Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Shenyang Normal University(Natural Science Edition)》 2016-01
Add to Favorite Get Latest Update

A new fast online learning algorithm based on distributed mining of big data

WU Jingna;YANG Shu;WANG Jianhui;College of Education Technology,Shenyang Normal University;  
In big data analysis and processing,there are many problems,such as data types,low processing efficiency.Getting useful information and knowledge to guide the subsequent decisions is the ultimate goal of machine learning.Effective learning samples increase gradually,so how effectively to learn classifier is a very valuable problem.Big data analysis requires a large amount of data flow to perform real-time distributed mining.It designs unique distributed mining system:online adapting to the characteristics of the incoming data;online processing a large amount of heterogeneous data;the limited data ability to access between distributed learners and communication.It proposes a basic framework of data mining,and based on this it researches a kind of efficient online learning algorithm.Framework contains the whole different learners and local learners which can only have access to the input data.By using the local correlation model,the learning algorithm can optimize the prediction precision than the existing advanced learning solutions,which requires less exchange of information and computational complexity.
【Fund】: 国家自然科学基金资助项目(60970112)
【CateGory Index】: TP311.13
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
Similar Journals
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved