Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Nouboukpo, A.; Allili, M. S.
Semi-supervised flow-augmented Gaussian mixture VAEs with weighted contrastive learning for out-of-distribution detection Journal Article
In: Knowledge-Based Systems, vol. 347, 2026, ISSN: 09507051 (ISSN).
Abstract | Links | BibTeX | Tags: Auto encoders, Benchmarking, Classification (of information), Clusterings, Contrastive Learning, Flow based, Flow-based GMM clustering, Gaussian distribution, Gaussian-mixtures, Learning algorithms, Learning systems, Out-of-distribution detection, Semantics, Semi-supervised, Semi-supervised learning, uncertainty, Variational autoencoder, Variational autoencoders (VAEs)
@article{nouboukpoSemisupervisedFlowaugmentedGaussian2026,
title = {Semi-supervised flow-augmented Gaussian mixture VAEs with weighted contrastive learning for out-of-distribution detection},
author = {A. Nouboukpo and M. S. Allili},
url = {https://www.scopus.com/pages/publications/105040505017?origin=resultslist},
doi = {10.1016/j.knosys.2026.116312},
issn = {09507051 (ISSN)},
year = {2026},
date = {2026-01-01},
journal = {Knowledge-Based Systems},
volume = {347},
publisher = {Elsevier B.V.},
abstract = {Out-of-distribution (OOD) detection is essential for the safe deployment of machine learning systems, particularly in high-stakes domains where identifying inputs that deviate from the in-distribution (ID) is critical. However, in real-world scenarios, true OOD data are typically unavailable at training time, and only auxiliary datasets acting as imperfect proxies can be used. This makes fully supervised approaches impractical and potentially biased toward specific anomaly types. To address this limitation, we propose FLoW-ssGMVAE, a semi-supervised generative–discriminative framework that leverages limited proxy anomaly supervision together with abundant unlabeled data for robust OOD detection. Our model integrates a flow-augmented Gaussian Mixture VAE, enabling flexible latent modeling that captures nonlinear and multimodal intra-class distributions. Unlike standard VAEs with unimodal Gaussian priors, it uses class-conditional normalizing flows to better represent complex ID and OOD variability. To further refine the latent space and strengthen ID/OOD separation, our model integrates a weighted contrastive learning objective guided by sample-wise attention scores derived from likelihood uncertainty. This mechanism emphasizes ambiguous or hard-to-classify instances, reinforcing semantic boundaries and reducing false detections. By combining expressive generative modeling with uncertainty-aware discriminative training, our method constructs a structured and interpretable latent space that reliably identifies OOD samples under limited supervision. Experiments on standard benchmarks validate the effectiveness and scalability of our approach, demonstrating state-of-the-art performance with reasonable computational cost. Our implementation will be available at: FLoW-ssGMVAE. © 2026},
keywords = {Auto encoders, Benchmarking, Classification (of information), Clusterings, Contrastive Learning, Flow based, Flow-based GMM clustering, Gaussian distribution, Gaussian-mixtures, Learning algorithms, Learning systems, Out-of-distribution detection, Semantics, Semi-supervised, Semi-supervised learning, uncertainty, Variational autoencoder, Variational autoencoders (VAEs)},
pubstate = {published},
tppubtype = {article}
}
Out-of-distribution (OOD) detection is essential for the safe deployment of machine learning systems, particularly in high-stakes domains where identifying inputs that deviate from the in-distribution (ID) is critical. However, in real-world scenarios, true OOD data are typically unavailable at training time, and only auxiliary datasets acting as imperfect proxies can be used. This makes fully supervised approaches impractical and potentially biased toward specific anomaly types. To address this limitation, we propose FLoW-ssGMVAE, a semi-supervised generative–discriminative framework that leverages limited proxy anomaly supervision together with abundant unlabeled data for robust OOD detection. Our model integrates a flow-augmented Gaussian Mixture VAE, enabling flexible latent modeling that captures nonlinear and multimodal intra-class distributions. Unlike standard VAEs with unimodal Gaussian priors, it uses class-conditional normalizing flows to better represent complex ID and OOD variability. To further refine the latent space and strengthen ID/OOD separation, our model integrates a weighted contrastive learning objective guided by sample-wise attention scores derived from likelihood uncertainty. This mechanism emphasizes ambiguous or hard-to-classify instances, reinforcing semantic boundaries and reducing false detections. By combining expressive generative modeling with uncertainty-aware discriminative training, our method constructs a structured and interpretable latent space that reliably identifies OOD samples under limited supervision. Experiments on standard benchmarks validate the effectiveness and scalability of our approach, demonstrating state-of-the-art performance with reasonable computational cost. Our implementation will be available at: FLoW-ssGMVAE. © 2026
2.
Sadfi, Y.; Amamou, H.; Davoust, A.; Avila, A. R.
Comparative Analysis of Machine Learning, LLMs, and RAG for Fake News Detection Proceedings Article
In: IEEE Conf. Artif. Intell., CAI, pp. 2128–2133, Institute of Electrical and Electronics Engineers Inc., 2026, ISBN: 979-833156039-3 (ISBN), (Journal Abbreviation: IEEE Conf. Artif. Intell., CAI).
Abstract | Links | BibTeX | Tags: Classification (of information), Comparative analyzes, Comprehensive assessment, decision making, Decision-making process, Fake detection, Generalisation, High-accuracy, Language model, Learning algorithms, Learning systems, Machine learning, Machine learning algorithms, Machine-learning, Network platforms, Performance
@inproceedings{sadfiComparativeAnalysisMachine2026,
title = {Comparative Analysis of Machine Learning, LLMs, and RAG for Fake News Detection},
author = {Y. Sadfi and H. Amamou and A. Davoust and A. R. Avila},
url = {https://www.scopus.com/pages/publications/105042025800?origin=resultslist},
doi = {10.1109/CAI68641.2026.11536343},
isbn = {979-833156039-3 (ISBN)},
year = {2026},
date = {2026-01-01},
booktitle = {IEEE Conf. Artif. Intell., CAI},
pages = {2128–2133},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The rapid spread of misinformation on social network platforms poses a serious threat to the decision-making processes in democratic societies. To mitigate the problem and cope with new misinformation scenarios several datasets have been proposed, followed by the emergence of new methods for detecting fake news. While several comparative analyses have been proposed to benchmark these solutions, the ever-growing development of new methods requires up-to-date analysis. For instance, recent approaches based on retrieval-augmented generation (RAG) have yet to be assessed and compared to previous methods used for fake news detection. In this study, we aim to fill this gap by presenting a comprehensive assessment of classical machine learning (ML) algorithms, Transformer-based models, such as BERT, large language models (LLMs), and RAG-based classifiers. We adopt four traditional fake news datasets, including a Portuguese one. Results indicate that classical ML and BERT deliver strong performance on in-domain tasks, demonstrating efficiency and high accuracy. RAG-augmented LLMs, on the other hand, offer enhanced generalization and robustness in cross-domain and cross-dataset settings, but are outperformed by traditional approaches for in-domain evaluation. © 2026 IEEE.},
note = {Journal Abbreviation: IEEE Conf. Artif. Intell., CAI},
keywords = {Classification (of information), Comparative analyzes, Comprehensive assessment, decision making, Decision-making process, Fake detection, Generalisation, High-accuracy, Language model, Learning algorithms, Learning systems, Machine learning, Machine learning algorithms, Machine-learning, Network platforms, Performance},
pubstate = {published},
tppubtype = {inproceedings}
}
The rapid spread of misinformation on social network platforms poses a serious threat to the decision-making processes in democratic societies. To mitigate the problem and cope with new misinformation scenarios several datasets have been proposed, followed by the emergence of new methods for detecting fake news. While several comparative analyses have been proposed to benchmark these solutions, the ever-growing development of new methods requires up-to-date analysis. For instance, recent approaches based on retrieval-augmented generation (RAG) have yet to be assessed and compared to previous methods used for fake news detection. In this study, we aim to fill this gap by presenting a comprehensive assessment of classical machine learning (ML) algorithms, Transformer-based models, such as BERT, large language models (LLMs), and RAG-based classifiers. We adopt four traditional fake news datasets, including a Portuguese one. Results indicate that classical ML and BERT deliver strong performance on in-domain tasks, demonstrating efficiency and high accuracy. RAG-augmented LLMs, on the other hand, offer enhanced generalization and robustness in cross-domain and cross-dataset settings, but are outperformed by traditional approaches for in-domain evaluation. © 2026 IEEE.
3.
Moudoud, H.; Houda, Z. A. El; Khoukhi, L.; Mouftah, H. T.
An SDN-based Adaptive Ensemble Learning Framework for Intrusion Mitigation in Wireless Networks Proceedings Article
In: M., Valenti; D., Reed; M., Torres (Ed.): IEEE Int Conf Commun, pp. 554–559, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 15503607 (ISSN); 979-833150521-9 (ISBN), (Journal Abbreviation: IEEE Int Conf Commun).
Abstract | Links | BibTeX | Tags: Aerial vehicle, Antennas, Artificial intelligence, Computer crime, Ensemble learning, Intrusion Detection, Intrusion Detection Systems, Jamming, Jamming Attacks, Learning algorithms, Learning frameworks, Network intrusion, Network operations, Radio communication, Security systems, Security threats, Sensors network, Unmanned aerial vehicle, Unmanned Aerial Vehicles, Unmanned aerial vehicles (UAV), Wireless networks, Wireless sensor, Wireless Sensor Networks, Zero-day attack
@inproceedings{moudoudSDNbasedAdaptiveEnsemble2025,
title = {An SDN-based Adaptive Ensemble Learning Framework for Intrusion Mitigation in Wireless Networks},
author = {H. Moudoud and Z. A. El Houda and L. Khoukhi and H. T. Mouftah},
editor = {Valenti M. and Reed D. and Torres M.},
url = {https://www.scopus.com/pages/publications/105018460686?origin=resultslist},
doi = {10.1109/ICC52391.2025.11161745},
isbn = {15503607 (ISSN); 979-833150521-9 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {IEEE Int Conf Commun},
pages = {554–559},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Jamming attacks are among the most critical security threats to Wireless Sensor Networks (WSNs), as they can severely disrupt normal network operations, leading to data loss, network downtime, and reduced system performance. Intrusion Detection Systems (IDSs) have therefore become essential to protect WSNs. However, conventional IDSs often struggle to detect zero-day attacks, creating a significant security gap. To address this, Artificial Intelligence (AI)-based IDSs have been introduced, offering improved detection capabilities but frequently encountering high bias or variance issues, which reduce their reliability. Recently, ensemble learning (EL) has emerged as a promising approach to build more adaptable and data-resilient models by combining multiple learning algorithms. In this context, we propose AdaptiveBoost, an SDN-based Adaptive Ensemble Learning Framework, specifically designed for effective jamming attack detection in WSNs. The SDN integration allows AdaptiveBoost to optimize network traffic flow, identify anomalies in real-time, and adaptively fine-tune detection mechanisms based on current network conditions. We conduct several experiments to evaluate AdaptiveBoost using real-world WSN attacks; using the well-known public network security dataset, WSN-DS, show that AdaptiveBoost outperforms AI-based algorithms in terms of accuracy, precision, recall, and F1 score, while achieving a remarkable reduction in training time by a factor of 235, making it an efficient, scalable solution for securing WSNs against jamming attacks. © 2025 IEEE.},
note = {Journal Abbreviation: IEEE Int Conf Commun},
keywords = {Aerial vehicle, Antennas, Artificial intelligence, Computer crime, Ensemble learning, Intrusion Detection, Intrusion Detection Systems, Jamming, Jamming Attacks, Learning algorithms, Learning frameworks, Network intrusion, Network operations, Radio communication, Security systems, Security threats, Sensors network, Unmanned aerial vehicle, Unmanned Aerial Vehicles, Unmanned aerial vehicles (UAV), Wireless networks, Wireless sensor, Wireless Sensor Networks, Zero-day attack},
pubstate = {published},
tppubtype = {inproceedings}
}
Jamming attacks are among the most critical security threats to Wireless Sensor Networks (WSNs), as they can severely disrupt normal network operations, leading to data loss, network downtime, and reduced system performance. Intrusion Detection Systems (IDSs) have therefore become essential to protect WSNs. However, conventional IDSs often struggle to detect zero-day attacks, creating a significant security gap. To address this, Artificial Intelligence (AI)-based IDSs have been introduced, offering improved detection capabilities but frequently encountering high bias or variance issues, which reduce their reliability. Recently, ensemble learning (EL) has emerged as a promising approach to build more adaptable and data-resilient models by combining multiple learning algorithms. In this context, we propose AdaptiveBoost, an SDN-based Adaptive Ensemble Learning Framework, specifically designed for effective jamming attack detection in WSNs. The SDN integration allows AdaptiveBoost to optimize network traffic flow, identify anomalies in real-time, and adaptively fine-tune detection mechanisms based on current network conditions. We conduct several experiments to evaluate AdaptiveBoost using real-world WSN attacks; using the well-known public network security dataset, WSN-DS, show that AdaptiveBoost outperforms AI-based algorithms in terms of accuracy, precision, recall, and F1 score, while achieving a remarkable reduction in training time by a factor of 235, making it an efficient, scalable solution for securing WSNs against jamming attacks. © 2025 IEEE.
4.
Soltani, N.; Nejadshamsi, S.; Houda, Z. A. El; Khoury, R.; Costa, K. A. P.; Falk, T. H.; Avila, A. R.
Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks Proceedings Article
In: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern., pp. 39–44, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 1062922X (ISSN); 979-833153358-8 (ISBN), (Journal Abbreviation: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.).
Abstract | Links | BibTeX | Tags: Adversarial machine learning, Adversarial networks, Classification (of information), Computer crime, Fast gradient sign method, Fast Gradient Sign Method (FGSM), Generative adversarial network, Generative Adversarial Network (GAN), Generative adversarial networks, Generative model, Generative Models, Intrusion Detection, Intrusion-Detection, Learning algorithms, Learning systems, Machine-learning, Multi-layers, Network intrusion, Network intrusion detection systems, Network layers, Network security, Second layer, Stackings
@inproceedings{soltaniEnhancingNetworkIntrusion2025,
title = {Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks},
author = {N. Soltani and S. Nejadshamsi and Z. A. El Houda and R. Khoury and K. A. P. Costa and T. H. Falk and A. R. Avila},
url = {https://www.scopus.com/pages/publications/105033159769?origin=resultslist},
doi = {10.1109/SMC58881.2025.11342479},
isbn = {1062922X (ISSN); 979-833153358-8 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
pages = {39–44},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems (NIDS), they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS towards adversarial attacks. To that end, we explore two adversarial methods for generating malicious network traffic. The first method is based on Generative Adversarial Networks (GAN) and the second one is the Fast Gradient Sign Method (FGSM). The adversarial examples generated by these methods are then used to evaluate a novel multilayer defense mechanism, specifically designed to mitigate the vulnerability of ML-based NIDS. Our solution consists of one layer of stacking classifiers and a second layer based on an autoencoder. If the incoming network data are classified as benign by the first layer, the second layer is activated to ensure that the decision made by the stacking classifier is correct. We also incorporated adversarial training to further improve the robustness of our solution. Experiments on two datasets, namely UNSW-NB15 and NSL-KDD, demonstrate that the proposed approach increases resilience to adversarial attacks. © 2025 IEEE.},
note = {Journal Abbreviation: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
keywords = {Adversarial machine learning, Adversarial networks, Classification (of information), Computer crime, Fast gradient sign method, Fast Gradient Sign Method (FGSM), Generative adversarial network, Generative Adversarial Network (GAN), Generative adversarial networks, Generative model, Generative Models, Intrusion Detection, Intrusion-Detection, Learning algorithms, Learning systems, Machine-learning, Multi-layers, Network intrusion, Network intrusion detection systems, Network layers, Network security, Second layer, Stackings},
pubstate = {published},
tppubtype = {inproceedings}
}
Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems (NIDS), they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS towards adversarial attacks. To that end, we explore two adversarial methods for generating malicious network traffic. The first method is based on Generative Adversarial Networks (GAN) and the second one is the Fast Gradient Sign Method (FGSM). The adversarial examples generated by these methods are then used to evaluate a novel multilayer defense mechanism, specifically designed to mitigate the vulnerability of ML-based NIDS. Our solution consists of one layer of stacking classifiers and a second layer based on an autoencoder. If the incoming network data are classified as benign by the first layer, the second layer is activated to ensure that the decision made by the stacking classifier is correct. We also incorporated adversarial training to further improve the robustness of our solution. Experiments on two datasets, namely UNSW-NB15 and NSL-KDD, demonstrate that the proposed approach increases resilience to adversarial attacks. © 2025 IEEE.
5.
Joudeh, I. O.; Cretu, A. -M.; Bouchard, S.
Predicting the Arousal and Valence Values of Emotional States Using Learned, Predesigned, and Deep Visual Features † Journal Article
In: Sensors, vol. 24, no. 13, 2024, ISSN: 14248220 (ISSN), (Publisher: Multidisciplinary Digital Publishing Institute (MDPI)).
Abstract | Links | BibTeX | Tags: adult, Affective interaction, Arousal, artificial neural network, Cognitive state, Cognitive/emotional state, Collaborative interaction, computer, Convolutional neural networks, correlation coefficient, Deep learning, emotion, Emotional state, Emotions, female, Forecasting, Helmet mounted displays, human, Humans, Learning algorithms, Learning systems, Long short-term memory, Machine learning, Machine-learning, male, Mean square error, Neural networks, physiology, Regression, Root mean squared errors, Video recording, virtual reality, Visual feature, visual features
@article{joudeh_predicting_2024,
title = {Predicting the Arousal and Valence Values of Emotional States Using Learned, Predesigned, and Deep Visual Features †},
author = {I. O. Joudeh and A. -M. Cretu and S. Bouchard},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198382238&doi=10.3390%2fs24134398&partnerID=40&md5=cefa8b2e2c044d02f99662af350007db},
doi = {10.3390/s24134398},
issn = {14248220 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {Sensors},
volume = {24},
number = {13},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
abstract = {The cognitive state of a person can be categorized using the circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. The purpose of this research is to select a machine learning model(s) to be integrated into a virtual reality (VR) system that runs cognitive remediation exercises for people with mental health disorders. As such, the prediction of emotional states is essential to customize treatments for those individuals. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database to predict arousal and valence values using machine learning techniques. RECOLA includes audio, video, and physiological recordings of interactions between human participants. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned, learned, or extracted implicitly using deep learners. Our previous work on video recordings focused on predesigned and learned visual features. In this paper, we extend our work onto deep visual features. Our deep visual features are extracted using the MobileNet-v2 convolutional neural network (CNN) that we previously trained on RECOLA’s video frames of full/half faces. As the final purpose of our work is to integrate our solution into a practical VR application using head-mounted displays, we experimented with half faces as a proof of concept. The extracted deep features were then used to predict arousal and valence values via optimizable ensemble regression. We also fused the extracted visual features with the predesigned visual features and predicted arousal and valence values using the combined feature set. In an attempt to enhance our prediction performance, we further fused the predictions of the optimizable ensemble model with the predictions of the MobileNet-v2 model. After decision fusion, we achieved a root mean squared error (RMSE) of 0.1140, a Pearson’s correlation coefficient (PCC) of 0.8000, and a concordance correlation coefficient (CCC) of 0.7868 on arousal predictions. We achieved an RMSE of 0.0790, a PCC of 0.7904, and a CCC of 0.7645 on valence predictions. © 2024 by the authors.},
note = {Publisher: Multidisciplinary Digital Publishing Institute (MDPI)},
keywords = {adult, Affective interaction, Arousal, artificial neural network, Cognitive state, Cognitive/emotional state, Collaborative interaction, computer, Convolutional neural networks, correlation coefficient, Deep learning, emotion, Emotional state, Emotions, female, Forecasting, Helmet mounted displays, human, Humans, Learning algorithms, Learning systems, Long short-term memory, Machine learning, Machine-learning, male, Mean square error, Neural networks, physiology, Regression, Root mean squared errors, Video recording, virtual reality, Visual feature, visual features},
pubstate = {published},
tppubtype = {article}
}
The cognitive state of a person can be categorized using the circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. The purpose of this research is to select a machine learning model(s) to be integrated into a virtual reality (VR) system that runs cognitive remediation exercises for people with mental health disorders. As such, the prediction of emotional states is essential to customize treatments for those individuals. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database to predict arousal and valence values using machine learning techniques. RECOLA includes audio, video, and physiological recordings of interactions between human participants. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned, learned, or extracted implicitly using deep learners. Our previous work on video recordings focused on predesigned and learned visual features. In this paper, we extend our work onto deep visual features. Our deep visual features are extracted using the MobileNet-v2 convolutional neural network (CNN) that we previously trained on RECOLA’s video frames of full/half faces. As the final purpose of our work is to integrate our solution into a practical VR application using head-mounted displays, we experimented with half faces as a proof of concept. The extracted deep features were then used to predict arousal and valence values via optimizable ensemble regression. We also fused the extracted visual features with the predesigned visual features and predicted arousal and valence values using the combined feature set. In an attempt to enhance our prediction performance, we further fused the predictions of the optimizable ensemble model with the predictions of the MobileNet-v2 model. After decision fusion, we achieved a root mean squared error (RMSE) of 0.1140, a Pearson’s correlation coefficient (PCC) of 0.8000, and a concordance correlation coefficient (CCC) of 0.7868 on arousal predictions. We achieved an RMSE of 0.0790, a PCC of 0.7904, and a CCC of 0.7645 on valence predictions. © 2024 by the authors.
6.
Joudeh, I. O.; Cretu, A. -M.; Bouchard, S.
Predicting the Arousal and Valence Values of Emotional States Using Learned, Predesigned, and Deep Visual Features † Journal Article
In: Sensors, vol. 24, no. 13, 2024, ISSN: 14248220 (ISSN).
Abstract | Links | BibTeX | Tags: adult, Affective interaction, Arousal, artificial neural network, Cognitive state, Cognitive/emotional state, Collaborative interaction, computer, Convolutional neural networks, correlation coefficient, Deep learning, emotion, Emotional state, Emotions, female, Forecasting, Helmet mounted displays, human, Humans, Learning algorithms, Learning systems, Long short-term memory, Machine learning, Machine-learning, male, Mean square error, Neural networks, physiology, Regression, Root mean squared errors, Video recording, virtual reality, Visual feature, visual features
@article{joudehPredictingArousalValence2024,
title = {Predicting the Arousal and Valence Values of Emotional States Using Learned, Predesigned, and Deep Visual Features †},
author = {I. O. Joudeh and A. -M. Cretu and S. Bouchard},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198382238&doi=10.3390%2fs24134398&partnerID=40&md5=cefa8b2e2c044d02f99662af350007db},
doi = {10.3390/s24134398},
issn = {14248220 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {Sensors},
volume = {24},
number = {13},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
abstract = {The cognitive state of a person can be categorized using the circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. The purpose of this research is to select a machine learning model(s) to be integrated into a virtual reality (VR) system that runs cognitive remediation exercises for people with mental health disorders. As such, the prediction of emotional states is essential to customize treatments for those individuals. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database to predict arousal and valence values using machine learning techniques. RECOLA includes audio, video, and physiological recordings of interactions between human participants. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned, learned, or extracted implicitly using deep learners. Our previous work on video recordings focused on predesigned and learned visual features. In this paper, we extend our work onto deep visual features. Our deep visual features are extracted using the MobileNet-v2 convolutional neural network (CNN) that we previously trained on RECOLA’s video frames of full/half faces. As the final purpose of our work is to integrate our solution into a practical VR application using head-mounted displays, we experimented with half faces as a proof of concept. The extracted deep features were then used to predict arousal and valence values via optimizable ensemble regression. We also fused the extracted visual features with the predesigned visual features and predicted arousal and valence values using the combined feature set. In an attempt to enhance our prediction performance, we further fused the predictions of the optimizable ensemble model with the predictions of the MobileNet-v2 model. After decision fusion, we achieved a root mean squared error (RMSE) of 0.1140, a Pearson’s correlation coefficient (PCC) of 0.8000, and a concordance correlation coefficient (CCC) of 0.7868 on arousal predictions. We achieved an RMSE of 0.0790, a PCC of 0.7904, and a CCC of 0.7645 on valence predictions. © 2024 by the authors.},
keywords = {adult, Affective interaction, Arousal, artificial neural network, Cognitive state, Cognitive/emotional state, Collaborative interaction, computer, Convolutional neural networks, correlation coefficient, Deep learning, emotion, Emotional state, Emotions, female, Forecasting, Helmet mounted displays, human, Humans, Learning algorithms, Learning systems, Long short-term memory, Machine learning, Machine-learning, male, Mean square error, Neural networks, physiology, Regression, Root mean squared errors, Video recording, virtual reality, Visual feature, visual features},
pubstate = {published},
tppubtype = {article}
}
The cognitive state of a person can be categorized using the circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. The purpose of this research is to select a machine learning model(s) to be integrated into a virtual reality (VR) system that runs cognitive remediation exercises for people with mental health disorders. As such, the prediction of emotional states is essential to customize treatments for those individuals. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database to predict arousal and valence values using machine learning techniques. RECOLA includes audio, video, and physiological recordings of interactions between human participants. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned, learned, or extracted implicitly using deep learners. Our previous work on video recordings focused on predesigned and learned visual features. In this paper, we extend our work onto deep visual features. Our deep visual features are extracted using the MobileNet-v2 convolutional neural network (CNN) that we previously trained on RECOLA’s video frames of full/half faces. As the final purpose of our work is to integrate our solution into a practical VR application using head-mounted displays, we experimented with half faces as a proof of concept. The extracted deep features were then used to predict arousal and valence values via optimizable ensemble regression. We also fused the extracted visual features with the predesigned visual features and predicted arousal and valence values using the combined feature set. In an attempt to enhance our prediction performance, we further fused the predictions of the optimizable ensemble model with the predictions of the MobileNet-v2 model. After decision fusion, we achieved a root mean squared error (RMSE) of 0.1140, a Pearson’s correlation coefficient (PCC) of 0.8000, and a concordance correlation coefficient (CCC) of 0.7868 on arousal predictions. We achieved an RMSE of 0.0790, a PCC of 0.7904, and a CCC of 0.7645 on valence predictions. © 2024 by the authors.
7.
Yapi, D.; Mejri, M.; Allili, M. S.; Baaziz, N.
A learning-based approach for automatic defect detection in textile images Proceedings Article
In: A., Zaremba M. Sasiadek J. Dolgui (Ed.): IFAC-PapersOnLine, pp. 2423–2428, 2015, ISBN: 24058963 (ISSN), (Journal Abbreviation: IFAC-PapersOnLine).
Abstract | Links | BibTeX | Tags: Algorithms, Artificial intelligence, Automatic defect detections, Barium compounds, Bayes Classifier, Computational efficiency, Contourlets, Defect detection, Defect detection algorithm, Defects, Detection problems, Feature extraction, Feature extraction and classification, Gaussians, Image classification, Learning algorithms, Learning systems, Learning-based approach, Machine learning approaches, Mixture of generalized gaussians, Mixtures of generalized Gaussians (MoGG), Textile defect detection, Textile images, Textiles, Textures
@inproceedings{yapi_learning-based_2015,
title = {A learning-based approach for automatic defect detection in textile images},
author = {D. Yapi and M. Mejri and M. S. Allili and N. Baaziz},
editor = {Zaremba M. Sasiadek J. Dolgui A.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84953865559&doi=10.1016%2fj.ifacol.2015.06.451&partnerID=40&md5=3dd0ef4c27cbd55700f6511af5f46772},
doi = {10.1016/j.ifacol.2015.06.451},
isbn = {24058963 (ISSN)},
year = {2015},
date = {2015-01-01},
booktitle = {IFAC-PapersOnLine},
volume = {28},
number = {3},
pages = {2423–2428},
abstract = {This paper addresses the textile defect detection problem using a machine-learning approach. We propose a novel algorithm that uses supervised learning to classify textile textures in defect and non-defect classes based on suitable feature extraction and classification. We use statistical modeling of multi-scale contourlet image decomposition to obtain compact and accurate signatures for texture description. Our defect detection algorithm is based on two phases. In the first phase, using a training set of images, we extract reference defect-free signatures for each textile category. Then, we use the Bayes classifier (BC) to learn signatures of defected and non-defected classes. In the second phase, defects are detected on new images using the trained BC and an appropriate decomposition of images into blocks. Our algorithm has the capability to achieve highly accurate defect detection and localisation in textile textures while ensuring an efficient computational time. Compared to recent state-of-the-art methods, our algorithm has yielded better results on the standard TILDA database. © 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.},
note = {Journal Abbreviation: IFAC-PapersOnLine},
keywords = {Algorithms, Artificial intelligence, Automatic defect detections, Barium compounds, Bayes Classifier, Computational efficiency, Contourlets, Defect detection, Defect detection algorithm, Defects, Detection problems, Feature extraction, Feature extraction and classification, Gaussians, Image classification, Learning algorithms, Learning systems, Learning-based approach, Machine learning approaches, Mixture of generalized gaussians, Mixtures of generalized Gaussians (MoGG), Textile defect detection, Textile images, Textiles, Textures},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper addresses the textile defect detection problem using a machine-learning approach. We propose a novel algorithm that uses supervised learning to classify textile textures in defect and non-defect classes based on suitable feature extraction and classification. We use statistical modeling of multi-scale contourlet image decomposition to obtain compact and accurate signatures for texture description. Our defect detection algorithm is based on two phases. In the first phase, using a training set of images, we extract reference defect-free signatures for each textile category. Then, we use the Bayes classifier (BC) to learn signatures of defected and non-defected classes. In the second phase, defects are detected on new images using the trained BC and an appropriate decomposition of images into blocks. Our algorithm has the capability to achieve highly accurate defect detection and localisation in textile textures while ensuring an efficient computational time. Compared to recent state-of-the-art methods, our algorithm has yielded better results on the standard TILDA database. © 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.
8.
Yapi, D.; Mejri, M.; Allili, M. S.; Baaziz, N.
A learning-based approach for automatic defect detection in textile images Proceedings Article
In: A., Zaremba M. Sasiadek J. Dolgui (Ed.): IFAC-PapersOnLine, pp. 2423–2428, 2015, ISBN: 24058963 (ISSN), (Journal Abbreviation: IFAC-PapersOnLine).
Abstract | Links | BibTeX | Tags: Algorithms, Artificial intelligence, Automatic defect detections, Barium compounds, Bayes Classifier, Computational efficiency, Contourlets, Defect detection, Defect detection algorithm, Defects, Detection problems, Feature extraction, Feature extraction and classification, Gaussians, Image classification, Learning algorithms, Learning systems, Learning-based approach, Machine learning approaches, Mixture of generalized gaussians, Mixtures of generalized Gaussians (MoGG), Textile defect detection, Textile images, Textiles, Textures
@inproceedings{yapiLearningbasedApproachAutomatic2015,
title = {A learning-based approach for automatic defect detection in textile images},
author = {D. Yapi and M. Mejri and M. S. Allili and N. Baaziz},
editor = {Zaremba M. Sasiadek J. Dolgui A.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84953865559&doi=10.1016%2fj.ifacol.2015.06.451&partnerID=40&md5=3dd0ef4c27cbd55700f6511af5f46772},
doi = {10.1016/j.ifacol.2015.06.451},
isbn = {24058963 (ISSN)},
year = {2015},
date = {2015-01-01},
booktitle = {IFAC-PapersOnLine},
volume = {28},
number = {3},
pages = {2423–2428},
abstract = {This paper addresses the textile defect detection problem using a machine-learning approach. We propose a novel algorithm that uses supervised learning to classify textile textures in defect and non-defect classes based on suitable feature extraction and classification. We use statistical modeling of multi-scale contourlet image decomposition to obtain compact and accurate signatures for texture description. Our defect detection algorithm is based on two phases. In the first phase, using a training set of images, we extract reference defect-free signatures for each textile category. Then, we use the Bayes classifier (BC) to learn signatures of defected and non-defected classes. In the second phase, defects are detected on new images using the trained BC and an appropriate decomposition of images into blocks. Our algorithm has the capability to achieve highly accurate defect detection and localisation in textile textures while ensuring an efficient computational time. Compared to recent state-of-the-art methods, our algorithm has yielded better results on the standard TILDA database. © 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.},
note = {Journal Abbreviation: IFAC-PapersOnLine},
keywords = {Algorithms, Artificial intelligence, Automatic defect detections, Barium compounds, Bayes Classifier, Computational efficiency, Contourlets, Defect detection, Defect detection algorithm, Defects, Detection problems, Feature extraction, Feature extraction and classification, Gaussians, Image classification, Learning algorithms, Learning systems, Learning-based approach, Machine learning approaches, Mixture of generalized gaussians, Mixtures of generalized Gaussians (MoGG), Textile defect detection, Textile images, Textiles, Textures},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper addresses the textile defect detection problem using a machine-learning approach. We propose a novel algorithm that uses supervised learning to classify textile textures in defect and non-defect classes based on suitable feature extraction and classification. We use statistical modeling of multi-scale contourlet image decomposition to obtain compact and accurate signatures for texture description. Our defect detection algorithm is based on two phases. In the first phase, using a training set of images, we extract reference defect-free signatures for each textile category. Then, we use the Bayes classifier (BC) to learn signatures of defected and non-defected classes. In the second phase, defects are detected on new images using the trained BC and an appropriate decomposition of images into blocks. Our algorithm has the capability to achieve highly accurate defect detection and localisation in textile textures while ensuring an efficient computational time. Compared to recent state-of-the-art methods, our algorithm has yielded better results on the standard TILDA database. © 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.