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

6,097 篇 会议
65 篇 期刊文献
51 册 图书
2 篇 学位论文

馆藏范围

6,215 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,624 篇 工学
- 2,546 篇 计算机科学与技术...
- 1,803 篇 软件工程
- 1,418 篇 信息与通信工程
- 991 篇 电气工程
- 424 篇 控制科学与工程
- 401 篇 电子科学与技术（可...
- 371 篇 光学工程
- 349 篇 生物工程
- 289 篇 生物医学工程（可授...
- 287 篇 仪器科学与技术
- 233 篇 机械工程
- 148 篇 安全科学与工程
- 139 篇 交通运输工程
- 114 篇 化学工程与技术
- 106 篇 材料科学与工程（可...
- 102 篇 网络空间安全
- 100 篇 动力工程及工程热...
- 83 篇 建筑学
1,492 篇 理学
- 691 篇 数学
- 542 篇 物理学
- 374 篇 生物学
- 232 篇 系统科学
- 215 篇 统计学（可授理学、...
- 117 篇 化学
538 篇 管理学
- 325 篇 管理科学与工程(可...
- 256 篇 图书情报与档案管...
- 129 篇 工商管理
347 篇 医学
- 327 篇 临床医学
- 164 篇 基础医学(可授医学...
- 110 篇 药学(可授医学、理...
98 篇 法学
60 篇 农学
48 篇 经济学
40 篇 教育学
27 篇 军事学
16 篇 文学
5 篇 艺术学

主题

325 篇 feature extracti...
305 篇 internet of thin...
258 篇 real-time system...
195 篇 internet
189 篇 image segmentati...
170 篇 signal processin...
167 篇 image processing
156 篇 accuracy
146 篇 deep learning
146 篇 image edge detec...
139 篇 signal processin...
130 篇 cameras
129 篇 training
127 篇 image coding
116 篇 image color anal...
106 篇 image retrieval
106 篇 visualization
98 篇 computational mo...
97 篇 robustness
89 篇 signal to noise ...

机构

11 篇 school of comput...
9 篇 faculty of infor...
8 篇 school of cyber ...
8 篇 school of electr...
8 篇 beijing universi...
8 篇 state key labora...
7 篇 school of inform...
7 篇 school of inform...
7 篇 college of elect...
7 篇 institute of sig...
7 篇 harbin institute...
7 篇 college of infor...
7 篇 school of electr...
6 篇 university of sc...
6 篇 school of inform...
6 篇 school of electr...
6 篇 chaoyang univ te...
6 篇 university of el...
6 篇 wuhan university...
6 篇 department of in...

作者

13 篇 yoshitaka sakura...
13 篇 tsuruta setsuo
13 篇 sakurai yoshitak...
13 篇 fan zhun
12 篇 setsuo tsuruta
11 篇 li li
11 篇 wang wei
10 篇 yetongnon kokou
9 篇 dipanda albert
9 篇 zhang yan
9 篇 lee chin-feng
8 篇 zhang lei
8 篇 jing wang
8 篇 wang hao
7 篇 zhu guijie
7 篇 kinshuk
7 篇 jeon gwanggil
7 篇 ahmad tohari
7 篇 shen jau-ji
7 篇 wang xin

语言

5,994 篇 英文
201 篇 其他
35 篇 中文
1 篇 土耳其文

检索条件"任意字段=International Conference on Signal-Image Technology and Internet-Based Systems"

共 6215 条记录，以下是241-250 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：

A Deep Learning-based Pre-Trained VGG19 Model for Optical Character Recognition 2

A Deep Learning-based Pre-Trained VGG19 Model for Optical Ch...

引用

2nd international conference on Intelligent Cyber Physical systems and internet of Things (ICoICI)

作者： Singh, Gurpreet Guleria, Kalpna Sharma, Shagun Chitkara Univ Inst Engn & Technol Rajpura Punjab India

ISBN: (纸本)9798331540661;9798331540678

Optical Character Recognition (OCR) stands as a pivotal technology in the digitization and processing of textual information from images. In this study, we propose a novel approach to OCR leveraging the VGG19 convolutional neural network (CNN) architecture. VGG19, renowned for its depth and performance in image classification tasks, is repurposed here to tackle the intricate challenges of character recognition. Through extensive experimentation and evaluation, this study demonstrate the efficacy of the proposed approach in achieving state-of-the-art accuracy and robustness in extracting textual information from images. This study uses diverse datasets comprising printed and handwritten text samples, augmenting them using various techniques to enhance model generalization. The VGG19 model is trained end-to-end, with its convolutional layers serving as feature extractors for character recognition. This paper presents a novel approach to Optical Character Recognition (OCR) using the VGG19 convolutional neural network (CNN). OCR is a fundamental technology that converts printed or handwritten text into digital format, facilitating document digitization and information retrieval. The proposed method leverages the hierarchical features learned by VGG19 to accurately extract textual information from images. This study has conducted experiments using publicly available datasets, achieving significant improvements in both training and test accuracy across epochs. Specifically, the proposed model has achieved a training accuracy of 94.34% and a test accuracy of 94.96% after ten epochs of training. Furthermore, we observed a consistent decrease in both training and test loss throughout the training process, indicating effective convergence and refinement of the model parameters. These results demonstrate the efficacy of the VGG19-based OCR model in accurately recognizing characters from diverse input images, highlighting its potential for various real-world applications such a

关键词： Machine learning Deep learning Handwriting VGG19 Model image recognition CNN Layers

来源：评论

学校读者我要写书评

暂无评论

Double-exponential trapezoidal shaping filtering algorithm based on FPGA 4

Double-exponential trapezoidal shaping filtering algorithm b...

引用

4th international conference on Advanced Algorithms and signal image Processing, AASIP 2024

作者： Wang, Chaoya Qu, Jinhui Li, Lang Yang, Hua Pan, Anyuan Wang, Shaofei Tang, Bin Zhang, Ying Zhi, Chao Chongqing University of Technology Chongqing Key Laboratory of Optical Fibre Sensing and Photodetection Chongqing400054 China East China University of Technology Nanchang China High-tech Enterprise Research and Development Centre for High-grade Servo Numerical Control System Zhejiang Province Jiaxing China

ISBN: (数字)9781510682818

ISBN: (纸本)9781510682801

With the rapid development of high-precision and high-speed ADC devices, traditional analog processing methods for nuclear pulse signals have gradually exited the historical stage. Digitizing nuclear pulse signals has become the main research direction in multi-channel nuclear energy spectrum measurement systems. The trapezoidal shaping filtering algorithm, as the most used nuclear pulse shaping algorithm, has a certain noise suppression capability. This paper studies the double-exponential trapezoidal shaping filtering method based on FPGA in practical applications and explores its role in further eliminating pile-up effects under high counting rates. © 2024 SPIE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Intersection lane line segmentation algorithm based on improved YOLOv8n-seg 4

Intersection lane line segmentation algorithm based on impro...

引用

4th international conference on Advanced Algorithms and signal image Processing, AASIP 2024

作者： Guo, Zhifan Zhang, Yongzhong Beijing Key Lab of Urban Road Traffic Intelligent Technology North China University of Technology Beijing100144 China

ISBN: (数字)9781510682818

ISBN: (纸本)9781510682801

Lane line segmentation technology is crucial for extracting traffic parameters at urban road intersections. Currently, manually delineating intersection lane lines can no longer meet the demands of constructing digital traffic systems. Due to significant environmental interference and the diverse distribution of lane lines in the perspective of intersection video surveillance, existing lane line segmentation algorithms are ineffective for intersection scenarios. To address this issue, we propose an improved intersection lane line segmentation model based on YOLOv8n-seg. Firstly, inspired by the architecture of the Vision Transformer (ViT), we optimize the C2f module and incorporate attention mechanisms to enhance the network's ability to integrate features and capture global information. Secondly, we replace strided convolutions with a Haar wavelet downsampling module, which preserves all feature map information during downsampling. The experimental results show that mAP@0.5 and mAP@0.5:0.95 of the improved YOLOv8n-seg in segmentation are 5.7% and 1.5 % higher than the original model, and the advantages of low parameters and high FPS are maintained, which can effectively realize segmenting intersection lane lines. © 2024 SPIE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Neural Network based Transceiver for Non-Coherent OFDM Optical Modulation 25

Neural Network based Transceiver for Non-Coherent OFDM Optic...

引用

25th international conference on Advanced Communication technology (ICACT) - New Cyber Security Risks for Enterprise Amidst COVID-19 Pandemic

作者： Ibrahim, Asmaa Elsheikh, Ahmed Abdelsalam, Ahmed M. Prat, Josep Univ Politecn Catalunya UPC Dept Signal Theory & Commun Barcelona Spain Cairo Univ Fac Engn Giza Egypt Egypt Japan Univ Cairo Egypt

ISBN: (纸本)9791188428106

Optical wireless and radio front-haul communication systems are deemed as potential technologies to the radio frequency wireless communications in several applications. Consequently, the clipped non-coherent optical modulation techniques have gained significant attention. The trade-off between the spectral efficiency and the powerefficiency of the benchmark techniques such as asymmetrical clipping optical OFDM (ACO-OFDM) and direct clipping optical OFDM (DCO-OFDM), pose a challenge of maintaining enhanced spectral and power efficiency for the design of the optical modulation techniques. In this paper, we propose a deep neural network (DNN) based optical transceiver. It uses simple but efficient DNN to predict the clipped negative parts of the transmitted signal at the receiver side. We evaluate and analyze several DNN-based optical transceiver architectures for different performance aspects. The DNN-based optical OFDM transceiver enhances the spectral and power efficiency compared to the latest works.

关键词： ACO-OFDM DCO-OFDM Deep neural network Supervised learning Optical modulation

来源：评论

学校读者我要写书评

暂无评论

Development of a Movie AI Question Answering System based on Knowledge Graph 4

Development of a Movie AI Question Answering System Based on...

引用

4th international signal Processing, Communications and Engineering Management conference, ISPCEM 2024

作者： Xu, Yihan Xie, Nan Hu, Xinjun Chen, Weimin College of Computer Science and Technology Zhejiang University of Water Resources and Electric Power Zhejiang Hangzhou China College of Mechanical and Electrical Engineering China Jiliang University Zhejiang Hangzhou China

ISBN: (纸本)9798331528676

With the increasing influence of the internet, information retrieval technology needs to be continuously upgraded. The development of the internet drives the transformation of the film industry, with an increase in the number of online movies, a flourishing of professional film websites and forums, and an increasing influence of online comments. There are still shortcomings in the relationship between the internet and film evaluation, and further exploration is needed. The development of this system adopts a front-end and back-end separation mode, with Vue technology architecture used in the front-end and Django framework used in the back-end. The knowledge graph can organize and express movie information, providing data support for intelligent question answering and comment systems. The system constructs a graph by collecting movie data, achieving storage, management, and querying, providing intelligent and personalized services, and designing movie review functions to provide comprehensive information and evaluation references;The question answering function is implemented through natural language processing technology (NLP) and graph database technology, which can recognize the user's query intention and retrieve relevant information, generate accurate and concise answers. Its core module is the movie AI question answering function based on Neo4j. After the user raises a question, the comment system will parse the question and construct a Cypher query statement. After execution, the result will be returned and displayed to the user, achieving intelligent answers and personalized services. In system design, the connection between the movie AI question answering module and the Neo4j database is crucial. This connection enables effective communication and information exchange between user questions and movie knowledge graphs, providing users with convenient and accurate movie related information. Through deep integration with the Neo4j database, the system can bette

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Residual-based feature enhancement for forgery audio detection 3

Residual-based feature enhancement for forgery audio detecti...

引用

3rd international conference on Advanced Algorithms and signal image Processing, AASIP 2023

作者： Zheng, Wei Ling, Xia Hai, Han China Academy of Information and Communication Technology. China

ISBN: (纸本)9781510668522

In recent years, speech synthesis technology has become increasingly advanced, leading to a proliferation of forged audio content on the internet, which poses significant threat to individuals and society. Many studies have utilized a range of deep learning-based techniques to differentiate fake audio content, but the features used in these studies are often limited in their rich and generalizable characteristics. In this paper, we propose a novel fake voice detection technology that utilizes the wav2vec2 model for feature extraction along with a custom-designed residual-based detection module to augment the detection of fake audio content with greater accuracy and precision. Additionally, we incorporate a data augmentation method to improve the performance of the model and enhance its ability to generalize. We trained our model on the ASVspoof2019 dataset and evaluated it on the LA and DF datasets of the ASVspoof2021 dataset. Supplementary experiments demonstrated that our approach achieved state-of-The-Art detection performance and illustrated its effectiveness and applicability. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Course recommendation model based on Knowledge Graph Embedding 16

Course recommendation model based on Knowledge Graph Embeddi...

引用

16th international conference on signal-image technology and internet-based systems (SITIS)

作者： Chetoui, Ismail El Bachari, Essaid El Adnani, Mohamed Cadi Ayyad Univ Dept Comp Sci Marrakech Morocco

ISBN: (纸本)9781665464956

The use of graphs as a method of storing data has begun to rise significantly in recent years, due to the new way of representing data in graphs. This is leveraged by the structure of graphs that facilitate modeling interactions between real-world entities. With the rapid development of technologies such as machine learning and deep learning, the digitalization of education has entered the era with artificial intelligence as the main feature. As an important part of artificial intelligence technology, knowledge graph as a format of data storing provides possibilities for smart education and promotes the innovation and development of smart education. In this context, we present in this communication a model that we built to facilitate reaching the appropriate lesson for each learner among a large group of lessons in an eLearning graph, this model is practically divided into two parts, the first in which we sort the learners by defining the profile of each of them, which will facilitate their classification into groups, and in the second part, we connect each learner with his appropriate path to achieve the desired lesson, by building a nodal path through sequential prediction until reaching the target lesson, relying mainly on embedding graph models.

关键词： Knowledge Graph Embedding Education Course Recommendation system

来源：评论

学校读者我要写书评

暂无评论

引用

2024 international conference on Optics, Electronics, and Communication Engineering, OECE 2024

作者： Yu, Jiayun Wang, Jinghong Xu, Zhanyang Li, Dingyu Lin, Wei School of Educational Science Nanjing Normal University Jiangsu Nanjing210023 China School of Software Nanjing University of Information Science & Technology Jiangsu Nanjing210044 China Jiangsu Shao Er Chun Internet Education Technology Co. Ltd. Nanjing Technology R&D Center Jiangsu Nanjing211899 China

ISBN: (纸本)9781510685437

With the advancement of calligraphy education, an array of intelligent handwriting evaluation systems has emerged to support teaching. However, existing handwriting evaluation systems fall short in analyzing and evaluating individual strokes of Chinese characters. To address this issue, we introduce SSRSE, a Single-Stroke Regional Segmentation Evaluation method for hard-pen regular script. Initially, we gather handwritten character images featuring 22 commonly used strokes in hard-pen regular script from primary and secondary schools. These strokes are then categorized into four regions based on their writing patterns, forming a stroke regional segmentation dataset through adjustments in size and region marking. We propose a single-stroke regional segmentation method based on an inverted residual U-net. This involves incorporating an inverse residual structure into the U-network and employing a loss function based on Intersection over Union(IoU) to tackle the imbalance in sample categories. Subsequently, Hu moments are computed for each region post-segmentation of both the copy strokes and template strokes. After mathematical conversion, the extent of image variance is measured, and stroke similarity levels are determined based on weighted assignments. Experimental findings demonstrate the superiority of our segmentation method over traditional approaches in terms of average pixel accuracy. Moreover, the region similarity calculation method yields results akin to manual evaluation, showcasing high feasibility. © 2024 SPIE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

signal simulation based on improved doppler filter 5

Signal simulation based on improved doppler filter

引用

2024 5th international conference on Electrical, Electronic Information and Communication Engineering, EEICE 2024

作者： Zhen, Mengyang Qi, Chundong Sun, Mengsu School of Information and Electronics Beijing Institute of Technology Beijing100081 China

In satellite communication, the signal is transmitted through a wireless channel, and distorted signals will appear under the influence of the actual environment. In this paper, an improved Doppler filter is proposed by mathematically fitting the actual signals, and the similarity of the time-frequency map of the signals output by this improved filter reaches 94.357% of the standard value, realizing the simulation of a kind of aberration appearing in the actual environment on the time-frequency image and finally realizing the self-adaptation. © Published under licence by IOP Publishing Ltd.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

APT system for omni-directional laser communication based o n image processing 3

APT system for omni-directional laser communication based o ...

引用

3rd international conference on signal image Processing and Communication, ICSIPC 2023

作者： Mao, Langzhou Xiao, Jie Wu, Xiaowei Wang, Wenhao Yang, Lei Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781510670945

In wireless laser communication systems, beam acquiring, pointing, and tracking (APT) technology is the key to establishing and maintaining a laser communication link. In order to solve the problem that the capture cameras used in APT systems usually have a small field of view and are inefficient in scanning the uncertain area and capturing the target spot, which leads to the inability to precisely locate the spot position, an image processing-based omnidirectional laser communication spot image detection technology solution is designed under the condition of using a large field of view of the capture camera, which has the characteristics of strong anti-interference capability and high detection accuracy. Firstly, the block design was simulated on matlab platform, and then the APT system of omnidirectional laser communication was built based on the panoramic camera with large field of view and two-dimensional turntable to verify the scheme. The scheme is implemented in 0.1° steps to sample the laser spot within 180° of the horizontal and tilt directions and obtain the spot coordinates. The spot position information is sent to the two-dimensional turntable through the serial port, and the 0.1° pointing of the turntable to the laser light source is accomplished, which verifies the feasibility and accuracy of the system solution. © 2023 SPIE.

关键词： Cameras

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 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：