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

4,122 篇 会议
38 册 图书
6 篇 期刊文献

馆藏范围

4,166 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,726 篇 工学
- 2,455 篇 计算机科学与技术...
- 2,045 篇 软件工程
- 616 篇 生物工程
- 581 篇 信息与通信工程
- 362 篇 生物医学工程（可授...
- 266 篇 控制科学与工程
- 212 篇 光学工程
- 212 篇 电气工程
- 148 篇 安全科学与工程
- 137 篇 机械工程
- 124 篇 电子科学与技术（可...
- 119 篇 化学工程与技术
- 106 篇 交通运输工程
- 92 篇 动力工程及工程热...
1,369 篇 理学
- 675 篇 数学
- 646 篇 生物学
- 332 篇 统计学（可授理学、...
- 307 篇 物理学
- 197 篇 系统科学
- 127 篇 化学
722 篇 管理学
- 395 篇 管理科学与工程(可...
- 388 篇 图书情报与档案管...
- 239 篇 工商管理
340 篇 医学
- 315 篇 临床医学
- 308 篇 基础医学(可授医学...
- 221 篇 药学(可授医学、理...
- 125 篇 公共卫生与预防医...
160 篇 法学
- 138 篇 社会学
156 篇 教育学
- 154 篇 教育学
142 篇 农学
- 141 篇 作物学
91 篇 经济学
9 篇 军事学
5 篇 文学

主题

517 篇 machine learning
240 篇 deep learning
118 篇 support vector m...
99 篇 adversarial mach...
92 篇 accuracy
92 篇 machine learning...
82 篇 forecasting
74 篇 convolutional ne...
70 篇 predictive model...
69 篇 feature extracti...
56 篇 artificial intel...
53 篇 students
51 篇 learning systems
48 篇 decision trees
48 篇 training
47 篇 reinforcement le...
47 篇 computational mo...
47 篇 computer vision
46 篇 internet of thin...
41 篇 sentiment analys...

机构

46 篇 chitkara univers...
15 篇 graphic era hill...
10 篇 college of manag...
9 篇 graphic era deem...
8 篇 computer science...
8 篇 beijing universi...
7 篇 school of comput...
7 篇 school of comput...
7 篇 school of comput...
7 篇 department of in...
6 篇 università di ca...
6 篇 infn sezione di ...
6 篇 north-west unive...
6 篇 computer science...
6 篇 lovely professio...
6 篇 in2p3 lpc campus...
6 篇 kkr and ksr inst...
6 篇 institut univers...
6 篇 national centre ...
6 篇 greater bay area...

作者

18 篇 kukreja vinay
15 篇 mehta shiva
10 篇 william p.
8 篇 sharma vikrant
7 篇 mahamudul hasan
7 篇 shiva mehta
6 篇 chen a.
6 篇 benoit d.m.
6 篇 ferrara g.
6 篇 ardid m.
6 篇 calvo d.
6 篇 gagliardini s.
6 篇 eddymaoui a.
6 篇 kulikovskiy v.
6 篇 labalme m.
6 篇 gal t.
6 篇 bozza c.
6 篇 khatun a.
6 篇 kalekin o.
6 篇 huang f.

语言

4,020 篇 英文
145 篇 其他
34 篇 中文

检索条件"任意字段=Proceedings of the 2023 4th International Conference on Machine Learning and Computer Application"

共 4166 条记录，以下是4131-4140 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：

machine-learning-Based Methods for Optimizing Smartphone Performance in Fitness Activity Recognition

Machine-Learning-Based Methods for Optimizing Smartphone Per...

引用

computer Science and Blockchain (CCSB), international conference on

作者： Xun Zhang Can Lin Xiaoyang Han Junqing Yuan Zengyi Yu Zhejiang University of Technology Hangzhou China

ISBN: (数字)9798350356502

ISBN: (纸本)9798350356519

With the expanding application areas of IoT, smart fitness has become an area of growing interest. IoT based fitness trackers are already playing an important role in the smart fitness domain. this paper presents a hierarchical Human Activity Recognition (HAR) framework based on smartphone sensors and an IoT fitness activity assistance system, aiming to build a tool to support fitness training without the requirement of a personal trainer. To begin with, we propose a novel hierarchical recognition framework and creatively introduce labels related to fitness activities. We use the SMOTE algorithm for data augmentation and evaluate the performance of six ML classifiers for fitness activity recognition with different feature subsets, and the experimental results clearly demonstrate the significant advantage of the hierarchical recognition strategy in terms of accuracy. After that we focus on the recognition performance of transitional postures. Comprehensive analyses reveal that SVM and RF models excel in recognizing Continuous Activities for real-time fitness tracking, while RF and KNN are effective for Counted Activities, ideal for transitional posture recognition. Additionally, we conduct ablation experiments with time-domain, frequency-domain, and time-frequency-domain features, which show that the model exhibits superior performance when time-frequency-domain features are used simultaneously. Finally, we delve into classifier performance in specific activities by introducing confusion matrices in order to find the most accurate classifier for a specific activity. the results highlight that specific classifier selection tailored to the activity type can significantly enhance the precision and reliability of fitness tracking systems.

关键词： Support vector machines Training Accuracy Frequency-domain analysis Real-time systems Human activity recognition Reliability Time-domain analysis Classification tree analysis Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Understanding Tourists Relationship Quality Using a machine learning ApproachUnderstanding Tourists Relationship Quality 23

Understanding Tourists Relationship Quality Using a Machine ...

引用

proceedings of the 2023 4th international conference on Big Data Economy and Information Management

作者： Dawei Shang Yufang Chi Zhengzhou University China Beijing Vocational College of Social Management (Ministry of Civil Affairs Training Centre) China

ISBN: (纸本)9798400716669

From the perspective of segmented industry sectors, the significance of big data economy and information management in the tourism industry cannot be underestimated. However, research on non-linear analysis of the relationship between tourists relationship quality and its influencing factors is still limited. this study examines the impact of tourist perceived value on relationship quality using neural network methods in the field of information management. Exploring the non-linear relationship used cross validation and independent variable importance analysis. the Root Mean Square Error (RMSE) test results show that the model evaluation in this study is effective and acceptable. the results show that perceived value plays the important nonlinear role in the relationship quality. the analysis of the importance of independent variables shows that results shows that perceived functional value, perceived cost effectiveness value, and perceived emotional value have the greatest nonlinear impact on relationship quality. Meanwhile, the non-linear impact of perceived social value and perceived environmental value on relationship quality is relatively small. this study contributes to improving the quality of tourist destinations, various tourism management themes, and tourist relationships, flourishing the tourism market, and promoting the sustainable development of the tourism industry in information management intelligence era.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Graph Matching Model Based on Cohesive Hypergraph Convolutional Network for Knowledge Graphs of Financial-field Regulatory Documents 23

A Graph Matching Model Based on Cohesive Hypergraph Convolut...

引用

proceedings of the 2023 4th international conference on computer Science and Management Technology

作者： Xiaoguo Wang Jiachen Shi Chao Chen Jianwen Cui College of Electronics and Information Engineering Tongji University China Data management and Application Department Bank of Shanghai China

ISBN: (纸本)9798400709517

Based on the actual demand of conducting banking business compliantly for intelligent retrieval of financial-field regulatory documents (FRDs), in view of the features of containing non-pairwise semantic information, high knowledge cohesion within segments and low knowledge coupling between segments in FRDs, in this paper, the hypergraph structure is adopted, and a model based on HGNN that can effectively classify graphs in this field is constructed to implement graph classification, called Cohesive Hypergraph Convolutional Network (CHCN) model. According to existing knowledge graphs of FRDs, a graph matching model in this field based on CHCN, BERT and other models is constructed to effectively solve the problem of graph matching, called Graph Matching model for Knowledge graph of Financial-field regulatory documents (FK-GM) model. the results of the experiments show that compared with other baseline models, CHCN model outperforms in F1, Precision and Recall in the graph classification task on public datasets and a dataset of banking regulatory documents, which verifies the effectiveness of FK-GM, the graph matching model proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

application of Multimodal machine learning for Image Recommendation Systems 11th

Application of Multimodal Machine Learning for Image Recom...

引用

11th international conference on Analysis of Images, Social Networks and Texts , AIST 2023

作者： Foniakov, Mikhail Bardukov, Anatoly Makarov, Ilya HSE University Moscow Russia AIRI Moscow Russia

ISBN: (纸本)9783031670077

In the era of information overload, making decisions about various aspects of our lives has become increasingly challenging. the rise of the internet and online platforms has provided access to vast amounts of information, including recommendations based on user preferences. this paper focuses on the development of a unique multimodal recommender system for images, leveraging machine learning and deep learning techniques. the results demonstrate the effectiveness of a complex recommender system, with an average accuracy of 0.814. the system outperforms algorithms based solely on CLIP embeddings or BERT vectors, showcasing the advantages of incorporating multiple modalities. the strengths of the model lie in its robust recognition of CLIP vectors and efficient processing of image features. However, there is room for improvement in text features and embeddings, suggesting the need for more detailed textual information and additional data sources. the innovation of this system is to utilize both image data and text descriptions to provide personalized recommendations. Images are vectorized and combined with relevant metrics, while text descriptions are obtained through object recognition or dataset text. the model incorporates various data, such as location, creation date, and event information, to enhance the recommendation process. Overall, this study highlights the potential of multimodal recommender systems for enhancing recommendation quality and providing users with a personalized experience. Ongoing efforts to refine the model with diverse data and parameter optimization can further improve its performance. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Geographic information enterprise risk management methodology taking into account multiple risk factors 23

Geographic information enterprise risk management methodolog...

引用

proceedings of the 2023 4th international conference on computer Science and Management Technology

作者： Yu Sang Shenghua Xu Cong Ma An Luo School of Marine Technology and Geomatics Jiangsu Ocean University China Research Centre of Geo-Spatial Big Data Application Chinese Academy of Surveying and Mapping China

ISBN: (纸本)9798400709517

Analyzing and assessing quality risk is essential to fully utilize the value of geographic information data. this paper proposes a more comprehensive approach to geographic information enterprise risk management. First, enterprise risk factors are categorized based on guidance provided by ENISA. Second, entities related to the geographic information enterprise are categorized, including enterprises, people, locations, qualifications, and products, and ensuring that attributes related to the risk factors are covered. the risk factors of the geographic information enterprise are then categorized according to the risk categorization methodology provided by ENISA. A number of aspects such as financial risk, credit risk, data risk, personnel risk, regional risk and qualification risk are used to ensure a comprehensive analysis of the risks faced by geographic information enterprise. Finally, the DREAD (Damage, Reproducibility, Exploitability, Affected Users, Discoverability) model is applied as a risk assessment tool to evaluate the potential risks faced by geographic information enterprise and provide guidance for the development of appropriate risk management strategies. this approach will help geographic information enterprises to better manage and respond to various risks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single object tracking based on OSTrack and NAS head 22

Single object tracking based on OSTrack and NAS head

引用

proceedings of the 2022 4th international conference on Robotics, Intelligent Control and Artificial Intelligence

作者： Conghao Li Haofeng Wang Pengjie Liu Beijing Institute of Computer Technology and Application China

ISBN: (纸本)9781450398343

Neural architecture search (NAS) has attracted much attention in recent years. Especially, Differentiable Architecture Search (DARTS) has become a mainstream NAS algorithm because of its differentiable architecture hyper-parameter and low time complexity, but few people apply it in the field of object tracking due to its high memory complexity. this paper redesigns the cell structure according to the characteristics of the target tracking head network and defines a simplified search space. We propose a NASHT model to replace the three head networks of OSTrack with the modified DARTS cell, which automatically searches for a target structure suitable for its task. We use two benchmarks, PTB-TIR and LSOTB-TIR, to train and evaluate the model. the accuracy of the proposed model reached 86.5% and the success rate reached 69.0% on the PTB-TIR benchmark. Compared with OSTrack, the accuracy has increased by 1.5%, and the success rate has a 0.8% improvement. the accuracy of the proposed model on the LSOTB-TIR reached 84.9% and the success rate was 71.4%, which achieved comparable effects to OSTrack while performing better in situations such as motion blur, low resolution, and aspect ratio changes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Pose Estimation Using Media-Pipe an Artificial Intelligence applications in Health and Fitness

Real-Time Human Pose Estimation Using Media-Pipe an Artifici...

引用

Artificial Intelligence and Signal Processing (AISP), INDIA, international conference on

作者： Ketan Totlani Shiva S. Dhavala S Sandeep Kumar Vijayarao Yagnesh Challagundla B Roy Eugenia R. Zhuo School of Computer and Systems Sciences Jaipur National University Rajasthan India School of Information Science and Engg. Rashtreeya Vidyalaya College of Engineering Bengaluru India Dept. of Computer Science and Engineering RM.K Engineering College Kavaraipettai Tamil Nadu India School of Electronics Engineering VIT-AP University Amaravati Andhra Pradesh India College of Information and Computing Sciences University of Santo Tomas Manila Philippines

ISBN: (数字)9798350350654

ISBN: (纸本)9798350350661

Significant progress has been achieved in the fields of Artificial Intelligence (AI), machine learning (ML), and Deep learning (DL) in recent years. Nevertheless, a significant gap continues to exist in the effective surveillance of human actions, activities, and the recognition of human movements or poses. machines and computers are fundamentally incapable of comprehending human activities without user intervention. Consequently, we now depend on technology to record and archive human actions through live broadcast data, videos, or images. the field of pose estimation, which is a critical area of research with applications in fields such as Augmented Reality, Animation, Gaming, Healthcare, and Sports, is expanding due to the rapid advancement of computer vision technology. this project implements innovative methods to train models and deter- mine poses, utilizing random inputs from internet images, videos, and live streaming. In particular, models that have been trained with artificial intelligence have been created for daily physical activities that necessitate intricate pose estimation. the initial step in the project is to utilize MediaPipe to estimate the poses of the human body. Subsequently, the angles between the body joints are calculated to create the desired models. Additionally, a web-based user interface (WEB-UI) was developed to enable access from any location. the methodology involves the extraction of data from critical body locations, the framing of models, and the utilization of the MediaPipe model due to its superior performance and features in comparison to other models. the objective of this method is to develop a web application for end-users, train AI models for daily physical activities, and establish an efficient system for single human pose estimation. this approach provides a cost-effective alternative to physical trainers and enables the monitoring of health and sports activities to be enhanced.

关键词： Deep learning Computational modeling Pose estimation Data visualization Feature extraction Data models Artificial intelligence Recommender systems Videos Sports

来源：评论

学校读者我要写书评

暂无评论

Does UI Labeling Data Quality Matter for Predicting Website Aesthetics 25th

Does UI Labeling Data Quality Matter for Predicting Website ...

引用

25th international conference on Data Analytics and Management in Data Intensive Domains, DAMDID/RCDL 2023

作者： Abbasov, Elnur Bakaev, Maxim Novosibirsk State Technical University Pr. K. Marksa 20 Novosibirsk630073 Russia

ISBN: (纸本)9783031678257

the adoption of today’s data-intensive digital services relies on the overall user experience (UX), which is shaped not just by "hard" functionality, but also by "soft" subjective satisfaction. In the latter, aesthetic impression plays an important role (particularly since visually pleasing products are known to be perceived as more usable) and became a popular prediction objective for machine learning (ML) based user behavior models. Since datasets in the field of Human-computer Interaction are generally too scarce for application of deep learning methods that could operate on raw website screenshots, they often undergo preliminary labeling. Although the common notion is that the quality of the labeling is important for the end quality of the predictive models, there were few attempts to quantify the effect. In a previous study, we unexpectedly found significant negative correlations between the input data quality and the models’ quality for Aesthetics and Orderliness subjective impressions. Our current paper is dedicated to validating the findings with another 557 website screenshots, 31 human participants labeling them, and 22 participants verifying the quality of their work. the non-parametrical models (Nadaraya-Watson kernel regression) with feature selection demonstrated somehow better performance, and the combined dataset better aligned with the expected effect of the labeling quality. Although our overall results are inconclusive, they might be of interest to ML practitioners and web designers who seek to automate the prediction of UX dimensions. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and application of the Digital Human Identity Attribute Data Synthesis System

Design and Application of the Digital Human Identity Attribu...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE international conference on

作者： Yapeng Ji Yangyang Li Yunji Liang Bin Guo Yangzhao Yang School of Computer Science Northwestern Polytechnical University Xi’an China Academy of Cyber Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

In the era of big data, increasing demand for identity data sharing in fields like healthcare and tourism, along with stricter cybersecurity regulations, has made generating realistic digital human identity attribute data and ensuring its efficient use a critical challenge. However, existing methods struggle with complex data types and distributions, often neglecting the social and logical consistency of the synthetic data. To address this, we propose a Conditional Generative Adversarial Network (CGAN)-based system for synthesizing digital human identity attribute data. the system features three modules: data preprocessing, data synthesis, and data verification. the preprocessing module uses a composite encoder to handle discrete, continuous, and mixed data types, with a Variational Gaussian Mixture Model (VGM)-based normalization for continuous variables. the synthesis module introduces conditional vector-based sampling to resolve data imbalance while preserving data distribution characteristics, enhancing the realism of the generated data. the verification module uses association rule mining for secondary validation, ensuring logical consistency. this modular design improves scalability, paving the way for multimodal data synthesis. Experimental results show that the system excels in statistical similarity and machine learning utility, with the verification module boosting rule retention by 15%, significantly improving data quality and practical value. this study provides an effective solution with important theoretical and practical implications for digital human identity attribute data synthesis.

关键词： Scalability Data integrity Data preprocessing Medical services Generative adversarial networks Regulation Digital humans Digital twins Gaussian mixture model Synthetic data

来源：评论

学校读者我要写书评

暂无评论

A deep learning framework: Prediction of the number of participants in Wordle and the distribution of game outcomes 23

A deep learning framework: Prediction of the number of parti...

引用

proceedings of the 2023 4th international conference on computer Science and Management Technology

作者： Shijie Wu Zhongzheng Wang Xinyi Liu Xue Bai School of Energy Science and Engineering Harbin Institute of Technology China Faculty of Computing Harbin Institute of Technology China School of Mathematics Harbin Institute of Technology China School of Economics and Management Harbin Institute of Technology China

ISBN: (纸本)9798400709517

Wordle is a new word guessing game that has become popular around the world. It compares the result entered by the player with the correct answer and gives hints through different letter colors. the player is considered successful if he or she matches the result to the hint and determines the correct answer within six attempts. the game has two modes: normal mode and hard mode. the data generated by New York Times allows us to know the total number of players who report the results every day and the total number of players in the difficult mode and the number of guesses by most people. Our purpose is to explore the future trend of the number of players for this game and to get the results of the prediction report for different words. In this paper, we make use of ARIMA time series model and CIWOA_BP neural network, which solve our needs well. We can provide innovative ideas and inspiration for game company managers and technicians, so that make users can have a better game experience.

关键词：

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417页 << < 408 409 410 411 412 413 414 415 416 417 > >>

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：