Abdelghani Djebbari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Abdelghani Djebbari has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Lyna Henaa Hasnaoui
Laboratory of Biomedical Engineering, Faculty of Technology, University of Tlemcen, BP 230, Chetouane, Tlemcen 13000, Algeria
3 shared publicationsAmel Benabdallah
Laboratory of Biomedical Engineering, Faculty of Technology, University of Tlemcen, BP 230, Chetouane, Tlemcen 13000, Algeria
2 shared publications- Ismail Hadj Ahmed
Laboratory of Biomedical Engineering, Department of Biomedical Engineering, Faculty of Technology, University of Tlemcen, Tlemcen, Algeria
2 shared publications L. Kadem
2 shared publications- Lyna Henaa Hasnaoui
Laboratory of Biomedical Engineering, Faculty of Technology, University of Tlemcen, Chetouane, Tlemcen, Algeria
2 shared publications M. Asaadi
2 shared publications
Latest Publications
- 9 January 2026
- Published by Springer Nature in Annals of Biomedical Engineering
- Vol. 54 (6) , 1808-1829
Unlocking Insights from Postictal EEGs: Investigating Predictive Markers of Seizure Recurrence
Purpose Seizure recurrence, often presenting as clusters, is a major clinical concern linked to increased morbidity. The immediate postictal period is a critical yet understudied window where recurrence frequently arises. This study evaluates whether EEG features from postictal intervals can distinguish postictal-to-ictal (P–I) from postictal-to-interictal (P–Inter) transitions, enabling early recurrence prediction. Methods EEG data from the CHB-MIT database were analyzed, comprising 73 postictal episodes from seven patients (44 P–I, 29 P–Inter). Each episode was segmented into 10-second windows, yielding 876 segments. Fifty wavelet-based features were extracted from low-sample entropy channels and classified using Decision Tree (DT) and Long Short-Term Memory (LSTM) models. Performance was evaluated using nested cross-validation and, to test inter-patient generalization, per-patient stratified nested cross-validation. Results In subject-independent nested CV, DT achieved accuracy 0.75 (95% CI ± 0.029), sensitivity 0.73 (±0.041), specificity 0.77 (±0.038), F1-score 0.70 (±0.032), AUC 0.75 (±0.028), and FPR 0.20 (±0.039). LSTM yielded accuracy 0.71 (±0.027), sensitivity 0.69 (±0.066), specificity 0.72 (±0.069), F1-score 0.65 (±0.027), AUC 0.73 (±0.035), and FPR 0.28 (±0.069). Under patient-stratified evaluation, accuracy decreased to 0.67 (±0.076) for DT and 0.65 (±0.093) for LSTM, reflecting inter-patient variability. Conclusion These proof-of-concept findings indicate that postictal EEG, particularly P–I transitions, may encode information relevant to seizure recurrence. While the observed performance remains moderate, these results provide preliminary evidence warranting further investigation rather than indicating immediate clinical applicability.
- 9 January 2026
- Published by Springer Nature in Annals of Biomedical Engineering
- Vol. 54 (6) , 1808-1829
Unlocking Insights from Postictal EEGs: Investigating Predictive Markers of Seizure Recurrence
Purpose Seizure recurrence, often presenting as clusters, is a major clinical concern linked to increased morbidity. The immediate postictal period is a critical yet understudied window where recurrence frequently arises. This study evaluates whether EEG features from postictal intervals can distinguish postictal-to-ictal (P–I) from postictal-to-interictal (P–Inter) transitions, enabling early recurrence prediction. Methods EEG data from the CHB-MIT database were analyzed, comprising 73 postictal episodes from seven patients (44 P–I, 29 P–Inter). Each episode was segmented into 10-second windows, yielding 876 segments. Fifty wavelet-based features were extracted from low-sample entropy channels and classified using Decision Tree (DT) and Long Short-Term Memory (LSTM) models. Performance was evaluated using nested cross-validation and, to test inter-patient generalization, per-patient stratified nested cross-validation. Results In subject-independent nested CV, DT achieved accuracy 0.75 (95% CI ± 0.029), sensitivity 0.73 (±0.041), specificity 0.77 (±0.038), F1-score 0.70 (±0.032), AUC 0.75 (±0.028), and FPR 0.20 (±0.039). LSTM yielded accuracy 0.71 (±0.027), sensitivity 0.69 (±0.066), specificity 0.72 (±0.069), F1-score 0.65 (±0.027), AUC 0.73 (±0.035), and FPR 0.28 (±0.069). Under patient-stratified evaluation, accuracy decreased to 0.67 (±0.076) for DT and 0.65 (±0.093) for LSTM, reflecting inter-patient variability. Conclusion These proof-of-concept findings indicate that postictal EEG, particularly P–I transitions, may encode information relevant to seizure recurrence. While the observed performance remains moderate, these results provide preliminary evidence warranting further investigation rather than indicating immediate clinical applicability.
- 19 June 2025
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 38 (01)
MULTIMODAL PHYSIOLOGICAL SIGNALS INTEGRATION FOR ROBUST BIOMETRIC IDENTIFICATION: A NOVEL APPROACH USING ECG, ICG, AND BLOOD PRESSURE SIGNALS WITH ADVANCED CLASSIFIERS
In response to the dynamic landscape of biometric identification, this research explores a novel paradigm by integrating physiological signals, including electrocardiography (ECG), impedance cardiography (ICG), and blood pressure (BP), to enhance precision and reliability in identity verification systems. Leveraging an unexplored database comprising these three signals collected from 30 individuals, advanced classifiers, specifically fine Gaussian support vector machines (FG-SVM) and a bi-layered artificial neural network (Bi-ANN) were employed to construct a robust identification model. Our investigation involved extracting diverse statistical and entropy features from the signals, enriching the dataset. Results indicate the FG-SVM model achieved an 88.14% accuracy during training, with a recall of 95.09%, precision of 94.33%, and a Kappa coefficient of 87.7%. In the test set, FG-SVM demonstrated 93.33% accuracy, balanced recall and precision of 93.33%, and a Kappa coefficient of 92.9%. The Bi-layered ANN model exhibited superior training performance, attaining 93.3% accuracy, 94.56% recall, 93.17% precision, and a Kappa coefficient of 93.1%. Notably, in the test set, Bi-layered ANN achieved perfect accuracy, recall, precision, and Kappa coefficient of 100%. Our study includes a critical comparison with previous studies, this comparison highlights the novel insights gained from our approach, emphasizing the potential for accurate and dependable biometric identification in real-world applications. Additionally, our research contributes to the field by emphasizing the significance of non-handcrafted features, further enhancing the richness of the dataset and reinforcing the robustness of the identification model.
- 19 June 2025
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 38 (01)
MULTIMODAL PHYSIOLOGICAL SIGNALS INTEGRATION FOR ROBUST BIOMETRIC IDENTIFICATION: A NOVEL APPROACH USING ECG, ICG, AND BLOOD PRESSURE SIGNALS WITH ADVANCED CLASSIFIERS
In response to the dynamic landscape of biometric identification, this research explores a novel paradigm by integrating physiological signals, including electrocardiography (ECG), impedance cardiography (ICG), and blood pressure (BP), to enhance precision and reliability in identity verification systems. Leveraging an unexplored database comprising these three signals collected from 30 individuals, advanced classifiers, specifically fine Gaussian support vector machines (FG-SVM) and a bi-layered artificial neural network (Bi-ANN) were employed to construct a robust identification model. Our investigation involved extracting diverse statistical and entropy features from the signals, enriching the dataset. Results indicate the FG-SVM model achieved an 88.14% accuracy during training, with a recall of 95.09%, precision of 94.33%, and a Kappa coefficient of 87.7%. In the test set, FG-SVM demonstrated 93.33% accuracy, balanced recall and precision of 93.33%, and a Kappa coefficient of 92.9%. The Bi-layered ANN model exhibited superior training performance, attaining 93.3% accuracy, 94.56% recall, 93.17% precision, and a Kappa coefficient of 93.1%. Notably, in the test set, Bi-layered ANN achieved perfect accuracy, recall, precision, and Kappa coefficient of 100%. Our study includes a critical comparison with previous studies, this comparison highlights the novel insights gained from our approach, emphasizing the potential for accurate and dependable biometric identification in real-world applications. Additionally, our research contributes to the field by emphasizing the significance of non-handcrafted features, further enhancing the richness of the dataset and reinforcing the robustness of the identification model.
- 27 November 2024
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 37 (03)
LEVERAGING EPILEPSY DETECTION ACCURACY THROUGH BURST ENERGY INTEGRATION IN CWT AND DECISION TREE CLASSIFICATION OF EEG SIGNALS
The biomedical field plays a pivotal role in advancing healthcare by leveraging technological innovations to enhance diagnostics and treatment strategies. In the context of neurological disorders, particularly epilepsy, automated EEG signal processing stands out as a critical facet of biomedical research. The ability to analyze and interpret vast amounts of electroencephalogram (EEG) data using sophisticated techniques, such as Continuous Wavelet Transform (CWT), contributes significantly to the timely and accurate detection of epileptic events. Automated EEG signal processing, which uses advanced algorithms and pattern recognition methods, enables the identification of subtle yet crucial patterns indicative of epileptic activity. This paper presents an in-depth exploration of epilepsy identification using the CWT on the CHB-MIT Scalp EEG database. The study uses nine complex mother wavelets from the Gaussian and Morlet families to look at 8920 EEG segments, including 197 seizure events. The performance of each wavelet in detecting epileptic convulsions within EEG signals is rigorously evaluated. Our study shows that the complex Gaussian wavelet of order 5 (cgau5) emerged as the optimal choice, with a sensitivity of 97.58% and a precision of 97.93%. To improve epilepsy detection, we introduce burst energy, a novel engineered feature. This method gets accurate information about brain activity from the CWT scalogram by detecting ictal and ictal-free EEGs at different energy levels. The use of burst energy has a significant impact on classification performance, highlighting its potential for improved accuracy in epilepsy identification. This comprehensive study contributes valuable insights into selecting appropriate wavelets and introduces an innovative feature for more effective EEG-based epilepsy detection.
- 27 November 2024
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 37 (03)
LEVERAGING EPILEPSY DETECTION ACCURACY THROUGH BURST ENERGY INTEGRATION IN CWT AND DECISION TREE CLASSIFICATION OF EEG SIGNALS
The biomedical field plays a pivotal role in advancing healthcare by leveraging technological innovations to enhance diagnostics and treatment strategies. In the context of neurological disorders, particularly epilepsy, automated EEG signal processing stands out as a critical facet of biomedical research. The ability to analyze and interpret vast amounts of electroencephalogram (EEG) data using sophisticated techniques, such as Continuous Wavelet Transform (CWT), contributes significantly to the timely and accurate detection of epileptic events. Automated EEG signal processing, which uses advanced algorithms and pattern recognition methods, enables the identification of subtle yet crucial patterns indicative of epileptic activity. This paper presents an in-depth exploration of epilepsy identification using the CWT on the CHB-MIT Scalp EEG database. The study uses nine complex mother wavelets from the Gaussian and Morlet families to look at 8920 EEG segments, including 197 seizure events. The performance of each wavelet in detecting epileptic convulsions within EEG signals is rigorously evaluated. Our study shows that the complex Gaussian wavelet of order 5 (cgau5) emerged as the optimal choice, with a sensitivity of 97.58% and a precision of 97.93%. To improve epilepsy detection, we introduce burst energy, a novel engineered feature. This method gets accurate information about brain activity from the CWT scalogram by detecting ictal and ictal-free EEGs at different energy levels. The use of burst energy has a significant impact on classification performance, highlighting its potential for improved accuracy in epilepsy identification. This comprehensive study contributes valuable insights into selecting appropriate wavelets and introduces an innovative feature for more effective EEG-based epilepsy detection.
- 18 June 2024
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 40 (3-4) , 463-484
Robust dimensionality-reduced epilepsy detection system using EEG wavelet packets and machine learning
- 18 June 2024
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 40 (3-4) , 463-484
Robust dimensionality-reduced epilepsy detection system using EEG wavelet packets and machine learning
- 27 July 2023
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 35 (04)
INVESTMENT OF BIOMEDICAL APPLICATIONS IN MARKETING: ELECTROENCEPHALOGRAM-BASED CONSUMER DECISION PREDICTION
The neuroscience field provides extensive knowledge regarding cerebral activity principles. Therefore, it enables congregating consumer information and anticipating its preferences. Unlike classical marketing techniques, for instance, interviews with consumers, in which they usually do not communicate their real preferences, biomedical methodologies provide more powerful tools such as electroencephalogram signals and brain imaging, to explore the activity within the brain and examine its miscellaneous responses, which contribute efficiently to understanding human behavior related to its purchasing decision-making. Aiming to highlight the impact of neuroscience on marketing advancement, we first present in this paper a thoughtful background based on state-of-the-art studies to investigate the rate of several neurology techniques’ contribution to the advancement of the marketing field and their effect on purchasing decision-making. Second, we propose a predictive modeling framework based on the analysis of EEG signals recorded during decision-making in terms of “like” or “dislike” of specific consumer products. The discrete wavelet transform (DWT) and kNN classifier were combined to develop such an automated model. For evaluation purposes, the developed model was performed on a well-known and public EEG dataset collected for marketing studies. Achieving promising results confirms that the developed framework can be used as a reliable tool for market strategy development.
- 27 July 2023
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 35 (04)
INVESTMENT OF BIOMEDICAL APPLICATIONS IN MARKETING: ELECTROENCEPHALOGRAM-BASED CONSUMER DECISION PREDICTION
The neuroscience field provides extensive knowledge regarding cerebral activity principles. Therefore, it enables congregating consumer information and anticipating its preferences. Unlike classical marketing techniques, for instance, interviews with consumers, in which they usually do not communicate their real preferences, biomedical methodologies provide more powerful tools such as electroencephalogram signals and brain imaging, to explore the activity within the brain and examine its miscellaneous responses, which contribute efficiently to understanding human behavior related to its purchasing decision-making. Aiming to highlight the impact of neuroscience on marketing advancement, we first present in this paper a thoughtful background based on state-of-the-art studies to investigate the rate of several neurology techniques’ contribution to the advancement of the marketing field and their effect on purchasing decision-making. Second, we propose a predictive modeling framework based on the analysis of EEG signals recorded during decision-making in terms of “like” or “dislike” of specific consumer products. The discrete wavelet transform (DWT) and kNN classifier were combined to develop such an automated model. For evaluation purposes, the developed model was performed on a well-known and public EEG dataset collected for marketing studies. Achieving promising results confirms that the developed framework can be used as a reliable tool for market strategy development.
- 15 July 2023
- Published by Springer Nature
- p. 137-147
A Robust Biometric Identification System Using ECG Statistical Features and SVM
- 15 July 2023
- Published by Springer Nature
- p. 137-147
A Robust Biometric Identification System Using ECG Statistical Features and SVM
- 25 March 2023
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 39 (2) , 365-387
Novel quadratic time-frequency features in EEG signals for robust detection of epileptic seizure
- 25 March 2023
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 39 (2) , 365-387
Novel quadratic time-frequency features in EEG signals for robust detection of epileptic seizure
- 24 March 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (11) , 13680-13709
Telemedical transport layer security based platform for cardiac arrhythmia classification using quadratic time–frequency analysis of HRV signal
- 24 March 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (11) , 13680-13709
Telemedical transport layer security based platform for cardiac arrhythmia classification using quadratic time–frequency analysis of HRV signal
- 8 February 2022
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 38 (2) , 369-388
Robust detection of CHF through new time–frequency features within HRV signals
- 8 February 2022
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 38 (2) , 369-388
Robust detection of CHF through new time–frequency features within HRV signals
- Open Access
- 10 August 2021
- Published by Springer Nature in Research Square
Telemedical Transport Layer Security Based Platform for Cardiac Arrhythmia Classification Using Quadratic Time-Frequency Analysis of HRV Signal
In this paper, we have developed a client-server model implemented as a telemedical platform for real-time remote monitoring of the cardiovascular function in patients suffering from arrhythmia. This technical platform capable of detecting and classifying in real-time cardiac arrhythmia via a Graphical User Interface (GUI) using Time-Frequency analysis methods, features extraction, features selection, and classification of the Heart Rate Variability signal recorded using a data acquisition system. The data acquisition system that we used is mainly designed around the Raspberry Pi zero which communicates with a server through the TCP/IP involving a 4G/3G connection secured by the transport layer security (TLS) for a reliably safe connection between client and server. This telemedical platform adopts continuous control and monitoring of the heart rhythm. By using this system, in case of an alarm, medical staff can easily communicate with their patients in the hospital or at home.
- 10 August 2021
- Published by Springer Nature in Research Square
Open AccessTelemedical Transport Layer Security Based Platform for Cardiac Arrhythmia Classification Using Quadratic Time-Frequency Analysis of HRV Signal
In this paper, we have developed a client-server model implemented as a telemedical platform for real-time remote monitoring of the cardiovascular function in patients suffering from arrhythmia. This technical platform capable of detecting and classifying in real-time cardiac arrhythmia via a Graphical User Interface (GUI) using Time-Frequency analysis methods, features extraction, features selection, and classification of the Heart Rate Variability signal recorded using a data acquisition system. The data acquisition system that we used is mainly designed around the Raspberry Pi zero which communicates with a server through the TCP/IP involving a 4G/3G connection secured by the transport layer security (TLS) for a reliably safe connection between client and server. This telemedical platform adopts continuous control and monitoring of the heart rhythm. By using this system, in case of an alarm, medical staff can easily communicate with their patients in the hospital or at home.