PRE-PROCESSING AND MODELING TOOLS FOR BIGDATA

被引：2

作者：

Hashem, Hadi ^{[1
]}

Ranc, Daniel ^{[1
]}

机构：

[1] Telecom SudParis, Evry, France

来源：

FOUNDATIONS OF COMPUTING AND DECISION SCIENCES | 2016年 / 41卷 / 03期

关键词：

Data Modeling; BigData; NoSQL; MapReduce; Pre-processing;

D O I：

10.1515/fcds-2016-0009

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Modeling tools and operators help the user / developer to identify the processing field on the top of the sequence and to send into the computing module only the data related to the requested result. The remaining data is not relevant and it will slow down the processing. The biggest challenge nowadays is to get high quality processing results with a reduced computing time and costs. To do so, we must review the processing sequence, by adding several modeling tools. The existing processing models do not take in consideration this aspect and focus on getting high calculation performances which will increase the computing time and costs. In this paper we provide a study of the main modeling tools for BigData and a new model based on pre-processing.

引用

页码：151 / 162

页数：12