Mohamad Khalil

Mohamad Khalil

Auto-generated profile, based on publicly available information

Mohamad Khalil

Azm center for research in biotechnology and its applications, EDST, Tripoli, Lebanon

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 April 2022 in Scientific Reports
Verified
Journal Article
Open access
PDF file
AKAya Kabbara
Aya Kabbara
GRGabriel Robert
Gabriel Robert
MKMohamad Khalil
Mohamad Khalil
MVMarc Verin
Marc Verin
PBPascal Benquet
Pascal Benquet
MHMahmoud Hassan
Mahmoud Hassan
Emerging evidence showed that major depressive disorder (MDD) is associated with disruptions of brain structural and functional networks, rather than impairment of isolated brain region. Thus, connectome-based models capable of predicting the depression severity at the individual level can be clinically useful. Here, we applied a machine-learning approach to predict the severity of depression using resting-state networks derived from source-reconstructed Electroencephalography (EEG) signals. Using regression models and three independent EEG datasets (N = 328), we tested whether resting state functional connectivity could predict individual depression score. On the first dataset, results showed that individuals scores could be reasonably predicted (r = 0.6, p = 4 × 10–18) using intrinsic functional connectivity in the EEG alpha band (8–13 Hz). In particular, the brain regions which contributed the most to the predictive network belong to the default mode network. We further tested the predictive potential of the established model by conducting two external validations on (N1 = 53, N2 = 154). Results showed statistically significant correlations between the predicted and the measured depression scale scores (r1 = 0.52, r2 = 0.44, p < 0.001). These findings lay the foundation for developing a generalizable and scientifically interpretable EEG network-based markers that can ultimately support clinicians in a biologically-based characterization of MDD.

1 October 2016
Verified
Conference Paper
Closed access
KSKhaled Safi
Khaled Safi
Samer MohammedSamer Mohammed
Samer Mohammed
AFAttal Ferhat
Attal Ferhat
MKMohamad Khalil
Mohamad Khalil
AYAmirat Yacine
Amirat Yacine
The human activity recognition is widely used for human behavior prediction especially for dependent people. This is achieved to provide safety, health monitoring, and well being of this population at home. In this paper, the problem of human activity recognition is reformulated as joint segmentation of multidimensional time series. The hidden Markov model regression (HMMR) is used to perform unsupervised segmentation strategy between activities using the expectation-maximization algorithm. This is accomplished over six logical scenarios of twelve daily activities such as stair descent, standing, sitting down, sitting, From sitting to sitting on the ground and sitting on the ground. To evaluate the performance of HMMR model, other unsupervised methods are used including K-means, Gaussian mixtures model and the hidden Markov model. The results show that the HMMR model provides the best results for the different scenarios with up to 97% in terms of correct classification rate.

1 October 2017
Verified
Conference Paper
Closed access
KSKhaled Safi
Khaled Safi
Samer MohammedSamer Mohammed
Samer Mohammed
AYAmirat Yacine
Amirat Yacine
MKMohamad Khalil
Mohamad Khalil
The tonic postural system guarantees the stability of the human body in upright stance and during locomotion. It is considered as a complex organization which involves several internal systems and has multiple sources of information. In this paper, we provide a review of techniques and materials for human stability assessment. The primary tools to record and evaluate human sways in static posture are presented such as video-based methods, sensors-based methods and force platform-based methods. Moreover, various protocols and postural conditions in the literature are presented for recording the center of pressure (CoP) displacements. In addition, several relevant studies in the literature are shown and analyzed by highlighting the performances and limitations of the proposed techniques.

18 March 2019 in Wireless Personal Communications
Verified
Journal Article
Closed access
PDF file
MKMohamad Khalil
Mohamad Khalil
MKMahmoud Kamarei
Mahmoud Kamarei
JJJalal Jomaah
Jalal Jomaah

24 April 2018 in Analog Integrated Circuits and Signal Processing
Verified
Journal Article
Closed access
PDF file
MKMohamad Khalil
Mohamad Khalil
MKMahmoud Kamarei
Mahmoud Kamarei
JJJalal Jomaah
Jalal Jomaah
MFMajida Fadlallah
Majida Fadlallah

1 October 2019
Verified
Conference Paper
Closed access
JTJudie Tabbal
Judie Tabbal
AKAya Kabbara
Aya Kabbara
MKMohamad Khalil
Mohamad Khalil
MHMahmoud Hassan
Mahmoud Hassan
PBPascal Benquet
Pascal Benquet
Estimating functional connectivity (FC) has become an increasingly powerful tool for understanding our brain and investigating healthy and abnormal brain functions. Most previous studies assume temporal stationarity, such as correlation and data-driven decompositions computed across the whole duration of the acquisition. However, emerging evidence revealed the presence of temporal variability of FC, leading to increasing interest in estimating the dynamic Functional Connectivity (dFC). In this context, several approaches have been proposed in order to extract the relevant brain networks fluctuating over time. Still, a clear comparative study among the existing methods is needed. Thus, we aimed here to compare three dimensionality reduction techniques, specifically Independent Component Analysis (ICA), Principle Component Analysis (PCA) and generalized Canonical Correlation Analysis (gCCA), on two Magnetoencephalography (MEG) datasets recorded during motor and memory tasks. First, source connectivity combined with a sliding window approach was used in order to reconstruct the dynamic brain networks at the cortical level. Then, for each algorithm, we extracted the significant patterns of brain network connections with their associated time variation. Results show characteristic properties of each method in terms of computation time, reproducibility and potentiality in extracting the top dominant networks.