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

551 篇 会议
4 册 图书
4 篇 期刊文献

馆藏范围

559 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

330 篇 工学
- 302 篇 计算机科学与技术...
- 222 篇 软件工程
- 66 篇 信息与通信工程
- 55 篇 控制科学与工程
- 41 篇 生物工程
- 36 篇 生物医学工程（可授...
- 33 篇 电气工程
- 26 篇 电子科学与技术（可...
- 24 篇 动力工程及工程热...
- 21 篇 机械工程
- 20 篇 网络空间安全
- 19 篇 光学工程
- 12 篇 化学工程与技术
- 12 篇 安全科学与工程
- 10 篇 仪器科学与技术
- 8 篇 交通运输工程
115 篇 理学
- 47 篇 数学
- 45 篇 物理学
- 45 篇 生物学
- 25 篇 统计学（可授理学、...
- 12 篇 化学
95 篇 管理学
- 60 篇 管理科学与工程(可...
- 34 篇 图书情报与档案管...
- 19 篇 工商管理
29 篇 医学
- 28 篇 临床医学
- 23 篇 基础医学(可授医学...
- 12 篇 药学(可授医学、理...
- 9 篇 公共卫生与预防医...
16 篇 教育学
- 15 篇 教育学
13 篇 法学
- 12 篇 社会学
6 篇 农学
4 篇 经济学
2 篇 文学

主题

95 篇 machine learning
72 篇 human computer i...
70 篇 accuracy
57 篇 deep learning
35 篇 feature extracti...
31 篇 training
29 篇 convolutional ne...
28 篇 emotion recognit...
27 篇 predictive model...
27 篇 machine learning...
26 篇 computational mo...
21 篇 adversarial mach...
19 篇 real-time system...
18 篇 computer vision
18 篇 data models
17 篇 support vector m...
17 篇 artificial intel...
15 篇 reliability
14 篇 face recognition
14 篇 prediction algor...

机构

4 篇 school of materi...
3 篇 school of comput...
3 篇 school of inform...
3 篇 graphic era deem...
3 篇 new york univers...
2 篇 department of co...
2 篇 saveetha institu...
2 篇 school of comput...
2 篇 school of xiamen...
2 篇 singapore univer...
2 篇 dept. of compute...
2 篇 wuhan digital en...
2 篇 dept. of softwar...
2 篇 dept. of electro...
2 篇 chitkara univers...
2 篇 south china univ...
2 篇 school of comput...
2 篇 school of comput...
2 篇 department of in...
2 篇 dept. of compute...

作者

3 篇 surendran r.
3 篇 ggaliwango marvi...
2 篇 zhou jing
2 篇 r surendran
2 篇 julian anitha
2 篇 wenle bai
2 篇 qingle quan
2 篇 hanqing sun
2 篇 sharma ajay
2 篇 jac fredo agasti...
2 篇 jing zhou
2 篇 kulkarni hrishik...
2 篇 wu kai
2 篇 shahade makarand
2 篇 bharti
2 篇 sharma shamneesh
2 篇 bingyao liu
2 篇 nakayiza hellen
2 篇 vishalakshmi
2 篇 schiller dominik

语言

454 篇 英文
105 篇 其他
8 篇 中文

检索条件"任意字段=5th International Conference on Machine Learning and Human-Computer Interaction, MLHMI 2024"

共 559 条记录，以下是441-450 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：

An Extra Tree Ensemble Optimization-Based Deep learning Framework for human Activity Recognition

An Extra Tree Ensemble Optimization-Based Deep Learning Fram...

引用

Innovative Trends in Information Technology (ICITIIT), international conference on

作者： Monika Arya Hanumat Sastry G Akhilesh Gaidhane Anand Motwani Dept. of CSE CMR Engineering College Hyderabad Telangana India School of Computer Science UPES Dehradun Uttarakhand India Mathematics SAGES M.G.Ward Kondagaon Chhattisgarh India School of Computing Science & Engineering VIT Bhopal University Sehore MP India

ISBN: (数字)9798350386813

ISBN: (纸本)9798350386820

human activity recognition (HAR) is a burgeoning field of study due to its real-life applications in the medical field, the e-health system, and elder care or care of physically impaired people in a smart healthcare environment. Using sensors built into wearable devices, such as smartphones, HAR provides an opportunity to identify human behavior and better understand an individual’s health. In the past years, conventional machine learning techniques have made significant progress in HAR. However, these methods significantly rely on conventional feature extraction, which may hinder the effectiveness of the generalization model. the other challenges these methods face for HAR are performance degradation of many models with the increase in the number of activities, lack of capability of models to capture different layers of activities, high dimensionality, overfitting, and optimization problems. these challenges attracted numerous people to explore this field. the development in deep learning techniques has addressed most of these problems by automatically extracting discriminative features from raw input sequences obtained by multimodal sensing devices to acknowledge human activities accurately. this paper proposes an extra tree ensemble optimization-based deep learning framework (DELETO) for HAR. the model shows better results than recent and conventional techniques, with an accuracy of 98.7% and a computation time of 2.533 seconds.

关键词： Deep learning Multimodal sensors Medical services Feature extraction human activity recognition Object recognition Wearable devices

来源：评论

学校读者我要写书评

暂无评论

Exploring a Cutting-Edge Convolutional Neural Network for Speech Emotion Recognition

Exploring a Cutting-Edge Convolutional Neural Network for Sp...

引用

Industrial Engineering and Artificial Intelligence (IEAI), international conference on

作者： Navod Neranjan thilakarathne Kasorn Galajit Candy Olivia Mawalim Hayati Yassin Faculty of Integrated Technologies Universiti Brunei Darussalam Brunei Darusalam NECTEC National Science and Technology Development Agency Pathum Thani Thailand Japan Advanced Institute of Science and Technology Ishikawa Japan

ISBN: (数字)9798350386363

ISBN: (纸本)9798350386370

In light of the ongoing expansion of human-computer interaction, advancements in the comprehension and interpretation of human emotions are of the utmost importance. SER, representing speech emotion recognition, is a critical element in this context as it enables computational systems to comprehend the emotions of humans. throughout the years, SER has employed a variety of techniques, including well-established speech analysis and classification methods. However, in recent years, techniques powered by deep learning have been suggested as a viable substitute for conventional SER methods, owing to their more encouraging outcomes in comparison to the aforementioned methods. In this regard, by utilizing a novel Convolutional Neural Network (CNN) model designed to assess and categorize seven emotional states based on speech signals retrieved from three distinct databases, this research presents a novel approach to SER that yields 88.76% accuracy. the purpose of this research is to enhance the accuracy and efficiency of emotion identification, with the end goal of boosting applications in fields such as interactive voice response systems, mental health monitoring, and personalized digital assistants.

关键词： Deep learning Emotion recognition Accuracy Speech analysis Mental health Industrial engineering Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Review on the Synergies and Challenges of Quantum Computing, Cloud Computing, and Fog Computing in New Era 23

Comprehensive Review on the Synergies and Challenges of Quan...

引用

Proceedings of the 5th international conference on Information Management & machine Intelligence

作者： Barkha Narang Harshita Virwani Nikita Jain Computer Engineering Poornima College of Engineering India

ISBN: (纸本)9798400709418

this paper explores the emerging technologies of quantum computing, cloud computing, and cloud computing, focusing on their principles, applications, advantages, challenges, and interactions. Quantum computing has the ability to adapt to solving problems in many areas using the principles of superposition and entanglement, but it faces problems such as de-coherence. Cloud computing provides convenience and accessibility but also faces security and data transfer issues. Fog computing is a method that increases efficiency by distributing tasks near the edge of the network and has applications in the Internet of things, smart cities, and data processing over time. this article introduces various types of quantum and cloud computing, including gate computing, adiabatic computing, topological computing, photonic computing, and quantum dot computing. Quantum computing enables quantum computing, advanced machine learning, cryptography, and cross-sectional innovation. Cloud computing enables increased efficiency, productivity and innovation across businesses, but it also faces security, data transfer and environmental issues. the interaction of technologies in the 3D printing industry highlights their importance in shaping the future of computer technology.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acoustic-based Speech Emotion Recognition Using CNN

Enhancing Acoustic-based Speech Emotion Recognition Using CN...

引用

international conference on Advanced Information Technologies (ICAIT)

作者： Hnin Oo Hlaing thet thet Zin thinn thinn Wai Aung Nway Oo University of Information Technology Yangon Myanmar Faculty of Computer Science University of Information Technology Yangon Myanmar

ISBN: (数字)9798331510046

ISBN: (纸本)9798331510053

Speech Emotion Recognition (SER) is a crucial field aiming to enhance machine understanding of human emotions. Among all the variety of data sources, we choose the acoustic features of the speech to explore both positive and negative aspects in feature extraction, aggressive data augmentation, and complex model architecture, highlighting its potential to inflate false confidence (overfitting) and hallucinations if not wielded with caution. Furthermore, our investigation explores the complex link between accuracy and feature set size, highlighting the need to extract rich emotional characteristics from speech. An intriguing finding of our analysis is: downscaling the filter size and learning rate of the neural network works better with small training dataset and the model can differentiate diverse emotions more accurately. this finding paves the way for improving the classification model, potentially leading to more robust emotion recognition systems. this multifaceted analysis goes beyond the conventional focus on accuracy, challenging assumptions and pinpointing areas for future exploration in the ever-evolving field of speech-based emotion recognition.

关键词： Deep learning Emotion recognition Accuracy Speech recognition Predictive models Speech enhancement Feature extraction Data models Complexity theory Overfitting

来源：评论

学校读者我要写书评

暂无评论

Influencing Factors of Aesthetic Education Class Co-constructed by School and Museum under human-computer interaction Background

Influencing Factors of Aesthetic Education Class Co-construc...

引用

international conference on Educational and Information Technology (ICEIT)

作者： Shijia Zhang Wei Gao National Research Center of Cultural Industries Central China Normal University Hubei Wuhan China

ISBN: (数字)9798350372663

ISBN: (纸本)9798350372670

Aesthetic education is a creative education that beautifies the soul and cultivates emotions. It plays an important role in schools, society, and family environments. the aesthetic education empowered by artificial intelligence presents unique characteristics, such as stimulating creativity, infiltrating the soul, and nourishing emotions. this article takes the joint construction of aesthetic education classrooms by schools and museums as the theme, exploring the impact of different factors on the construction of virtual aesthetic education classrooms by schools and museums. Using the Analytic Hierarchy Process, it is divided into 4 dimensions and 18 indicators. the evaluation results indicate that: (1) artificial intelligence technology plays an extremely important role in the virtualization creation of aesthetic education classrooms, with intelligent aesthetic education classroom environments, aesthetic education technology, and resource mining scores exceeding 5(average score); (2) the impact of the aesthetic education curriculum system is most significant (with a score of 7.22), and the aesthetic education teaching model with teachers and students as the main body has not changed; (3) However, in the process of cooperation with the school, the interactivity of the museum is weak, mainly manifested in the unsatisfactory feedback mechanism scores of aesthetic education teaching, and the security system needs to be strengthened.

关键词： human computer interaction Privacy Education Analytic hierarchy process Speech recognition machine learning Museums

来源：评论

学校读者我要写书评

暂无评论

Designing human Pose Recognition for Yoga Posture in Web-based Augmented Reality

Designing Human Pose Recognition for Yoga Posture in Web-bas...

引用

Smart Electronics and Communication (ICOSEC), international conference on

作者： Fazliaty Edora Fadzli Muhammad Imtiaaz Syaqib Adanan Ajune Wanis Ismail Norhaida Mohd Suaib Nur Ameerah Abdul Halim Muhammad Anwar Ahmad Mixed and Virtual Reality Research Lab ViCubeLab Faculty of Computing Universiti Teknologi Malaysia Johor Malaysia Faculty of Computing Universiti Teknologi Malaysia Johor Malaysia

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

this study presents the design of a system to recognize human yoga postures in a web-based augmented reality (AR). the system provides real-time feedback and personalized guidance through web browsers, enhancing the traditional practice of yoga with advanced technological support. the system employs computer vision techniques to accurately identify yoga poses, ensuring proper form. Leveraging modern web technologies, the solution is accessible and scalable, allowing users to practice yoga from anywhere with an internet connection. the design phase focuses on creating a posture identifier system that calculates angles between body landmarks for pose detection. the implementation incorporates MediaPipe and TensorFlow for efficient tracking and analysis. this study highlights the technical challenges and solutions in implementing pose recognition within a web-based AR framework, demonstrating the potential of this approach to revolutionize digital yoga training. By bridging tradition and innovation, this research empowers practitioners to deepen their practice, improve alignment, and promote holistic wellness.

关键词： Training Technological innovation computer vision Pose estimation Refining machine learning Real-time systems Usability Augmented reality Testing

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Potential of Graph Neural Networks in SME Credit Risk Assessment

Unveiling the Potential of Graph Neural Networks in SME Cred...

引用

Intelligent Computing and human-computer interaction (ICHCI), international conference on

作者： Bingyao Liu Iris Li Jianhua Yao Yuan Chen Guanming Huang Jiajing Wang University of California Irvine Irvine USA New York University New York USA Trine University Phoenix USA Rice University Houston USA University of Chicago Chicago USA Columbia University New York USA

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

this paper takes the graph neural network as the technical framework, integrates the intrinsic connections between enterprise financial indicators, and proposes a model for enterprise credit risk assessment. the main research work includes: Firstly, based on the experience of predecessors, we selected 29 enterprise financial data indicators, abstracted each indicator as a vertex, deeply analyzed the relationships between the indicators, constructed a similarity matrix of indicators, and used the maximum spanning tree algorithm to achieve the graph structure mapping of enterprises; secondly, in the representation learning phase of the mapped graph, a graph neural network model was built to obtain its embedded representation. the feature vector of each node was expanded to 32 dimensions, and three GraphSAGE operations were performed on the graph, with the results pooled using the Pool operation, and the final output of three feature vectors was averaged to obtain the graph's embedded representation; finally, a classifier was constructed using a two-layer fully connected network to complete the prediction task. Experimental results on real enterprise data show that the model proposed in this paper can well complete the multi-level credit level estimation of enterprises. Furthermore, the tree-structured graph mapping deeply portrays the intrinsic connections of various indicator data of the company, and according to the ROC and other evaluation criteria, the model's classification effect is significant and has good “robustness”.

关键词： Representation learning Economics Accuracy Scalability Predictive models Graph neural networks Data models Vectors Stability analysis Risk management

来源：评论

学校读者我要写书评

暂无评论

Microe- A Comprehensive Dataset of Facial Micro Expressions for Building Responsible Software Systems with Emotion Recognition

Microe- A Comprehensive Dataset of Facial Micro Expressions ...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 international conference on

作者： Patricia Kirabo Nakalembe Calvin Kirabo Edwin Micheal Kibuuka Derrick Ahumuza Nakayiza Hellen Ggaliwango Marvin Department of Computer Science Makerere university Kampala Uganda Department of Computer Sciencey Makerere university Kampala Uganda Department of Computer and Information Sciences Muni university Arua Uganda

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Micro expressions are facial expressions that occur for a short period of time, usually less than a second. these expressions usually go unnoticed but represent the true expression that is felt by the person because they are involuntary. there have been recent attempts to make datasets that contain micro expressions in an attempt to carry out accurate Facial Emotion Recognition. However, many of these datasets have had various limitations, ranging from low diversity of the dataset, which introduced bias into the emotion detection models, low quality images, a limited number of images that resulted into low accuracy of the model, etc. the study introduces a dataset called Microe dataset, which contains images that were collected from various sources to ensure a high diversity and more features that are going to be discussed in sections below. Experiments were also carried out to evaluate this dataset and the results that were acquired have been included in this paper.

关键词： human computer interaction Deep learning Emotion recognition Accuracy Psychology Focusing Software systems Feature extraction Distance measurement Data models

来源：评论

学校读者我要写书评

暂无评论

Development of Raspberry Pi Based Election Logistic Intelligent Robot

Development of Raspberry Pi Based Election Logistic Intellig...

引用

IEEE international conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Ayobami Adedokun Dozie Ekwunife Department of Computer Engineering Federal University of Technology Akure Nigeria Department of Electronic and Computer Engineering Nnamdi Azikiwe University Awka Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

the electoral empire saddled with election process in Nigeria faces numerous logistical challenges which include the timely distribution of election materials, secure transportation of ballot boxes, and effective monitoring of voting stations. these challenges are exacerbated by factors such as inadequate infrastructure, security concerns, and the sheer scale of operations across diverse and most especially in remote regions. this paper proposes a solution to these challenges by developing an Election Logistics Intelligent Robot (ELIR) based on the Raspberry Pi platform. the ELIR is engineered to automate and optimize election logistics, thereby reducing human intervention and minimizing errors. the robot integrates sensors, cameras, and communication modules, enabling it to navigate complex environments autonomously while providing real-time data on election material status. machine learning algorithms enhance its decision-making capabilities, ensuring efficient operation even in unpredictable situations. By leveraging this technology, the aim is to improve the reliability, speed, and security of Nigeria’s electoral logistics, ultimately contributing to a more transparent and efficient electoral process.

关键词： Navigation Voting Transportation Real-time systems Security Reliability Intelligent robots Intelligent sensors Logistics Testing

来源：评论

学校读者我要写书评

暂无评论

An Emotion Recognition Using Electrocardiogram Signals 25

An Emotion Recognition Using Electrocardiogram Signals

引用

2025 5th international conference on Bioinformatics and Intelligent Computing, BIC 2025

作者： Guo, Wei Teng, Fei Lin, Yongzhong Zhao, Wenzhi Liu, Wenlong School of Information and Communication Engineering Dalian University of Technology Liaoning Dalian China Central Hospital of Dalian University of Technology Liaoning Dalian China The Second Affiliated Hospital of Dalian Medical University Liaoning Dalian China Dalian Key Laboratory of Artificial Intelligence DUT Artificial Intelligence Institute Liaoning Dalian China

ISBN: (纸本)9798400712203

With the increasing focus on mental health, emotion recognition based on Electrocardiogram (ECG) shows great potential in applications such as human-computer interaction and the treatment of emotion-related diseases. Deep learning has advantages over traditional machine learning methods for automatic feature extraction. However, overcoming individual differences and achieving highly accurate emotion recognition on lightweight models remains a major challenge. To address this issue, this paper proposes an emotion recognition method based on an improved residual network (ResNet) architecture, which aims to improve the representation of ECG signals on different time scales. In addition, the proposed method combines Squeeze-and-Excitation Networks (SENet) to dynamically assign weights to ECG features from different channels, effectively accounting for individual differences. Deeply separable convolution (DWConv) is also employed to reduce computational complexity, enabling its use on portable devices. Validation on three publicly available datasets shows that the proposed method identifies valence, arousal and explicitness with 94.7%, 92.9% and 94.6% accuracy in the SWELL dataset for valence, 92.9% and 94.6% respectively, and 98.6% in the WESAD dataset for emotional states, and correctly identifies value and arousal with 78.5% and 83.8% in the CASE dataset. the results show that the method has significant advantages in multi-class emotion recognition tasks. © 2025 Copyright held by the owner/author(s).

关键词： Attention mechanisms Deep learning ECG Emotion classification

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56页 << < 41 42 43 44 45 46 47 48 49 50 > >>

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：