A Cognitive Ensemble of Extreme Learning Machines for Steganalysis Based on Risk-Sensitive Hinge Loss Function

Vasily Sachnev, Savitha Ramasamy, Suresh Sundaram, Hyong Joong Kim, Hee Joon Hwang

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In this paper, we propose a risk-sensitive hinge loss function-based cognitive ensemble of extreme learning machine (ELM) classifiers for JPEG steganalysis. ELM is a single hidden-layer feed-forward network that chooses the input parameters randomly and estimates the output weights analytically. For steganalysis, we have extracted 548-dimensional merge features and trained ELM to approximate the functional relationship between the merge features and class label. Further, we use a cognitive ensemble of ELM classifier with risk-sensitive hinge loss function for accurate steganalysis. As the hinge loss error function is shown to be better than mean-squared error function for classification problems, here, the individual ELM classifiers are developed based on hinge loss error function. The cognition in the ensemble of ELM obtains the weighted sum of individual classifiers by enhancing the outputs of winning classifiers for a sample, while penalizing the other classifiers for the sample. Thus, the cognitive ensemble ELM classifier positively exploits the effect of initialization in each classifier to obtain the best results. The performance of the cognitive ensemble ELM in performing the steganalysis is compared to that of a single ELM, and the existing ensemble support vector machine classifier for steganalysis. Performance results show the superior classification ability of the cognitive ensemble ELM classifier.

Original languageEnglish
Pages (from-to)103-110
Number of pages8
JournalCognitive Computation
Volume7
Issue number1
DOIs
Publication statusPublished - 2014

Fingerprint

Hinges
Learning systems
Classifiers
Cognition
Machine Learning
Aptitude
Support vector machines
Labels
Weights and Measures

Keywords

  • Extreme learning machine
  • JPEG steganography
  • Steganalysis
  • Undetectable data hiding

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

A Cognitive Ensemble of Extreme Learning Machines for Steganalysis Based on Risk-Sensitive Hinge Loss Function. / Sachnev, Vasily; Ramasamy, Savitha; Sundaram, Suresh; Kim, Hyong Joong; Hwang, Hee Joon.

In: Cognitive Computation, Vol. 7, No. 1, 2014, p. 103-110.

Research output: Contribution to journalArticle

Sachnev, Vasily ; Ramasamy, Savitha ; Sundaram, Suresh ; Kim, Hyong Joong ; Hwang, Hee Joon. / A Cognitive Ensemble of Extreme Learning Machines for Steganalysis Based on Risk-Sensitive Hinge Loss Function. In: Cognitive Computation. 2014 ; Vol. 7, No. 1. pp. 103-110.
@article{70e963c000c64dfb9b7047dca185e897,
title = "A Cognitive Ensemble of Extreme Learning Machines for Steganalysis Based on Risk-Sensitive Hinge Loss Function",
abstract = "In this paper, we propose a risk-sensitive hinge loss function-based cognitive ensemble of extreme learning machine (ELM) classifiers for JPEG steganalysis. ELM is a single hidden-layer feed-forward network that chooses the input parameters randomly and estimates the output weights analytically. For steganalysis, we have extracted 548-dimensional merge features and trained ELM to approximate the functional relationship between the merge features and class label. Further, we use a cognitive ensemble of ELM classifier with risk-sensitive hinge loss function for accurate steganalysis. As the hinge loss error function is shown to be better than mean-squared error function for classification problems, here, the individual ELM classifiers are developed based on hinge loss error function. The cognition in the ensemble of ELM obtains the weighted sum of individual classifiers by enhancing the outputs of winning classifiers for a sample, while penalizing the other classifiers for the sample. Thus, the cognitive ensemble ELM classifier positively exploits the effect of initialization in each classifier to obtain the best results. The performance of the cognitive ensemble ELM in performing the steganalysis is compared to that of a single ELM, and the existing ensemble support vector machine classifier for steganalysis. Performance results show the superior classification ability of the cognitive ensemble ELM classifier.",
keywords = "Extreme learning machine, JPEG steganography, Steganalysis, Undetectable data hiding",
author = "Vasily Sachnev and Savitha Ramasamy and Suresh Sundaram and Kim, {Hyong Joong} and Hwang, {Hee Joon}",
year = "2014",
doi = "10.1007/s12559-014-9268-x",
language = "English",
volume = "7",
pages = "103--110",
journal = "Cognitive Computation",
issn = "1866-9956",
publisher = "Springer New York",
number = "1",

}

TY - JOUR

T1 - A Cognitive Ensemble of Extreme Learning Machines for Steganalysis Based on Risk-Sensitive Hinge Loss Function

AU - Sachnev, Vasily

AU - Ramasamy, Savitha

AU - Sundaram, Suresh

AU - Kim, Hyong Joong

AU - Hwang, Hee Joon

PY - 2014

Y1 - 2014

N2 - In this paper, we propose a risk-sensitive hinge loss function-based cognitive ensemble of extreme learning machine (ELM) classifiers for JPEG steganalysis. ELM is a single hidden-layer feed-forward network that chooses the input parameters randomly and estimates the output weights analytically. For steganalysis, we have extracted 548-dimensional merge features and trained ELM to approximate the functional relationship between the merge features and class label. Further, we use a cognitive ensemble of ELM classifier with risk-sensitive hinge loss function for accurate steganalysis. As the hinge loss error function is shown to be better than mean-squared error function for classification problems, here, the individual ELM classifiers are developed based on hinge loss error function. The cognition in the ensemble of ELM obtains the weighted sum of individual classifiers by enhancing the outputs of winning classifiers for a sample, while penalizing the other classifiers for the sample. Thus, the cognitive ensemble ELM classifier positively exploits the effect of initialization in each classifier to obtain the best results. The performance of the cognitive ensemble ELM in performing the steganalysis is compared to that of a single ELM, and the existing ensemble support vector machine classifier for steganalysis. Performance results show the superior classification ability of the cognitive ensemble ELM classifier.

AB - In this paper, we propose a risk-sensitive hinge loss function-based cognitive ensemble of extreme learning machine (ELM) classifiers for JPEG steganalysis. ELM is a single hidden-layer feed-forward network that chooses the input parameters randomly and estimates the output weights analytically. For steganalysis, we have extracted 548-dimensional merge features and trained ELM to approximate the functional relationship between the merge features and class label. Further, we use a cognitive ensemble of ELM classifier with risk-sensitive hinge loss function for accurate steganalysis. As the hinge loss error function is shown to be better than mean-squared error function for classification problems, here, the individual ELM classifiers are developed based on hinge loss error function. The cognition in the ensemble of ELM obtains the weighted sum of individual classifiers by enhancing the outputs of winning classifiers for a sample, while penalizing the other classifiers for the sample. Thus, the cognitive ensemble ELM classifier positively exploits the effect of initialization in each classifier to obtain the best results. The performance of the cognitive ensemble ELM in performing the steganalysis is compared to that of a single ELM, and the existing ensemble support vector machine classifier for steganalysis. Performance results show the superior classification ability of the cognitive ensemble ELM classifier.

KW - Extreme learning machine

KW - JPEG steganography

KW - Steganalysis

KW - Undetectable data hiding

UR - http://www.scopus.com/inward/record.url?scp=84922752943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922752943&partnerID=8YFLogxK

U2 - 10.1007/s12559-014-9268-x

DO - 10.1007/s12559-014-9268-x

M3 - Article

AN - SCOPUS:84922752943

VL - 7

SP - 103

EP - 110

JO - Cognitive Computation

JF - Cognitive Computation

SN - 1866-9956

IS - 1

ER -