Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Science of Surveying and Mapping》 2016-01
Add to Favorite Get Latest Update

Study on a streaming parallel method for massive spatial data processing

LIU Jiping;WU Lixin;DONG Chun;ZHANG Fuhao;KANG Xiaochen;Chinese Academy of Surveying and Mapping;Northeastern University;  
Aiming at the problem that I/O time for spatial data usually has high proportion,the paper proposed a stream processing method which overlaps the spatial computation and the I/O processes for alleviating the bottleneck that impedes the further performance improvement of spatial algorithms.Moreover,the adopted tilling strategy in the proposed method sharply reduced the memory usage,and then dedicated a better applicability.Finally,the experiment selected the terrain surface area algorithm,the most time consuming algorithm in the statistical analysis in geographical conditions monitoring.Result showed that with the streaming method,the time consumed and the memory usage would be both reduced obviously;in addition,the streaming method could be used in other statistical algorithms with its low degree of coupling.
【Fund】: 测绘地理信息公益性行业科研专项经费项目(201512032);; 国家863计划项目(2011AA20302);; 国家自然科学基金重点项目(40930104);; 辽宁省自然科学基金资助项目(2015020581)
【CateGory Index】: P208
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【Co-citations】
Chinese Journal Full-text Database 2 Hits
1 ZHAO Sisi,ZHOU Chenghu(State Key Laboratory of Resources and Environmental Information System,Institute of Geographical Sciences and Natural Resources Research,CAS,Beijing 100101,China);Accelerating polygon overlay analysis by GPU[J];Progress in Geography;2013-01
2 DAI Jian;DING Zhing-Ming;University of Chinese Academy of Sciences;National Fundamental Software Research Center,Institute of Software,Chinese Academy of Sciences;;MapReduce Based Fast kNN Join[J];Chinese Journal of Computers;2015-01
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved