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

756 篇 会议
3 册 图书
2 篇 期刊文献

馆藏范围

761 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

655 篇 工学
- 535 篇 计算机科学与技术...
- 465 篇 软件工程
- 247 篇 信息与通信工程
- 147 篇 生物工程
- 114 篇 光学工程
- 93 篇 电气工程
- 92 篇 控制科学与工程
- 91 篇 电子科学与技术（可...
- 76 篇 生物医学工程（可授...
- 54 篇 化学工程与技术
- 39 篇 机械工程
- 34 篇 仪器科学与技术
- 34 篇 材料科学与工程（可...
- 30 篇 安全科学与工程
- 27 篇 动力工程及工程热...
- 25 篇 交通运输工程
- 24 篇 土木工程
439 篇 理学
- 204 篇 数学
- 159 篇 物理学
- 152 篇 生物学
- 71 篇 统计学（可授理学、...
- 66 篇 化学
- 34 篇 系统科学
199 篇 管理学
- 123 篇 图书情报与档案管...
- 98 篇 管理科学与工程(可...
- 39 篇 工商管理
52 篇 医学
- 49 篇 基础医学(可授医学...
- 49 篇 临床医学
- 36 篇 药学(可授医学、理...
28 篇 法学
- 25 篇 社会学
15 篇 经济学
15 篇 农学
14 篇 教育学
2 篇 军事学

主题

23 篇 deep learning
19 篇 machine learning
16 篇 support vector m...
15 篇 feature extracti...
14 篇 computer vision
11 篇 convolution
11 篇 natural language...
11 篇 sentiment analys...
10 篇 internet of thin...
10 篇 object detection
10 篇 big data
10 篇 semantics
10 篇 convolutional ne...
9 篇 natural language...
7 篇 signal processin...
7 篇 visualization
6 篇 signal detection
6 篇 deep neural netw...
6 篇 graphics process...
6 篇 neural networks

机构

7 篇 key laboratory o...
7 篇 school of inform...
6 篇 school of comput...
6 篇 xinjiang key lab...
6 篇 school of inform...
6 篇 xinjiang key lab...
6 篇 key laboratory o...
4 篇 nss college of e...
4 篇 school of comput...
4 篇 college of infor...
4 篇 school of contro...
3 篇 school of comput...
3 篇 department of co...
3 篇 college of compu...
3 篇 college of intel...
3 篇 guangdong polyte...
3 篇 school of comput...
3 篇 school of comput...
3 篇 academy for engi...
2 篇 hefei university...

作者

10 篇 hamdulla askar
6 篇 ablimit mijit
5 篇 gao yanxia
5 篇 liu yiwen
4 篇 shi yuanquan
4 篇 xiao jianhua
3 篇 faisal rehman
3 篇 wang chao
3 篇 xiao hongbo
3 篇 sharif hanan
3 篇 peng xiaoning
3 篇 rehman faisal
3 篇 chen xi
3 篇 mala c.
3 篇 shi zhen-gang
3 篇 li chao
3 篇 jiang huiming
3 篇 yuan jing
3 篇 li jing
3 篇 zhao qian

语言

753 篇 英文
8 篇 其他

检索条件"任意字段=2022 3rd International Conference on Signal Processing and Computer Science, SPCS 2022"

共 761 条记录，以下是71-80 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 Simultaneous Hole, Groove and Defect Detection Method Based on Yolov4-tiny and MMOE 3

A Simultaneous Hole, Groove and Defect Detection Method Base...

引用

3rd international conference on computer Vision, Image and Deep Learning and international conference on computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Lin, Haicheng Gong, Jie Chen, Xiang Xie, Xiaohua Tang, Hengliang Jiang, Junfeng Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Electronics and Information Technology Guangzhou China Guangdong Xinguang Intelligent System Co. Ltd. Zhongshan China

ISBN: (纸本)9781665459112

The quality detection of furniture boards is one of the most important parts of the furniture board quality control process. The boards may contain round holes, grooves, and defects for various reasons. In industry, it is necessary to detect them in real time. This paper proposes a multi-objective detection method based on the Yolov4-tiny and Multi-Gate Mixture-of-Experts(MMOE) structure that can simultaneously detect round holes, grooves and defects in high resolution board images in real time. Considering the high resolution of the board image and the small size of the dataset, data pre-processing and data augmentation are performed to reduce the size of the image and increase the size of the dataset. In consideration of the difference in the characteristics of the hole, groove and defect. the task of detecting defects and the task of detecting holes and grooves are decoupled, and different task headers and gate networks are designed. Finally, it is tested on a real production line and the combined mAP reaches 75.49% and the detection takes only 20ms. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A new double scrambling color image encryption algorithm based on multi chaotic systems and image segmentation 3

A new double scrambling color image encryption algorithm bas...

引用

3rd international conference on computer science and Management Technology, ICCSMT 2022

作者： Tian, Junfeng Wang, Ke Liu, Cheng Henan University Key Laboratory of Big Data Analysis and Processing of Henan Province Kaifeng China

ISBN: (纸本)9798350320404

Aiming at low security of traditional encryption methods, this paper give a new encryption method by using multi chaotic systems and image segmentation. Firstly, use Arnold transform to perturb the RGB component matrices of the source image. Subsequently, the chaotic image chunking algorithm is applied to the mixed component matrix, and the chunked mixed matrix is perturbed by Hyperchaotic Chen system and Logistic mapping. Moreover, Diffusion of pixel transformations to the whole image by inverse transform operations. Finally, logistic system is applied to the secondary pixels scrambling, which achieves image encryption. The experimental data indicate that this encryption method encryption effect is good, and can effectively prevent ciphertext attack and noise attack. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Method for Building Chinese Domain Lexicon Based on New Words Recommendation 3

A Method for Building Chinese Domain Lexicon Based on New Wo...

引用

3rd international conference on computer science and Management Technology, ICCSMT 2022

作者： Duan, Jinjian Wang, Meiqing Guan, Yibo Lin, Qiu Beihang University School of Mechanical Engineering and Automation Beijing China Beijing Aerocim Technology Co. Ltd Beijing China Beijing Institute of Control and Electronic Technology Beijing China

ISBN: (纸本)9798350320404

Professional domain lexicon construction is the basis for Domain-specific Natural Language processing. Current new words detection algorithms struggle with migration and sparsity and are unable to facilitate the building of domain lexicons. In this paper, a method for building a domain-specific lexicon based on new words recommendation is proposed. A model of the domain lexicon construction process was developed, including domain corpus pre-processing, new words detection, saliency evaluation, and new words recommendation. The problem of the sparsity of unsupervised new words discovery algorithms is solved by using Enhanced Mutual Information and Branch Entropy to identify small word frequency words and NC-value to identify domain words. According to experiments on a guided domain dataset, the method is effective at enhancing the precision of domain new words recommendations, lowering the complexity of expert work, and has significant implications for the building of a domain-specific lexicon. © 2022 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Fusion recommendation algorithm based on DeepWalk and Item-Based collaborative filtering 3

Fusion recommendation algorithm based on DeepWalk and Item-B...

引用

3rd international conference on computer science and Management Technology, ICCSMT 2022

作者： Yu, Yicheng Li, Rongbin Yin, Jun Qinghai Normal University School of Computing Xi'Ning China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xi'Ning China

ISBN: (纸本)9798350320404

Collaborative filtering techniques have been applied to personalised recommendation systems in recommender systems. However, with the gradual increase in the number of platform users and goods, the user rating data on the entire project matrix is extremely sparse, resulting in the inaccuracy of the prediction results. DeepWalk, on the other hand, still performs well when the data is sparse. Therefore, DeepWalk is introduced into collaborative filtering, and a fusion recommendation algorithm based on DeepWalk and collaborative filtering is proposed to reduce the impact of cold start and sparsity on the recommendation results. Experiments show that the proposed fusion recommendation algorithm has higher recommendation accuracy when the data is sparse compared with other traditional algorithms, which improves the recommendation quality to a certain extent. © 2022 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Calculation of intersection signal timing based on electronic police passing data 3

Calculation of intersection signal timing based on electroni...

引用

3rd international conference on computer science and Communication Technology, ICCSCT 2022

作者： Wang, Hao Gu, Bao Zhang, Yibo Shanghai Institute of Technology SIT Shanghai China Ningbo Municipal Public Security Bureau Zhenhai Branch Ningbo China

ISBN: (纸本)9781510661240

The passing data from the electronic police are increasingly used for traffic state identification and signal optimization. Obtaining the specific settings of signal timing is very important for refined traffic analysis. In this paper, traffic signal timing settings are directly calculated from the passing data of electronic police equipment to solve the problem of not being able to obtain signal timing for various reasons in practice. In the experiment, the bidirectional sliding window was used to evaluate the probability of the signal light indication at each time, and the evaluation probability for each time of the sliding range was added up to obtain the overall green probability of the sliding range. The experiment shows that the electronic police data can not only calculate the intersection signal timing effectively, but also eliminates the influence of abnormal vehicles. © 2022 SPIE.

关键词： Law enforcement

来源：评论

学校读者我要写书评

暂无评论

Research on Machine Translation (MT) System Based on Deep Reinforcement Learning 3

Research on Machine Translation (MT) System Based on Deep Re...

引用

3rd international conference on computer science and Management Technology, ICCSMT 2022

作者： He, Junchen Fuzhou University of International Studies and Trade School of Foreign Languages Fujian Fuzhou350202 China University of Perpetual Help System DALTA Graduate School Las Pinas Philippines

ISBN: (纸本)9798350320404

With the deepening of globalization and the rapid development of human society and economic society in the world, the demand for machine translation in human society is also increasing rapidly, and the progress of artificial intelligence technology has put forward new requirements for the quality of machine translation. At the same time, the development of machine translation research has set a benchmark for other fields of natural language processing. Therefore, the research on machine translation not only has high practical value, but also can promote the progress of the theoretical research on natural language processing. Based on the idea of deep learning, this paper selects English language features as feature parameters, uses fine-tuning Python model training technology and feature-based deep learning method, and conducts deep reinforcement learning on Anglo-German MACHINE translation model. The comparative experiment of Indian English-German neural machine translation model shows that, The machine translation system based on deep learning is obviously better than traditional machine translation, and the translation effect is obviously improved. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

AQtrans: Q&A Sentence Matching Method for Single-Hop Knowledge Based Question Answering 3

AQtrans: Q&A Sentence Matching Method for Single-Hop Knowled...

引用

3rd international conference on Electronic Communication and Artificial Intelligence, IWECAI 2022

作者： Lin, Qingwen Zhan, Minghao Wu, Jiayang Wu, Biao Computer Science Guangdong University of Technology Guangdong Guangzhou China School of Mathematics And Big Data Foshan University Guangdong Foshan China

ISBN: (纸本)9781665479974

KBQA is the key technology of natural language processing. The single-hop KBQA task is usually divided into entity recognition and answer link. Among them, improving the effect of answer links is the key to improving performance. The current mainstream answer linking methods often face the challenge that the identified predicate cannot be linked to the knowledge base. Therefore, this paper proposes to match question and answer sentences by transforming candidate answers into natural language answer sentences and forming context with the question sentences. Since question and answer sentences are essentially different expressions of the same triple, the unsupervised triple data in the knowledge base can be used to further improve the effect of the model by training the answer-question conversion model. It solves the problem that the current mainstream methods cannot use unsupervised triple data at low cost. And achieved state-of-the-art results in the WC2014 dataset and the NLPCC 2016 KBQA dataset. © 2022 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Research on R-wave recognition method for ECG signal in the optimized firing process 3

Research on R-wave recognition method for ECG signal in the ...

引用

3rd international conference on computers, Information processing and Advanced Education, CIPAE 2022

作者： Qiu, Jingjie Zhao, Fadong Lu, Ling Zhuang, Hongwei Engineering University of PAP Xi'an710086 China

ISBN: (纸本)9781665468121

R wave, as an important reference for determining each band of ECG signal, is the premise of ECG automatic analysis. In view of the problem that the preprocessing process of most R-wave recognition algorithms affects the recognition accuracy, a new R-wave recognition method based on the combination of wavelet transform and adaptive threshold method is proposed, which improves the stability and accuracy of R-wave recognition. Firstly, the ECG signal is decomposed based on wavelet, and the 23rd layer wavelet signal is obtained. Then the sliding window width and initial threshold are set. The threshold is adjusted according to the signal situation and the window width is increased to quickly identify the R wave. Finally, the simulation results show that the algorithm is effective in R-wave recognition of heart rate variability ECG signal during shooting. © 2022 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

An Extensible Framework for Task Partitioning on Heterogeneous Systems 3

An Extensible Framework for Task Partitioning on Heterogeneo...

引用

3rd international conference for Emerging Technology, INCET 2022

作者： Yekbote, Pavan Raj, Poojita Anupindi, Ravi S. Sudarshan, T.S.B. Pes University Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9781665494991

High performance computing applications have witnessed significant speedups in performance from leveraging the compute capabilities of heterogeneous platforms. These speedups are seldom taken advantage of in practice partly due to the inefficacy of mapping parallel sections of an application to specific processing units. Ascertaining this mapping necessitates taking into account the run time and compile time features of the application on a heterogeneous platform. This paper proposes a framework capable of classifying a high performance computing application to its optimal partitioning in a heterogeneous CPU-GPU target system. This classifier has been trained on a combination of run time execution metrics and compile time static code features of applications from different domains collected from benchmark suites such as Rodinia [1] and OmpSCR [2]. The contribution of this work is twofold - an extensible framework demonstrating the utility of accurate mapping and a pair of data sets that exhibit the significance of run time and compile time features on the framework estimating the effect of varied input type and size. © 2022 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Analysis of Learners' Sentiments on MOOC Forums using Natural Language processing Techniques 3

Analysis of Learners' Sentiments on MOOC Forums using Natura...

引用

3rd international conference on Innovations in computer science and Software Engineering, ICONICS 2022

作者： Marfani, Hania Hina, Saman Tabassum, Huma NED University of Engineering and Technology Department of Computer Science and Information Technology Karachi Pakistan

ISBN: (纸本)9781665461412

MOOCs have gained a lot of popularity for past few years. Especially after the outbreak of Coronavirus, everyone is trying to gain some knowledge and skill while being at the comfort of home and making themselves safe. Due to sudden increase in the number of participants on MOOCs there is a need for an automated system to be able to assess the reviews and feedbacks given by the learners and find the sentiments behind their statements. This analysis will help trainers identify their shortcoming and make their courses even better. For sentiments analysis, several approaches may be used. This research aims to provide a system which will perform sentiments analysis on the novel dataset and show the comparison of lexicon-based vs transformer-based sentiment analysis models. For lexicon based, VADER was chosen and for transformer-based, state-of-The-Art BERT was chosen. BERT was found to be exceptionally good with an accuracy of 84% and F1-score of 0.64. © 2022 IEEE.

关键词： Sentiment analysis

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77页 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：