On Combining Deep Neural Network Classifiers for Source Device Identification

This paper proposes combining deep neural network classifiers while simultaneously optimizing the networks. The proposed combination scheme enhances the accuracy of each classifier, which, in turn, boosts the overall combined accuracy during a post-processing step. The proposed classification scheme...

Full description

Saved in:
Bibliographic Details
Main Authors: Ioannis Tsingalis, Constantine Kotropoulos
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10942326/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850264505256247296
author Ioannis Tsingalis
Constantine Kotropoulos
author_facet Ioannis Tsingalis
Constantine Kotropoulos
author_sort Ioannis Tsingalis
collection DOAJ
description This paper proposes combining deep neural network classifiers while simultaneously optimizing the networks. The proposed combination scheme enhances the accuracy of each classifier, which, in turn, boosts the overall combined accuracy during a post-processing step. The proposed classification scheme is thoroughly evaluated on a dataset specifically designed for multimedia forensics research. The combined classifiers include shallow and deep neural networks, with input data comprising original and manipulated content processed through online social networks such as YouTube, WhatsApp, and Facebook. The experimental results demonstrate promising performance, proving the usability of the proposed classifier combination scheme. Specifically, it is observed that the accuracy of shallow neural networks improves significantly when combined with deep neural networks. This performance enhancement is particularly notable when the combined classifiers are trained on data manipulated by online social network platforms.
format Article
id doaj-art-23a2976f29814b3185b2013b2d303e92
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-23a2976f29814b3185b2013b2d303e922025-08-20T01:54:41ZengIEEEIEEE Access2169-35362025-01-0113584255844110.1109/ACCESS.2025.355514110942326On Combining Deep Neural Network Classifiers for Source Device IdentificationIoannis Tsingalis0https://orcid.org/0000-0003-2590-325XConstantine Kotropoulos1https://orcid.org/0000-0001-9939-7930Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Informatics, Aristotle University of Thessaloniki, Thessaloniki, GreeceThis paper proposes combining deep neural network classifiers while simultaneously optimizing the networks. The proposed combination scheme enhances the accuracy of each classifier, which, in turn, boosts the overall combined accuracy during a post-processing step. The proposed classification scheme is thoroughly evaluated on a dataset specifically designed for multimedia forensics research. The combined classifiers include shallow and deep neural networks, with input data comprising original and manipulated content processed through online social networks such as YouTube, WhatsApp, and Facebook. The experimental results demonstrate promising performance, proving the usability of the proposed classifier combination scheme. Specifically, it is observed that the accuracy of shallow neural networks improves significantly when combined with deep neural networks. This performance enhancement is particularly notable when the combined classifiers are trained on data manipulated by online social network platforms.https://ieeexplore.ieee.org/document/10942326/Classifier combinationfusionproduct ruleensemble learningsource device identification (SDI)multimodal
spellingShingle Ioannis Tsingalis
Constantine Kotropoulos
On Combining Deep Neural Network Classifiers for Source Device Identification
IEEE Access
Classifier combination
fusion
product rule
ensemble learning
source device identification (SDI)
multimodal
title On Combining Deep Neural Network Classifiers for Source Device Identification
title_full On Combining Deep Neural Network Classifiers for Source Device Identification
title_fullStr On Combining Deep Neural Network Classifiers for Source Device Identification
title_full_unstemmed On Combining Deep Neural Network Classifiers for Source Device Identification
title_short On Combining Deep Neural Network Classifiers for Source Device Identification
title_sort on combining deep neural network classifiers for source device identification
topic Classifier combination
fusion
product rule
ensemble learning
source device identification (SDI)
multimodal
url https://ieeexplore.ieee.org/document/10942326/
work_keys_str_mv AT ioannistsingalis oncombiningdeepneuralnetworkclassifiersforsourcedeviceidentification
AT constantinekotropoulos oncombiningdeepneuralnetworkclassifiersforsourcedeviceidentification