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

588 篇 会议
13 篇 期刊文献
2 册 图书

馆藏范围

603 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

471 篇 工学
- 412 篇 计算机科学与技术...
- 218 篇 软件工程
- 112 篇 信息与通信工程
- 80 篇 电气工程
- 71 篇 控制科学与工程
- 29 篇 生物工程
- 27 篇 机械工程
- 21 篇 交通运输工程
- 19 篇 石油与天然气工程
- 18 篇 安全科学与工程
- 16 篇 电子科学与技术（可...
- 16 篇 网络空间安全
- 14 篇 生物医学工程（可授...
- 13 篇 光学工程
- 13 篇 动力工程及工程热...
- 9 篇 力学（可授工学、理...
- 8 篇 环境科学与工程（可...
162 篇 管理学
- 118 篇 管理科学与工程(可...
- 78 篇 图书情报与档案管...
- 56 篇 工商管理
117 篇 理学
- 77 篇 数学
- 41 篇 统计学（可授理学、...
- 32 篇 生物学
- 19 篇 物理学
- 16 篇 系统科学
21 篇 法学
- 20 篇 社会学
18 篇 经济学
- 18 篇 应用经济学
16 篇 医学
- 15 篇 基础医学(可授医学...
- 14 篇 临床医学
- 11 篇 公共卫生与预防医...
7 篇 农学
3 篇 教育学
1 篇 文学
1 篇 军事学

主题

100 篇 big data
27 篇 cloud computing
26 篇 machine learning
24 篇 artificial intel...
19 篇 deep learning
15 篇 conferences
14 篇 computational mo...
13 篇 data mining
12 篇 internet of thin...
11 篇 edge computing
10 篇 optimization
10 篇 blockchain
10 篇 data models
8 篇 neural networks
8 篇 mapreduce
8 篇 clustering algor...
7 篇 semantics
7 篇 training
6 篇 reinforcement le...
6 篇 hadoop

机构

9 篇 college of compu...
7 篇 anhui xinhua uni...
7 篇 school of big da...
7 篇 national univers...
4 篇 nanjing univ pos...
4 篇 jiangsu engn lab...
4 篇 nanjing univ pos...
4 篇 school of comput...
3 篇 univ chinese aca...
3 篇 beijing univ pos...
3 篇 north univ china...
3 篇 college of intel...
3 篇 deakin universit...
3 篇 nanjing univ sci...
3 篇 nanjing univ inf...
2 篇 univ sci & techn...
2 篇 school of artifi...
2 篇 people's liberat...
2 篇 information and ...
2 篇 shanghai univ sc...

作者

9 篇 mariano vladimir...
6 篇 xu xiaolong
5 篇 yue dong
4 篇 zhang tengfei
4 篇 zhang peng
4 篇 li wei
4 篇 wang yong
3 篇 dai fei
3 篇 shang yu
3 篇 hu bin
3 篇 zhang rui
3 篇 ren fuji
3 篇 blancaflor eric
3 篇 gui zhiguo
3 篇 qiang zhang
3 篇 wu chao
3 篇 cao yong
3 篇 abisado mideth
3 篇 li lei
3 篇 zhang ming

语言

586 篇 英文
11 篇 其他
6 篇 中文

检索条件"任意字段=5th IEEE International Conference on Big Data Intelligence and Computing, DataCom 2019"

共 603 条记录，以下是31-40 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：

Constructing Fine-Tuning datasets for Bid-Generation-Model Using Title-Content Similarity 5

Constructing Fine-Tuning Datasets for Bid-Generation-Model U...

引用

5th international conference on Computer, big data and Artificial intelligence, ICCBD+AI 2024

作者： Wang, Ruiping Wu, Shihong Wu, Yongtao Zhu, Yanlin Gan, Xiaofang Shi, Biying Ygsoft INC. Research Institute of Yuanguang Zhuhai China Ygsoft INC. Artificial Intelligence Division Wuhan China Ygsoft INC. Artificial Intelligence Division Zhuhai China Zhuhai College Beijing Institute of Technology School of Information Zhuhai China

ISBN: (纸本)9798331533991

As AI-generated content and large-scale models evolve, fine-tuning models for specific vertical domains is crucial for improving performance. this research focuses on the bid generation field and proposes a method for constructing fine-tuning datasets based on title and content similarity. By analyzing the relationships between bid template titles and bid content in the dataset, a standardized process for building fine-tuning datasets is developed. the method uses word embedding, similarity calculations, and preprocessing techniques such as part-of-speech tagging and stop-word filtering. Experiments show that the proposed method significantly improves the accuracy, precision, and generalization of bid generation models. this work offers an automated dataset construction method for bid models and provides insights for fine-tuning in other domains. © 2024 ieee.

关键词： bid generation model fine-tuning fuzzy computing title-content similarity

来源：评论

学校读者我要写书评

暂无评论

Research on Large-scale data Anomaly Detection based on Deep Learning 5

Research on Large-scale Data Anomaly Detection based on Deep...

引用

5th international conference on Information Science, Parallel and Distributed Systems, ISPDS 2024

作者： Zhuang, Gancheng Northeastern University School of Computer Science and Engineering Shenyang China

ISBN: (纸本)9798350352719

With the continuous progress of big data, Internet of things, artificial intelligence and other technologies, we are living in an era of information explosion. A large amount of data is constantly recorded, and this data contains important information at the critical moment. With the rapid increase in data volume, traditional statistical methods are gradually unable to meet the needs due to high computational complexity and poor adaptability. In this work, we utilize autoencoder and generative adversarial network deep learning methods to detect anomalies in large-scale data. Autoencoders learn low-dimensional representations of data through the encoding and decoding process, and are mainly used to reconstruct normal data and identify anomalies by reconstructing errors. the generative adversarial network grasps the distribution characteristics of the data through the adversarial learning of its generative model and discriminant model, and uses this ability to detect abnormal patterns in the data. the effectiveness of the proposed model was verified by conducting experiments on multiple real-world datasets. Experimental results show that compared with the traditional method, the proposed deep learning model has significant improvement in detection accuracy and computing efficiency. © 2024 ieee.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Unidirectional Generative Summary Model with Bidirectional Coding 5

Unidirectional Generative Summary Model with Bidirectional C...

引用

5th international conference on Machine Learning, big data and Business intelligence, MLBDBI 2023

作者： Yang, Chen Juanatas, Roben A. National University College of Computing and Information Technologies Manila Philippines Anhui Xinhua University School of Big Data and Artificial Intelligence Hefei China

ISBN: (纸本)9798350359930

Due to the rapid growth of big data and artificial intelligence technology, the conventional automatic summarizing study has been shifting from abstracted summarization to generated summarization with the goal of offering higher quality, natural, and fluent text summary. the study of generative summaries has made extensive use of deep learning technology in recent years. One of the most popular models in this field is the seq2seq model, which is based on the attention mechanism and has produced impressive results in the summary generation job. Unfortunately, the majority of neural network-based generative abstract models now in use are one-way language models that lack abstract fluency, ambiguity processing, and context awareness. this research suggests a unidirectional generative summary model with bidirectional coding in light of this. the model mixes the two by having the input section have bidirectional language model coding capabilities and the output part retain unidirectional structure. the usefulness and development of the suggested strategy are demonstrated by experiments conducted on the CNewSum Chinese data set. © 2023 ieee.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A parallel DBSCAN algorithm based on KD-tree partitioning and a merging strategy 5

A parallel DBSCAN algorithm based on KD-tree partitioning an...

引用

5th international conference on Machine Learning, big data and Business intelligence, MLBDBI 2023

作者： Zeng, Hongbin Qian, Xuezhong Song, Wei Jiangnan University School of Artificial Intelligence and Computer Science Wuxi China

ISBN: (纸本)9798350359930

DBSCAN algorithm is a representative density-based clustering algorithm that has gained widespread application due to its ability to discover cluster of arbitrarily shapes and effectively handle noisy data. However, as the size of data increases, the performance of the classical single-machine sequential DBSCAN algorithm deteriorates significantly, failing to meet the efficiency requirements of real-world big data environments. To address this issue, this paper proposes a distributed parallel clustering algorithm - pDBSCAN. pDBSCAN uses Spark, a big data computing framework, to parallelize the algorithm. Furthermore, pDBSCAN leverages K-D Tree neighborhood queries to reduce distance calculations between points, and it divides the dataset into multiple balanced data partitions, thereby enhancing the algorithm's parallel performance. Additionally, to improve clustering effectiveness, an improved cluster merging strategy based on natural domain similarity is proposed for partial cluster merging. the performance and effectiveness of the pDBSCAN algorithm are evaluated in this paper based on real datasets, fully demonstrating the effectiveness and superiority of the proposed algorithm. © 2023 ieee.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Resource Scheduling and Optimization Strategy in Edge computing Environment 5

Resource Scheduling and Optimization Strategy in Edge Comput...

引用

5th international conference on Industrial IoT, big data and Supply Chain, IIoTBDSC 2024

作者： Zhao, Chuanqi Wang, Lanruo Zhang, Qizhe Song, Rui Haidian100080 China

ISBN: (纸本)9798331539818

With the rapid development of the Internet of things (IoT), big data and artificial intelligence (AI) technologies, edge computing, as a new computing model, is gradually becoming a key technology for processing massive data and realizing low latency services. Edge computing emerged as a cutting-edge computing paradigm. By pushing computing resources and data storage to the edge of the network, it greatly shortens the data processing path and provides an efficient solution for dealing with large-scale data processing and low latency requirements. In order to further improve the utilization efficiency of computing resources and optimize system performance indicators, the optimization of resource allocation and task scheduling in edge computing has become the focus of academic and industrial circles. this paper innovatively proposes a resource scheduling and optimization model based on edge computing, which deeply integrates AI algorithm to achieve dynamic optimal allocation of resources and intelligent scheduling of tasks. through simulation experiments, it has been verified that the model not only significantly improves resource utilization and reduces task completion time, but also effectively responds to network fluctuations and load changes, demonstrating strong robustness and adaptability. © 2024 ieee.

关键词： edge computing optimization strategy resource scheduling

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation Scheme for Named Entity Recognition Model Based on BERT 5

Knowledge Distillation Scheme for Named Entity Recognition M...

引用

5th international conference on Machine Learning, big data and Business intelligence, MLBDBI 2023

作者： Ye, Chengqiong Hernandez, Alexander A. National University College of Computing and Information Technologies Manila Philippines Anhui Xinhua University School of Big Data and Artificial Intelligence Hefei China

ISBN: (纸本)9798350359930

In order to improve the applicability of named entity recognition model in industrial application scenarios, this paper studies the BERT named entity recognition task. From the perspective of lightweight model, an adaptive weight distillation method is designed to compress the BERT named entity recognition model. By adjusting the weight hyperparameter of distillation loss to an adaptive function, this method enables the model to automatically adjust the weight value according to the training process, avoiding the influence of manual parameter adjustment. Furthermore, by decreasing the middle hidden layer's dimension, this method compresses the teacher model from the width and incorporates the distillation of the middle Transformer layer of the model into the distillation process, allowing it to fully utilize the rich semantic information in the deep structure of the model. Ultimately, a light-weight, well-functioning model with a straightforward structure and few parameters is trained. By employing the suggested technique, the model's inference speed can be increased by seven times while reducing the number of model parameters to 15% of the original model with little loss of accuracy. © 2023 ieee.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Predicting Cryptocurrencies Market Phases through On-Chain data Long-Term Forecasting 5

Predicting Cryptocurrencies Market Phases through On-Chain D...

引用

5th ieee international conference on Blockchain and Cryptocurrency (ICBC)

作者： Casella, Bruno Paletto, Lorenzo Univ Turin Dept Comp Sci Turin Italy Univ Turin Comp Sci Dpt Corso Svizzera 185 Turin Italy

ISBN: (纸本)9798350310191

Blockchain, the underlying technology of Bitcoin and several other cryptocurrencies, like Ethereum, produces a massive amount of open-access data that can be analyzed, providing important information about the network's activity and its respective token. the on-chain data have extensively been used as input to Machine Learning algorithms for predicting cryptocurrencies' future prices;however, there is a lack of study in predicting the future behaviour of on-chain data. this study aims to show how on-chain data can be used to detect cryptocurrency market regimes, like minimum and maximum, bear and bull market phases, and how forecasting these data can provide an optimal asset allocation for long-term investors.

关键词： Blockchain Bitcoin cryptocurrencies on-chain data artificial intelligence prediction asset allocation trading rules markets

来源：评论

学校读者我要写书评

暂无评论

Research on Pedestrian Recognition Based on Deep Learning 5

Research on Pedestrian Recognition Based on Deep Learning

引用

5th international conference on Machine Learning, big data and Business intelligence, MLBDBI 2023

作者： Liqin, Liu Blancaflor, Eric Abisado, Mideth National University College of Computing and Information Technologies Manila Philippines Anhui Xinhua University School of Big Data and Artificial Intelligence Hefei China Mapua University School of Information Technology Manila Philippines

ISBN: (纸本)9798350359930

In the realm of computer vision, pedestrian recognition has gained popularity as a study topic in recent years, and has received widespread attention and research from scholars. How to extract more discriminative pedestrian information for pedestrian re recognition has always been a noteworthy issue. While deep learning models can extract features independently, they may face gradient vanishing as the number of network layers increases. Traditional pedestrian recognition techniques rely on the human construction of visual features, which have low recognition accuracy and are easily influenced by other external circumstances. An additional aspect influencing pedestrian recognition accuracy is partial occlusion of pedestrian images. this article proposes an enhanced neural network that combines random erasure and residual attention networks for pedestrian recognition to improve the accuracy of recognition. © 2023 ieee.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Prediction Method Based on Deep Learning 5

Air Pollution Prediction Method Based on Deep Learning

引用

5th international conference on Robotics, Intelligent Control and Artificial intelligence, RICAI 2023

作者： Qiang, Wang Mariano, Vladimir Y. College of Computing and Information Technologies National University Manila Philippines College of Big Data and Artificial Intelligence Anhui Xinhua University Hefei China

ISBN: (纸本)9798350357950

the formation mechanism and process of PM2.5 are relatively complex, with nonlinear, non-stationary, and multi-dimensional characteristics in both time and space, which increases the difficulty of long-term prediction. this article takes PM2.5 pollution as the research object and proposes a PM2.5 air pollution prediction method based on CNN-LSTM deep learning model. It integrates the feature learning and extraction advantages of CNN and the temporal memory advantages of LSTM to improve the accuracy of long-term prediction of PM2.5 pollution in small areas. through experimental research, it has been shown that the integrated CNN-LSTM hybrid prediction model can fully explore the temporal and interactive characteristics of air pollutants and meteorological factor data, and has higher prediction accuracy and accuracy than a single LSTM prediction model. It is suitable for deep learning hybrid models in processing data such as meteorological data, stock market data, economic data, transportation data and other big data with time series characteristics provides reference. © 2023 ieee.

关键词： CNN Deep learning LSTM PM2.5 pollution prediction

来源：评论

学校读者我要写书评

暂无评论

Cloud Diagnosis System Based on High-Voltage Transmission Line Faults 5

Cloud Diagnosis System Based on High-Voltage Transmission Li...

引用

5th international conference on Smart Power and Internet Energy Systems, SPIES 2023

作者： Zhiwang, Yang Zhiqin, Zhang Wude, Xue Power China Shanghai Electric Power Engineering Co. Ltd. New Energy Engineering Dept Shanghai China College of Electrical Engineering Shanghai University of Electric Power Shanghai China

ISBN: (纸本)9798350371741

this paper introduces the research achievements of artificial intelligence cloud diagnosis system for high-voltage transmission line fault monitoring and diagnosis and wide application prospects in smart grid. It describes the artificial intelligence based on cloud diagnosis core & big data cloud computing processing & the application of Internet mode, the whole process of smart cloud development is expounded in detail. Further, power engineers have developed the HV transmission line fault cloud diagnosis system, to ensure the transmission line equipment safe operation, and the realization of fault diagnosis and management mode. We used the artificial intelligent cloud diagnosis examples, to prove the value and effectiveness of the HV transmission line cloud diagnosis system. © 2023 ieee.

关键词： big data

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61页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：