Osman Salem
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Osman Salem has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Ahmed Mehaoua
12 shared publications- Ahmed Mehaoua
Universite Paris Cite
5 shared publications Anthony Marcus
3 shared publicationsBorko Furht
3 shared publications- Raouf Boutaba
University of Waterloo, Waterloo, Canada
3 shared publications Yaning Liu
JCP-Connect, Rennes, France
3 shared publications
Latest Publications
- Open Access
- 26 August 2026
- Published by Elsevier in SSRN Electronic Journal
Reliability Monitoring of QUIC Application Classifiers under Temporal Drift
QUIC is widely used by modern encrypted applications, making payload-free application classification important for network monitoring and management. However, classifiers trained on traffic from one period may become less reliable when deployed on future traffic because application behavior, service usage, and traffic composition evolve over time. This paper studies this deployment problem on weekly splits of CESNET-QUIC22 and proposes a reliability-monitoring framework for QUIC application classifiers under temporal drift.The framework estimates, diagnoses, and controls classifier reliability when target-week labels are unavailable. It combines label-free accuracy estimation, unsafe predicted-class detection, conformal coverage diagnostics, and risk-based selective rejection. Using W2022-44 as the labeled source week and W-2022-45–W-2022-47 as future target weeks, the source-only classifier shows consistent temporal degradation, while a retraining oracle confirms that fresh labels can recover part of the lost accuracy. In the label-free setting, the best accuracy estimator tracks target accuracy with a mean absolute error of 0.35 percentage points. Unsafe predicted classes are detected with AUROC values in the 0.95–0.98 range at a precision threshold of 0.70. Selective rejection further improves operational reliability: with a 10% review budget, accepted-flow accuracy reaches 0.731, comparable to the retraining-oracle range, while removing 24.7% of errors; with a 20% review budget, accepted-flow accuracy reaches 0.782 while removing 45.7% of errors. These results show that reliability monitoring can make deployed QUIC classifiers more measurable, auditable, and controllable under temporal drift.
- 26 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessReliability Monitoring of QUIC Application Classifiers under Temporal Drift
QUIC is widely used by modern encrypted applications, making payload-free application classification important for network monitoring and management. However, classifiers trained on traffic from one period may become less reliable when deployed on future traffic because application behavior, service usage, and traffic composition evolve over time. This paper studies this deployment problem on weekly splits of CESNET-QUIC22 and proposes a reliability-monitoring framework for QUIC application classifiers under temporal drift.The framework estimates, diagnoses, and controls classifier reliability when target-week labels are unavailable. It combines label-free accuracy estimation, unsafe predicted-class detection, conformal coverage diagnostics, and risk-based selective rejection. Using W2022-44 as the labeled source week and W-2022-45–W-2022-47 as future target weeks, the source-only classifier shows consistent temporal degradation, while a retraining oracle confirms that fresh labels can recover part of the lost accuracy. In the label-free setting, the best accuracy estimator tracks target accuracy with a mean absolute error of 0.35 percentage points. Unsafe predicted classes are detected with AUROC values in the 0.95–0.98 range at a precision threshold of 0.70. Selective rejection further improves operational reliability: with a 10% review budget, accepted-flow accuracy reaches 0.731, comparable to the retraining-oracle range, while removing 24.7% of errors; with a 20% review budget, accepted-flow accuracy reaches 0.782 while removing 45.7% of errors. These results show that reliability monitoring can make deployed QUIC classifiers more measurable, auditable, and controllable under temporal drift.
- 19 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 177-182
Cyberbullying Detection on tweets from Twitter using Machine Learning Algorithms
Cyberbullying has become a serious concern in today’s society, with the widespread use of social media platforms and other online communication channels. The negative impact of cyberbullying can be severe, ranging from emotional distress to even suicide. In this paper, we explore the use of machine learning algorithms to analyze the content of messages and identify those that contain abusive or harassing language. We used six popular algorithms, namely Logistic Regression (LR), k-Nearest Neighbors (KNN), Random Forest (RF), Classification and Regression Trees (CART), Naive Bayes and Support Vector Machine (SVM), to train and test our models on a dataset of Twitter tweets. To evaluate the performance of these models, we calculated several metrics, including accuracy, F1-score, cross-validation score and receiver operating characteristic (ROC) curve. Results show that Random Forest outperformed the other algorithms with an accuracy of 94%. The results suggest that the proposed method can be an effective automated tool for detecting and preventing cyberbullying on social media platforms like Twitter.
- 19 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 177-182
Cyberbullying Detection on tweets from Twitter using Machine Learning Algorithms
Cyberbullying has become a serious concern in today’s society, with the widespread use of social media platforms and other online communication channels. The negative impact of cyberbullying can be severe, ranging from emotional distress to even suicide. In this paper, we explore the use of machine learning algorithms to analyze the content of messages and identify those that contain abusive or harassing language. We used six popular algorithms, namely Logistic Regression (LR), k-Nearest Neighbors (KNN), Random Forest (RF), Classification and Regression Trees (CART), Naive Bayes and Support Vector Machine (SVM), to train and test our models on a dataset of Twitter tweets. To evaluate the performance of these models, we calculated several metrics, including accuracy, F1-score, cross-validation score and receiver operating characteristic (ROC) curve. Results show that Random Forest outperformed the other algorithms with an accuracy of 94%. The results suggest that the proposed method can be an effective automated tool for detecting and preventing cyberbullying on social media platforms like Twitter.
- 15 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (3) , 2053-2062
Man-in-the-Middle Attack Mitigation in Internet of Medical Things
The Internet of Medical Things are susceptible to Man-in-the-Middle (MitM) attack, which can identify healthcare emergency of monitored patients and replay normal physiological data to prevent the system from raising an alarm. In this article, we propose a framework to prevent a MitM from disrupting the operations and prohibiting the raise of alarms by the remote healthcare monitoring system. To reduce energy consumption for normal data transmission, and preserve the privacy of health data, our framework transmits a smaller size signature derived from acquired data with message authentication code, where the key is derived from received signal strength indication. Our experimental results for emergency detection show that our approach can achieve a high detection accuracy with a low false alarm rate of 3%.
- 15 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (3) , 2053-2062
Man-in-the-Middle Attack Mitigation in Internet of Medical Things
The Internet of Medical Things are susceptible to Man-in-the-Middle (MitM) attack, which can identify healthcare emergency of monitored patients and replay normal physiological data to prevent the system from raising an alarm. In this article, we propose a framework to prevent a MitM from disrupting the operations and prohibiting the raise of alarms by the remote healthcare monitoring system. To reduce energy consumption for normal data transmission, and preserve the privacy of health data, our framework transmits a smaller size signature derived from acquired data with message authentication code, where the key is derived from received signal strength indication. Our experimental results for emergency detection show that our approach can achieve a high detection accuracy with a low false alarm rate of 3%.
- 29 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 39 (2) , 526-540
Markov Models for Anomaly Detection in Wireless Body Area Networks for Secure Health Monitoring
The use of Wireless Body Area Networks (WBANs) in healthcare for pervasive monitoring enhances the lives of patients and allows them to fulfill their daily life activities while being monitored. Various non-invasive sensors are placed on the skin to monitor several physiological attributes, and the measured data are transmitted wirelessly to a centralized processing unit to detect changes in the health of the monitored patient. However, the transferred data are vulnerable to various sources of interference, sensor faults, measurement faults, injection and alteration by malicious attackers, etc. In this article, we propose a change point detection model based on a Markov chain for centralized anomaly detection in WBANs. The model is derived from the Root Mean Square Error (RMSE) between the forecasted and measured values for whole attributes. The RMSE transforms the monitored attributes into a univariate times series which is divided into overlapping sliding window. The joint probability of the sequence of RMSE values in each sliding window is calculated to decide whether a change has occurred or not. When an effective change is detected over k consecutive windows, the number of deviated attributes is used to distinguish faulty measurements from a health emergency. We apply our proposed approach on real physiological data from the Physionet database and compare it with existing approaches. Our experimental results prove the effectiveness of our proposed approach, as it achieves high detection accuracy with a low false alarm rate (5.2%).
- 29 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 39 (2) , 526-540
Markov Models for Anomaly Detection in Wireless Body Area Networks for Secure Health Monitoring
The use of Wireless Body Area Networks (WBANs) in healthcare for pervasive monitoring enhances the lives of patients and allows them to fulfill their daily life activities while being monitored. Various non-invasive sensors are placed on the skin to monitor several physiological attributes, and the measured data are transmitted wirelessly to a centralized processing unit to detect changes in the health of the monitored patient. However, the transferred data are vulnerable to various sources of interference, sensor faults, measurement faults, injection and alteration by malicious attackers, etc. In this article, we propose a change point detection model based on a Markov chain for centralized anomaly detection in WBANs. The model is derived from the Root Mean Square Error (RMSE) between the forecasted and measured values for whole attributes. The RMSE transforms the monitored attributes into a univariate times series which is divided into overlapping sliding window. The joint probability of the sequence of RMSE values in each sliding window is calculated to decide whether a change has occurred or not. When an effective change is detected over k consecutive windows, the number of deviated attributes is used to distinguish faulty measurements from a health emergency. We apply our proposed approach on real physiological data from the Physionet database and compare it with existing approaches. Our experimental results prove the effectiveness of our proposed approach, as it achieves high detection accuracy with a low false alarm rate (5.2%).
- 31 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 15 (3) , 1018-1034
Event Detection in Wireless Body Area Networks Using Kalman Filter and Power Divergence
The collected data by biomedical sensors must be analyzed for automatic detection of physiological changes. The early identification of an event in collected data is required to trigger an alarm upon detection of patient health degradation. Such alarms inform healthcare professionals and allow them to quickly react by taking appropriate actions. However, events result from physiological change or faulty measurements, and lead to false alarms and unnecessary medical intervention. In this paper, we propose a framework for automatic detection of events from collected data by biomedical sensors. The proposed approach is based on kalman filter to forecast the current measurement and to derive the baseline of the time series. The power divergence is used to measure the distance between the forecasted and measured values. When a change occurs, this metric significantly deviates from past values. To distinguish emergency events from faulty measurements, we exploit the spatial correlation between the monitored attributes. We conduct experiments on real physiological data set and our results show that our proposed framework achieves a good detection accuracy with a low false alarm rate. Its simplicity and processing speed make our proposed framework efficient and effective for real-world deployment.
- 31 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 15 (3) , 1018-1034
Event Detection in Wireless Body Area Networks Using Kalman Filter and Power Divergence
The collected data by biomedical sensors must be analyzed for automatic detection of physiological changes. The early identification of an event in collected data is required to trigger an alarm upon detection of patient health degradation. Such alarms inform healthcare professionals and allow them to quickly react by taking appropriate actions. However, events result from physiological change or faulty measurements, and lead to false alarms and unnecessary medical intervention. In this paper, we propose a framework for automatic detection of events from collected data by biomedical sensors. The proposed approach is based on kalman filter to forecast the current measurement and to derive the baseline of the time series. The power divergence is used to measure the distance between the forecasted and measured values. When a change occurs, this metric significantly deviates from past values. To distinguish emergency events from faulty measurements, we exploit the spatial correlation between the monitored attributes. We conduct experiments on real physiological data set and our results show that our proposed framework achieves a good detection accuracy with a low false alarm rate. Its simplicity and processing speed make our proposed framework efficient and effective for real-world deployment.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Detection of Nocturnal Epileptic Seizures from Wireless Inertial Measurements and Muscular Activity
The goal of this paper is to provide a lightweight approach for the early detection of epileptic seizures using data from inertial measurement unit and muscular activity. The detection procedure runs in a portable data collection device and raises an alarm for family member or other persons in the vicinity for fast assistance and eventually for saving the life of the monitored patient. The instantaneous power of sliding window is derived for inertial measurements from 3D Accelerometer (ACM), 3D Gyroscope (Gyro) and for the muscular activity from the ElectroMyoGram (EMG). The residual between forecasted and measured power is used as input for the detection algorithm based on Shewhart control chart. When the error between forecasted and derived power exceeds statistical chart limits [lower, upper] for several consecutive slots, an alarm is raised. The proposed approach is intended to improve the performance of existing detection systems by increasing the detection accuracy and reducing the false alarms through correlation analysis of collected data from 3D ACM, 3D Gyro and EMG. Our experimental results on real data set collected in Necker hospital from epileptic patients show that our proposed approach is robust against nocturnal movements and achieves a high level of detection accuracy with low false alarm rate.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Detection of Nocturnal Epileptic Seizures from Wireless Inertial Measurements and Muscular Activity
The goal of this paper is to provide a lightweight approach for the early detection of epileptic seizures using data from inertial measurement unit and muscular activity. The detection procedure runs in a portable data collection device and raises an alarm for family member or other persons in the vicinity for fast assistance and eventually for saving the life of the monitored patient. The instantaneous power of sliding window is derived for inertial measurements from 3D Accelerometer (ACM), 3D Gyroscope (Gyro) and for the muscular activity from the ElectroMyoGram (EMG). The residual between forecasted and measured power is used as input for the detection algorithm based on Shewhart control chart. When the error between forecasted and derived power exceeds statistical chart limits [lower, upper] for several consecutive slots, an alarm is raised. The proposed approach is intended to improve the performance of existing detection systems by increasing the detection accuracy and reducing the false alarms through correlation analysis of collected data from 3D ACM, 3D Gyro and EMG. Our experimental results on real data set collected in Necker hospital from epileptic patients show that our proposed approach is robust against nocturnal movements and achieves a high level of detection accuracy with low false alarm rate.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 280-285
Intelligent remote control of smart home devices using physiological parameters
The goal of this paper is to propose a new approach for controlling smart home devices using physiological and movements signals (electromyogram, accelerometer and gyroscope). Our proposed approach exploits the ElectroMyoGram (EMG) signal to detect user muscles contraction and to trigger the associated actions on the controlled device. The triggered action is based on the position of the hand or its movement pattern. The Support Vector Machine (SVM) is used to classify the gyroscope data and to detect hand movements. The position of the hand is determined using the K-Nearest Neighbors (KNN) algorithm. Our proposed approach can be used to command any electronic device or connected objects and it is intended to work with data from wearable arm band containing triaxial accelerometer, gyroscope and able to measure EMG signal. Our experimental results are very encouraging where we achieve fast processing and reliable evaluation of hand movement with very low rate of actions miss interpretation.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 280-285
Intelligent remote control of smart home devices using physiological parameters
The goal of this paper is to propose a new approach for controlling smart home devices using physiological and movements signals (electromyogram, accelerometer and gyroscope). Our proposed approach exploits the ElectroMyoGram (EMG) signal to detect user muscles contraction and to trigger the associated actions on the controlled device. The triggered action is based on the position of the hand or its movement pattern. The Support Vector Machine (SVM) is used to classify the gyroscope data and to detect hand movements. The position of the hand is determined using the K-Nearest Neighbors (KNN) algorithm. Our proposed approach can be used to command any electronic device or connected objects and it is intended to work with data from wearable arm band containing triaxial accelerometer, gyroscope and able to measure EMG signal. Our experimental results are very encouraging where we achieve fast processing and reliable evaluation of hand movement with very low rate of actions miss interpretation.
- 1 October 2014
- Published by IGI Global Scientific Publishing in International Journal of E-Health and Medical Communications
- Vol. 5 (4) , 20-38
Detection of Faulty Measurements in WBANs using Gaussian Mixture Model and Ant Colony
Wireless sensor networks are subject to different types of faults and interferences after their deployment. Abnormal values reported by sensors should be separated from faulty or injected measurements to ensure reliable monitoring operation. The aim of this paper is to propose a lightweight approach for the detection and suppression of faulty measurements in medical wireless sensor networks. The proposed approach is based on the combination of statistical model and machine learning algorithm. The authors begin by collecting physiological data and then they cluster the data collected during the first few minutes using the Gaussian mixture decomposition. They use the resulted labeled data as the input for the Ant Colony algorithm to derive classification rules in the central base station. Afterward, the derived rules are transmitted and installed in each associated sensor to detect abnormal values in distributed manner, and notify anomalies to the base station. Finally, the authors exploit the spatial and temporal correlations between monitored attributes to differentiate between faulty sensor readings and clinical emergency. They evaluate their approach with real and synthetic patient datasets. The experimental results demonstrate that their proposed approach achieves a high rate of detection accuracy for clinical emergency with reduced false alarm rate when compared to robust Mahalanobis distance.
- 1 October 2014
- Published by IGI Global Scientific Publishing in International Journal of E-Health and Medical Communications
- Vol. 5 (4) , 20-38
Detection of Faulty Measurements in WBANs using Gaussian Mixture Model and Ant Colony
Wireless sensor networks are subject to different types of faults and interferences after their deployment. Abnormal values reported by sensors should be separated from faulty or injected measurements to ensure reliable monitoring operation. The aim of this paper is to propose a lightweight approach for the detection and suppression of faulty measurements in medical wireless sensor networks. The proposed approach is based on the combination of statistical model and machine learning algorithm. The authors begin by collecting physiological data and then they cluster the data collected during the first few minutes using the Gaussian mixture decomposition. They use the resulted labeled data as the input for the Ant Colony algorithm to derive classification rules in the central base station. Afterward, the derived rules are transmitted and installed in each associated sensor to detect abnormal values in distributed manner, and notify anomalies to the base station. Finally, the authors exploit the spatial and temporal correlations between monitored attributes to differentiate between faulty sensor readings and clinical emergency. They evaluate their approach with real and synthetic patient datasets. The experimental results demonstrate that their proposed approach achieves a high rate of detection accuracy for clinical emergency with reduced false alarm rate when compared to robust Mahalanobis distance.
- 1 September 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 18 (5) , 1541-1551
Online Anomaly Detection in Wireless Body Area Networks for Reliable Healthcare Monitoring
In this paper, we propose a lightweight approach for online detection of faulty measurements by analyzing the data collected from medical wireless body area networks. The proposed framework performs sequential data analysis using a smart phone as a base station, and takes into account the constrained resources of the smart phone, such as processing power and storage capacity. The main objective is to raise alarms only when patients enter in an emergency situation, and to discard false alarms triggered by faulty measurements or ill-behaved sensors. The proposed approach is based on the Haar wavelet decomposition, nonseasonal Holt-Winters forecasting, and the Hampel filter for spatial analysis, and on for temporal analysis. Our objective is to reduce false alarms resulting from unreliable measurements and to reduce unnecessary healthcare intervention. We apply our proposed approach on real physiological dataset. Our experimental results prove the effectiveness of our approach in achieving good detection accuracy with a low false alarm rate. The simplicity and the processing speed of our proposed framework make it useful and efficient for real time diagnosis.
- 1 September 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 18 (5) , 1541-1551
Online Anomaly Detection in Wireless Body Area Networks for Reliable Healthcare Monitoring
In this paper, we propose a lightweight approach for online detection of faulty measurements by analyzing the data collected from medical wireless body area networks. The proposed framework performs sequential data analysis using a smart phone as a base station, and takes into account the constrained resources of the smart phone, such as processing power and storage capacity. The main objective is to raise alarms only when patients enter in an emergency situation, and to discard false alarms triggered by faulty measurements or ill-behaved sensors. The proposed approach is based on the Haar wavelet decomposition, nonseasonal Holt-Winters forecasting, and the Hampel filter for spatial analysis, and on for temporal analysis. Our objective is to reduce false alarms resulting from unreliable measurements and to reduce unnecessary healthcare intervention. We apply our proposed approach on real physiological dataset. Our experimental results prove the effectiveness of our approach in achieving good detection accuracy with a low false alarm rate. The simplicity and the processing speed of our proposed framework make it useful and efficient for real time diagnosis.
- 1 June 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15503607,p. 3529-3534
Epileptic seizure detection from EEG signal using Discrete Wavelet Transform and Ant Colony classifier
Electroencephalogram (EEG) is the electrical signal of brain which contains valuable information about its activities. In this paper, we propose a new approach for the early detection of epileptic seizure in EEG. The proposed approach is based on Discrete Wavelet Transform (DWT) and Ant Colony (AC) Classifier. We started by applying DWT to decompose the EEG signal into its sub-bands to extract the energy ratio from wavelet coefficients. Beside we extract some statistical features from the original signal, and we use the extracted features as the input for the AC algorithm to derive classification rules, which are used to detect epileptic seizures in the EEG of the monitored patient. Our experimental results on real dataset show that our proposed approach achieves a high level of detection accuracy.
- 1 June 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15503607,p. 3529-3534
Epileptic seizure detection from EEG signal using Discrete Wavelet Transform and Ant Colony classifier
Electroencephalogram (EEG) is the electrical signal of brain which contains valuable information about its activities. In this paper, we propose a new approach for the early detection of epileptic seizure in EEG. The proposed approach is based on Discrete Wavelet Transform (DWT) and Ant Colony (AC) Classifier. We started by applying DWT to decompose the EEG signal into its sub-bands to extract the energy ratio from wavelet coefficients. Beside we extract some statistical features from the original signal, and we use the extracted features as the input for the AC algorithm to derive classification rules, which are used to detect epileptic seizures in the EEG of the monitored patient. Our experimental results on real dataset show that our proposed approach achieves a high level of detection accuracy.