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4991-5000 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：

Contrastive learning with Global Representation for Face Anti-spoofing 20th

Contrastive Learning with Global Representation for Face Ant...

引用

20th international conference on Intelligent computing (ICIC)

作者： Wang, Kai Dong, Jiwen Feng, Guang Gao, Xizhan Zhao, Hui Dong, Zihao Tian, Jinglan Liu, Bowen Niu, Sijie Jinan Univ Sch Informat Sci & Engn Jinan 250022 Peoples R China

ISBN: (纸本)9789819755936;9789819755943

Face anti-spoofing (FAS) technology plays a crucial role in enhancing the face recognition system's safety and reliability. However, existing FAS methods generally rely on a significant volume of annotated data. Labeling the data is time-consuming and expensive. With the aim of solving the problem, PTL (progressive transfer learning) proposed an online learning framework for training FAS models with a few amount of labeled training data, such as only 50 face images. Despite its remarkable achievements, the approach does not explore the spoofing patterns inherent in face anti-spoofing task. To address this issue, we introduce a contrastive learning strategy with global representation (GRCL) into the training framework. By training the model to make it learn the global representation of the training data and create contrast loss for the overlapping regions of real faces and spoofing faces in the feature space, the feature generation ability of the model can be enhanced without destroying the original feature distribution. At the same time, we create a support set to dynamically generate global representative features in the training data for learning feature representations. Our approach can effectively work with the online learning framework to enhance the performance of models by using unlabeled data. Extensive experiments on four datasets with few labeled data validate the efficacy of our method.

关键词： Face Anti-spoofing Contrastive learning Curriculum learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning-Based Emotion Recognition using CNN, LSTM for Multimodal Text, Speech, and Facial Analysis 5

Deep Learning-Based Emotion Recognition using CNN, LSTM for ...

引用

5th international conference on data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Firdou, Talat Binti Ashra, Mohammed Kalpan, A.V. School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Kattankulathur India

ISBN: (纸本)9798350389609

Emotion detection is a critical field in AI as well as computer vision, seeking to recognize or detect human emotions from facial expressions. Although this area has been greatly advanced through Convolutional Neural Networks (CNNs), current methods using only single-modal data often exhibit reduced accuracy. In this work, we confront these challenges with a hybrid deep learning method for disparate modalities of information such as speech, video, and text. We pre-process and then use CNN feature extractors for the FER2013 data set. The hybrid deep learning model, hence proposed, achieved a weighted accuracy of 79.3% on FER2013, overcoming the conventional unimodal methods. We are using transformers library with the pre-trained RoBERTa model for text. For speech emotion features, we are using TESS dataset then using a CNN and LSTM (Long Short-Term Memory) model. The CNN extracts feature from the speech, while the LSTM is used for temporal analysis to detect emotions. Once these multimodal features have been obtained, our work would be to fuse in order to get the final emotion recognition using Deep Neural Networks (DNNs). The process increases the precision and reliability of the recognition systems, helping to accumulate even more detailed intuition for different emotional states for a combined approach. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TransFlowGAN: Generation and Balancing of Network Traffic data 24

TransFlowGAN: Generation and Balancing of Network Traffic Da...

引用

2024 Asia Pacific conference on computing Technologies, Communications and Networking, CTCNet 2024

作者： Zhang, Hongzheng National Key Laboratory of Science and Technology on Information System Security China

ISBN: (纸本)9798400709609

In recent years, with the rapid development of deep learning technology, researchers in the field of network security have begun to explore the use of deep learning to solve the problem of encrypted traffic classification. However, existing publicly available encrypted traffic datasets suffer from severe class imbalance issues, which significantly impact the performance of deep learning classification methods. Constructing a complete encrypted traffic dataset from scratch is both time-consuming and costly. To address this issue, this paper proposes an innovative model named TransFlowRGAN, which is an encrypted traffic sequence feature generation model that combines Transformer and Relative Generative Adversarial Network (RGAN). Our model leverages the advantages of RGAN, effectively mitigating the instability and mode collapse issues that traditional GAN models often encounter during training. Additionally, it incorporates the Transformer architecture. The self-attention mechanism of the Transformer can better capture the complex features and long-term dependencies in traffic data, resulting in the generation of higher-quality data. We evaluated the performance of our model on the ISCXVPN2016 public dataset. The results demonstrate that TransFlowRGAN excels in handling imbalanced datasets, significantly outperforming other data augmentation models. © 2024 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Utilizing data Analytics in Sports Performance Optimization 1

Utilizing Data Analytics in Sports Performance Optimization

引用

1st IEEE international conference on Advances in computing, Communication and Networking, ICAC2N 2024

作者： Sharma, Madhuri Kaushik, Vikas Rathore, Manisha Yadav, Vivit Kumar Gangwar, Pallavi Nibiya, Anto Dept. of Life Sciences CHRI Campus Gwalior India Madhav University Dept. of Commerce & Management Pindwara India J.S. University Dept. of Physical Education Shikohabad India Lingayas Vidyapeeth Dept. of Education Faridabad India Meenakshi A.H. Edu. & Research Dept. of Mathematics Chennai India

ISBN: (纸本)9798350356816

data analytics has been a game-changing instrument in sports in recent years, transforming strategies for strategic planning and performance optimization. The use of data analytics to improve sports performance is examined in this study, with a particular emphasis on the advanced approaches that can be used to enhance player performance, team strategy, and game outcomes overall. Sports data analytics uses a variety of techniques, such as machine learning algorithms for predictive modeling and statistical analysis of player metrics. Through the examination of various datasets, including player statistics, game film, and physiological data, coaches and teams can derive valuable insights that inform tactical choices and improve training regimens. This study focuses at case studies from several sports disciplines to show how data-driven methods have improved performance in quantifiable ways. It also looks at how cutting-edge technology like computer vision systems and wearable sensors can be integrated to offer real-time data and enable thorough performance analysis. The study also discusses the difficulties of applying data analytics to sports, such as problems with data quality, the requirement for interdisciplinary knowledge, and striking a balance between human intuition and data-driven choices. This research intends to emphasize the major impact of data analytics on sports performance optimization through a thorough evaluation of current practices and future developments. It also provides recommendations for optimizing the efficacy of analytical tactics. This study helps to create novel strategies that improve individual athlete performance as well as team achievement by bridging the gap between data science and sports management. © 2024 IEEE.

关键词： data Analytics Game Strategy Performance Optimization Predictive Modeling Sports Performance Wearable Technology

来源：评论

学校读者我要写书评

暂无评论

Lung Opacity Classification in Chest X-Ray Images with a DenseNet201 Transfer learning-Based Pre-Trained Convolutional Neural Network Model

Lung Opacity Classification in Chest X-Ray Images with a Den...

引用

2024 international conference on Communication, computing and Internet of Things, IC3IoT 2024

作者： Singla, Muskan Gill, Kanwarpartap Singh Rajput, Kapil Singh, Vijay Chitkara University Institute Of Engineering And Technology Chitkara University Punjab India Graphic Era Hill University Computer Science & Engineering Uttarakhand Dehradun248002 India Graphic Era Deemed To Be University Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350352689

Using transfer learning, this study presents a new method for classifying lung opacity in chest X-ray pictures;the method centers on Keras and the DenseNet201 model. This paper examines the RSNA Pneumonia Detection Challenge dataset and its extensive preprocessing procedures, such as dataset overview, splitting, and balancing. Importantly, Keras has been modified to be DICOM compatible, which solves problems with processing chest X-ray pictures. The generated model is more resilient thanks to the deployment of basic data augmentation techniques, which increase the dataset. The study describes the pretrained DenseNet201 model in great detail, including the extra layers that were added to improve the model's performance on the lung opacity classification task. A comprehensive examination of a model includes looking at its architecture, parameters, and performance indicators including F1-score, recall, and precision. Insights into test-time augmentation tactics are presented in the study's conclusion, with an emphasis on the significance of making two predictions for each image to increase reliability. A 79% success rate in classifying lung opacity in chest X-ray pictures using a combination of transfer learning and Keras is a major step forward for medical imaging as a whole. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

QH-Bird: A Fine-Grained Bird Visual dataset and Hierarchical Consistency Denoising Method 3

QH-Bird: A Fine-Grained Bird Visual Dataset and Hierarchical...

引用

3rd international conference on Artificial Intelligence, Internet of Things and Cloud computing Technology, AIoTC 2024

作者： Song, Wenjing Geng, Shengling Zhang, Dan School of Computer Science Qinghai Normal University China Academy of Plateau Science and Sustainability People's Government of Qinghai Province Beijing Normal University China Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining China

ISBN: (纸本)9798331530280

To address the lack of bird image datasets in the field of fine-grained image recognition, this paper introduces a new fine-grained bird image dataset and a deep learning-based denoising method. The dataset encompasses 50,000 images across 200 species. Initially, we constructed an initial bird image dataset by sourcing and compiling images from specialized books and online resources. Subsequently, we employed image deduplication methods based on difference hashing (dHash) and structural similarity index (SSIM) to clean duplicate images from the dataset. Following this, we applied a deep learning-based hierarchical consistency learning method to identify noisy web images, using classification loss and semantic consistency prediction. To further enhance the dataset's diversity and balance, we expanded the number of images for each bird species using data augmentation techniques such as rotation, mirroring, random cropping, and adjustments in brightness and contrast. Ultimately, we constructed a high-quality, balanced, and diverse bird image dataset, named QH-Bird, which serves as a valuable resource for research and applications in fine-grained image recognition. We evaluated our dataset using four deep learning models: VGG-16, ResNet-50, EfficientNet, and HCLNet, achieving accuracies of 87.17%, 88.59%, 90.28%, and 91.59%, respectively. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Maximizing Marketing ROI with Advanced Deep learning Techniques for Predictive Modeling and Customer Segmentation 15

Maximizing Marketing ROI with Advanced Deep Learning Techniq...

引用

15th international conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： SivaKumar, Challa Venkata Naga Mariyappan, M.S.R. Borugadda, Subbaiah Murthy, B.G.K. Shareef, S.K.J. Rahaman, Md S. Business School Koneru Lakshmaiah Education Foundation A.P. Vaddeswaram India School of Management Vel Tech Rangarajan Dr.Sagunthala R&D Institute ofScience and Technology Chennai India Department of Commerce and Management Studies Andhra University Visakhapatnam India Dhruva College of Management Hyderabad Medchal India Department of ManagementStudies Sri Mittapalli College of Engineering Guntur India Department of BusinessAdministration PB Siddhartha College of Artsand Science Vijayawada India

ISBN: (纸本)9798350370249

One common and successful tactic for optimising marketing return on investment is the application of sophisticated deep learning techniques for consumer segmentation and predictive modelling. A family of algorithms known as "deep learning" is able to extract intricate patterns from data, which makes predictions and segmentations more precise. The capacity of sophisticated deep learning methods to handle big and complicated datasets is one of its main advantages. In the constantly evolving digital landscape, marketers have access to a wealth of customer data from a variety of sources, including social media, website interactions, and purchase histories. Deep learning algorithms may be able to process these massive volumes of data and produce relevant information that aids in campaign targeting and consumer segmentation. Furthermore, deep learning techniques can reveal patterns and links in the data that were previously unknown, giving marketers a better insight of the requirements, preferences, and behaviours of their target audience. This makes it possible to implement relevant and customised marketing tactics that connect with customers and increase engagement and conversion rates. Having the capacity to continually learn and get better over time is another benefit of adopting cutting edge deep learning techniques for predictive modelling. Compared to conventional statistical methods, these algorithms are more accurate and dependable since they are trained on big datasets and can adapt to new data. ©2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Enabling Rapid data Transfer in Medical IoT Systems with a High-Throughput PRESENT Cipher Hardware Framework

Enabling Rapid Data Transfer in Medical IoT Systems with a H...

引用

2024 international conference on Sustainable computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： Reddy, Uma Rangaiah, Yagateela Pandu Nagpal, Amandeep Goyal, Himanshu Rai Sundari, Mandapati Venkata Rama Adnan, K. Department of Artificial Intelligence and Machine Learning New Horizon College of Engineering Bangalore India Department of Electronics and Communication Enfineering Institute of Aeronautical Engineering Hyderabad Dundigal500043 India LPU Phagwara India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India GRIET Bachupally Telangana Hyderabad India Hilla University College Babylon Iraq

ISBN: (纸本)9798350355338

The timely and dependable sharing of essential medical information is dependent on fast and secure data transfer in the arena of Medical Internet of Things (IoT) technologies. In order to facilitate quick data transmission in Medical IoT devices, a high-throughput PRESENT Cipher hardware architecture is presented here. The suggested technique is comprised of various integral parts, such as the design of the hardware framework, the selection of the algorithm, the management of the keys, and the optimization of the performance. Important features of the proposed technique, such encryption, data compression, and error correction, are represented by mathematical equations. At its heart, our method is the PRESENT Cipher Algorithm, which is lauded for its efficiency and its high level of security. This technique is quite effective at encrypting data, protecting it while in transit. data compression methods like Run-Length Encoding (RLE) are used to decrease data size and improve efficiency. ReedSolomon codes provide error correction and hence ensure the reliability of transmitted data. Encryption keys are also protected by means of key management and other security procedures. It is determined how successful the suggested approach is by defining and evaluating a variety of performance assessment measures such as encryption speed, energy efficiency, data transmission rate, latency, resource usage, data integrity, compatibility, and scalability. The results show that the suggested technique is superior to the status quo methods in many respects. It is well-suited to the requirements of Medical IoT systems because to its faster encryption speed, reduced energy usage, larger data transmission speeds, and enhanced data integrity. © 2024 IEEE.

关键词： data integrity

来源：评论

学校读者我要写书评

暂无评论

Federated learning on low-power Arduino Nano33 BLE Sense to predict the length of stay using a linear regression model 2

Federated learning on low-power Arduino Nano33 BLE Sense to ...

引用

2nd international conference on machine learning and data Engineering, ICMLDE 2023

作者： Sriram, S. Rk, Hariharathmajan Barathi Babu, M. Pradeep, Amal Karthi, R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

Federated learning (FL) is a collaborative learning paradigm where multiple clients are used to build the model without sharing data and preserving privacy. An FL-based linear regression model is designed to predict the length of stay for patients at hospitals using the low-power Arduino Nano 33 BLE Sense microcontroller unit (MCU). FL uses a distributed learning technique that allows model building from decentralized data sources. The Arduino Nano 33 BLE Sense is a compact and energy-efficient MCU providing an ideal platform for implementing FL in resource-constrained environments. FL algorithms aggregate model parameters from multiple Arduino clients and collectively train and build a predictive model to estimate the length of stay at the hospital by patients. Experiments were conducted to understand the performance of FL on clients with data of equal and varying sizes and heterogeneous data from multiple sources. The performance of the algorithm is evaluated based on Mean Absolute Error (MAE), Percentage Decrease in Training error (PDTE), and Percentage Difference with Optimal Testing (PDOT) value. Experimental results show that the number of local epochs and FL rounds affects the convergence of clients to the optimal value. The experimental results demonstrate the applicability of FL on low-power MCUs, preserving privacy which is a core requirement for healthcare solutions. © 2024 Elsevier B.V.. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Effectiveness of Project-Based learning: Significant learning in the Subject of Programming and Algorithm for Engineering Careers 43

Evaluation of the Effectiveness of Project-Based Learning: S...

引用

43rd international conference of the Chilean Computer science Society, SCCC 2024

作者： Manriquez Barria, Jacqueline Universidad de Atacama Uda Departamento de Ingeniería en Informática y Ciencias de la Computación Copiapó Chile

ISBN: (纸本)9798331527891

Currently, higher education is oriented towards competency-based teaching, promoting meaningful learning. Many universities in our country are implementing a student-centered teaching-learning model, where the teacher acts as a facilitator through educational innovation projects. However, there remains a need to evaluate the effectiveness of these practices. This study describes an empirical experience of incorporating project-based learning as active methodologies in the context of higher education, focusing on meaningful, dynamic, participatory learning, and the autonomous development of students. Students from various majors from the Faculty of Engineering participated: 56 from Civil Engineering in computing, 15 from Civil Engineering in Metallurgy, 9 from Civil Industrial Engineering (all at level 100), and 16 from Civil Engineering in Mines (level 400). The students worked on a graphic visualization project of data linked to their careers in the subject of Programming and Algorithm. The exploratory and descriptive study used questionnaires as verification methods to measure approaches to teaching (ATI), learning processes (SPQ), course experience (CEQ), satisfaction with methodological innovation, and autonomous work. The results obtained indicate that the implementation of active methodologies in the classroom significantly contributes to the development of learning. © 2024 IEEE.

关键词： Students

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：