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

1,327 篇 会议
27 册 图书
7 篇 期刊文献

馆藏范围

1,361 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

974 篇 工学
- 919 篇 计算机科学与技术...
- 636 篇 软件工程
- 236 篇 信息与通信工程
- 131 篇 控制科学与工程
- 101 篇 生物工程
- 97 篇 电气工程
- 64 篇 安全科学与工程
- 60 篇 动力工程及工程热...
- 58 篇 交通运输工程
- 58 篇 网络空间安全
- 47 篇 机械工程
- 47 篇 生物医学工程（可授...
- 42 篇 仪器科学与技术
- 29 篇 建筑学
- 28 篇 环境科学与工程（可...
355 篇 理学
- 184 篇 数学
- 113 篇 生物学
- 75 篇 统计学（可授理学、...
- 58 篇 化学
- 41 篇 物理学
- 31 篇 系统科学
347 篇 管理学
- 237 篇 管理科学与工程(可...
- 213 篇 图书情报与档案管...
- 121 篇 工商管理
62 篇 法学
- 52 篇 社会学
61 篇 医学
- 54 篇 临床医学
- 50 篇 基础医学(可授医学...
- 32 篇 药学(可授医学、理...
47 篇 经济学
- 47 篇 应用经济学
28 篇 教育学
- 28 篇 教育学
14 篇 农学
7 篇 文学
2 篇 军事学

主题

256 篇 big data
79 篇 artificial intel...
67 篇 cloud computing
63 篇 machine learning
50 篇 computational mo...
49 篇 deep learning
42 篇 internet of thin...
41 篇 data models
35 篇 training
27 篇 data mining
25 篇 neural networks
24 篇 smart cities
23 篇 predictive model...
23 篇 edge computing
21 篇 computational in...
21 篇 feature extracti...
19 篇 industries
18 篇 object detection
17 篇 social networkin...
16 篇 data privacy

机构

14 篇 ajou univ dept a...
13 篇 school of big da...
12 篇 renmin univ chin...
11 篇 beijing key lab ...
9 篇 college of compu...
7 篇 university of ch...
7 篇 beijing universi...
6 篇 school of comput...
6 篇 key laboratory o...
6 篇 school of comput...
6 篇 key laboratory o...
6 篇 shandong fundame...
5 篇 college of big d...
5 篇 national enginee...
5 篇 shiga university...
5 篇 ajou univ dept i...
5 篇 riken center for...
5 篇 gaoling school o...
5 篇 chongqing univ s...
5 篇 college of intel...

作者

13 篇 shin hyunjung
10 篇 liu yong
7 篇 geng xin
6 篇 zhou xiaokang
6 篇 dai fei
6 篇 mariano vladimir...
6 篇 li shaojie
6 篇 wang jun
5 篇 xu ning
5 篇 wang xiaofei
5 篇 li xiuhua
5 篇 yang yang
5 篇 su bing
5 篇 kim myungjun
5 篇 zhao wei
5 篇 qi jinli
5 篇 wu yanmin
5 篇 jin hai
5 篇 gao yanxia
5 篇 liu yiwen

语言

1,220 篇 英文
134 篇 其他
12 篇 中文
1 篇 西班牙文

检索条件"任意字段=International Conference on Big Data Intelligence and Computing, DataCom 2022"

共 1361 条记录，以下是811-820 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：

Progressive Purification for Instance-Dependent Partial Label Learning 40

Progressive Purification for Instance-Dependent Partial Labe...

引用

40th international conference on Machine Learning

作者： Xu, Ning Liu, Biao Lv, Jiaqi Qiao, Congyu Geng, Xin Southeast Univ Sch Comp Sci & Engn Nanjing Peoples R China RIKEN Ctr Adv Intelligence Project Tokyo 1030027 Japan

Partial label learning (PLL) aims to train multi-class classifiers from the examples each annotated with a set of candidate labels where a fixed but unknown candidate label is correct. In the last few years, the instance-independent generation process of candidate labels has been extensively studied, on the basis of which many theoretical advances have been made in PLL. Nevertheless, the candidate labels are always instance-dependent in practice and there is no theoretical guarantee that the model trained on the instance-dependent PLL examples can converge to an ideal one. In this paper, a theoretically grounded and practically effective approach named POP, i.e. PrOgressive Purification for instance-dependent partial label learning, is proposed. Specifically, POP updates the learning model and purifies each candidate label set progressively in every epoch. Theoretically, we prove that POP enlarges the region appropriately fast where the model is reliable, and eventually approximates the Bayes optimal classifier with mild assumptions. Technically, POP is flexible with arbitrary PLL losses and could improve the performance of the previous PLL losses in the instance-dependent case. Experiments on the benchmark datasets and the real-world datasets validate the effectiveness of the proposed method. Source code is available at https://***/palm-ml/POP.

关键词： Purification

来源：评论

学校读者我要写书评

暂无评论

Distilling Knowledge from Topological Representations for Pathological Complete Response Prediction 25th

Distilling Knowledge from Topological Representations for Pa...

引用

25th international conference on Medical Image computing and Computer Assisted Intervention (MICCAI)

作者： Du, Shiyi Lao, Qicheng Kang, Qingbo Li, Yiyue Jiang, Zekun Zhao, Yanfeng Li, Kang Sichuan Univ West China Biomed Big Data Ctr West China Hosp Chengdu Peoples R China Beijing Univ Posts & Telecommun Sch Artificial Intelligence Beijing Peoples R China Shanghai Artificial Intelligence Lab Shanghai Peoples R China

ISBN: (纸本)9783031164347;9783031164330

In breast radiology, pathological Complete Response (pCR) predicts the treatment response after neoadjuvant chemotherapy, and therefore is a vital indicator for both personalized treatment and prognosis. Current prevailing approaches for pCR prediction either require complex feature engineering or employ sophisticated topological computation, which are not efficient while yielding limited performance boosts. In this paper, we present a simple yet effective technique implementing persistent homology to extract multi-dimensional topological representations from 3D data, making the computation much faster. To incorporate the extracted topological information, we then propose a novel approach to distill the extracted topological knowledge into deep neural networks with response-based knowledge distillation. Our experimental results quantitatively show that the proposed approach achieves superior performance by increasing the accuracy from previously 85.1% to 90.5% in the pCR prediction and reducing the topological computation time by about 66% on a public dataset for breast DCE-MRI images.

关键词： Knowledge distillation Topological information Persistent homology Pathological complete response Breast radiology

来源：评论

学校读者我要写书评

暂无评论

Dependency and Association Enhanced Finding Similar Exercises in Online Education System 8

Dependency and Association Enhanced Finding Similar Exercise...

引用

8th IEEE international conference on Cloud computing and intelligence Systems, CCIS 2022

作者： Tang, Zihang Wang, Hao Gao, Weibo Huang, Zhenya Liu, Qi Yu, Jun University of Science and Technology of China School of Data Science China University of Science and Technology of China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology China IFLYTEK CO. LTD. IFLYTEK Research

ISBN: (纸本)9781665477352

Finding Similar Exercises (FSE) is a tough nut to crack in online education systems, especially among large scale exercise corpus. Given exercises with associated attributes, contents (texts and images) and knowledge concepts, most solutions learn exercise representations in isolation, where only contents or concepts are exploited. Though a few works try to combine concept-exercise associations for capturing long-range similarity among exercises, they just utilize a single relation among concepts but neglect the multiple dependencies. In this paper, we propose a novel Dependency and Association enhanced Finding Similar Exercises framework, namely DAFSE, which can consider both the concept-exercise associations and the multiple dependency relations among concepts, simultaneously. Specifically, we first build a concept-exercise-content multi-layer graph and embed each concept, exercise and content node through an Embedding Layer. Then we introduce Attentive Combination Layer to effectively preserve the long-range similarity as well as rich domain knowledge to exercise representations by propagating on the multi-layer graph. Finally, we use a Similarity Score Layer to assess the similarity of exercise pairs. Extensive experiments on real-world datasets demonstrate the effectiveness of DAFSE. © 2022 IEEE.

关键词： Online systems

来源：评论

学校读者我要写书评

暂无评论

9th international conference on big data Analytics, BDA 2021

9th International Conference on Big Data Analytics, BDA 2021

引用

9th international conference on big data Analytics, BDA 2021

ISBN: (纸本)9783030965990

The proceedings contain 20 papers. The special focus in this conference is on big data Analytics. The topics include: GA-ProM: A Genetic Algorithm for Discovery of Complete Process Models from Unbalanced Logs;cascaded Anomaly Detection with Coarse Sampling in Distributed Systems;Journey of database Migration from RDBMS to NoSQL data Stores;Forecasting AQI data with IoT Enabled Indoor Air Quality Monitoring System;skin Cancer Recognition for Low Resolution Images;deep Learning Application for Reconstruction of Large-Scale Structure of the Universe;autonomous Real-Time Science-Driven Follow-up of Survey Transients;a Front-End Framework Selection Assistance System with Customizable Quantification Indicators Based on Analysis of Repository and Community data;enhanced Bond Energy Algorithm for Vertical Fragmentation of IoT data in a Fog Environment;approximate Fault-Tolerant data Stream Aggregation for Edge computing;Video Indexing System Based on Multimodal Information Extraction Using Combination of ASR and OCR;big data Management for Policy Support in Sustainable Development;preface;Internet of Things Integrated with Multi-level Authentication for Secured IoT data Stream Through TLS/SSL Layer;blockchain-Enabled System for Interoperable Healthcare;cosmic Density Field Reconstruction with a Sparsity Prior Using Images of Distant Galaxies;identification of Distinctive Behavior Patterns of Bots and Human Teams in Soccer;symbolic Regression for Interpretable Scientific Discovery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SERG: A Sequence-To-Sequence Model for Chinese ECG Report Generation 4

SERG: A Sequence-To-Sequence Model for Chinese ECG Report Ge...

引用

4th international conference on Robotics, Intelligent Control and Artificial intelligence, RICAI 2022

作者： Yang, Cong Li, Ziliang Fan, Haoyi Chen, Yongxia Lin, Nan Wei, Na School of Cyber Science and Engineering Zhengzhou University China School of Computer and Artificial Intelligence Zhengzhou University China

ISBN: (纸本)9781450398343

Medical report generation is a rising application of big data, which mitigates burden on doctors in clinical trail. However, the serious imbalanced distribution of diseases leads to data bias, an important issue in qualified medical reports generation. To address this issue, a sequence-To-sequence model with incorporation of clinical experience is proposed to generate Chinese ElectroCardioGraph (ECG) reports. The proposed model consists of Electrocardiograph Feature Extractor (EFE), Posterior Knowledge Embedding (PKE) and Report Generator (RG). Firstly, we introduce a novel spatial-Temporal information fusion module in EFE to extract robust features from ECG data. Then, embeddings of ECG tags extracted from clinical ECG reports combined with output of EFE are then feed into PKE, which builds a bridge between ECG tags and ECG data, alleviating the problem caused by data bias. Finally, a transformer-based decoder is used in RG to generate ECG reports step by step with output of PKE as key and value. Experiments conducted on private data show that the proposed model can obtain an accuracy 50.26% on BLEU-4, 7.69% higher than state-of-The-Art. Our method can also achieve better fluent reports, as demonstrated by the performance on CIDEr, a commonly used content metric. © 2022 ACM.

关键词： Report generators

来源：评论

学校读者我要写书评

暂无评论

Software and Algorithms for High-throughput Multimodal Experiments at Advanced Synchrotron Light Sources

Software and Algorithms for High-throughput Multimodal Exper...

引用

2022 conference on Infrared, Millimeter, Terahertz Waves and Applications, IMT 2022

作者： Li, Chun Zhang, Chenglong Liu, Yu Zhang, Yi Bi, Xiaoxue Beijing Synchrotron Radiation Facility Institute of High Energy Physics Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China Spallation Neutron Source Science Center Guangdong Dongguan523803 China

ISBN: (纸本)9781510662476

With advancements on synchrotron radiation instrumentations particularly the emergence of next-generation light sources with ultra-low emittance and high intensity, scientific experiments have shifted from 2D static to multidimensional dynamic characterizations with multimodal approaches, enabling new capabilities of probing structural and functional changes across multiple length scales with extreme spatial and temporal resolution. However, such advancement on synchrotron hardware imposes tremendous challenges on the data processing end. Effective software tools and algorithms addressing image denoising, segmentation and data compression problems can be of great use to alleviate the burden, fully releasing the power of advanced instrumentations. Instead of separately utilizing modular image processing algorithms, this review suggests a unified experimental control and data acquisition software framework that naturally interfaces and integrates advanced software and algorithms with extensive AI assistance would be best suitable for next-generation beamlines. The review will also discuss prospective applications artificial intelligence and large-scale high performance computing infrastructures could bring about to facilitate scientific discoveries at next-generation synchrotron light sources. © 2023 SPIE.

关键词： big data

来源：评论

学校读者我要写书评

暂无评论

Handwritten Chemical Equations Recognition Based on Lightweight Networks 1

引用

18th international conference on Intelligent computing (ICIC)

作者： Wang, Xiao-Feng He, Zhi-Huang Wu, Zhi-Ze Wei, Yun-Sheng Wang, Kai Zou, Le Hefei Univ Sch Artificial Intelligence & Big Data Anhui Prov Engn Lab Big Data Technol Applicat Urb Hefei 230601 Anhui Peoples R China Hefei Univ Sch Artificial Intelligence & Big Data Inst Appl Optimizat Hefei 230601 Anhui Peoples R China Hefei Univ Sch Energy Mat & Chem Engn Hefei 230601 Anhui Peoples R China

ISBN: (数字)9783031138706

ISBN: (纸本)9783031138706;9783031138690

Handwritten chemical equations recognition is one of the important research directions of optical character recognition (OCR) and text recognition technology, which is widely used in life. Although the mainstream deep learning text recognition model can get good recognition results, the number of parameters of the model is too large to be carried on some portable devices. We develop a new lightweight network model (LCRNN) based on the CRNN model for handwritten chemical equations recognition. Firstly, in the convolutional layer of the LCRNN model, we propose a new MobileNetV3 (MobileNetV3M) to reduce number of the model parameters. The MobileNetV3M changed the original down-sampling method to max-pooling, so it can extract more critical information. Secondly, we use the bigRU model in the recurrent layer. Finally, a new chemical equations encoding method is proposed, which can change the two-dimensional chemical equation into one-dimensional chemical equation encoding, so as to facilitate handwritten chemical equations recognition. The experiments demonstrate that the character precision of the LCRNN model is 2.1% lower than the CRNN model, but the number of parameters is significantly reduced.

关键词： Text recognition Lightweight network Chemical equations CRNN MobileNet

来源：评论

学校读者我要写书评

暂无评论

An Artificial intelligence-Based Technique to Optimize Hybrid Vehicle Using Renewable Energy Sources 7th

An Artificial Intelligence-Based Technique to Optimize Hybri...

引用

7th international conference on big data and Cloud computing Challenges, ICBCC 2022

作者： Dhanush Hariharan, S. Manikantaa, Challapalli Manigandaa, C.S. Anush Kumar, V. Priya, Vetri Ambeth Kumar, V.D. Department of AI&DS Panimalar Engineering College Chennai600123 India Department of Computer Engineering Mizoram University Aizawl796004 India

ISBN: (纸本)9789819910502

A review of water electrolysis technologies for hydrogen production is presented in this paper, and a sustainable, economical, and eco-friendly method to save the environment yet normally carries out the everyday activity of new age man which is "Transportation". Current electrolyzers must be reduced in energy consumption, cost, and maintenance in order to facilitate water electrolysis expansion and, on the other hand, made more durable, efficient, and safe. Due to its harmful environmental effects, fossil fuel use in vehicles is a growing concern. A hybrid electric vehicle is among the most promising technologies currently being developed, as it is high-performing, fuel-efficient, low emission, and has an impressive range. The main aim of this paper is to integrate artificial intelligence and transportation machines and engineer a feasible and non-polluting vehicle that contributes to the making of a sustainable environment. The successful implementation of this project will result in the creation of a better and pollution-free environment that contributes to the conservation of energy and fossil fuels. This paper also discusses a better yet safer way to store hydrogen fuel on a small scale and prevent accidents and save the lives of the users with the help Anti-Accident protocol. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fossil fuels

来源：评论

学校读者我要写书评

暂无评论

An Agentless Private Cloud Maintenance System Based on Open Source Toolbox 10

An Agentless Private Cloud Maintenance System Based on Open ...

引用

10th international conference on Orange Technology, ICOT 2022

作者： Ling, Mingsheng Wang, Wenjuan Zou, Xiaohua Tseng, Shih-Pang School of Software and Big Data Changzhou College of Information Technology Changzhou213164 China Academic Affairs Office Hohai University Changzhou Jiangsu China School of Information Science and Technology Sanda University Shanghai201209 China

ISBN: (纸本)9781665454193

The cloud computing provides the more elastic organization of computing resources, and more efficiency of computing works. However, the private cloud is still necessary to various companies and institutions because of the security requirements. Therefore, these companies and institutions must manage and maintain their private clouds by themselves. The low-cost and effective private cloud maintenance alternative is an important issue to the private cloud. This paper proposes an agentless maintenance system based on the open-souce tool, Ansible. The proposed approach integrate the Ansible with the Web platform. It is unnecessary to install any software on the client machines. The maintenance system can remotely control the client machine to complete asset management, performance monitoring, Risk reporting, and so on. The proposed approach can effectively reduce the maintenance cost for the private cloud. © 2022 IEEE.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

Fine-grained classification network for fish based on the attention mechanism and EfficientNet 4

Fine-grained classification network for fish based on the at...

引用

4th international conference on Robotics, Intelligent Control and Artificial intelligence, RICAI 2022

作者： Gong, Yaohan Gu, Shenming Guan, Linting School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhejiang Ocean University Zhoushan316022 China

ISBN: (纸本)9781450398343

Many countries have been interested in the sustainable development of marine resources. Countries can protect the sustainable development of fishery resources by joining international fisheries organizations such as CCSBT, IATTC, IOTC, ICCAT, and others, and by adhering to the Code of Conduct for Responsible Fisheries. Traditional fishing supervision methods, on the other hand, frequently have the issue that the amount of original data is cumbersome and expensive, which cannot be handled manually and wastes a lot of manpower. This paper investigates fine-grained fish classification methods based on deep learning and attention mechanisms and proposes one that can target complex background and actual working scenarios, allowing countries to reallocate human capital to management and law enforcement activities. © 2022 ACM.

关键词： Fisheries

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137页 << < 78 79 80 81 82 83 84 85 86 87 > >>

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：