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

7,771 篇 会议
95 篇 期刊文献
55 册 图书

馆藏范围

7,921 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,799 篇 工学
- 2,020 篇 计算机科学与技术...
- 1,394 篇 软件工程
- 660 篇 控制科学与工程
- 508 篇 信息与通信工程
- 500 篇 电气工程
- 251 篇 机械工程
- 207 篇 仪器科学与技术
- 188 篇 电子科学与技术（可...
- 138 篇 生物医学工程（可授...
- 124 篇 生物工程
- 91 篇 光学工程
- 82 篇 网络空间安全
- 79 篇 动力工程及工程热...
- 67 篇 化学工程与技术
- 65 篇 力学（可授工学、理...
- 53 篇 材料科学与工程（可...
- 53 篇 交通运输工程
1,057 篇 理学
- 681 篇 数学
- 288 篇 统计学（可授理学、...
- 222 篇 物理学
- 179 篇 系统科学
- 149 篇 生物学
- 80 篇 化学
674 篇 管理学
- 552 篇 管理科学与工程(可...
- 199 篇 工商管理
- 163 篇 图书情报与档案管...
130 篇 医学
- 100 篇 临床医学
- 81 篇 基础医学(可授医学...
68 篇 法学
- 67 篇 社会学
49 篇 经济学
- 48 篇 应用经济学
33 篇 教育学
20 篇 农学
20 篇 军事学
10 篇 文学
2 篇 艺术学

主题

1,896 篇 computational mo...
1,025 篇 measurement
442 篇 computer archite...
423 篇 neural networks
414 篇 predictive model...
347 篇 computer science
301 篇 accuracy
287 篇 biological syste...
258 篇 analytical model...
242 篇 noise measuremen...
228 篇 real-time system...
223 篇 computer simulat...
221 篇 training
216 篇 brain modeling
216 篇 mathematical mod...
214 篇 feature extracti...
187 篇 power system mod...
182 篇 data models
181 篇 neurons
173 篇 temperature meas...

机构

20 篇 school of comput...
17 篇 department of el...
15 篇 school of electr...
14 篇 budapest univ te...
13 篇 chitkara univers...
13 篇 school of comput...
12 篇 department of co...
11 篇 department of co...
10 篇 college of compu...
10 篇 college of compu...
9 篇 tsinghua univers...
8 篇 school of comput...
8 篇 department of el...
8 篇 department of co...
7 篇 graphic era deem...
7 篇 school of comput...
7 篇 school of comput...
7 篇 peng cheng labor...
7 篇 school of contro...
6 篇 college of compu...

作者

11 篇 towsley don
10 篇 varró dániel
9 篇 wei wang
8 篇 liu alex x.
8 篇 anon
7 篇 liu yang
7 篇 wei li
7 篇 wang jia
6 篇 li zhang
6 篇 byung-ju yi
6 篇 reiner r. dumke
6 篇 yang liu
5 篇 deepak banerjee
5 篇 chunyan miao
5 篇 li li
5 篇 hao li
5 篇 t.m. khoshgoftaa...
5 篇 rizzi antonello
5 篇 j.c. principe
5 篇 sakorn mekruksav...

语言

7,669 篇 英文
227 篇 其他
28 篇 中文
5 篇 俄文

检索条件"任意字段=Joint International Conference on Measurement and Modeling of Computer Systems"

共 7921 条记录，以下是1171-1180 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：

Photovoltaic Array Fault Detection Based on Manifold Learning and Neural Network

Photovoltaic Array Fault Detection Based on Manifold Learnin...

引用

computer Vision, Image and Deep Learning (CVIDL), international conference on

作者： Kai Wang Yanru Zhong Xiaonan Luo Guangxi Key Laboratory of Intelligent Processing of computer Images and Graphic Guilin University of Electronic Science and Technology Guilin China Navigation Positioning and Location Services National and Local Joint Engineering Research Center Guilin University of Electronic Science and Technology Satellite Guilin China

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

This paper endeavors to devise an ingenious methodology rooted in artificial intelligence, which, in turn, can be effectively employed to identify sundry categories of faults that are closely associated with photovoltaic arrays. This novel approach amalgamates the manifold learning algorithm with a formidable multilayer perceptron neural network (MLP). Intriguingly, it substantiates that the initial reduction in data dimensionality is achieved through the remarkable Isomap algorithm. Consequently, this compressed data is seamlessly channeled into the MLP, thereby yielding remarkable outcomes concerning fault detection. To validate and scrutinize the aforementioned proposition, a quintessential circuit representing a photovoltaic array is initially simulated utilizing the venerable Matlab/Simulink tool. During this simulation, an extensive corpus of both normal and faulty data is meticulously generated. Subsequently, the manifold learning algorithm is artfully applied to drastically diminish the dimensionality of this extensive dataset The resultant compressed data is then deftly fed into the MLP, allowing it to discern the salient characteristics pertaining to the sundry fault types. Through incessant iterations of intensive training, these faults can be astutely detected and discerned with remarkable accuracy. The results conclusively demonstrate the efficacy of combining manifold-based learning and multilayer perceptron neural network in detecting faults in photovoltaic arrays. The proposed method achieves high precision and effectiveness, surpassing the traditional approach by 2.52%.

关键词： Photovoltaic systems Training Accuracy Fault detection Computational modeling Multilayer perceptrons Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Enhanced Convolutional Neural Networks for Breast Cancer Detection

Enhanced Convolutional Neural Networks for Breast Cancer Det...

引用

Intelligent systems for Cybersecurity (ISCS), international conference on

作者： Ashok Reddy Kandula Pujitha Ganta Grace Apoorva Gali Sandeep Kasagani Devi Venkata Karthik Tikkisetti Department of Artificial Intelligence and Data Science Seshadri Rao Gudlavalleru Engineering College Gudlavalleru India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

For women all around the world, breast cancer is a serious concern. Catching it early is like having a superhero move - it can make all the difference, turning a potentially life-threatening situation into one with a shot at successful treatment. So, finding it sooner rather than later is a real lifesaver. To evaluate the performance of the proposed model, the researchers trained and tested the model on the Breast ultrasound Images dataset. These images, meticulously prepared through resizing, normalization, and augmentation, have been widely utilized in prior studies focusing on breast cancer prediction. The study focuses on refining accuracy through the utilization of Convolutional Neural Networks (CNNs) in combination with Transfer Learning for initial improvement. Following this, the approach shifts to leveraging the potential of the Adam optimizer with the CNN and Transfer Learning architecture to further boost accuracy. The implications of this study transcend the conventional confines of traditional medical image analysis, providing a glimpse into a prospective era where intelligent algorithms harmoniously collaborate with medical professionals. This collaboration serves to elevate the benchmarks of diagnostic accuracy. With the augmentation of early detection potential, patient outcomes stand to witness marked enhancement, thus underscoring the transformative prowess embedded within the capabilities of deep learning in the domain of breast cancer diagnosis.

关键词： measurement Adaptation models Accuracy Computational modeling Transfer learning computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Image-Based 3D Gaussian Rendering: A Hybrid Approach for Scene Visualization

Image-Based 3D Gaussian Rendering: A Hybrid Approach for Sce...

引用

Information systems and Computing Technology (ISCTech), international conference on

作者： Jianfeng Xuan Yanling Huang Yanan Guo Bo Jia School of Information and Communication Engineering Beijing Information Science and Technology University Beijing China

ISBN: (数字)9798350379860

ISBN: (纸本)9798350379877

Recently, substantial advancements have occurred in the field of 3D rendering, driven by the success of the 3D Gaussian splatting method. However, current 3D Gaussian models rely on structure-from-motion (SfM) feature points, which face limitations in rendering quality due to the restricted use of image feature information and their dependence on initial training viewpoints. To address these limitations, we propose a novel hybrid feature representation method that combines point cloud-based features with image semantic *** core of this method is to utilize a lightweight convolutional neural network to extract fine-grained semantic features from multi-view images and to employ a novel composite distance metric to precisely align these features with point cloud data. This approach ensures accurate alignment of features and enhances the richness of 3D scene representations. The proposed method significantly improves rendering quality and generalization ability, making it more robust in handling diverse and complex viewing scenarios. Experimental results validate the effectiveness of this method across a wide range of 3D rendering applications, demonstrating its exceptional generalization capabilities under complex viewing conditions.

关键词： Point cloud compression measurement Training Solid modeling Three-dimensional displays Accuracy Semantics Rendering (computer graphics) Feature extraction Information systems

来源：评论

学校读者我要写书评

暂无评论

Multi-culture Sign Language Detection and Recognition Using Fine-tuned Convolutional Neural Network

Multi-culture Sign Language Detection and Recognition Using ...

引用

Smart Computing and Application (ICSCA), international conference on

作者： M Faisal Nurnoby El-Sayed M. El-Alfy Information and Computer Science King Fahd University of Petroleum & Minerals (KFUPM) Saudi Arabia SDAIA-KFUPM Joint Research Center for Artificial Intelligence (JRC-AI) *Affiliate Interdisciplinary Research Center for Intelligent Secure Systems (IRC-ISS) KFUPM

Communication through hand gestures is an active research topic in computer vision and Human computer Interaction (HCI). Deaf and speech-impaired community may benefit from the advancement of sign gesture recognition as an intermediary visual communication technique. There is no universal sign language, but different nationalities have their own sign languages. Usually sign gestures ought to be distinct and independently distinguishable and researchers in this domain have always focused on techniques for a particular sign language. However, recognizing sign languages from multiple nations could be helpful in various situations such as dealing with multiple signing persons without knowing their nationalities. This paper presents a novel approach where a two-phased system is designed based on deep learning for identification of the sign language and recognition of the sign gesture. This approach opens a new research direction for the advancement of multi-sign language development. The proposed approach has been implemented and evaluated using two custom-based CNN models and compared to some other popular CNN models. More than 98% accuracy can be achieved when tested on two different datasets.

关键词： Human computer interaction Deep learning computer vision Visual communication Computational modeling Gesture recognition computer architecture

来源：评论

学校读者我要写书评

暂无评论

Q2Cypher: Converting Natural Language Questions to Cypher with Fine-Tuned Large Language Models

Q2Cypher: Converting Natural Language Questions to Cypher wi...

引用

Artificial Intelligence and computer Engineering (ICAICE), international conference on

作者： Yunqi Zou Yongli Wang Dongmei Liu School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9798331528911

ISBN: (纸本)9798331528928

Knowledge Base Question Answering (KBQA) intends to obtain credible answers to natural language questions based on knowledge bases. Knowledge graphs, also known as graph databases, explicitly present a large amount of factual knowledge and the associations among them. Neo4j, one of the most popular graph databases, uses the Cypher Query Language (CQL) for efficient querying. Due to its complexity, converting natural language questions into CQL, i.e., Text-to-CQL, is in demand, but the performance is undesirable for existing models. To address the issue, we propose Q2Cypher, a Text-to-CQL framework that is able to generate corresponding CQL based on natural language questions by fine-tuning open-source large language models (LLMs). Q2Cypher employs an unsupervised joint retrieval method to further align entity and relation names in the CQL, thus improving generation from the models more directly. We conduct experiments on open-source LLMs such as ChatGLM2, Baichuan2 and Llama-2, using different fine-tuning methods such as LoRA, Freeze and QLoRA for comparison. The experimental results demonstrate that Q2Cypher is effective and achieves better performance than existing methods on the SpCQL dataset.

关键词： Ciphers Accuracy Databases Large language models Computational modeling Natural languages Knowledge based systems Knowledge graphs Question answering (information retrieval) Database languages

来源：评论

学校读者我要写书评

暂无评论

Research on Software Vulnerability Information Knowledge Graph Construction Method Based on Text Mining

Research on Software Vulnerability Information Knowledge Gra...

引用

IEEE international conference on Artificial Intelligence and computer Applications (ICAICA)

作者： Yechao Wang Wuqiang Shen Chaosheng Yao Zitong Zhang Guangdong Power Grid Corporation Guangzhou China China Southern Power Grid Joint Laboratory on Cyberspace Security Guangzhou China Shenzhen E-Link Information Technology Co. Ltd Guangzhou China

ISBN: (数字)9798350377255

ISBN: (纸本)9798350377262

With the rapid development of information technology and the widespread adoption of software applications, software vulnerabilities have become a significant challenge in the field of cybersecurity. Effective processing of software vulnerability information is crucial not only for the security and reliability of information systems but also directly impacts the data security of organizations and individuals. This paper comprehensively explores the application of text mining technology and knowledge graph construction technology in the processing of software vulnerability information, aiming to improve the efficiency of vulnerability information acquisition, analysis, and management. By examining existing technologies and methods, this study focuses on the key technologies of text mining in entity recognition and relation extraction, as well as the role of knowledge graphs in integrating and managing vulnerability information. Moreover, this paper discusses the challenges faced in the big data environment and corresponding solutions, including data noise processing, entity ambiguity resolution, and high-dimensional feature processing. Through practical application case analysis, this paper demonstrates the actual effects and potential value of text mining and knowledge graph technology in enhancing the capability of software vulnerability information processing. The findings of this study not only provide new perspectives and methods for software vulnerability information processing but also offer robust technical support for cybersecurity protection.

关键词： Text mining Computational modeling Noise Knowledge graphs Information processing Network security Software Data models Protection computer security

来源：评论

学校读者我要写书评

暂无评论

Traffic sign detection using Deep learning techniques

Traffic sign detection using Deep learning techniques

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), international conference on

作者： P Someswari R Cristin T Daniya Dept. of CSE GMR Institute of Technology Rajam India

In this fast-growing world, the trend of self-driving cars and advanced driving systems is increasing rapidly. For humans, identifying a traffic sign is an easy task. However, for self-driving cars, accurate and fast road sign location and classification remains an incredible challenge. So, detection of traffic sign in autonomous vehicles has been catching the attention of the computer vision community incessantly for several decades. With the intensive development of artificial intelligence and computer vision technologies, Deep Learning appears to be one of the most effective solutions for complex detection tasks such as traffic sign detection, which has high demands on accuracy and response speed in multi-object detection. Our proposed work involves in developing a model based on Convolution Neural Network (CNN) in Deep Learning that can be utilized to characterize the traffic signs with great exactness. The performance of our model will be measured by using different metrics like accuracy, F1 score.

关键词： Deep learning measurement computer vision Computational modeling Roads Neural networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

Discharging Stage Prediction of Lithium Ion Battery Using CNN - DenseNet Architecture

Discharging Stage Prediction of Lithium Ion Battery Using CN...

引用

international conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Mukhidin Akhmad Fauzan Ali Muhammad Abdillah Hayati Yassin Erly Krisnanik Wahyu Caesarendra Faculty of Integrated Technologies Universiti Brunei Darussalam Bandar Seri Begawan Brunei Darussalam Department of Electrical Engineering Pertamina University Jakarta Indonesia Faculty of Computer Science Veterans National Development University Jakarta Jakarta Indonesia Faculty of Mechanical Engineering Opole University of Technology Opole Poland

ISBN: (数字)9798331533243

ISBN: (纸本)9798331533250

Lithium-ion batteries are one of the most widely used types of batteries in various applications, including electronic devices, electric vehicles, and energy storage systems. However, battery discharging caused by parasitic reactions between electrodes and electrolytes is one of the most common problems. New methods such as Convolutional Neural Networks (CNN) can help predict discharging modes and improve battery reliability and safety. CNN is used to predict discharging in lithium-ion batteries based on data collected during battery monitoring experiments at different load levels. The data is processed and modeled to support the predictive model. The methodological process involves data collection, data preprocessing, feature selection, and artificial intelligence model training. Model performance is tested using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) as metrics. The developed CNN model is observed to follow data trends. For the CNN model, an RMSE of 0.0255, MAE of 0.0182, and MAPE of 0.216% were obtained during the training process on 80% of the data for voltage prediction. The model has been tested to be applicable in real-world scenarios for detecting battery discharging.

关键词： Lithium-ion batteries measurement Computational modeling computer architecture Voltage Predictive models Data models Convolutional neural networks Long short term memory Load modeling

来源：评论

学校读者我要写书评

暂无评论

Automatic Recognition of Social Engagement for Children with Autism Spectrum Disorder

Automatic Recognition of Social Engagement for Children with...

引用

IEEE international conference on systems, Man and Cybernetics

作者： Xinming Wang Xiangdong Zhang Zhiyong Wang Wei Nie Hanlin Zhang Xiu Xu Honghai Liu State Key Laboratory of Robotics and Systems School of Mechanical and Automation Harbin Institute of Technology (Shenzhen) Shenzhen China Lishui Maternity and Child Health Care Hospital Center of Medical Prenatal Diagnosis Lishui China Department of Child Health Care Children's Hospital of Fudan University Shanghai China School of Computing University of Portsmouth Portsmouth U.K Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Estimating children's engagement levels improves their understanding of their social behaviors, since they can reflect their devotion to social interaction with others. This paper proposes an automatic method to recognize children's engagement levels in a triadic social interaction context. First, an overall metric function containing behavior, cognition, and affective dimensions is proposed to estimate children's multidimensional engagement levels. Then, the automatic feature extraction method based on gaze estimation, facial expression recognition, pose estimation, and object recognition models is illustrated to extract features to compute the engagement levels. Videos of 24 children, including 13 children with autism spectrum disorder (ASD), in triadic social interaction were collected for the engagement recognition experiment and cross-group analysis. The experimental results validate the effectiveness of the proposed automatic feature extraction method compared to human observations. Cross-group analyses revealed significant differences in affective engagement between children with ASD and typical developmental (TD) children.

关键词： measurement Autism computer vision Computational modeling Face recognition Pose estimation Feature extraction Object recognition Cybernetics Videos

来源：评论

学校读者我要写书评

暂无评论

Ultra-High-Frequency Harmony: mmWave Radar and Event Camera Orchestrate Accurate Drone Landing 25

Ultra-High-Frequency Harmony: mmWave Radar and Event Camera ...

引用

Proceedings of the 23rd ACM conference on Embedded Networked Sensor systems

作者： Haoyang Wang Jingao Xu Xinyu Luo Xuecheng Chen Ting Zhang Ruiyang Duan Yunhao Liu Xinlei Chen Shenzhen International Graduate School Tsinghua University Shenzhen Guangdong China Carnegie Mellon University Pittsburgh USA Tsinghua University Shenzhen Guangdong China Tsinghua-Berkeley Shenzhen Institute Shenzhen International Graduate School Tsinghua University Shenzhen Guangdong China Meituan Technology Shenzhen Guangdong China Tsinghua University beijing China Pengcheng Laboratory Shenzhen Guangdong China RISC-V International Open Source Laboratory Shenzhen Guangdong China

ISBN: (纸本)9798400714795

For precise, efficient, and safe drone landings, ground platforms should real-time, accurately locate descending drones and guide them to designated spots. While mmWave sensing combined with cameras improves localization accuracy, lower sampling frequency of traditional frame cameras compared to mmWave radar creates bottlenecks in system throughput. In this work, we replace traditional frame camera with event camera, a novel sensor that harmonizes in sampling frequency with mmWave radar within ground platform setup, and introduce mmE-Loc, a high-precision, low-latency ground localization system designed for drone landings. To fully leverage the temporal consistency and spatial complementarity between these modalities, we propose two innovative modules, consistency-instructed collaborative tracking and graph-informed adaptive joint optimization, for accurate drone measurement extraction and efficient sensor fusion. Real-world experiments in landing scenarios from a drone delivery company demonstrate that mmE-Loc outperforms SOTA methods in both accuracy and latency.

关键词： drone ground localization

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 << < 114 115 116 117 118 119 120 121 122 123 > >>

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：