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

13,379 篇 会议
18 篇 期刊文献
13 册 图书

馆藏范围

13,410 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,114 篇 工学
- 6,410 篇 计算机科学与技术...
- 5,128 篇 软件工程
- 1,743 篇 信息与通信工程
- 1,025 篇 控制科学与工程
- 736 篇 生物工程
- 724 篇 电气工程
- 665 篇 生物医学工程（可授...
- 597 篇 网络空间安全
- 512 篇 光学工程
- 452 篇 安全科学与工程
- 404 篇 电子科学与技术（可...
- 347 篇 交通运输工程
- 329 篇 动力工程及工程热...
- 304 篇 机械工程
- 268 篇 仪器科学与技术
2,699 篇 理学
- 1,326 篇 数学
- 881 篇 生物学
- 641 篇 统计学（可授理学、...
- 540 篇 物理学
- 331 篇 系统科学
- 244 篇 化学
1,882 篇 管理学
- 1,305 篇 管理科学与工程(可...
- 792 篇 图书情报与档案管...
- 574 篇 工商管理
946 篇 医学
- 686 篇 临床医学
- 679 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...
509 篇 法学
- 470 篇 社会学
265 篇 经济学
- 265 篇 应用经济学
226 篇 农学
207 篇 教育学
198 篇 文学
9 篇 军事学
1 篇 艺术学

主题

2,084 篇 accuracy
1,684 篇 deep learning
1,188 篇 computational mo...
1,185 篇 machine learning
1,044 篇 training
1,026 篇 data models
969 篇 predictive model...
725 篇 real-time system...
691 篇 convolutional ne...
684 篇 feature extracti...
676 篇 machine learning...
584 篇 support vector m...
534 篇 federated learni...
496 篇 adversarial mach...
338 篇 contrastive lear...
311 篇 medical services
295 篇 random forests
286 篇 analytical model...
278 篇 prediction algor...
270 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...
45 篇 department of co...
42 篇 the islamic univ...
40 篇 shandong provinc...
37 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

12,117 篇 英文
1,292 篇 其他
343 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 13410 条记录，以下是191-200 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：

Evaluation of Document Deduplication Algorithms for Large Text Corpora 10th

Evaluation of Document Deduplication Algorithms for Large ...

引用

10th international conference on machine learning, Optimization, and data science, LOD 2024

作者： Leveling, Johannes Helmer, Lennard Stein, Benny Joerg Wegener, Dennis Sheikh, Zoha Fernandes, Elanton Abdelwahab, Hammam Sankt Augustin Germany Lamarr Institute for Machine Learning and Artificial Intelligence Sankt Augustin Germany

ISBN: (纸本)9783031824807

Performance of large language models (LLMs) is correlated with diverse and high-quality training data. One aspect of data quality is the presence of duplicate documents in the training data. In this paper, we evaluate five algorithms for deduplicating large data sets, namely MinHash/LSH, Exact Hashes, SimHash, Scalable Bloom filter, and Suffix Array. We report on their precision, recall, memory requirements and runtime on deduplicating OpenSubtitles and Oscar data for five languages (EN, DE, ES, FR, IT). We find that the best overall performance is achieved by using a MinHash/LSH, but other options such as Scalable Bloom filter can be more suitable in resource-critical situations. While precision varies between 0.833 and 0.985 across algorithms, recall varies between 0.247 and 0.989, indicating different levels of aggressiveness. We conclude that MinHash/LSH is the most suitable algorithm to deduplicate pretraining data for LLMs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

Land Use Land Cover Change Analysis Based on Deep learning and SVM Classifier Using Geospatial data (Case Study Mandalay Township) 16th

Land Use Land Cover Change Analysis Based on Deep Learning a...

引用

16th international conference on Genetic and Evolutionary computing, ICGEC 2024

作者： Thein, Aye Mya Htwe, Ah Nge Remote Sensing Department Mandalay Technological University Mandalay Myanmar Faculty of Computer Science University of Computer Studies Yangon Myanmar

ISBN: (纸本)9789819615308

Analyzing land use and land cover (LULC) change is critical for understanding environmental impacts and informing urban planning. This study investigates LULC changes in Mandalay Township over the years 2014 to 2023, employing deep learning with a CNN model and a Support Vector machine (SVM) model on geospatial data. Satellite imagery and ancillary data from these years were used to classify six classes: built-up areas, bare land, water, wetland, plantation forest, and herbaceous. The output results included two classification maps and an accuracy assessment. In this classification, the SVM model classifier showed the best accuracy assessment, so this classification was used to identify change area, change type map, and change detection map. The main aim of this paper is to monitor and detect land use and land cover changes in Mandalay Township based on deep learning with a CNN model and an SVM model classifier over 10 years. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

15th international Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th international conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2024

15th International Workshop on Computational Diffusion MRI, ...

引用

15th international Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th international conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2024

ISBN: (纸本)9783031869198

The proceedings contain 19 papers. The special focus in this conference is on Computational Diffusion MRI. The topics include: Ground-Truth Effects in learning-Based Fiber Orientation Distribution Estimation in Neonatal Brains;synthesizing 3D Axon Morphology: Springs are All We Need;Randomly COMMITting: Iterative Convex Optimization for Microstructure-Informed Tractography;AID-DTI: Accelerating High-Fidelity Diffusion Tensor Imaging with Detail-Preserving Model-Based Deep learning;multi-dimensional Parameter Space Exploration for Streamline-Specific Tractography;cross-Domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction;can Transfer learning Improve Supervised Segmentation of White Matter Bundles in Glioma Patients?;Image Quality Transfer of Diffusion MRI Guided By High-Resolution Structural MRI;QID2: An Image-Conditioned Diffusion Model for Q-Space Up-Sampling of DWI data;Ts-FWE: Token-Aware Single-Shell Free Water Estimation for Brain Diffusion MRI;Assessing Early Motor System Degeneration in the Spinal Cord of ALS Patients Using Diffusion MRI: An Exploratory Study;RobNODDI: Robust NODDI Parameter Estimation with Adaptive Sampling Under Continuous Representation;introducing QuantConn: Overcoming Challenging Diffusion Acquisitions with Harmonization;learning Low-Rank Tensor Approximation for GPU-Based Tractography;deep Multivariate Autoencoder for Capturing Complexity in Brain Structure and Behaviour Relationships;heritability and Genetic Correlations Along the Corticospinal Tract;corpus Callosum Parcellation Methods: What Can Tractography Tell Us About Them?.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human emotion recognition using deep learning 4th

Human emotion recognition using deep learning

引用

4th international conference on Computational Methods in science and Technology, ICCMST 2024

作者： Rajpoot, Shivam Singh, Jagrati Centre for Advanced Studies AKTU India Indira Gandhi Delhi Technical University for Women Delhi India

ISBN: (纸本)9781032911571

Human-computer interface and pitiful computing profoundly rely on emotion recognition from facial expressions. Deep learning approaches have recently established astonishing performance in a variety of computer vision applications, including emotion recognition. In-depth research on the use of deep learning techniques for identifying human emotions from facial photographs is obtainable in this publication. Convolutional Neural Network (CNN) is used in the recommended method to repeatedly extract emotional information from facial picture. For training and testing, a dataset with a wide assortment of facial expressions instead of various emotions is used. To recover the resilience and generalization capacities of the model, preprocessing approaches including data expansion and normalization are used. To obtain the paramount performance, the network design is tuned using hyperparameters and irritatedvalidated. Extensive experiments are carried out to contrast the performance of a variety of deep learning architectures, counting conventional CNN and more complicated architectures like VGG-16, in order to judge the effectiveness of the recommended approach. Aspects of valuation measures include F1-score, recall, accuracy, and precision. The results of the research show that deep learning approaches are more efficient than conventional ones at identify multifaceted patterns in facial expressions, which lead to improved emotion recognition performance. The planned method achieved an accuracy of 92.28 percent on fre2013 consisting of 7 classes. The experimental study show that the projected move toward is far more efficient and yield improved performance. © 2025 the Author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

DPGame: Game-Based learning for Dynamic Programming Algorithms 23rd

DPGame: Game-Based Learning for Dynamic Programming Algorit...

引用

23rd IFIP TC 14 international conference on Entertainment computing, ICEC 2024

作者： Zhu, Ying Georgia State University Atlanta United States

ISBN: (纸本)9783031743528

Dynamic programming is one of the most challenging topics in data structures and algorithms courses. Students often struggle to grasp dynamic programming techniques and apply them to solve problems. The common advice to students is to study lots of dynamic programming examples. However, analyzing source code is not an engaging experience for most students. This issue motivated us to design a game-based learning environment for dynamic programming. Although game-based methods have been used in computer science education, there have been no examples of games specifically designed to teach dynamic programming. In this paper, we introduce DPGame, a multi-level puzzle game that facilitates the learning process by guiding students through the construction of dynamic programming algorithms via increasingly challenging examples. In the game, the player’s goal is to construct a logical dependency diagram by answering a series of questions, similar to assembling a visual puzzle. This game can help students identify recurring logical patterns in dynamic programming and fosters a high-level understanding of the algorithm prior to tackling the low-level details of code implementation. © 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 Privacy in Federated learning: Secure Aggregation for Real-World Healthcare Applications 9th

Enhancing Privacy in Federated Learning: Secure Aggregation ...

引用

27th international conference on Medical Image computing and Computer Assisted Intervention (MICCAI)

作者： Taiello, Riccardo Cansiz, Sergen Vesin, Marc Cremonesi, Francesco Innocenti, Lucia Onen, Melek Lorenzi, Marco Inria Epione Res Project Paris France EURECOM Paris France Univ Cote dAzur Nice France

ISBN: (纸本)9783031776090;9783031776106

Deploying federated learning (FL) in real-world scenarios, particularly in healthcare, poses challenges in communication and security. In particular, with respect to the federated aggregation procedure, researchers have been focusing on the study of secure aggregation (SA) schemes to provide privacy guarantees over the model's parameters transmitted by the clients. Nevertheless, the practical availability of SA in currently available FL frameworks is currently limited, due to computational and communication bottlenecks. To fill this gap, this study explores the implementation of SA within the open-source Fed-BioMed framework. We implement and compare two SA protocols, Joye-Libert (JL) and Low Overhead Masking (LOM), by providing extensive benchmarks in a panel of healthcare data analysis problems. Our theoretical and experimental evaluations on four datasets demonstrate that SA protocols effectively protect privacy while maintaining task accuracy. Computational overhead during training is less than 1% on a CPU and less than 50% on a GPU for large models, with protection phases tacking less than 10 s. Incorporating SA into Fed-BioMed impacts task accuracy by no more than 2% compared to non-SA scenarios. Overall this study demonstrates the feasibility of SA in real-world healthcare applications and contributes in reducing the gap towards the adoption of privacy-preserving technologies in sensitive applications.

关键词： Federated learning Secure Aggregation Healthcare Applications

来源：评论

学校读者我要写书评

暂无评论

Fraud Detection Using machine learning Models and Encryption Techniques 26th

Fraud Detection Using Machine Learning Models and Encryptio...

引用

26th international conference on Artificial Intelligence and Applications, ICAI 2024, held as part of the World Congress in Computer science, Computer Engineering and Applied computing, CSCE 2024

作者： Agrawal, Jigyasa Nguyen, Hien Penn State Harrisburg Middletown 17036 PA United States

ISBN: (纸本)9783031866227

In the era of increasing digital transactions and data exchange, safeguarding financial assets and data from fraudulent activities is a critical concern. Although existing algorithms have shown success, they face challenges in achieving a commendable level of precision for encrypted data. This research investigates the integration of Fully Homomorphic Encryption (FHE) into Logistic Regression and XGBoost models for credit card fraud detection, addressing a gap in existing literature. The results indicate that FHE does not significantly compromise model accuracy, with Logistic Regression and XGBoost achieving comparable performance on encrypted and plain text data. Real-world applicability is demonstrated using the ULB and Vesta datasets. The findings contribute to the discourse on privacy-preserving machine learning and offer insights for secure credit card fraud detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Credit Card Fraud Detection Fully Homomorphic Encryption Logistic Regression XGBoost

来源：评论

学校读者我要写书评

暂无评论

FedScale: A Federated Unlearning Method Mimicking Human Forgetting Processes 18th

FedScale: A Federated Unlearning Method Mimicking Human Forg...

引用

18th international conference on Wireless Artificial Intelligent computing Systems and Applications, WASA 2024

作者： Huang, Wenshu Wu, Huiwen Fang, Liming Zhou, Lu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Shenzhen Research Institute Nanjing University of Aeronautics and Astronautics Shenzhen China Research Center for Data Hub and Security Zhejiang Laboratory Hangzhou311000 China

ISBN: (纸本)9783031714634

The heightened demands for privacy protection, combined with legal mandates granting users the right to be forgotten, emphasize the growing importance of endowing models with the capability to forget specific sample information. Unlearning is akin to the reverse process of model training, which involves the elimination of the influence of training data on a machine learning model. In the context of federated learning, conducting unlearning is notably more demanding, as data is dispersed across multiple client endpoints. Due to privacy and security concerns, many conventional machine unlearning methods are no longer applicable. This paper draws inspiration from the forgetting processes in the human brain, highlighting that memory attrition is not solely a passive process. Therefore, we dichotomize the federated unlearning process into two components: active forgetting and passive forgetting. We make respective modifications to the updates of these two components to achieve efficient unlearning. We propose an approach called FedScale, which only sacrifices a fraction of storage space, enabling a rapid federated unlearning process without the need for retraining the federated model when it becomes necessary to forget a user’s data. Experimental evaluations are conducted on four datasets, demonstrating the effectiveness of FedScale unlearning. Furthermore, we show its resilience against backdoor attacks and membership inference attacks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Secure Resource Allocation via Constrained Deep Reinforcement learning 6th

Secure Resource Allocation via Constrained Deep Reinforceme...

引用

6th international conference on machine learning for Cyber Security, ML4CS 2024

作者： Sun, Jianfei Gao, Qiang Wu, Cong Li, Yuxian Wang, Jiacheng Niyato, Dusit School of Computing and Information Systems Singapore Management University Singapore188065 Singapore School of Computing and Artificial Intelligence Southwestern University of Finance and Economics Chengdu611130 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

ISBN: (纸本)9789819645657

The proliferation of Internet of Things (IoT) devices and the advent of 6G technologies have introduced computationally intensive tasks that often surpass the processing capabilities of user devices. Efficient and secure resource allocation in serverless multi-cloud edge computing environments is essential for supporting these demands and advancing distributed computing. However, existing solutions frequently struggle with the complexity of multi-cloud infrastructures, robust security integration, and effective application of traditional deep reinforcement learning (DRL) techniques under system constraints. To address these challenges, we present SARMTO, a novel framework that integrates an action-constrained DRL model. SARMTO dynamically balances resource allocation, task offloading, security, and performance by utilizing a Markov decision process formulation, an adaptive security mechanism, and sophisticated optimization techniques. Extensive simulations across varying scenarios-including different task loads, data sizes, and MEC capacities-show that SARMTO consistently outperforms five baseline approaches, achieving up to a 40% reduction in system costs and a 41.5% improvement in energy efficiency over state-of-the-art methods. These enhancements highlight SARMTO ’s potential to revolutionize resource management in intricate distributed computing environments, opening the door to more efficient and secure IoT and edge computing applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Application with Digital Currencies Trading Using machine learning 18th

Application with Digital Currencies Trading Using Machine L...

引用

18th international conference on Wireless Artificial Intelligent computing Systems and Applications, WASA 2024

作者： Zheng, Tengjiao Ning, Li Zhao, Yanming Yiu, Siu Ming The University of Hong Kong Pok Fu Lam Hong Kong University of Chinese Academy of Science ShenZhen China

ISBN: (纸本)9783031714634

At present, with the rapid development of blockchain technology and digital currencies, digital assets have gradually become a crucial component of investment portfolios, with Bitcoin standing out as the most prominent. Our aim is to reduce the investment risk for stakeholders in the highly volatile Bitcoin market by expanding predictions beyond Bitcoin and into other digital currencies. Through the application of machine learning models tailored for time series data and deep learning models, we have discovered methods for predicting Bitcoin prices with a high degree of accuracy. This article centers around predicting the closing price of Bitcoin using attributes from various categories of digital currencies, including Bitcoin itself, Ethereum and stablecoins. We employ multiple evaluation techniques to assess the performance of our models. Our findings indicate that using Bitcoin’s attributes or stablecoins pegged to Bitcoin can achieve accuracy rates of up to 98%, with Ethereum closely following, boasting accuracy rates exceeding 90%. In the practical application domain, we innovatively employed a stablecoin model pegged to Bitcoin for backtesting Bitcoin returns. This model not only filled a significant gap in this field but also surpassed models trained solely on Bitcoin itself, yielding returns that exceeded 40 times. This approach underscores the potential of diversifying predictive analytics in digital asset investments. © 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

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 << < 16 17 18 19 20 21 22 23 24 25 > >>

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：