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.