of defective and non-defective cases by creating new defective instances. Unfortunately, these methods would result in non-diverse synthetic instances as well as a large number of unneeded noise instances, creating an imbalanced class problem. As a result, we propose a hybrid synthetic minority oversampling (HSMOTE) to address the problem of imbalance in SDP. In this paper, we introduce the hybrid Synthetic Minority Oversampling Technique (HSMOTE), a method that utilizes Extra Tree, Random Forest (RF), and Extreme Gradient Boosting (Xgboost) for classification. We develop and deploy the proposed method on the National Aeronautics and Space Administration (NASA) dataset, evaluating its performance on three datasets: JM1, KC1, and PC3. We compared the parameters for accuracy, precision, AUC, recall, F-measure, and Mathew Correlation Coefficient to those of the existing SDP. The findings from the simulations on the JM1 data showed that the proposed techniques work better than the current best models. The proposed SMOTE+RF technique surpasses the existing techniques with an accuracy of 93.69%, an AUC of 82.70%, and an F-measure of 32.98%. Similarly, the proposed SMOTE+Xgboost method outperforms the existing techniques with an accuracy of 93.432%, an AUC of 82.64%, and an F-measure of 34.13%, whi

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

Towards a Model: Exploring Fatigue Factors in ZOOM Online Classes 12

Towards a Model: Exploring Fatigue Factors in ZOOM Online Cl...

引用

12th international conference on Current Trends in Advanced computing, ICCTAC 2024

作者： Thomas, Lijo P Menon, Vishnu Achutha Thomas, Juby Ashique Ali, K.A. Soman, K.K. Sateesh Kumar, T.K. Department of Computer Science Bengaluru India Central University of Tamil Nadu Department of Media and Communication Bengaluru India Department of Media Studies Thiruvarur India Central University of Tamil Nadu Deprtment of Commerce Thiruvarur India Central University of Tamil Nadu Department of Education Bengaluru India Departemnt of Commerce Bengaluru India

ISBN: (纸本)9798350395808

The ascent of Zoom as the predominant platform for facilitating online classes signifies a notable paradigm shift in the domain of remote education. Its rapid adoption can be attributed to several factors, such as its intuitive interface, robust technological infrastructure, and adaptability across various educational contexts. Against the backdrop of the global pandemic, which has mandated a widespread transition to remote learning, Zoom has emerged as a pivotal tool for educators endeavoring to transcend geographical constraints and engage with students in virtual classrooms. Its pervasive presence has reshaped pedagogical approaches, facilitating interactive and collaborative learning experiences irrespective of geographical boundaries. This study examines the correlations between visual fatigue, physical fatigue, mental fatigue, tech-savvy behavior, and online learning among 724 teachers in Karnataka conducting online classes through Zoom. The survey, administered from January to June 2023, utilized purposive sampling. Rigorous data analysis comprised factor loadings, Cronbach's alpha, Rho_A, CR, HTMT ratio, Fornell-Larcker Criterion, assessments of multicollinearity, R square, path coefficients, and predictive validity, employing Smart PLS software. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Application of Self-supervised learning in Tunnel Lining Detection 8th

Application of Self-supervised Learning in Tunnel Lining Det...

引用

8th international conference on computing, Control and Industrial Engineering, CCIE 2024

作者： Jiang, Zhijie Hu, Nan Song, Heng Duan, Lanxi Cheng, Weiguo Cao, Ping State Key Laboratory of Particle Detection and Electronics University of Science and Technology of China Hefei230026 China Management and Technology Institute China Railway No.4 Engineering Group Co. Ltd. Anhui Hefei230000 China

ISBN: (纸本)9789819769360

Ground penetrating radar (GPR) is an important nondestructive technique in bridge and tunnel defect detection, and its signal intelligent analysis is a research hotspot. The radar data interpretation method using neural networks requires labeling a large amount of radar data. However, in actual work, there are problems such as sparse void sample data and morphological diversity. In this paper, the self-supervised learning method is adopted, and only a small amount of labeling data is needed to train the model parameters, which solves the problem of scarce radar data and large amount of labeling tasks, and improves the accuracy of identification of voids. By using different models to analyze the radar data, the results show that compared with the traditional supervised learning method, the self-supervised learning method has higher accuracy and stronger robustness, and has better industrial application value in the future. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Criminal Activities/Criminal Through CCTV by Live Footage Analysis

Detection of Criminal Activities/Criminal Through CCTV by Li...

引用

2024 OPJU international Technology conference on Smart computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Kumar, Rahul Rajpurohit, Divyajeet Singh Hanief, Mushraf Sharma, Shilpi Choudhury, Tanupriya Sar, Ayan Amity School of Engineering and Technology Department of Computer Science and Engineering Uttar Pradesh Noida India Graphic Era Deemed to Be University Cse Dept Uttarakhand Dehradun248002 India University of Petroleum and Energy Studies School of Computer Science Uttarakhand Dehradun248007 India

ISBN: (纸本)9798350373783

The integration of deep learning techniques, particularly the You Only Look Once (YOLO) object detection model, with Closed-Circuit Television (CCTV) systems has significantly transformed the landscape of crime detection and prevention. This research paper provides a comprehensive analysis of YOLO-based CCTV crime detection, elucidating the innovative strategies, challenges, and potential implications for enhancing public safety. The YOLO framework is well-known for its real-time object detection capabilities, which enable it to swiftly and accurately identify multiple objects within a single image frame. In the context of CCTV surveillance, YOLO has proven invaluable in the identification and tracking of criminal activities. The paper explores how YOLO's object detection architecture is adapted to the unique challenges of CCTV crime detection, including variable lighting conditions, occlusions, and diverse camera angles. One of the fundamental contributions of this research is the development of a YOLO-based CCTV crime detection system. This system combines YOLO's speed and accuracy with a sophisticated backend for video analysis and real-time alerting. The system not only detects suspicious activities but also classifies them into different categories, such as theft, vandalism, or violent behavior, thus facilitating immediate responses from law enforcement agencies. Moreover, the paper delves into the application of deep learning in data pre-processing, noise reduction, and the handling of extensive video feeds. Techniques such as transfer learning and data augmentation are explored to enhance the model's generalization and adaptability to different surveillance environments. The scalability of the system is also discussed, allowing it to be deployed in urban centers, commercial spaces, and residential areas. While the advantages of YOLO-based CCTV crime detection are evident, this research also highlights potential challenges, including privacy concerns, ethical

关键词： Closed circuit television systems

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Brain Tumor Analysis: Unleashing the Potential of Residual UNet for Enhanced Segmentation Accuracy 4

Revolutionizing Brain Tumor Analysis: Unleashing the Potenti...

引用

4th IEEE international conference on Advance computing and Innovative Technologies in Engineering, ICACITE 2024

作者： Tiwari, Pradeep Kumar Johri, Prashant Galgotias University School of Computing Science and Engineering Greater Noida India

ISBN: (纸本)9798350360165

Advances in diagnosis have been made, leading to significant changes in the approach to mental health diagnosis. This update delivers the powerful segmentation algorithms needed to provide accurate diagnosis and treatment planning. Within the scope of this research, a new technology that uses the Residual UNet deep learning architecture is proposed to increase segmentation accuracy. Our method solves the problem of incompleteness while ensuring that the model captures the correct data. This is done by taking advantage of the fixed connection available in the UNet design. The results show that this method is more efficient than other methods. This is done through long-term experiments on large datasets, including multimodal neuroimaging. An unlikely oncology surrogate is Residual UNet, which has proven to be accurate and useful in most cases. Specifically, our strategy achieved 0.9897 accuracy, 0.9726 accuracy, 0.9985 accuracy, and 0.8665 accuracy. BraST 2020 profile is used for this purpose. Additionally, our study proves that Residual UNet exceeds standards for brain tumors. This shows that it can provide superior segmentation for existing and specific technologies. © 2024 IEEE.

关键词： Brain Tumor Medical Imaging Residual UNet Segmentation

来源：评论

学校读者我要写书评

暂无评论

GLAM-SERP: Building a Graph learning-Assisted Model for Soft Error Resilience Prediction in GPGPUs 23rd

GLAM-SERP: Building a Graph Learning-Assisted Model for Soft...

引用

23rd international conference on Algorithms and Architectures for Parallel Processing (ICA3PP)

作者： Wei, Xiaohui Zhao, Jianpeng Jiang, Nan Yue, Hengshan Jilin Univ Coll Comp Sci & Technol Changchun Peoples R China

ISBN: (纸本)9789819708581;9789819708598

Due to their efficient data-parallel computing capabilities, General-Purpose Graphics Processing Units (GPGPUs) have become increasingly prevalent in deep learning and scientific computing domains. Because of the growing chip integration density, GPGPUs are becoming more susceptible to soft errors, which can cause catastrophic results in safety-critical systems. Consequently, conducting a GPGPU program error resilience analysis is essential to provide guidance for enhancing reliability. Unfortunately, traditional analysis methods such as Statistical Fault Injection (SFI) suffer from colossal time overhead, while machine learning-based resilience prediction methods are constrained in characterizing program error propagation behavior. To address the above challenges, we propose GLAM-SERP, a Graph learning-Assisted Model for Soft Error Resilience Prediction in GPGPUs. Our critical insight is that the error resilience of GPGPU instructions is related to their inherent properties and error propagation characteristics. Thus, we construct a Dependency Graph (DG) for the GPGPU program, where nodes represent individual GPGPU instructions, node features capture the resilience characteristics of each instruction, and graph edges depict the error propagation pathway between GPGPU instructions. Based on the established DG, we then drive a Graph Attention Network (GAT) to predict Silent data Corruption (SDC) proneness of GPGPU instructions under the soft error influences. The experimental results demonstrate that our approach achieves an average prediction performance of 94.14% on individual programs and 89.50% on unseen programs, showcasing its accurate and general error resilience prediction capability in GPGPUs.

关键词： GPGPU Soft Error Error Resilience Graph Neural Network

来源：评论

学校读者我要写书评

暂无评论

HybridFL: Hybrid Approach Toward Privacy-Preserving Federated learning 6th

HybridFL: Hybrid Approach Toward Privacy-Preserving Federate...

引用

6th international conference on Security and Privacy in New computing Environments, SPNCE 2023

作者： Ali, Sheraz Mamoon, Saqib Usman, Areeba Abidin, Zain ul Zhao, Chuan School of Information Science and Engineering University of Jinan Jinan250022 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China University of Sargodha Sargodha Pakistan Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Software Engineering University of Jinan Jinan250022 China

ISBN: (纸本)9783031736988

In this study, we introduce a novel Hybrid Federated learning (HybridFL) approach aimed at enhancing privacy and accuracy in collaborative machine learning scenarios. Our methodology integrates Differential Privacy (DP) and secret sharing techniques to address inference risks during training and protect against information leakage in the output model. Drawing inspiration from recent advances, we present a HybridFL framework that combines the strengths of Homomorphic Encryption (HE) and Multi-Party Computation (MPC) to achieve secure computation without the computational overhead of pure HE methods. Our contributions include a privacy-preserving design for Federated learning (FL) that ensures local data privacy through secret sharing while leveraging DP mechanisms for noise addition. The system offers resilience against unreliable participants and is evaluated using various machine learning models, including Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), and linear regression. Furthermore, we address potential external threats by deploying predictive model outputs as robust services against inference attacks. Experimental results demonstrate improved accuracy and convergence speed, establishing the viability of HybridFL as an effective solution for collaborative machine learning with enhanced privacy guarantees. © ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Federated learning Anomaly Detection Approach for IoT Environments 2nd

A Federated Learning Anomaly Detection Approach for IoT Env...

引用

2nd international conference on Advances in computing Research, ACR 2024

作者： Suleiman, Basem Anaissi, Ali Yan, Wenbo Bello, Abubakar Zou, Sophie Tong, Ling Nga Meric School of Computer Science The University of Sydney Camperdown Australia School of Social Sciences Western Sydney University Penrith Australia

ISBN: (纸本)9783031569494

The fast-growing development of smart home environments and the popularity of IoT devices have increasingly raised security concerns about anomalous behaviour and events. Traditional methods employ machine learning (ML) models that require sharing data collected from many IoT devices from smart homes so anomalous behaviour can be learned and detected. Such approaches introduce many problems in terms of privacy of sensitive IoT data to be shared over the network, models performance overhead, and scalability. We propose a novel Federated learning Anomaly Detection (FLAD) approach for IoT smart home environments that address these problems. Our FLAD approach maintains the privacy of IoT data and faster training and detection performance by training several local models, instead of sharing it with a global model, on data collected from local devices. The local models require sharing only the learning parameter values with a global model which aggregates these values and sent them back to the local models to update their learning accordingly. Our experimental analysis of our FLAD approach on real IoT smart devices demonstrated very high accuracy (reaching over 99%) which is very comparable with the accuracy of the non-FL approach. Furthermore, our FLAD approach maintains the highest level of IoT privacy and faster model training time as it retains the IoT data within its local models and reduces network communication overhead, which has the potential to scale to a very large number of IoT devices. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Anomaly detection

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 << < 482 483 484 485 486 487 488 489 490 491 > >>

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：