Satisfiable Integer Programming Algorithm On Distributed Inter Process Communication (SIP-DIPC)
Data Analytics is a superset to Data Mining. Data mining algorithm is getting popular support in recent development of Big Data. Among popular methods in Data Mining is Rough Classification Modeling (RCM), Neural Network and Statistical Analysis. RCM is capable of giving more accurate reducts calcul...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute of Advanced Scientific Research, Inc.
2019
|
Online Access: | http://eprints.utem.edu.my/id/eprint/24160/2/%5B26%5D%20FTMK.PDF http://eprints.utem.edu.my/id/eprint/24160/ https://www.jardcs.org/archivesview.php?volume=1&issue=16&page=2 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Teknikal Malaysia Melaka |
Language: | English |
Summary: | Data Analytics is a superset to Data Mining. Data mining algorithm is getting popular support in recent development of Big Data. Among popular methods in Data Mining is Rough Classification Modeling (RCM), Neural Network and Statistical Analysis. RCM is capable of giving more accurate reducts calculation on huge dataset. However, RCM consume a lot of computation times to operate on even a small dataset. Satisfiable Integer Programming (SIP) has been used to quantify dataset in Rough Classification Modeling (RCM). Previously SIP has been ported on a single node. In order to expedite the computing times, SIP has been ported on distributed computing environment. The result on RCM using SIP in this paper perform faster than the current Neural Network utilizing Multilayer Perceptron (MLP) and Statistical Analysis using Multiple Regression (MR) on a different distributed computing platforms. Computation time has been recorded and compared. Result and analysis of the comparisons made between the three algorithms will be presented |
---|