检索结果-内蒙古大学图书馆

21st International Conference on Cooperative Design, Visualization, and Engineering (CDVE)

作者： Yang, Jinshun Huang, Shuangxi Huang, Mingfeng Tsinghua Univ Beijing Peoples R China

ISBN: (纸本)9783031713149;9783031713156

Event evolution analysis can help understand the current status and trends of our society, has attracted a lot of interest from the industry and academia. Previous evolution methods include the storyline-based methods and event knowledge graph-based methods. However, the existing methods have many deficiencies. We propose a framework of event evolution analysis for network texts, which includes a novel event extraction model, an event relation prediction model and a new type of event knowledge graph. Our event extraction model outperforms the previous best model by 2.9% in trigger extraction F1 score, and 3.37% in argument extraction F1 score. Our approach to exploring event relations and connections simplifies the traditional event relation extraction method, and is experimentally proven effective.

关键词： Social networks big data processing big data fusion Event extraction Event knowledge graph Event relation prediction

来源：评论

学校读者我要写书评

暂无评论

Exploring the Feasibility of Raspberry Pi 4 Model B Clusters as an Alternative to Advanced Process Chip Computers 1

引用

39th CCF National Conference on Computer Applications

作者： Liu, Peng Cao, Xiaofan Jia, Yujiao Changchun Univ Sci & Technol Inst Energy & Elect Engn Changchun Peoples R China North China Elect Power Univ Sch Control & Comp Engn Beijing Peoples R China North China Elect Power Univ Yangzhong Intelligent Elect Res Ctr Beijing Peoples R China

ISBN: (数字)9789819796748

ISBN: (纸本)9789819796731;9789819796748

Faced with the challenges of utilizing advanced process chips, this study explores and verifies the feasibility of using Raspberry Pi 4 Model B (RPi 4B) clusters with mature process chips as an alternative to desktop computers that utilize more advanced process chips. By constructing a multi-node RPi 4B cluster and comparing its performance with that of a single x86 architecture computer equipped with an i5-12490F processor through HPL (High-Performance Linpack) and Hadoop benchmark, the study found that a cluster of 13 RPi 4B units can achieve comparable performance to a single x86 architecture computer in the HPL test, with significantly higher energy efficiency. Although there is still a performance gap in processing big data tasks, optimizing the cluster's hardware configuration and software system is expected to yield substantial improvements. Through this study, we aim to provide a potential solution for countries, regions, or organizations that struggle to obtain or afford advanced process chips. Furthermore, we hope to encourage people to consider how to improve computational performance through algorithmic optimization, architectural innovation, and other means when faced with limitations in chip technology, in order to meet the growing demand for computation.

关键词： Raspberry Pi cluster High-performance computing big data processing Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Walks on Algebraic Small World Graphs of Large Girth and New Secure Stream Ciphers

Walks on Algebraic Small World Graphs of Large Girth and New...

引用

Intelligent Systems Conference

作者： Ustimenko, Vasyl Chojecki, Tymoteusz Royal Holloway Univ London Inst Math Dept Math Egham Hill Egham TW20 0EX Surrey England Inst Telecommun & Global Informat Space Cybersecur Dept 25 Chokolivskiy BulvAp 13 UA-186 Kyiv Ukraine Univ Maria Curie Sklodowska Inst Math 20-031 Pl Marii Curie Sklodowskiej 1 Lublin Poland

ISBN: (纸本)9783031664304;9783031664311

The paper is dedicated to computer evaluation of parameters of members of family A(n, F-q), n >= 2 of small world algebraic graphs of large girth with well defined projective limit. We present the applications of these computations to the area of optimisation problems for algebraic graphs over various fields and Cryptography. We show the impact of high girth property of known family of graphs A(n, Fq) on properties of fast stream ciphers based on these graphs. Finally we modify these symmetric encryption algorithms to make them resistant to linearization attacks.

关键词： Graph based cryptography big data processing GIS protection Multivariate cryptography

来源：评论

学校读者我要写书评

暂无评论

MapReduce-Based Improved Random Forest Model for Massive Educational data processing and Classification

引用

MOBILE NETWORKS & APPLICATIONS 2021年第1期26卷 191-199页

作者： Xu, Wei Hoang, Vinh Truong Xian Univ Finance & Econ Business Sch Xian 710100 Shaanxi Peoples R China Ho Chi Minh City Open Univ Fac Comp Sci Ho Chi Minh City 70000 Vietnam

This paper takes education data mining as the research theme, mine the existing massive education big data, compares the analysis methods of existing data models, and proposes an improved random forest reference model. The information gain of various features is calculated by introducing the feature weighting system, and the evaluation index is used to improve the existing data analysis. The simulation results show that the improved model is highly efficient as compared to the existing models for classification. In order to resolve the performance bottleneck of a single node in multiple data classification tasks in the era of big data, a classification and prediction model of graduates' large-scale employment data, based on distributed improved RF algorithm, is proposed. The MapReduce distributed computing framework is used to complete the serial writing and deserialization loading of the training model between the local disk and the distributed file system, and realizing the distributed expansion of the large-scale data classification model based on the improved RF model.

关键词： Machine learning data classification model big data processing MapReduce

来源：评论

学校读者我要写书评

暂无评论

Profit Maximization of big data Jobs in Cloud Using Stochastic Optimization

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2021年第4期9卷 1563-1574页

作者： Nabavinejad, Seyed Morteza Goudarzi, Maziar Inst Res Fundamental Sci IPM Sch Comp Sci Tehran Iran Sharif Univ Technol Dept Comp Engn Tehran Iran

Reserved instances offered by cloud providers make it possible to reserve resources and computing capacity for a specific period of time. One should pay for all the hours of that time interval;in exchange, the hourly rate is significantly lower than on-demand instances. Reserved Instances can significantly reduce the monetary cost of resources needed to process big data applications in cloud. However, purchases of these instances are non-refundable, and hence, one should be able to estimate the required resources prior to purchase to avoid over-payment. It becomes important especially when the results obtained by big data job has monetary value, such as business intelligence applications. But, estimating the resource demand of big data processing jobs is hard because of numerous factors that affect them such as data locality, data skew, stragglers, internal settings of big data processing framework, interference among instances, instances availability, etc. To maximize the profit of processing such big data jobs in cloud considering fluctuating nature of their resource demand, as well as reserved instances limitations, we propose Reserved Instances Stochastic Allocation (RISA) approach. Using historical traces of resource demand of big data jobs submitted by user, RISA leverages stochastic optimization to determine the amount of resources needed to be reserved for that user to maximize the profit. Our evaluation using real-world traces shows that RISA can increase the net profit by up to 10x, compared to previous approaches. RISA can also find solutions as close as 2 percent to the best possible solution.

关键词： Cloud computing big data processing reserved instances stochastic optimization profit maximization

来源：评论

学校读者我要写书评

暂无评论

Methodology for Creating a Digital Bathymetric Model Using Neural Networks for Combined Hydroacoustic and Photogrammetric data in Shallow Water Areas

引用

SENSORS 2024年第1期24卷 175页

作者： Lacka, Malgorzata Lubczonek, Jacek Maritime Univ Szczecin Waly Chrobrego 1-2 PL-70500 Szczecin Poland

This study uses a neural network to propose a methodology for creating digital bathymetric models for shallow water areas that are partially covered by a mix of hydroacoustic and photogrammetric data. A key challenge of this approach is the preparation of the training dataset from such data. Focusing on cases in which the training dataset covers only part of the measured depths, the approach employs generalized linear regression for data optimization followed by multilayer perceptron neural networks for bathymetric model creation. The research assessed the impact of data reduction, outlier elimination, and regression surface-based filtering on neural network learning. The average values of the root mean square (RMS) error were successively obtained for the studied nearshore, middle, and deep water areas, which were 0.12 m, 0.03 m, and 0.06 m, respectively;moreover, the values of the mean absolute error (MAE) were 0.11 m, 0.02 m, and 0.04 m, respectively. Following detailed quantitative and qualitative error analyses, the results indicate variable accuracy across different study areas. Nonetheless, the methodology demonstrated effectiveness in depth calculations for water bodies, although it faces challenges with respect to accuracy, especially in preserving nearshore values in shallow areas.

关键词： digital bathymetric model big data processing MLP neural network data reduction USV UAV data fusion regression shallow water area

来源：评论

学校读者我要写书评

暂无评论

KFIML: Kubernetes-Based Fog Computing IoT Platform for Online Machine Learning

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第19期9卷 19463-19476页

作者： Wan, Ziyu Zhang, Zheng Yin, Rui Yu, Guanding Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Zhejiang Univ City Coll Sch Informat & Elect Engn Hangzhou 310015 Peoples R China

The massive onsite data produced by the Internet of Things (IoT) can bring valuable information and immense potentials, thus empowering a new wave of emerging applications. However, with the rapid increase of onsite IoT data streams, it has become extremely challenging to develop a scalable computing platform and provide a comprehensive workflow for processing IoT data streams with lower latency and more intelligence. To this end, we present a Kubernetes-based scalable fog computing platform (KFIML), integrating big data streaming processing with machine learning (ML)-based applications. We also provide a comprehensive IoT data processing workflow, including data access and transfer, big data processing, online ML, long-term storage, and monitoring. The platform is feasibly validated on a clustered testbed, which comprises a master node, IoT broker servers, worker nodes, and a local database server. By leveraging the lightweight orchestration system, namely Kubernetes, we can readily scale and manage containerized software frameworks on our testbed. The big data processing layer utilizes the advanced data flow frameworks such as Apache Flink, to support both streaming processing and statistical analysis with low latency. In addition, the specified long short-term memory (LSTM)-based ML pipelines are employed on the online ML layer, to enable the real-time predictive analysis of IoT data streams. The experiments on a real-world smart grid use case demonstrate that the container-based KFIML platform can be well-scaled with Kubernetes to efficiently perform big data processing increased onsite IoT data streams with lower latency and conduct ML-based applications.

关键词： Internet of Things big data Edge computing Real-time systems Distributed databases Sparks Computer architecture big data processing fog computing Internet of Things (IoT) Kubernetes online machine learning (ML) predictive analysis

来源：评论

学校读者我要写书评

暂无评论

High-efficient energy saving processing of big data of communication under mobile cloud computing

引用

International Journal of Modeling, Simulation, and Scientific Computing 2019年第4期10卷 96-106页

作者： Yazhen Liu Pengfei Fan Jiyang Zhu Liping Wen Xiongfei Fan Information Communication Operation and Maintenance Center Information and Communication Branch State Grid Inner Mongolia Eastern Electric Power Co. Ltd.HohhotInner Mongolia Autonomous Region 010020P.R.China Hohhot Power Supply Bureau Inner Mongolia Power(Group)Co.Ltd.HohhotInner Mongolia Autonomous Region 010020P.R.China Training Center Inner Mongolia Power(Group)Co.Ltd.HohhotInner Mongolia Autonomous Region 010020P.R.China

From 21st century,it is hard for traditional storage and algorithm to provide service with high quality because of big data of communication which grows ***,cloud computing technology with relatively low cost of hardware facilities is ***,to guarantee the quality of service in the situation of the rapid growth of data volume,the energy consumption cost of cloud computing begins to exceed the hardware *** order to solve the problems mentioned above,this study briefly introduced the virtual machine and its energy consumption model in the mobile cloud environment,introduced the basic principle of the virtual machine migration strategy based on the artificial bee colony algorithm and then simulated the performance of processing strategy to big data of communication based on artificial bee colony algorithm in mobile cloud computing environment by CloudSim3.0 software,which was compared with the performance of two algorithms,resource management(RM)and genetic algorithm(GA).The results showed that the power consumption of the migration strategy based on the artificial bee colony algorithm was lower than the other two strategies,and there were fewer failed virtual machines under the same number of requests,which meant that the service quality was higher.

关键词： Mobile cloud computing big data processing artificial bee colony algorithm energy saving

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained data processing Framework for Heterogeneous IoT Devices in Sub-aquatic Edge Computing Environment

引用

WIRELESS PERSONAL COMMUNICATIONS 2021年第2期116卷 1407-1422页

作者： Koo, Jahwan Qureshi, Nawab Muhammad Faseeh Sungkyunkwan Univ Coll Software Suwon South Korea Sungkyunkwan Univ Dept Comp Educ Seoul South Korea

Sub-aquatic data processing is a procedure that exchanges datasets through underwater sensory devices in the distributed computing environment. This paradigm has evolved techniques of data exchange and signal processing over time and uses big data frameworks to store processed datasets at edge nodes. Also, it uses modern IoT devices that capture sensory data tuples of water temperature, turbidity, speed, and pressure levels. Recently, we observe that the edge nodes that acquire the dataset of heterogeneous IoT devices are becoming overwhelmed with the issue of tuple non-classification at the level of data encapsulation. This issue raises a few concerns such as (a) ineffective tuple wrapup, (b) bundle compression failovers, (c) bundle block placement latency, and (d) end-of-file replica build latency. This paper proposes a fine-grained processing framework that normalizes tuple non-classification through enhanced false-positive function and assembles IoT sensory tuples with the in-memory capacity to rectify compression failovers. This solution leads to a tremendous decrease in bundle block placement and end-of-file replica latencies. The simulation results depict the effectiveness of fine-grained processing framework through easing the edge nodes in the sub-aquatic distributed environment.

关键词： Edge computing Internet of things (IoT) big data processing Bloom filter

来源：评论

学校读者我要写书评

暂无评论

A Literature Review on AWS-Based Cloud Computing: A Case in South Korea

A Literature Review on AWS-Based Cloud Computing: A Case in ...

引用

IEEE International Conference on big data and Smart Computing (bigComp)

作者： Lee, Byeongcheon Oh, Jinyeong Shon, Woojin Moon, Jihoon Soonchunhyang Univ Dept AI & Big Data Asan South Korea

ISBN: (纸本)9781665475785

A collection of information technology (IT) services known as "cloud computing" is offered to customers across a network on a subscription basis with the flexibility to scale up or down based on their service needs. The emergence of cloud computing technology, which has tremendous advantages, is one of the major advancements in recent times. Many computers and servers are specifically devoted to meeting the demands of businesses in a cloud computing system for internal communications. Users can access their services via an internet connection. Registered users have remote access to both hardware and software, thanks to the cloud service, which has made essential adjustments to how information is stored and made accessible. This paper investigates the use of Amazon Web Services (AWS) for big data processing and analytics in South Korea. We collected several domestic journal and conference papers that studied local cloud services based on AWS to introduce distributed systems and cloud computing technologies. This study can provide researchers with a compact version of the extensive AWS-based data processing literature and potential future insights. It can also provide stakeholders tailored services, information about cutting-edge solutions that can influence academics, and details about current research needs.

关键词： Amazon Web Services (AWS) big data processing cloud computing distributed system

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：