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

6,860 篇 会议
72 篇 期刊文献
44 册 图书

馆藏范围

6,977 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,967 篇 工学
- 3,667 篇 计算机科学与技术...
- 2,767 篇 软件工程
- 1,207 篇 信息与通信工程
- 718 篇 控制科学与工程
- 518 篇 电气工程
- 475 篇 生物工程
- 338 篇 网络空间安全
- 314 篇 生物医学工程（可授...
- 274 篇 电子科学与技术（可...
- 262 篇 动力工程及工程热...
- 221 篇 交通运输工程
- 221 篇 安全科学与工程
- 216 篇 机械工程
- 211 篇 仪器科学与技术
- 179 篇 光学工程
- 170 篇 石油与天然气工程
- 167 篇 化学工程与技术
1,728 篇 理学
- 1,027 篇 数学
- 494 篇 生物学
- 372 篇 统计学（可授理学、...
- 309 篇 物理学
- 257 篇 化学
- 195 篇 系统科学
1,374 篇 管理学
- 782 篇 图书情报与档案管...
- 755 篇 管理科学与工程(可...
- 352 篇 工商管理
342 篇 医学
- 272 篇 临床医学
- 260 篇 基础医学(可授医学...
- 170 篇 公共卫生与预防医...
196 篇 法学
- 164 篇 社会学
130 篇 经济学
87 篇 农学
72 篇 教育学
19 篇 文学
8 篇 军事学
2 篇 艺术学

主题

311 篇 big data
297 篇 machine learning
213 篇 deep learning
211 篇 data mining
203 篇 data models
158 篇 cloud computing
139 篇 machine learning...
124 篇 training
120 篇 computational mo...
116 篇 feature extracti...
108 篇 signal processin...
103 篇 predictive model...
97 篇 internet of thin...
96 篇 signal processin...
94 篇 prediction algor...
89 篇 support vector m...
83 篇 data privacy
81 篇 artificial intel...
75 篇 sentiment analys...
72 篇 edge computing

机构

88 篇 maharishi school...
67 篇 centre of interd...
31 篇 department of ar...
28 篇 tianjin universi...
28 篇 college of compu...
27 篇 vishwakarma inst...
26 篇 department of co...
26 篇 department of el...
25 篇 chitkara univers...
25 篇 department of co...
22 篇 department of in...
20 篇 vivekananda glob...
19 篇 university of ch...
18 篇 vishwakarma inst...
17 篇 chitkara univers...
17 篇 lovely professio...
17 篇 department of sc...
16 篇 department of el...
15 篇 vishwakarma inst...
14 篇 key laboratory o...

作者

13 篇 ramakrishnan ram...
11 篇 dipannita mondal
10 篇 wang jing
10 篇 nitin n. sakhare
10 篇 mondal dipannita
10 篇 rajeswari d.
8 篇 kumar ritesh
8 篇 akhilendra prata...
8 篇 xu xiaolong
8 篇 li zuoyong
8 篇 jambi ratna raja...
7 篇 chen chen
7 篇 liu ying
7 篇 wang tao
7 篇 vaishali singh
7 篇 kodipalli ashwin...
7 篇 zhang jing
6 篇 zheng-guang wu
6 篇 bin wang
6 篇 ye jun

语言

3,941 篇 英文
3,029 篇 其他
156 篇 中文

检索条件"任意字段=2023 International Conference on Algorithms, Computing and Data Processing, ACDP 2023"

共 6977 条记录，以下是4361-4370 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：

Construction of Intelligent Health Management Cloud Platform Based on Big data

Construction of Intelligent Health Management Cloud Platform...

引用

Evolutionary algorithms and Soft computing Techniques (EASCT), international conference on

作者： Rui Ma Fengjiao Zhou Health and Rehabilitation College Chengdu University of Traditional Chinese Medicine Chengdu China Acupuncture School Affiliated Hospital of Chengdu University of Traditional Chinese Medicine Chengdu China

With the advent of the era of big data, more and more people get the information they need and are interested in through various channels in daily life, and the traditional medical model can no longer meet the needs of human health management. In order to solve this problem, this paper builds an intelligent health management cloud platform based on big data, and uses big data and cloud computing technology to provide users with a new health management platform, which can provide health records, health checks, health monitoring and other functional services. The platform carries out health risk assessment from three aspects: information collection, risk calculation and assessment report, and carries out risk assessment on human health. The average abnormal detection rate of volunteers after intervention is about 23.2%. Based on the application of the big data intelligent health management cloud platform, the detection rate of abnormal diseases among volunteers decreased by about 5%. It can be seen that the application of the intelligent health management cloud platform based on big data has significantly reduced the detection rate of abnormal diseases in volunteers. The construction of such a platform can help individuals maintain their health, provide users with a more personalized and humanized service experience, and meet the diverse needs of people at different levels. This advance in smart medicine helps to improve healthcare delivery and outcomes across the board.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADASemSeg: An Active Learning Based data Adaptation Strategy for Improving Cross dataset Breast Tumor Segmentation 3rd

ADASemSeg: An Active Learning Based Data Adaptation Strategy...

引用

3rd international conference on Machine Learning, Image processing, Network Security and data Sciences, MIND 2021

作者： Mishra, Arnab Kumar Roy, Pinki Bandyopadhyay, Sivaji Das, Sujit Kumar Department of CSE National Institute of Technology Silchar Assam Silchar788010 India

ISBN: (纸本)9789811958670

Highly efficient breast ultrasound (BUS) segmentation models trained and tested on samples from one dataset do not usually have a high performance when inference is done on samples from other datasets. The solution to this data adaptation problem is crucial when it comes to deploying a trained model in a new diagnostic center. In this work, a novel active learning-based strategy ADASemSeg is proposed for dealing with this problem, where a model adapts itself from a source dataset to a target dataset via active interactions with an Expert/Oracle. Experimental analysis on two publicly available datasets suggests that the proposed approach can achieve (12–25)% improvements over baselines. Moreover, ADASemSeg can ensure a quick adaptation to the target dataset while requiring a very small amount of Oracle feedback. With such a generic approach, any segmentation model can be effectively adapted to new data distributions, improving cross-center BUS tumor segmentation performances. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Provisional Study of data Mining Classification algorithms in Predicting Credit Card Defaulters Using Weka Tools

A Provisional Study of Data Mining Classification Algorithms...

引用

Recent Advances and Innovations in Engineering (ICRAIE)

作者： Nur Fadhlin Sakina Rosdi Nur Shafiqah Ibrahim Intan Hajariah Shamsudin Sofianita Mutalib Shuzlina Abdul-Rahman School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam Malaysia

data mining is a field of study that seeks to draw out significant patterns from large amounts of data. This study explores the classification algorithms for spotting new trends in massive volumes of credit card data. This work covers the performance analysis of various data mining techniques, namely, Naïve Bayes, J48, and Support Vector Machine (SVM), in predicting credit card defaulters. The dataset is gathered from Kaggle, with 25 attributes and 30,000 instances used to assess the performance of algorithms. Additionally, each classification algorithm's effect on feature selection is mentioned. A variety of data mining classification approaches is used to compare the models in this study. The experiment finds J48 and SVM as the best algorithms at 81.56% and 80.92%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research and Applications of RBF Big data processing Technology Based on Artificial Intelligence algorithms

Research and Applications of RBF Big Data Processing Technol...

引用

data Science and Network Security (ICDSNS), international conference on

作者： Xueying Duan Meng Wang Department of Information Engineering Jilin Police College Changchun China Department of Technology and Tactics Hebei Public Security Vocational College Shijiazhuang China

Among the processing technologies of big data, the most widely and deeply applied technology is prediction technology. The accuracy of predictions has important guiding significance for scientific decision-making. RBF neural networks have the advantages of simple structure, fast training speed, and strong approximation ability. The self-adaptability of its structure effectively avoids the limitation of initial weights. This article is based on artificial intelligence algorithms and optimizes the RBF neural network to obtain a more accurate prediction model. We will apply the improved RBF big data processing technology to the prediction of express delivery business volume. We have selected improved RBF big data processing technology and RBF big data processing technology to simultaneously predict the delivery volume of the business. Practice has shown that the improved RBF big data processing technology has higher prediction accuracy and lower mean square error. This article provides a reference for the improvement and innovation of RBF big data processing technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep Neural Network Training Techniques for Overfitting Avoidance 24th

Efficient Deep Neural Network Training Techniques for Overfi...

引用

24th international conference on Enterprise Information Systems (ICEIS)

作者： Sabiri, Bihi EL Asri, Bouchra Rhanoui, Maryem Mohammed V Univ Rabat ENSIAS Rabat IT Ctr IMS TeamADMIR Lab Rabat Morocco Sch Informat Sci LYRICA Lab Meridian Team Rabat Morocco

ISBN: (纸本)9783031393853;9783031393860

A deep learning neural network's ultimate goal is to produce a model that does well on both the training data and the incoming data that it will use to make predictions. Overfitting is the term used to describe how successfully the prediction model created by the machine learning algorithm adapts to the training data. When a network is improperly adapted to a limited set of input data, overfitting occurs. In this scenario, the predictive model will be able to offer very strong predictions on the data in the training set, and will also capture the generalizable correlations and the noise produced by the data, but it will predict poorly on the data that it has not yet seen during his learning phase. Two methods to lessen or prevent overfitting are suggested in this publication among many others. Additionally, by examining dynamics during training, we propose a consensus classification approach that prevents overfitting, and we assess how well these two types of algorithms function in convolutional neural networks. Firstly, Early stopping makes it possible to store a model's hyper-parameters when it's appropriate. Additionally, the dropout makes learning the model more challenging. The fundamental concept behind dropout neural networks is to remove nodes to allow the network to focus on other features which reducing the model's loss rate allows for gains of up to more than 50%. This study looked into the connection between node dropout regularization and the quality of randomness in terms of preventing neural networks from becoming overfit.

关键词： data overfitting Early stopping Dropout regularization Machine learning Neural network Deep learning

来源：评论

学校读者我要写书评

暂无评论

Preserving the Privacy in IoT Medical data in Edge computing using Modified AES Model with Discrete-Time Alternating Quantum Walk

Preserving the Privacy in IoT Medical data in Edge Computing...

引用

Evolutionary algorithms and Soft computing Techniques (EASCT), international conference on

作者： Dileep M R Vineeth L Sashikanth Reddy Avula Navaneeth A V Department of Master of Computer Applications Nitte Meenakshi Institute of Technology Bengaluru India

The rapid growth of IoT edge devices has caused in an unprecedented explosion of data volume. Extremely often, the created data is gathered and disseminated via edge-based IoT structures. When hostile IoT devices make requests to steal private data from a cloud storage system via edge nodes, the data-sharing privacy exposure issue becomes even more concerning. We provide evolutionary privacy protection learning algorithms for an IoT data sharing scheme based on edge computing as a solution to the stated problem. Deep learning of medical models in an IoT-based healthcare scheme is described here via a federated learning approach. Using a combination of the alternating quantum walk (AQW) and the Advanced encryption standard (AES), this research suggests a new method of picture encryption. A keystream generator associated with AQW limits is used to build a likelihood distribution matrix, and the study makes use of quantum features to enhance the AES algorithm. To unlock the AES method, we must first extract certain singular values from the matrix. Elements of the probability distribution matrix stand in for Rcon in the AES algorithm. The AES algorithm's S-box and ShiftRow transformation mapping rules are then jumbled based on the increasing size of the clone probability distribution matrix. The preprocessing is done with a likelihood distribution matrix and a plaintext XOR operation, and the encryption is done with a modified version of the AES algorithm. To prevent an adversary from concluding confidential medical data via assaults like a perfect reconstruction attack, etc., this encryption technique may be applied to better safeguard local models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-GPU Parallel Pipeline Rendering with Splitting Frame 40th

Multi-GPU Parallel Pipeline Rendering with Splitting Frame

引用

40th Computer Graphics international conference (CGI)

作者： Zhang, Haitang Ma, Junchao Qiu, Zixia Yao, Junmei Al Sibahee, Mustafa A. Abduljabbar, Zaid Ameen Nyangaresi, Vincent Omollo Shenzhen Technol Univ Coll Big Data & Internet Shenzhen Peoples R China Shenzhen Univ Coll Appl Technol Shenzhen Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen Peoples R China Univ Basrah Coll Educ Pure Sci Dept Comp Sci Basrah Iraq Al Kunooze Univ Coll Comp Engn Dept Basrah Iraq Huazhong Univ Sci & Technol Shenzhen Inst Shenzhen Peoples R China Tom Mboya Univ Fac Biol & Phys Sci Homabay Kenya

ISBN: (纸本)9783031500718;9783031500725

In order to achieve real-time rendering of cloud gaming, a large amount of computing resources of graphics processing units (GPU) are required. In this paper, we propose a multi-GPU parallel pipeline rendering approach that makes full use the computing power of multiple GPUs to accelerate real-time ray tracing rendering effectively. This approach enables heterogeneous GPUs to render the same frame cooperatively through a dynamic splitting frame load balancing scheme, and ensures that each GPU is assigned with the suitable size of splitting frame based on its rendering ability. A fine-grained parallel pipeline method divides the process of rendering into more detailed steps that enable multiple frames to be rendered in parallel, which improves the utilization of each step and speeds up the output of frames. With the experiments on various dynamic scenes, the results show that the number of frames per second (FPS) of the multi-GPU system composed of two GPUs is 2.2 times higher than that of the single GPU system, while the multi-GPU system composed of three GPUs has increased to 3.3 times.

关键词： Multi-GPU Ray tracing Split frame rendering Parallel pipeline 3D render

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Recent data-Level Methods for Imbalance Classification

Comparative Analysis of Recent Data-Level Methods for Imbala...

引用

computing and Communication Systems (I3CS), international conference on

作者： Zahid Ahmed S. Md. S. Askari Sufal Das Department of Information Technology North-Eastern Hill University Shillong India Department of CSE Rajiv Gandhi University Itanagar India

In recent days Machine Learning Technique has become one of the ubiquitous techniques used for solving different real-life problems. The data sets used in Machine Learning techniques play a vital role in enhancing the efficiency and performance of the algorithm. An accurate outcome is not possible most of the time because of multiple factors. One of them may also be the nature of the data set. Real-world data sets are more cluttered, complex, and unorganized. Because of this reason, real-world data sets are imbalanced in nature. Machine learning experts believe that imbalanced data is a significant issue and researchers are working to tackle this. Three approaches are employed to fix this issue, those are data level, Algorithm level, and Hybrid level approaches. We have made an effort to conduct a comparative study on recent data-level approaches and also try to conduct a thorough analysis of the undersampling and oversampling approaches.

关键词： Machine learning algorithms Communication systems Machine learning Market research Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Secured Framework for Banking Chatbots using AI, ML and NLP

Secured Framework for Banking Chatbots using AI, ML and NLP

引用

international conference on ent computing and Control Systems (ICICCS)

作者： Rajat Chanda Sandeep Prabhu Symbiosis Institute of Digital and Telecom Management of Aff. Symbiosis International Deemed University Pune India

Artificial intelligence (AI) Machine Learning (ML), and Natural Language processing (NLP)are being employed in a growing number of sectors and is evolving as the technology of the future. It has been widely used to improve the quality of decision-making and problem-solving. This research study proposes a secured framework for banking chatbots using AI-ML and NLP. The framework based on qualitative in-depth experts interviews can be used for developing efficient chartbots for managing customer interactions of various data forms. AI enabled chatbots involves use of machine learning algorithms that can communicate with consumers in a conversational manner. AI enabled chatbots can speak common man’s language language and utilize voice as a user interface. Chatbots are used in the public and private sectors to provide virtual help in areas such as telecommunications, media, tourism, retail, stock markets, and banking. In the banking business, chatbot can act as a communication tool between customers and banks. It has a special advantage in financial industry as it can be automated and does not necessitate human interaction; and can enhance accessibility and provide a lot of features to customers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Screening Application for Possible Mental Health Issues in Adolescents and PWDs Using data Science 2nd

Screening Application for Possible Mental Health Issues in A...

引用

2nd international conference on Advances in data-driven computing and Intelligent Systems, ADCIS 2023

作者： Gunasundari, S. Nandhithaa, B. Mahalakshmi, L. Aparna, P. Velammal Engineering College Chennai India Fleet Studio Technologies Pvt Ltd Chennai India Power of N TechStudio Private Limited Chennai India Light and Wonder Chennai India

ISBN: (纸本)9789819995172

Mental health issues, such as depression, anxiety, and stress, are prevalent among adolescents and Persons with Disabilities (PwDs), yet access to mental health professionals is limited, especially in rural areas. A screening application for mental health issues in adolescents and PwDs is developed to address this challenge, utilizing Flutter, Dart, and a fine-tuned NLP model of GPT-4. The application consists of a questionnaire module that analyzes user responses, a Results module providing mental health assessments, and a Support and resources module offering over 100+ healthcare resources. data on mental health issues faced by adolescents is collected from Kilpauk Medical Hospital (KMC) and Velammal Medical College to inform the application’s development. The GPT-4 model is fine-tuned for phobia screening, resulting in an 80% accuracy rate in identifying phobia types and levels. The application effectively diagnoses various mental health issues, including anxiety disorders, bipolar disorder, depression, eating disorders, obsessive–compulsive disorder, post-traumatic stress disorder, schizophrenia, and various phobias. The application holds promise in enabling early identification and intervention for mental health issues, particularly in underserved areas. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Natural language processing systems

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 << < 433 434 435 436 437 438 439 440 441 442 > >>

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：