Utilizing Architecture Aspects for in Data Mining for Computer System Design

Utilizing Architecture Aspects for in Data Mining for Computer System Design

Chantana Chantrapornchai (Kasetsart University, Thailand), Aree Kaegjing (Silpakorn University, Thailand), Sathaporn Srakaew (Silpakorn University, Thailand), Warot Piyanuntcharatsr (Silpakorn University, Thailand) and Songchok Krakhaeng (Silpakorn University, Thailand)
Copyright: © 2017 |Pages: 28
DOI: 10.4018/978-1-5225-1776-4.ch009
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Data mining has been a popular technique. It has been for many applications in many areas nowadays. In this chapter, we are interested in utilizing architecture features and apply data mining techniques for a computer design. Since data mining requires lot of collected data for building models, the relevant data needs to be properly generated. We demonstrate the applications and their methodology starting from data set generation, feature extraction, modeling and evaluations. Important characteristics of the architecture are considered for data set generation and feature extractions: particularly, the instruction set, and memory access pattern features. The chapter utilizes these features given with observations for building the models for cache prediction, branch prediction, and malware detection.
Chapter Preview
Top

Background

The features related to computer architecture that are useful in this research work are presented in this section: the background knowledge about instruction, memory and conditional branch.

Complete Chapter List

Search this Book:
Reset