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

11,503 篇 会议
102 篇 期刊文献
44 册 图书

馆藏范围

11,649 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,886 篇 工学
- 6,413 篇 计算机科学与技术...
- 3,782 篇 软件工程
- 1,494 篇 控制科学与工程
- 1,377 篇 电气工程
- 1,236 篇 信息与通信工程
- 873 篇 生物工程
- 557 篇 机械工程
- 429 篇 动力工程及工程热...
- 417 篇 生物医学工程（可授...
- 381 篇 交通运输工程
- 361 篇 电子科学与技术（可...
- 268 篇 光学工程
- 259 篇 安全科学与工程
- 236 篇 材料科学与工程（可...
- 223 篇 化学工程与技术
2,874 篇 理学
- 1,791 篇 数学
- 930 篇 生物学
- 484 篇 物理学
- 450 篇 统计学（可授理学、...
- 321 篇 系统科学
- 199 篇 化学
1,739 篇 管理学
- 1,288 篇 管理科学与工程(可...
- 584 篇 工商管理
- 536 篇 图书情报与档案管...
497 篇 医学
- 368 篇 临床医学
- 345 篇 基础医学(可授医学...
- 184 篇 药学(可授医学、理...
353 篇 教育学
- 343 篇 教育学
209 篇 法学
- 191 篇 社会学
204 篇 经济学
- 204 篇 应用经济学
112 篇 农学
28 篇 军事学
23 篇 文学
7 篇 艺术学

主题

988 篇 deep learning
908 篇 optimization
770 篇 machine learning
579 篇 accuracy
410 篇 reinforcement le...
297 篇 computational mo...
284 篇 feature extracti...
277 篇 predictive model...
276 篇 training
249 篇 real-time system...
209 篇 neural networks
204 篇 support vector m...
177 篇 particle swarm o...
165 篇 convolutional ne...
148 篇 adversarial mach...
146 篇 machine learning...
145 篇 data models
144 篇 genetic algorith...
141 篇 learning systems
132 篇 analytical model...

机构

56 篇 chitkara univers...
31 篇 chitkara centre ...
22 篇 chitkara univers...
19 篇 university of ch...
14 篇 university of sc...
14 篇 misr int univ fa...
14 篇 department of co...
13 篇 univ chinese aca...
13 篇 institutes for r...
12 篇 centre of resear...
12 篇 al-farahidi univ...
12 篇 lviv polytech na...
12 篇 school of comput...
11 篇 guangdong provin...
11 篇 lovely professio...
11 篇 lovely professio...
11 篇 school of comput...
11 篇 the islamic univ...
11 篇 national energy ...
11 篇 king mongkuts un...

作者

15 篇 wang tao
13 篇 liu yang
13 篇 yang yang
13 篇 wang wei
13 篇 wang hao
11 篇 zhang jie
10 篇 zhang tao
10 篇 lima jose
10 篇 wang lei
10 篇 li hao
9 篇 hassanien aboul ...
9 篇 liu fang
8 篇 shiva mehta
8 篇 zhang lei
8 篇 aleven vincent
8 篇 liu jun
8 篇 wang chao
8 篇 singh jagendra
8 篇 pereira ana i.
8 篇 nojima yusuke

语言

10,170 篇 英文
1,453 篇 其他
74 篇 中文
1 篇 西班牙文
1 篇 法文
1 篇 俄文
1 篇 土耳其文

检索条件"任意字段=4th Conference on Learning and Intelligent Optimization"

共 11649 条记录，以下是701-710 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：

Deep learning for Speaker Recognition: A Comparative Analysis of 1D-CNN and LSTM Models Using Diverse Datasets 4

Deep Learning for Speaker Recognition: A Comparative Analysi...

引用

4th IEEE Interdisciplinary conference on Electrics and Computer (INTCEC)

作者： Hassanzadeh, Hiwa Qadir, Jihad Anwar Omer, Saman Muhammad Ahmed, Mohammed Hussein Khezri, Edris Univ Raparin Dept Software & Informat Engn Rania Kurdistan Regio Iraq Islamic Azad Univ Dept Comp Engn Boukan Branch Boukan Iran

ISBN: (纸本)9798350349467;9798350349450

Speaker recognition is a vital component of identity verification and security systems that has made significant progress through the use of deep neural networks. this article examines the comparative performance of two neural network models, namely a one-dimensional convolutional neural network (1D-CNN) and a long short-term memory (LSTM-based) network in identifying individuals based on their recorded voices. the article uses three diverse datasets, including the Raparin Artificial intelligent Lab (RAIL) dataset, which was created locally, and two public datasets, namely the TIMIT dataset and the Jordan dataset. the results show that the proposed 1D-CNN model consistently outperforms the LSTM model and has a significant accuracy rate, especially in the RAIL dataset, which achieves an accuracy of over 95.22%. this study emphasizes the potential of deep learning algorithms in improving sound-based identity recognition and highlights its effects on system security and communications.

关键词： Speaker recognition 1D-CNN LSTM Deep neural networks Identity verification

来源：评论

学校读者我要写书评

暂无评论

Research on Image Segmentation Method of Plant Leaf Diseases Based on SK-Attention Attention Mechanism 24

Research on Image Segmentation Method of Plant Leaf Diseases...

引用

4th International conference on Internet of things and Machine learning

作者： Hu, Huili Ye, Xi Yang, Zhihong Zhang, Quanxin Jianghan Univ Inst Intelligent Manufacture Wuhan Peoples R China

ISBN: (纸本)9798400710353

Traditional image segmentation models have certain limitations in the field of view, leading to insufficient performance in capturing global information for large-scale tasks and difficulty in integrating multi-scale features, which in turn reduces the accuracy of the algorithm and affects the segmentation effect. this paper proposes a Unet3+ plant leaf disease image segmentation method based on the SK-Attention attention mechanism. this improved attention mechanism introduces a "Selective Kernel" (SK) convolution technology, which can dynamically adjust the size of the convolution kernel to adapt to different field of view requirements, that is, by mixing the outputs of convolution kernels of different scales. the introduction of SK-Attention enhances the network's adaptability and selectivity to different scale features, thereby improving the network's segmentation performance. Finally, the image segmentation experiments conducted on the plant leaf disease dataset prove that this method can effectively improve the segmentation skills of plant leaf disease images, proving its correctness and effectiveness.

关键词： Unet3+ Plant Leaf Disease Image Segmentation SK-Attention Convolution kernel

来源：评论

学校读者我要写书评

暂无评论

Innovative Practices on Machine learning Models for Statistical Interpretation 4

Innovative Practices on Machine Learning Models for Statisti...

引用

4th International conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Gunasekaran, K.R. Babu, K G Raja Sabarish Nagpal, Amandeep Aswini, Kilaru Priyadharshini, L. Niranjana, K. Saveetha Institute of Medical and Technical Science Saveetha School of Law India Sourashtra College Madurai Research Department of Business Administration Tamilnadu India Lovely Professional University Phagwara India Institute of Aeronautical Engineering Hyderabad India

ISBN: (纸本)9798350307757

this project investigates the ways in which big data, machine learning, and hyperspectral information might be used in order to enhance agricultural operations. Because hyperspectral photography offers precise spectral information for each pixel, it is now feasible to detect and evaluate a broad variety of plant conditions. this is particularly useful in light of the explosion of data related to agriculture. A new paradigm in farm management is generated when the massive storage and processing powers of big data technologies are combined with the predictive capabilities of machine learning algorithms. this research analyzes how the convergence of these technologies might revolutionize yield prediction, disease diagnosis, and crop monitoring, therefore paving the way for more intelligent and data-driven decisions to be made in the agricultural sector. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on the Digital Twin System of intelligent Production Line 4

An Empirical Study on the Digital Twin System of Intelligent...

引用

4th International conference on Computer Science and Blockchain, CCSB 2024

作者： Zhu, Xiuli Li, Chengwei Mai, Junjie Yang, Junsong Kuang, Ziyang School of Robotics Guangdong Polytechnic of Science and Technology Zhuhai China

ISBN: (纸本)9798350356502

this paper focuses on the exploration of the digital twin system for intelligent production lines to address the various challenges encountered during the operation of such lines. the digital twin technology connects the physical and digital worlds by constructing virtual models, optimizing manufacturing processes such as simulating production processes, monitoring equipment operation, and rationally allocating resources. the system's architecture includes physical entity layers, data transmission layers, data layers, tools and visualization layers, and application layers. Its implementation involves modeling, data processing and analysis, real-time monitoring and prediction, optimization and simulation, and system integration and testing. the system offers diverse robot control modes, and experimental verification shows that it has excellent real-time performance, meeting the requirements for synchronized tasks in virtual and physical environments. the system integrates various functions, which help improve production efficiency, enhance safety, and optimize management processes, making significant contributions to the virtual-real joint tuning of intelligent production lines and the intelligent development of the manufacturing industry. In the future, digital twin technology will deeply integrate with other technologies and be widely applied in more fields. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Time-optimal trajectory planning for robotic arm based on improved particle swarm optimization 24

Time-optimal trajectory planning for robotic arm based on im...

引用

4th International conference on Control and intelligent Robotics, ICCIR 2024

作者： Gao, Feng Jiang, Tao Yu, Zhuonan Changchun University of Science and Technology Changchun China

ISBN: (纸本)9798400709937

Aiming at the problem of robotic arm motion efficiency and stability, a time-optimized trajectory planning method based on the improved particle swarm algorithm is proposed, which is based on the 3-5-3 combined segmented polynomial interpolation algorithm, with the time in the segmented interval as the optimization objective, and optimizes the particle swarm algorithm by dynamically adjusting the learning factor and the inertia weights. Taking the Aubo-i3 robotic arm as the research object, the inverse kinematics is used to find out the sequence of each joint angle corresponding to the end path point of the given robotic arm, and the segmented polynomial is used to fit the motion trajectory under the joint space;under the velocity and acceleration constraints, the improved particle swarm algorithm is used to optimize the motion trajectory of the robotic arm with the shortest time. the simulation is carried out by MATLAB software and experimental analysis is performed. the convergence speed and accuracy of the method are significantly improved, and the algorithm does not fall into local convergence, and the final optimization result has 29.9% improvement. Under this trajectory, the joint angle, velocity and acceleration curves of the robotic arm are smooth without sudden changes, and the robotic arm moves smoothly, and the method is feasible. © 2024 held by the owner/author(s).

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Differential diagnosis of radiation encephalopathy and post-radiation brain tumor recurrence by machine learning models based on contrast-enhanced MRI 4

Differential diagnosis of radiation encephalopathy and post-...

引用

4th International conference on Bioinformatics and intelligent Computing (BIC)

作者： Li, Te Wang, Lingfei Wang, Xi Sun, Hong Zhejiang Police Vocat Acad Dept Secur & Precaut Hangzhou Peoples R China Hangzhou Med Coll Dept Oncol 903 Hosp PLA Joint Logist Support Force Xi Hu Affiliated Hosp Hangzhou Peoples R China

ISBN: (纸本)9798400716645

Purpose: Discriminating radiation encephalopathy (REP) from brain tumor recurrence is often difficult. this study aims to develop and validate an approach to distinguish REP from post-radiation brain tumor recurrence using machine learning. Methods: this study involved 102 patients diagnosed and treated in our institution between 2020 and 2023. A total of 2153 radiomics features were extracted from contrast-enhanced MRI by using 3D-Slicer software and Pycharm platform. Nine diagnostic models were built and compared based on three selection methods and three classification algorithms. the sensitivity, specificity, accuracy, and area under curve (AUC) of each model were calculated, and based on these the optimal model was chosen. Results: the least absolute shrinkage and selection operator with correlation (LASSO+corr) was chosen as the optimal selection method, which selected 17 important radiomics features. the most promising model was a combination of LASSO+corr as the selection method and logistic regression (LR) as the classification algorithm. the combination models of LASSO+corr with LR, random forest (RF) and support vector machine (SVM) showed sensitivities of 0.88, 0.86 and 0.97, and specificities of 0.98, 0.93 and 0.90 with AUC of 0.9805, 0.9452 and 0.9743, respectively. Conclusion: Radiomics-based machine learning has potential to be utilized in differentiating REP from recurrent brain tumor after radiotherapy accurately.

关键词： Radiation encephalopathy (REP) brain tumor radiomics machine learning differential diagnosis

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-modal Data Management System for intelligent Connected Vehicle 4

Research on Multi-modal Data Management System for Intellige...

引用

4th IEEE International conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2024

作者： Zhang, Lu Guangxi Vocational Normal University School of Computer and Information Engineering Guangxi China

ISBN: (纸本)9798350363586

the development of intelligent networked vehicle technology and the testing of related algorithms require a large number of datasets as the foundation. the existing datasets are mainly collected from foreign traffic scenarios, which are significantly different from the actual road traffic environment of China. therefore, it is particularly important to construct local datasets and data management systems. this paper describes in detail the design of multi-modal data management system for intelligent Connected Vehicle, covering the overall architecture of systems, hardware composition, the design of software function modules, database design, and key steps for data processing. Experiments and tests verified the reliability and effectiveness of the data management system. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Online Monitoring and Image optimization of Overhead Transmission Line Operating Environment under Rain Weather Conditions 4

Online Monitoring and Image Optimization of Overhead Transmi...

引用

4th International conference on intelligent Power and Systems, ICIPS 2024

作者： Wang, Qiru Li, Hualiang Pang, Zhicheng Shen, Yali Li, Jining Lin, Ziyue Guangdong Power Grid Co. Ltd. Electric Power Science Research Institute Guangzhou510000 China Shandong University of Technology School of Electrical and Electronic Engineering Zibo255000 China

ISBN: (纸本)9798331532765

Transmission lines are an important part of the safe and reliable operation of the power grid, and the monitoring of transmission lines is an important task for the safe operation of the power grid. therefore, the main purpose of this paper is to remove the rain traces in the transmission line inspection images under severe rain and snow conditions, and get a clear background image. In order to achieve better rain removal effect of single image, this paper researches and analyzes the a priori rain removal algorithms, obtains the algorithm with the best rain removal effect, and applies it to the transmission line images so as to find faults in time and react to them. © 2024 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

D-KAN Model: Enhancing Power Load Forecasting with Kolmogorov-Arnold Networks 4

D-KAN Model: Enhancing Power Load Forecasting with Kolmogoro...

引用

4th International conference on Energy Engineering and Power Systems, EEPS 2024

作者： Jiang, Mengyuan Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9798350366914

As the demand for power load forecasting continues to grow in modern society, this paper proposes an improved D-KAN model that integrates Kolmogorov-Arnold Networks (KAN) into the DLinear power load time series prediction framework. the model utilizes KAN's learnable activation functions, parameterized by spline functions, to enhance the accuracy of electricity demand forecasting. this study focuses on the electricity load data from Huanggang City, Hubei Province, covering the period from April 2022 to July 2023. Experimental results show that the D-KAN model performs more accurately in short-term predictions compared to the DLinear model. © 2024 IEEE.

关键词： D-KAN Deep learning electricity load forecasting Kolmogorov-Arnold Networks (KAN) Machine learning styling Time Series Analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Knowledge Graph Representation learning Method Based on Logical Rule Fusion 4

Research on Knowledge Graph Representation Learning Method B...

引用

4th IEEE International conference on Software Engineering and Artificial Intelligence (SEAI)

作者： Li, Lin Zhao, Haili Meng, Lingshuai Luo, Haitao Chen, Zixuan Li, Weikuang Lin, Shenwen Coordinat Ctr China Natl Comp Network Emergency Response Tech Team Beijing Peoples R China Changan Commun Technol Co LTD Beijing Peoples R China

ISBN: (纸本)9798350374353;9798350374346

this paper presents a knowledge graph representation learning framework based on Horn clause rules, designed to efficiently integrate logical information into knowledge graphs (KGs) in continuous vector spaces. Due to the challenge of rule uncertainty, it is difficult to devise a principled framework in continuous vector spaces where encoding the logical background knowledge of rules is usually not straightforward. therefore, we propose a solution that calculates the Horn rule constraint among relations, obtained through iterative optimization learning with labeled triplets, objective score functions, and relation modeling. this method enables us to achieve better regulation of rule-based effects, merely enforcing relation representations to satisfy constraints introduced by Horn rules. Finally, we analyze the proposed method on several FB15K datasets. the analysis results demonstrate that our scheme effectively improves the performance of link prediction evaluation on public datasets.

关键词： knowledge graph representation learning Horn rule embedding 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 << < 67 68 69 70 71 72 73 74 75 76 > >>

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：