Research Repository

SoCodeCNN: Program Source Code for Visual CNN Classification Using Computer Vision Methodology

Dey, Somdip and Singh, Amit Kumar and Prasad, Dilip Kumar and McDonald-Maier, Klaus (2019) 'SoCodeCNN: Program Source Code for Visual CNN Classification Using Computer Vision Methodology.' IEEE Access, 7. pp. 157158-157172. ISSN 2169-3536

08882216.pdf - Published Version
Available under License Creative Commons Attribution.

Download (3MB) | Preview


Automated feature extraction from program source-code such that proper computing resources could beallocated to the program is very difficult given the current state of technology. Therefore, conventionalmethods call for skilled human intervention in order to achieve the task of feature extraction from programs.This research is the first to propose a novel human-inspired approach to automatically convert programsource-codes to visual images. The images could be then utilized for automated classification by visualconvolutional neural network (CNN) based algorithm. Experimental results show high prediction accuracyin classifying the types of program in a completely automated manner using this approach.

Item Type: Article
Uncontrolled Keywords: Classification, intermediate representation, LLVM, MPSoC, resource management,program, source code, computer vision, energy consumption, resource optimization, dynamic powermanagement, machine learning
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 23 Oct 2019 10:01
Last Modified: 15 Jan 2022 01:30

Actions (login required)

View Item View Item