Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Abdollahi, M.; Zhu, Y.; Guimãraes, H. R.; Coallier, N.; Maucourt, S.; Giovenazzo, P.; Falk, T. H.
On the Prediction of Varroa Mite Infestations in Honey Bee Colonies via Acoustic Monitoring Journal Article
In: IEEE Sensors Journal, vol. 26, no. 8, pp. 12157–12167, 2026, ISSN: 1530437X (ISSN).
Abstract | Links | BibTeX | Tags: Acoustic measuring instruments, Acoustic monitoring, Acoustic variables measurement, Acoustics, Beehive acoustic, Beehive acoustics, Ecosystems, Food products, Honey bee, honey bees, Honeybee colonies, Learning systems, Machine learning approaches, Modulation spectrogram, Motion compensation, Nearest neighbor search, Parasite-, Random forests, Sanitary sewers, Spectrograms, Spectrographs, Support vector machines, Varroa destructor, Varroa mite infestation
@article{abdollahiPredictionVarroaMite2026,
title = {On the Prediction of Varroa Mite Infestations in Honey Bee Colonies via Acoustic Monitoring},
author = {M. Abdollahi and Y. Zhu and H. R. Guimãraes and N. Coallier and S. Maucourt and P. Giovenazzo and T. H. Falk},
url = {https://www.scopus.com/pages/publications/105031477347?origin=resultslist},
doi = {10.1109/JSEN.2026.3666127},
issn = {1530437X (ISSN)},
year = {2026},
date = {2026-01-01},
journal = {IEEE Sensors Journal},
volume = {26},
number = {8},
pages = {12157–12167},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Honey bees play a vital role in global ecosystems and agriculture through their pollination services. However, the Varroa destructor mite remains one of the most damaging parasites affecting honey bee health, contributing significantly to colony decline. Early detection of Varroa infestation is essential for effective beekeeping management. In this study, we propose a machine learning approach for predicting Varroa mite infestation levels based on the acoustic analysis of hive recordings. We introduce a set of nine spectral shape descriptors (SSDs) computed from conventional and modulation spectrograms to characterize the acoustic environment within hives. We evaluate the predictive power of these features against traditional cepstral features across multiple classifiers, including support vector machines (SVMs), random forests (RFs), and k-nearest neighbors (KNNs). Our results demonstrate that the proposed SSDs significantly improve the classification performance relative to conventional features across numerous figures of merit, particularly in hive-independent test settings. This work highlights the potential of spectral acoustic monitoring combined with the supervised learning as a scalable and noninvasive tool for precision beekeeping and early detection of parasitic threats. © 2001-2012 IEEE.},
keywords = {Acoustic measuring instruments, Acoustic monitoring, Acoustic variables measurement, Acoustics, Beehive acoustic, Beehive acoustics, Ecosystems, Food products, Honey bee, honey bees, Honeybee colonies, Learning systems, Machine learning approaches, Modulation spectrogram, Motion compensation, Nearest neighbor search, Parasite-, Random forests, Sanitary sewers, Spectrograms, Spectrographs, Support vector machines, Varroa destructor, Varroa mite infestation},
pubstate = {published},
tppubtype = {article}
}
Honey bees play a vital role in global ecosystems and agriculture through their pollination services. However, the Varroa destructor mite remains one of the most damaging parasites affecting honey bee health, contributing significantly to colony decline. Early detection of Varroa infestation is essential for effective beekeeping management. In this study, we propose a machine learning approach for predicting Varroa mite infestation levels based on the acoustic analysis of hive recordings. We introduce a set of nine spectral shape descriptors (SSDs) computed from conventional and modulation spectrograms to characterize the acoustic environment within hives. We evaluate the predictive power of these features against traditional cepstral features across multiple classifiers, including support vector machines (SVMs), random forests (RFs), and k-nearest neighbors (KNNs). Our results demonstrate that the proposed SSDs significantly improve the classification performance relative to conventional features across numerous figures of merit, particularly in hive-independent test settings. This work highlights the potential of spectral acoustic monitoring combined with the supervised learning as a scalable and noninvasive tool for precision beekeeping and early detection of parasitic threats. © 2001-2012 IEEE.
2.
Soultana, O. A.; Moudoud, H.
Adaptive Heterogeneous Ensemble Learning for Attack Detection in IoT Networks Proceedings Article
In: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern., pp. 27–32, 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: Attack detection, Classification (of information), Computational efficiency, Detection accuracy, Ensemble learning, Ensemble techniques, Heterogeneous ensembles, Internet of thing security, Internet of things, Intrusion Detection, Intrusion-Detection, IoT Security, Learning systems, Nearest neighbor search, Security vulnerabilities, Stackings, Support vector machines, Zero-day attack, Zero-day detection
@inproceedings{soultanaAdaptiveHeterogeneousEnsemble2025,
title = {Adaptive Heterogeneous Ensemble Learning for Attack Detection in IoT Networks},
author = {O. A. Soultana and H. Moudoud},
url = {https://www.scopus.com/pages/publications/105033149093?origin=resultslist},
doi = {10.1109/SMC58881.2025.11343130},
isbn = {1062922X (ISSN); 979-833153358-8 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
pages = {27–32},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The proliferation of Internet of Things (IoT) devices has introduced significant security vulnerabilities, particularly in detecting zero-day attacks within highly dynamic and heterogeneous environments. Traditional machine learning models often fall short due to their static nature and computational demands. In this paper, we propose an adaptive ensemble learning framework that dynamically selects optimal detection models on a per-attack-class basis to improve detection accuracy while maintaining computational efficiency. Our approach combines multiple base classifiers (Random Forest, K-Nearest Neighbors, and Support Vector Machine) using ensemble techniques including bagging, boosting, and stacking. Ensemble techniques such as Bagging, Boosting, Voting, and Stacking. The key innovation lies in a class-aware model selection mechanism that identifies the most effective classifier-ensemble combination for each specific attack category, rather than applying a single model across all threat types. This targeted approach recognizes that different attack patterns exhibit distinct characteristics that may be better captured by different algorithmic approaches. Finally, we propose a decision-rule mechanism that selects the best-performing model for each attack class to improve detection accuracy. The proposed framework is evaluated through extensive experiments. The results show that our approach significantly enhances classification performance, especially for complex and rare attack types. © 2025 IEEE.},
note = {Journal Abbreviation: Conf. Proc. IEEE Int. Conf. Syst. Man Cybern.},
keywords = {Attack detection, Classification (of information), Computational efficiency, Detection accuracy, Ensemble learning, Ensemble techniques, Heterogeneous ensembles, Internet of thing security, Internet of things, Intrusion Detection, Intrusion-Detection, IoT Security, Learning systems, Nearest neighbor search, Security vulnerabilities, Stackings, Support vector machines, Zero-day attack, Zero-day detection},
pubstate = {published},
tppubtype = {inproceedings}
}
The proliferation of Internet of Things (IoT) devices has introduced significant security vulnerabilities, particularly in detecting zero-day attacks within highly dynamic and heterogeneous environments. Traditional machine learning models often fall short due to their static nature and computational demands. In this paper, we propose an adaptive ensemble learning framework that dynamically selects optimal detection models on a per-attack-class basis to improve detection accuracy while maintaining computational efficiency. Our approach combines multiple base classifiers (Random Forest, K-Nearest Neighbors, and Support Vector Machine) using ensemble techniques including bagging, boosting, and stacking. Ensemble techniques such as Bagging, Boosting, Voting, and Stacking. The key innovation lies in a class-aware model selection mechanism that identifies the most effective classifier-ensemble combination for each specific attack category, rather than applying a single model across all threat types. This targeted approach recognizes that different attack patterns exhibit distinct characteristics that may be better captured by different algorithmic approaches. Finally, we propose a decision-rule mechanism that selects the best-performing model for each attack class to improve detection accuracy. The proposed framework is evaluated through extensive experiments. The results show that our approach significantly enhances classification performance, especially for complex and rare attack types. © 2025 IEEE.
3.
Lahmiri, S.; Gagnon, S.
A sequential probabilistic system for bankruptcy data classification Book
IGI Global, 2018, ISBN: 978-1-5225-5644-2 1-5225-5643-5 978-1-5225-5643-5, (Publication Title: Intelligent Systems: Concepts, Methodologies, Tools, and Applications).
Abstract | Links | BibTeX | Tags: Bankruptcy prediction, Corporate finance, Data classification, Discriminant analysis, Forecasting, Human resource management, Independent variables, Neural networks, Nonlinear problems, Probabilistic systems, Real-world problem, Soft computing, Softcomputing techniques, Support vector machines
@book{lahmiri_sequential_2018,
title = {A sequential probabilistic system for bankruptcy data classification},
author = {S. Lahmiri and S. Gagnon},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059712022&doi=10.4018%2f978-1-5225-5643-5.ch064&partnerID=40&md5=21c0d2da6087916a6c372529e2b13784},
doi = {10.4018/978-1-5225-5643-5.ch064},
isbn = {978-1-5225-5644-2 1-5225-5643-5 978-1-5225-5643-5},
year = {2018},
date = {2018-01-01},
publisher = {IGI Global},
abstract = {In the last decade, the development of bankruptcy prediction models has been one of important issues in accounting and corporate finance research fields. Indeed, bankruptcy is a critical event that yields important loss to management, shareholders, employees, and also to government. Statistical methods such as discriminant analysis, logistic and probit models were widely used for developing bankruptcy prediction systems. However, statistical-based approaches are assumes strong assumptions including linearity of the relationship among dependent and independent variables, normality of the errors which limit their applicability in bankruptcy real world problems. Recently, machine learning and soft computing techniques including artificial neural networks, support vector machines, and evolutionary intelligence have brought forth new alternatives in solving nonlinear problems with applications in bankruptcy prediction. The purpose of this chapter is to present a sequential probabilistic system for bankruptcy data classification to help manager in making decisions. © 2018, IGI Global. All rights reserved.},
note = {Publication Title: Intelligent Systems: Concepts, Methodologies, Tools, and Applications},
keywords = {Bankruptcy prediction, Corporate finance, Data classification, Discriminant analysis, Forecasting, Human resource management, Independent variables, Neural networks, Nonlinear problems, Probabilistic systems, Real-world problem, Soft computing, Softcomputing techniques, Support vector machines},
pubstate = {published},
tppubtype = {book}
}
In the last decade, the development of bankruptcy prediction models has been one of important issues in accounting and corporate finance research fields. Indeed, bankruptcy is a critical event that yields important loss to management, shareholders, employees, and also to government. Statistical methods such as discriminant analysis, logistic and probit models were widely used for developing bankruptcy prediction systems. However, statistical-based approaches are assumes strong assumptions including linearity of the relationship among dependent and independent variables, normality of the errors which limit their applicability in bankruptcy real world problems. Recently, machine learning and soft computing techniques including artificial neural networks, support vector machines, and evolutionary intelligence have brought forth new alternatives in solving nonlinear problems with applications in bankruptcy prediction. The purpose of this chapter is to present a sequential probabilistic system for bankruptcy data classification to help manager in making decisions. © 2018, IGI Global. All rights reserved.
4.
Lahmiri, S.; Gagnon, S.
A sequential probabilistic system for bankruptcy data classification Book
IGI Global, 2018, ISBN: 978-1-5225-5644-2 1-5225-5643-5 978-1-5225-5643-5, (Publication Title: Intelligent Systems: Concepts, Methodologies, Tools, and Applications).
Abstract | Links | BibTeX | Tags: Bankruptcy prediction, Corporate finance, Data classification, Discriminant analysis, Forecasting, Human resource management, Independent variables, Neural networks, Nonlinear problems, Probabilistic systems, Real-world problem, Soft computing, Softcomputing techniques, Support vector machines
@book{lahmiriSequentialProbabilisticSystem2018,
title = {A sequential probabilistic system for bankruptcy data classification},
author = {S. Lahmiri and S. Gagnon},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059712022&doi=10.4018%2f978-1-5225-5643-5.ch064&partnerID=40&md5=21c0d2da6087916a6c372529e2b13784},
doi = {10.4018/978-1-5225-5643-5.ch064},
isbn = {978-1-5225-5644-2 1-5225-5643-5 978-1-5225-5643-5},
year = {2018},
date = {2018-01-01},
publisher = {IGI Global},
abstract = {In the last decade, the development of bankruptcy prediction models has been one of important issues in accounting and corporate finance research fields. Indeed, bankruptcy is a critical event that yields important loss to management, shareholders, employees, and also to government. Statistical methods such as discriminant analysis, logistic and probit models were widely used for developing bankruptcy prediction systems. However, statistical-based approaches are assumes strong assumptions including linearity of the relationship among dependent and independent variables, normality of the errors which limit their applicability in bankruptcy real world problems. Recently, machine learning and soft computing techniques including artificial neural networks, support vector machines, and evolutionary intelligence have brought forth new alternatives in solving nonlinear problems with applications in bankruptcy prediction. The purpose of this chapter is to present a sequential probabilistic system for bankruptcy data classification to help manager in making decisions. © 2018, IGI Global. All rights reserved.},
note = {Publication Title: Intelligent Systems: Concepts, Methodologies, Tools, and Applications},
keywords = {Bankruptcy prediction, Corporate finance, Data classification, Discriminant analysis, Forecasting, Human resource management, Independent variables, Neural networks, Nonlinear problems, Probabilistic systems, Real-world problem, Soft computing, Softcomputing techniques, Support vector machines},
pubstate = {published},
tppubtype = {book}
}
In the last decade, the development of bankruptcy prediction models has been one of important issues in accounting and corporate finance research fields. Indeed, bankruptcy is a critical event that yields important loss to management, shareholders, employees, and also to government. Statistical methods such as discriminant analysis, logistic and probit models were widely used for developing bankruptcy prediction systems. However, statistical-based approaches are assumes strong assumptions including linearity of the relationship among dependent and independent variables, normality of the errors which limit their applicability in bankruptcy real world problems. Recently, machine learning and soft computing techniques including artificial neural networks, support vector machines, and evolutionary intelligence have brought forth new alternatives in solving nonlinear problems with applications in bankruptcy prediction. The purpose of this chapter is to present a sequential probabilistic system for bankruptcy data classification to help manager in making decisions. © 2018, IGI Global. All rights reserved.
5.
Ouyed, O.; Allili, M. S.
Feature relevance for kernel logistic regression and application to action classification Proceedings Article
In: Proceedings - International Conference on Pattern Recognition, pp. 1325–1329, Institute of Electrical and Electronics Engineers Inc., 2014, ISSN: 10514651, (ISSN: 10514651).
Abstract | Links | BibTeX | Tags: Action classifications, Action recognition, Classification (of information), Classification methods, Classification performance, Feature relevance, Kernel logistic regression, Logistic regression, Multinomial kernels, Pattern Recognition, Supervised classification, Support vector machines
@inproceedings{ouyed_feature_2014,
title = {Feature relevance for kernel logistic regression and application to action classification},
author = {O. Ouyed and M. S. Allili},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84919884283&doi=10.1109%2fICPR.2014.237&partnerID=40&md5=616038cd7924614fd633061dfed32903},
doi = {10.1109/ICPR.2014.237},
issn = {10514651},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings - International Conference on Pattern Recognition},
pages = {1325–1329},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {An approach is proposed for incorporating feature relevance in mutinomial kernel logistic regression (MKLR) for classification. MKLR is a supervised classification method designed for separating classes with non-linear boundaries. However, it assumes all features are equally important, which may decrease classification performance when dealing with high-dimensional or noisy data. We propose a feature weighting algorithm for MKLR which automatically tunes features contribution according to their relevance for classification and reduces data over-fitting. The proposed algorithm produces more interpretable models and is more generalizable than MKLR, Kernel-SVM and LASSO methods. Application to simulated data and video action classification has provided very promising results compared to the aforementioned classification methods. © 2014 IEEE.},
note = {ISSN: 10514651},
keywords = {Action classifications, Action recognition, Classification (of information), Classification methods, Classification performance, Feature relevance, Kernel logistic regression, Logistic regression, Multinomial kernels, Pattern Recognition, Supervised classification, Support vector machines},
pubstate = {published},
tppubtype = {inproceedings}
}
An approach is proposed for incorporating feature relevance in mutinomial kernel logistic regression (MKLR) for classification. MKLR is a supervised classification method designed for separating classes with non-linear boundaries. However, it assumes all features are equally important, which may decrease classification performance when dealing with high-dimensional or noisy data. We propose a feature weighting algorithm for MKLR which automatically tunes features contribution according to their relevance for classification and reduces data over-fitting. The proposed algorithm produces more interpretable models and is more generalizable than MKLR, Kernel-SVM and LASSO methods. Application to simulated data and video action classification has provided very promising results compared to the aforementioned classification methods. © 2014 IEEE.
6.
Ouyed, O.; Allili, M. S.
Feature relevance for kernel logistic regression and application to action classification Proceedings Article
In: Proceedings - International Conference on Pattern Recognition, pp. 1325–1329, Institute of Electrical and Electronics Engineers Inc., 2014, ISSN: 10514651.
Abstract | Links | BibTeX | Tags: Action classifications, Action recognition, Classification (of information), Classification methods, Classification performance, Feature relevance, Kernel logistic regression, Logistic regression, Multinomial kernels, Pattern Recognition, Supervised classification, Support vector machines
@inproceedings{ouyedFeatureRelevanceKernel2014,
title = {Feature relevance for kernel logistic regression and application to action classification},
author = {O. Ouyed and M. S. Allili},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84919884283&doi=10.1109%2fICPR.2014.237&partnerID=40&md5=616038cd7924614fd633061dfed32903},
doi = {10.1109/ICPR.2014.237},
issn = {10514651},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings - International Conference on Pattern Recognition},
pages = {1325–1329},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {An approach is proposed for incorporating feature relevance in mutinomial kernel logistic regression (MKLR) for classification. MKLR is a supervised classification method designed for separating classes with non-linear boundaries. However, it assumes all features are equally important, which may decrease classification performance when dealing with high-dimensional or noisy data. We propose a feature weighting algorithm for MKLR which automatically tunes features contribution according to their relevance for classification and reduces data over-fitting. The proposed algorithm produces more interpretable models and is more generalizable than MKLR, Kernel-SVM and LASSO methods. Application to simulated data and video action classification has provided very promising results compared to the aforementioned classification methods. © 2014 IEEE.},
keywords = {Action classifications, Action recognition, Classification (of information), Classification methods, Classification performance, Feature relevance, Kernel logistic regression, Logistic regression, Multinomial kernels, Pattern Recognition, Supervised classification, Support vector machines},
pubstate = {published},
tppubtype = {inproceedings}
}
An approach is proposed for incorporating feature relevance in mutinomial kernel logistic regression (MKLR) for classification. MKLR is a supervised classification method designed for separating classes with non-linear boundaries. However, it assumes all features are equally important, which may decrease classification performance when dealing with high-dimensional or noisy data. We propose a feature weighting algorithm for MKLR which automatically tunes features contribution according to their relevance for classification and reduces data over-fitting. The proposed algorithm produces more interpretable models and is more generalizable than MKLR, Kernel-SVM and LASSO methods. Application to simulated data and video action classification has provided very promising results compared to the aforementioned classification methods. © 2014 IEEE.