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

167 篇 会议
1 册 图书

馆藏范围

168 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

125 篇 工学
- 114 篇 计算机科学与技术...
- 42 篇 软件工程
- 15 篇 控制科学与工程
- 9 篇 光学工程
- 8 篇 信息与通信工程
- 8 篇 生物工程
- 6 篇 电气工程
- 5 篇 生物医学工程（可授...
- 3 篇 仪器科学与技术
- 3 篇 安全科学与工程
- 2 篇 材料科学与工程（可...
- 2 篇 冶金工程
- 2 篇 交通运输工程
- 2 篇 航空宇航科学与技...
31 篇 理学
- 15 篇 数学
- 11 篇 生物学
- 8 篇 统计学（可授理学、...
- 7 篇 物理学
- 2 篇 化学
- 1 篇 大气科学
- 1 篇 系统科学
15 篇 管理学
- 9 篇 管理科学与工程(可...
- 7 篇 工商管理
- 6 篇 图书情报与档案管...
4 篇 经济学
- 4 篇 应用经济学
3 篇 法学
- 3 篇 社会学
3 篇 教育学
- 3 篇 教育学
2 篇 医学
- 2 篇 基础医学(可授医学...
- 2 篇 临床医学
- 2 篇 公共卫生与预防医...
1 篇 农学

主题

26 篇 deep learning
20 篇 machine learning
16 篇 accuracy
10 篇 feature extracti...
10 篇 training
8 篇 data mining
5 篇 training data
5 篇 visualization
5 篇 convolutional ne...
4 篇 support vector m...
4 篇 image segmentati...
4 篇 information tech...
4 篇 optimization
4 篇 predictive model...
4 篇 classification
4 篇 estimation
4 篇 federated learni...
4 篇 data models
3 篇 reinforcement le...
3 篇 transfer learnin...

机构

3 篇 zarqa university...
3 篇 university of bu...
3 篇 data science & a...
3 篇 computer enginee...
3 篇 department of el...
2 篇 graduate school ...
2 篇 graduate school ...
2 篇 cyber security d...
2 篇 graduate school ...
2 篇 data science & a...
2 篇 fairleigh dickin...
2 篇 university of po...
2 篇 chitkara univers...
2 篇 aonic sdn bhd su...
2 篇 national cerebra...
2 篇 department of in...
2 篇 institute of sys...
2 篇 univ jaen andalu...
2 篇 graduated school...
2 篇 centre of multi-...

作者

5 篇 moubayed abdalla...
5 篇 mohammadnoor inj...
5 篇 injadat mohammad...
5 篇 abdallah moubaye...
3 篇 julian vicente
3 篇 naranjo valery
3 篇 mihaescu marian ...
2 篇 wakabayashi tets...
2 篇 mohammad kanan
2 篇 ali elrashidi
2 篇 yasunori endo
2 篇 hammer barbara
2 篇 elrashidi ali
2 篇 alberola juan m.
2 篇 tetsushi wakabay...
2 篇 kanan mohammad
2 篇 ala’ alyabrodi
2 篇 morita kento
2 篇 shrouq al-daja
2 篇 endo yasunori

语言

158 篇 英文
9 篇 其他
1 篇 中文

检索条件"任意字段=25th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2024"

共 168 条记录，以下是111-120 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：

Head Pose Estimation Using a Chest-Mounted Camera and Its Evaluation Based on CG Images

Head Pose Estimation Using a Chest-Mounted Camera and Its Ev...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Taisei Yamada Hirotake Yamazoe Graduate School of Engineering University of Hyogo Himeji Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

In everyday life, we naturally turn our heads or focus our gaze on objects of interest. By capturing a person's head pose or gaze direction, it is possible to record their actions and identify the objects they are focusing on. this study proposes a head pose estimation to infer and document the objects of interest based on head movements. We utilize a camera mounted on the user's chest and develop a deep-learning model to estimate head pose from the captured images. the training data was generated using a CG model, and the model's performance was validated.

关键词： Head Pose estimation Training data Focusing Cameras Magnetic heads data models Object recognition

来源：评论

学校读者我要写书评

暂无评论

Contact Lens Automatic Optical Inspection Method Based on YOLOv9

Contact Lens Automatic Optical Inspection Method Based on YO...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Tae-yun Kim Bumshik Lee Suk-seung Hwang Institute of AI Convergence Chosun University Gwangju Korea Department of Information and Communications Engineering Chosun University Gwangju Korea Interdisciplinary Program in IT-Bio Convergence System School of Electronic Engineering Chosun University Gwangju Korea

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

Traditional inspection methods for contact lenses primarily involved manual examination, where workers directly assessed the physical properties and manufacturing defects of the lenses. Consequently, the quality determination relied on the workers' judgment, leading to inconsistencies. In order to address this issue, although automated Optical Inspection (AOI) was introduced, it has limitations in applying to various types of contact lenses. As part of research to utilize deep learning in AOI, this paper introduces a You Only Look Once (YOLO) v9-based contact lens inspection technique that leverages a small dataset of contact lens images. this method involves training YOLO v9 with the limited number of images that include various defects such as bubbles, cracks, and foreign particles, as well as images of defect-free contact lenses.

关键词： YOLO Training Deep learning Manuals Optical imaging Manufacturing Automatic optical inspection Lenses

来源：评论

学校读者我要写书评

暂无评论

Whole Time-Series Clustering by Embedding Relational Graphs into Vector Spaces Using DeepWalk

Whole Time-Series Clustering by Embedding Relational Graphs ...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Koh Kumamoto Yasunori Endo Degree Programs in Systems and Information Engineering University of Tsukuba Tsukuba Japan Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

Clustering is a type of unsupervised learning, which can be broadly classified into static and dynamic methods. Whole time-series clustering, one of the dynamic methods, is performed on multiple time-series data and classifies them. However, few whole time-series clustering methods take into account the fact that the clusters belonging to each time-series data change with time. therefore, the purpose of this study is to propose a method to adapt static clustering methods to whole time-series clustering that takes into account the time variation of cluster classification. Specifically, we propose a method to perform static clustering for each time point of time-series data, embed a relationship graph consisting of clusters at each time point into a vector space, and perform time-series clustering by analyzing relationships among clusters at different time points. For embedding the graph into the vector space, we use DeepWalk, a method based on random walk. Numerical experiments are then conducted to verify the behavior of the proposed method.

关键词： Clustering methods Vectors Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

User-Adaptive Chat Dialogue System Based on User's Feedback

User-Adaptive Chat Dialogue System Based on User's Feedback

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Toru Sugimoto Airi Teraoka Faculty of Engineering Shibaura Institute of Technology Tokyo Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

We develop a chat dialogue system that responds according to the preferences of each user, aiming to improve user satisfaction when interacting with the system. this system receives explicit feedbacks from the user on whether or not the user prefers each response of the system during the dialogue, and thus it recognizes the user's preference regarding the style of response such as dialogue acts and politeness. the system generates multiple candidate response sentences using a deep learning model T5 and selects the one that best matches the user's preference. In this way, our dialogue system responds according to the user's preference. the result of an evaluation experiment shows that the proposed system generates responses that match the user's preferences better than a system that does not take user's preferences into account.

关键词： Deep learning Prototypes Oral communication Feature extraction data mining

来源：评论

学校读者我要写书评

暂无评论

Review on Research of automated Machine learning 23

Review on Research of Automated Machine Learning

引用

Proceedings of the 2023 7th international conference on Computer Science and Artificial Intelligence

作者： Yuyanzhen Zhong Chuan Yang Xinyi Su Biao Li Xiaoping Huang Yong Shuai Chongqing CEPREI Industrial Technology Research Institute Co. Ltd China

ISBN: (纸本)9798400708688

automated Machine learning (AutoML) can automatically discover high-performance models to build deep learning systems without human assistance, with the ultimate goal of reducing the complexity and entry barriers of building deep learning systems. Although AutoML has achieved a certain degree of automation through four important steps: data preparation, feature engineering, model generation, and model evaluation, there is still a significant gap compared to the ultimate ideal of achieving truly intelligent lifelong learning. therefore, a deep understanding of AutoML can help drive the development of artificial intelligence. Firstly, we comprehensively reviewed the latest technologies and achievements involved in these four steps, then we introduced their shortcomings and challenges. Secnodly, a detailed introduction was given to the existing AutoML libraries and the theoretical and practical applications of AutoML. Finally, we summarized AutoML models and Proposed an outlook.

关键词： automated Machine learning Automatic Processing Lifelong learning Neural Architecture Search

来源：评论

学校读者我要写书评

暂无评论

Crack Detection and 3D Scene Creation of Road Bridge Using Deep learning and Image Processing

Crack Detection and 3D Scene Creation of Road Bridge Using D...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Kotaro Ishida Yasutoshi Nomura Graduate school of science and engineering Ritsumeikan University Kusatsu Japan Civil and environmental engineering Ritsumeikan University Kusatsu Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

In Japan, the number of social infrastructure facilities, such as bridges and tunnels, which were constructed during a period of high economic growth and have been in existence for 50 years, has been increasing, and inspection is important for managing them. In 2014, it became obligatory to inspect structures once every 5 years. From the above decision, the inspection of structures by engineers using close-up visual observation and visible light images has been carried out periodically. However, damage inspection by visual inspection has become a problem from the viewpoint of cost such as human cost, the viewpoint of labor, and time cost. the periodical inspection is determined to utilize close-up visual observation by engineers or the equivalent diagnosis, and digitization and sharing of the inspection results are important in the management of infrastructure. therefore, the construction of a system that carries out the diagnosis equivalent to close-up visual observation and digitizes the result is tried.

关键词： YOLO Visualization three-dimensional displays Costs Accuracy Structural panels Transfer learning Training data Inspection Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

A Bias in Training data Degrades the Quality of Variable Importance Scores of Random Forests

A Bias in Training Data Degrades the Quality of Variable Imp...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Shuhei Kimura Kenta Yuasa Masato Tokuhisa Faculty of Engineering Tottori University Tottori Japan Graduate School of Sustainability Sciences Tottori University Tottori Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

the random forest, a machine learning technique, offers several preferable features that have drawn the interest and focus of researchers. In practically applying the random forest, we found that the training data containing many examples similar to each other degraded the quality of the importance scores. To overcome this harmful effect, we have proposed a method that assigns weight values to the training data. Our experimental results showed that the quality decline of the importance scores could be resolved by considering the weight values determined by the weighting method in the training of the random forest. It turned out, however, that this harmful effect and the effectiveness of the weighting method in overcoming it could only be confirmed on a specified task. Although the main purpose of machine learning techniques is to obtain a good approximation of the target function, the importance scores are often used to extract information from the given data. From what we can see, the degradation in the quality of the importance scores is not yet widely known. In this study we attempted to reveal the conditions under which this harmful effect occurs. We confirmed that the weighting approach works well even in other problems.

关键词： Training Degradation Correlation Accuracy Input variables Training data Forestry Function approximation data mining Random forests

来源：评论

学校读者我要写书评

暂无评论

A Twin Dual-Arm Robot Testbed to Collect the Human Demonstration data for Imitation learning*

A Twin Dual-Arm Robot Testbed to Collect the Human Demonstra...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Juhyung Kim Sungwon Heo Songwoo Kim Ho-Jin Jung Han Ul Yoon Division of Computer and Telecomm. Engineering Yonsei University Mirae Campus Wonju Korea Department of Computer Science Graduate School Yonsei University Wonju Korea Division of Software Yonsei University Mirae Campus Wonju Korea

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

Collecting consistent human demonstrations has been a problematic issue in the field of a learning from demonstration. this paper presents a twin dual-arm robot testbed to collect human demonstration data while performing manual tasks in the activities of daily livings such as opening/closing a window, opening-up/closing-down a sauce bottle cap, etc. the testbed consists of the two sets of a dual-arm robot; for each robot, one-side arm has 6-DoF with a crab-gripper as its hand. Two dual-arm robots are mounted at the front and back of a table-type station. A human operator performs actions to complete a given task with the one at the back; the human operator's actions, meanwhile, are duplicated by the other robot at the front simultaneously. the experimental results show the testbed's potential to gather consistent human demonstration data for training a machine learning agent to manipulate the dual-arm robot under an imitation learning framework.

关键词： Training Imitation learning Manuals Grasping Manipulators 6-DOF Robots Sorting

来源：评论

学校读者我要写书评

暂无评论

Health Classification on Oil Palm UAV Images Using Machine learning with Features Reduction

Health Classification on Oil Palm UAV Images Using Machine L...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Zi Choong Tee Lee Choo Tay Weng Kin Lai Sheng Siang Lee Department of Mechanical Engineering Tunku Abdul Rahman University of Management and Tehnology Kuala Lumpur Malaysia Centre of Multi-modal Signal Processing Tunku Abdul Rahman University of Management and Tehnology Kuala Lumpur Malaysia Aonic Sdn Bhd Subang Jaya Malaysia

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

the sheer size of oil palm plantations is causing challenges in managing the plantation efficiently and effectively. Among the many challenges affecting the palms, timely disease control is crucial in maintaining high yield and sustainable agriculture practice. this paper investigates the health monitoring of oil palms using images taken with unmanned aerial vehicles (UAVs), enabling proactive intervention and targeted disease management. Based on 2002 real-world oil palm images provided by the industry, support vector machine (SVM) optimized with a radial basis function (RBF) kernel was able to achieve an Fl score of 0.975 on test data and a macro Fl score of 0.88 on inference data, paving the way for its application in large scale diseased tree identification in the plantation.

关键词： Support vector machines Accuracy Oils Plantations Machine learning Autonomous aerial vehicles data models Kernel Monitoring Diseases

来源：评论

学校读者我要写书评

暂无评论

EC-Net: Efficient Compound Network with Dendritic learning for Cataract Eye Detection

EC-Net: Efficient Compound Network with Dendritic Learning f...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Haiqing Wang Zeyuan Ju Chouyu Chen Zhipeng Liu Qiong Fu Shangce Gao Faculty of Engineering University of Toyama Toyama Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

As the leading cause of visual impairment and blindness, automatic methods for diagnosing cataracts from retinal images are desired. With the advancement of computer technology, deep learning-based approaches have demonstrated superior performance compared to traditional manual methods. these algorithms are particularly advantageous in terms of conserving human and material resources and minimizing the dependency on clinical expertise. However, existing methods often struggle with extracting the non-linear characteristics inherent in cataract data. To alleviate this challenge, we propose a novel Efficient-dendritic Cataract-detection Network (EC-Net), which integrates the Dendritic Neuron Model for efficient and accurate detection of cataracts. this network leverages the nonlinear properties of dendritic neurons in conjunction with advanced deep learning feature extraction techniques to enhance the accuracy of cataract identification. Experimental results on publicly available datasets demonstrate that EC-Net significantly outperforms traditional models in the classification of cataract fundus images, providing a promising solution for medical image classification and supporting auxiliary diagnosis.

关键词： Cataracts Deep learning Accuracy Biological system modeling Neurons Visual impairment Feature extraction Compounds Medical diagnostic imaging Image 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17页 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：