The Random Subspace Method for Constructing Decision Forests
IEEE Transactions on Pattern Analysis and Machine Intelligence
Ensembling neural networks: many could be better than all
Artificial Intelligence
Detecting LSB Steganography in Color and Gray-Scale Images
IEEE MultiMedia
Detection of LSB Steganography via Sample Pair Analysis
IH '02 Revised Papers from the 5th International Workshop on Information Hiding
A tutorial on support vector regression
Statistics and Computing
Ensemble selection from libraries of models
ICML '04 Proceedings of the twenty-first international conference on Machine learning
A Theoretical and Experimental Analysis of Linear Combiners for Multiple Classifier Systems
IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistically undetectable jpeg steganography: dead ends challenges, and opportunities
Proceedings of the 9th workshop on Multimedia & security
Generic Adoption of Spatial Steganalysis to Transformed Domain
Information Hiding
Proceedings of the 11th ACM workshop on Multimedia and security
Edge adaptive image steganography based on LSB matching revisited
IEEE Transactions on Information Forensics and Security
Using high-dimensional image models to perform highly undetectable steganography
IH'10 Proceedings of the 12th international conference on Information hiding
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
"Break our steganographic system": the ins and outs of organizing BOSS
IH'11 Proceedings of the 13th international conference on Information hiding
Ensemble Methods: Foundations and Algorithms
Ensemble Methods: Foundations and Algorithms
Diversity regularized ensemble pruning
ECML PKDD'12 Proceedings of the 2012 European conference on Machine Learning and Knowledge Discovery in Databases - Volume Part I
Hi-index | 0.00 |
In order to achieve higher estimation accuracy of the embedding change rate of a stego object, an ensemble learning-based estimation method is presented. First of all, a framework of embedding change rate estimation based on estimator ensemble is proposed. Then an algorithm of building the estimator ensemble, the core of the framework, is concretely described. Finally, a pruning method for estimator ensemble is proposed in consideration of both the diversity among the base estimators and accuracy of each of them. The experimental results for three modern steganographic algorithms (nsF5, PQ and PQt) indicate that the proposed method acquired better performance than the existed typical method. Furthermore, the pruned estimator ensemble with less base estimators maintained, even slightly improved the estimation accuracy, compared to the one without purning.