A resource aware MapReduce based parallel SVM for large scale image classification

Guo, W., Khalid, N., Liu, Y., Li, M. and Qi, M. (2015) A resource aware MapReduce based parallel SVM for large scale image classification. Neural Processing Letters, 44 (1). pp. 161-184. ISSN 1370-4621.

[img] PDF
17177_A Resource Aware MapReduce based Parallel SVM for Large Scale Image Classifications (2).pdf - Accepted Version
Restricted to Repository staff only

Download (4kB)

Abstract

Machine learning techniques have facilitated image retrieval by automatically classifying and annotating images with keywords. Among them support vector machines (SVMs) are used extensively due to their generalization properties. However, SVM training is notably a computationally intensive process especially when the training dataset is large.

This paper presents RASMO, a resource aware MapReduce based parallel SVM algorithm for large scale image classifications which partitions the training data set into smaller subsets and optimizes SVM training in parallel using a cluster of computers. A genetic algorithm based load balancing scheme is designed to optimize the performance of RASMO in heterogeneous computing environments. RASMO is evaluated in both experimental and simulation environments.

The results show that the parallel SVM algorithm reduces the training time significantly compared with the sequential SMO algorithm while maintaining a high level of accuracy in classifications

Item Type: Article
Uncontrolled Keywords: Parallel SVM; MapReduce; image classification and annotation; load balancing
Subjects: T Technology
Divisions: Faculty of Social and Applied Sciences > School of Law, Criminal Justice and Computing
Depositing User: Dr Man Qi
Date Deposited: 03 Apr 2018 10:12
Last Modified: 03 Apr 2018 10:17
URI: https://create.canterbury.ac.uk/id/eprint/17177

Actions (login required)

Update Item (CReaTE staff only) Update Item (CReaTE staff only)

Downloads

Downloads per month over past year

View more statistics

Share

Connect with us

Last edited: 29/06/2016 12:23:00