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4901-4910 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：

Progressive Federated learning Scheme Based on Model Pruning 10th

Progressive Federated Learning Scheme Based on Model Pruning

引用

10th international conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2024

作者： Li, Xinsheng Sun, Chaochao Peng, Yuan Zhang, Ting College of Computer Science and Technology Shanghai University of Electric Power Shanghai China

ISBN: (纸本)9789819787456

Federated learning is an effective distributed learning framework that protects privacy and allows multiple edge devices to work together to train models jointly without exchanging data. However, edge devices usually have limited computing capabilities, and limited network bandwidth is often a major bottleneck. In order to reduce communication and computing costs, we introduced a horizontal pruning mechanism, combined federated learning and progressive learning, and proposed a progressive federated learning scheme based on model pruning. It gradually trains from simple models to more complex ones and trims the uploaded models horizontally. Our approach effectively reduces computational and bidirectional communication costs while maintaining model performance. Several image classification experiments on different models have been conducted by us, and the experimental results demonstrate that our approach can effectively save approximately 10% of the computational cost and 48% of the communication cost when compared to FedAvg. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Element Gathering Optimization-Based Probabilistic Multi-model Neural Network Classification Algorithm for Stock Market Prediction 6th

An Element Gathering Optimization-Based Probabilistic Multi-...

引用

6th international conference on Recent Innovations in computing, ICRIC 2023

作者： Nivetha, S. Sheshasaayee, Ananthi PG & Research Department of Computer Science Quaid-E-Millath Government College for Women Chennai India

ISBN: (纸本)9789819728381

Stock market prediction is the practice of predicting the performance of a specific stock or the market as a whole using statistical and machine learning approaches. Stock market forecasting is to give investors a better knowledge of the prospective risks and benefits of purchasing or selling a specific stock. Since machine learning algorithms create predictive models that can anticipate future stock prices or market trends using previous market data as well as other pertinent variables, this approach fills any missing information by utilizing a preprocessed supervised algorithm called as, depth adjacent surrounding (DSA). Then, a novel optimization algorithm, known as, element gathering (EG) is used to optimize the required features extracted from the data. This process aids in lowering the quantity of input information needed to generate reliable predictions and enhances the effectiveness of the prediction model. Based on the input data, a probabilistic multi-model neural network (PMNN) predicts whether to buy or not to buy a stock. This neural network combines the results of various distinct models to provide a single, more precise and reliable forecast. The main objective of this procedure is to create a tool that can assist investors in making more informed choices regarding whether to invest in a specific stock or not, based on a data-driven study of pertinent market and company data. In comparison with more conventional approaches, this strategy can offer a more accurate and dependable prediction of stock performance by employing machine learning algorithms to analyze and understand massive amounts of data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Two step Federated learning approach in Brain Stroke identification and classification via fine-tuning EfficientNetB0 network at Edge nodes 5

Two step Federated Learning approach in Brain Stroke identif...

引用

5th IEEE India Council international Subsections conference, INDISCON 2024

作者： Turjya, Sapthak Mohajon Singh, Raj Sarkar, Pritam Rout, Suchismita Swain, Sujata Bandyopadhyay, Anjan Computer Science and Engineering Bhubaneswar India

ISBN: (纸本)9798350376753

Brain stroke identification and classification is a crucial job in the medical sector, where timely and proper diagnosis is essential for beginning with necessary remedies. With the addition of edge computing gadgets, there is a possibility to utilize Federated learning (FL) to design effective and privacy-maintaining resolutions for brain stroke identification and classification utilizing deep neural network frameworks. In this research article, we present a Federated learning strategy for supervised brain stroke identification and categorization by fine-tuning EfficientNetB0 a CNN-based deep neural network on edge nodes. The strategy interests spreading the dataset among various edge gadgets, which can also be hospitals, where every node executes training of a local model utilizing its data while maintaining data confidentiality. A central server governs the training procedure by aggregating model weight updations from edge nodes via suitable aggregation functions, promoting cooperative learning without data accumulation at a central space. This suggested strategy executes a two-step federated training procedure, wherein in the first step the model achieves a weighted average accuracy of 100.0% to identify whether any brain stroke has taken place or not for both the edge nodes, and in the second step it involves classifying the brain stroke type reaching a state-of-art weighted average accuracy of 99.5% for both the edge nodes, thereby holding the guarantee for scalable and productive brain stroke identification and classification systems in resource-limited frameworks like edge computing networks. Alongside this, a comparison-based analysis between the proposed federated and centralized training procedure was also performed to further validate the outcomes of the proposed FL architecture. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Internet of Things (IoT) for Remote Earthquake and Fire Detection Monitoring: Linking Safety 2

Internet of Things (IoT) for Remote Earthquake and Fire Dete...

引用

2nd IEEE international conference on Trends in Quantum computing and Emerging Business Technologies, TQCEBT 2024

作者： Gayathri, S. Umaeswari, P. Muktasandhu, Muktasandhu Vignesh, M. Ramyamaranan, Ramyamaranan Dhondiyal, Shivashish R.M.K. Engineering College India R. M. K. Engineering College Department of Computer Science and Business Systems Kavaraipettai 601206 India Shri Vishwakarma Skill University DudholaHaryana Palwal121102 India Department of Civil Engineering Tamil Nadu Coimbatore641 021 India Saveetha School of Engineering Simats Department of Research and Innovation Tamil Nadu Chennai602105 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350384277

Two examples of interconnected systems and gadgets that have evolved as a result of fast technological developments are the Internet of Things (IoT) and the Internet of Vehicles (IoV). The public safety and catastrophe management sectors are only two of many that may see revolutionary changes brought forth by this technology. An Internet of Things (IoT) and Internet of Vehicles (IoV)-based safety system for remote real-time monitoring and seismic detection is proposed in this *** monitor seismic activity and detect impending fires, the proposed system employs a network of sensors installed in various buildings and vehicles. Among the many data-gathering instruments included in these sensors are vibration sensors, which can detect earthquakes, and smoke detectors, which may detect fires. The acquired data is received by a centralised control unit using wireless *** order to accurately detect earthquakes and fires, the control unit processes the provided data using advanced data analytics and machine learning techniques. The system also makes use of the IoV concept to make the reaction measures more efficient and effective. It utilises the real-time position and trajectory data of cars to aid in rapid emergency response and optimise evacuation *** are several advantages to the proposed method over more traditional forms of monitoring and safety systems. Authorities can respond swiftly to earthquakes and fires because to its real-time monitoring capabilities, which in turn reduces the likelihood of human deaths and property damage. Improving the system's responsiveness, the integration of IoV enables intelligent decision-making based on the varying traffic circumstances and available resources. © 2024 IEEE.

关键词： Smoke detectors

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinal Images Severity Prediction Using Feature Extraction Mechanism with Deep learning Method 10

Diabetic Retinal Images Severity Prediction Using Feature Ex...

引用

10th international conference on Advanced computing and Communication Systems, ICACCS 2024

作者： Murugesan, M. Sharmila, S. M Kumarasamy College of Engineering Department of Computer Science and Engineering Tamil Nadu Karur India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

Blindness occurs when lens correction, surgery, or medicine fails to improve vision. Vision is affected by diabetic retinopathy. A disease that damages retinal tissues. To avoid blindness, a computational system that automatically assesses diabetes-related retinopathy is a high goal. Transfer learning is suggested as an alternative to developing deep neural networks to scratch. This work exploits graph neural systems' excellent connection capture capabilities to present a novel DR smart categorization methodology that employs data augmentation to overcome convolutional neural systems' deficit. The theory is evaluated using APTOS2019 and Messidor-2. The suggested version has a 1.3% higher F1-score and 1.1% greater grade dependability on APTOS2019 than prior versions. Grading reliability and F1-score improved 1.4% and 1.8% on Messidor-2. © 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

Optimization of data Structures and Trade-Offs with Concurrency Control in Multithread Software Structures Using Artificial Intelligence 5

Optimization of Data Structures and Trade-Offs with Concurre...

引用

5th IEEE international conference on computing, Power, and Communication Technologies, IC2PCT 2024

作者： Cherukuri, Bangar Raju Arulkumar, V. Germantown MD United States School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore India

ISBN: (纸本)9798350383522

The optimization of data structures and trade-offs is a complex problem. This is simplified and provides solutions through the aid of artificial intelligence. There are various synchronization problems occur due to the concurrent access to the data structures. This affects the overall performance of the system. To overcome various challenges, deep learning with optimization algorithms is implemented. This helps to achieve the potential areas for optimization in multithread software by evaluating the historical patterns and performance information. Trade-offs are defined as the choices that are initiated in the optimization process for data structures in concurrency. Deep learning helps to analyze the impacts of these trade-offs by developing training models on the historical data. A large amount of data is retrieved through the deep learning techniques. This includes extracting image data for CNN and time series data for RNN and LSTM. The reduction of using data compression techniques helps in obtaining optimal performance parameters. The various forms of threats are neglected through data loading and preprocessing stages. The concurrency is essential due to the usage of multiple threats working on the neural networks. This is further accessed through synchronizing access to shared data structures. They must be properly done because excess synchronization leads to the origin of bottlenecks. A balance between data structure optimization and concurrency control must be maintained properly. Excessive concurrency control may reduce the performance. The execution speed of the CNN is enhanced through the aid of hardware accelerators. Thus the fine-tuning of trade-offs and creation of software are done through training and testing to obtain increased use of multi-core processors. © 2024 IEEE.

关键词： Artificial intelligence Concurrency data structures Deep learning Multi-core processors Multithread software Trade-offs

来源：评论

学校读者我要写书评

暂无评论

Toward Smart Scheduling in Tapis

Toward Smart Scheduling in Tapis

引用

2024 IEEE international conference on Big data, Bigdata 2024

作者： Stubbs, Joe Padhy, Smruti Cardone, Richard University of Texas at Austin Texas Advanced Computing Center AustinTX United States

ISBN: (纸本)9798350362480

The Tapis framework and APIs enable a wide range of research and scientific discovery by automating job execution on remote resources, including HPC clusters and servers running in the cloud. While Tapis simplifies interactions with cyberinfrastructure (CI), users still need to specify all details of a job they want to run, including the system, queue, node count, and maximum run time, among other attributes. Moreover, system and application resources must be defined in Tapis before a job is submitted. It can be a challenge for scientists to provide exact configurations and resource requirements for their jobs, which if incorrectly specified can delay their *** this paper, we investigate developing an intelligent job scheduling capability in Tapis, where job configuration can be partially automated and computational resources can be dynamically provisioned by Tapis. We outline an architecture for such a feature and identify a set of core challenges to be solved. Then, we focus on one specific challenge: predicting queue times for a job on different HPC systems and queues, and we present two sets of results based on machine learning methods. Our first set casts the problem as a regression, which can be used to select the best system from a list of existing options. Our second set frames the problem as a classification, which allows us to compare the use of an existing system with a dynamically provisioned resource. © 2024 IEEE.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

New Approach Based on Word Embedding and Deep learning Algorithms to Optimize the Sentiment Analysis Performance in Social Business Intelligence 6

New Approach Based on Word Embedding and Deep Learning Algor...

引用

6th international conference on Intelligent computing in data sciences, ICDS 2024

作者： Tbaikhi, Sanae Jakha, Hamza Elhoussaini, Souad Elhoussaini, Mohammed-Alamine Elkafi, Jamal Chouaib Doukkali University Faculty of Sciences Department of Computer Science El Jadida Morocco Chouaib Doukkali University ESEF Department of Computer Science El Jadida Morocco

ISBN: (纸本)9798350351200

Sentiment analysis is an essential component of Natural Language Processing (NLP) that involves analysing the polarity of sentences in a corpus. This paper aims to present a new approach of sentiments analysis. Unlike traditional feature extraction methods such as TFIDF and bag of words. The proposed method is based on word embeddings which preserve the semantic relationships between words. Additionally, the power of deep learning algorithms is more robustness in handling complex tasks, highlighting the importance of finding the optimal combination of deep learning algorithms and word embedding models that improve the accuracy of sentiment analysis models. In this study, we present various word embedding models, specifically Word2Vec, GloVe, and FastText using with an ensemble of deep learning algorithms including Recurrent Neural Networks (RNN), Gated Recurrent Units (GRU), Long Short-Term Memory networks (LSTM), Bidirectional LSTM (BiLSTM), and Convolutional Neural Networks (CNN). These models are applied on an English dataset of hotel reviews. Moreover, we explore hybrid approaches that combine different architectures, such as CNN with BiLSTM, CNN with LSTM, RNN with LSTM and RNN with BILSTM to determine the optimal configuration of these models. Our approach spans various hyperparameter settings to carefully evaluate the performance of the model configuration. According to the best of the authors' knowledge, the method, using various combinations of word embedding models and deep learning algorithms with different hyperparameters in the context of sentiment analysis, represents a new approach over exiting methodologies. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Seeking Consent for Programming Process data Collection with Trustee-Based Encryption 24

Seeking Consent for Programming Process Data Collection with...

引用

20th Annual conference on international computing Education Research (ICER)

作者： Fischer, Bjoern Barthelmes, Berit Panitz, Sven Eric Iwer, Eva-Maria Doerner, Ralf RheinMain Univ Appl Sci Wiesbaden Germany Univ Zurich Zurich Switzerland

ISBN: (纸本)9798400704758

Collecting fine-grained programming process data may require students' informed consent in order to comply with ethical and legal regulations. Previous studies suggest that such consent is not always given in the context of graded introductory programming courses due to students' concerns about being accused of plagiarism. Little is known about the students' willingness to give consent in these contexts and what strategies can be used to increase consent. In this work, we propose a novel strategy that combines data encryption with a data trustee to address a conflict of interest that arises when instructors are involved in research. Trustee-based encryption prevents instructors and researchers from accessing collected data until students have been graded while ensuring that data can be recovered if students drop out of the course. We present initial evidence that student councils are suitable candidates to serve as data trustees in higher education. To determine the impact of our strategy on consent, we conducted two experiments with computer science students enrolled in graded introductory programming courses at a German university. While we were unable to find evidence for increased willingness to consent, we found evidence that trustee-based encryption reduces signs of anxiety about the misuse of collected data. As such, our strategy can be considered beneficial for obtaining informed consent. In contexts where such consent is not required, trustee-based encryption could prevent missing or biased data caused by students who attempt to bypass data collection.

关键词： educational data mining learning analytics programming education CS1 programming environment higher education general data protection regulation de-identification trusted third party

来源：评论

学校读者我要写书评

暂无评论

Implementation of Diffusion Model in Realistic Face Generation 9

Implementation of Diffusion Model in Realistic Face Generati...

引用

9th international conference on Image, Vision and computing, ICIVC 2024

作者： Rahman, Abidur Al-Mamoon, Faiyaz Saquib, Mohammad Nazmus Fabia, Mukarrama Tun Bahar, Farhan Bin Khalilur Rhaman, Md School of Data and Sciences BRAC University Dhaka Bangladesh

ISBN: (纸本)9798350385991

This research focuses on adapting and fine-tuning diffusion models specifically to realistic face generation which has emerged as a compelling research area. By following a novel architecture that combines the diffusion process with a latent space model, which is popularly known as Stable Diffusion, enabling it to focus on facial attributes such as age, gender, facial features, and so on, without requiring massive computational units. Furthermore, we are using a dataset having diverse facial images to train and evaluate the performance of our model. This study looks into numerous sectors where the applications of this realistic face-generation technique can make the overall process more efficient including the consideration of related practical challenges. Our custom fine-tuned model has been put up for comparison with state-of-the-art diffusion models in the sector of face generation based on prompts of their facial descriptions. © 2024 IEEE.

关键词： Contrastive 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 << < 487 488 489 490 491 492 493 494 495 496 > >>

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：