Mohamad Diab

Followers

Following

Public Views

Interests

Uploads

Papers by Mohamad Diab

Anti-Fog Face Mask While Wearing Glasses in the Coronavirus Pandemic

The number of diseases has greatly increased in the last decades in addition to the global pandem... more The number of diseases has greatly increased in the last decades in addition to the global pandemic that affected everyone’s life and killed a lot of humans. With this increase, the use of masks has greatly increased as well. Modern masks have various problems and can be inconvenient to keep all day long. One of its worst problems is that they cause the fogging up of eyeglasses. Many products have tried to solve this problem, but none was completely successful. This paper aims to design a new mask that tackles this problem in an innovative way by optimizing the airflow of warm breath to exit the mask from the sides instead of going upward. The mask is for human use and can be adopted by global standards.

Sensors' Ground Reaction Force behavior for both Normal and Parkinson subjects--A qualitative study

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2015

Characterization of normal and abnormal Gait has been a major research field for decades, whether... more Characterization of normal and abnormal Gait has been a major research field for decades, whether in fall prevention, sports biomechanics or even disease indication. In this paper, we assess time domain statistical properties of the Vertical Ground Reaction Force (VGRF) during moderate-pace walking, aiming eventually to create a reliable mathematical model of VGRF for normal and abnormal cases. For that endeavor, first order statistical analysis was performed upon signal segmentation in order to determine the degree of stationarity and base the model upon it. Furthermore, we performed curve fitting of the VGRF time series between present and past values, which led us to model the waveform with linear regression via Autoregressive Model for both Normal Walking Signals and Parkinson diseased patients' walking signals. However this is done only for one chosen sensor. However, it would be crucial to take the advantage of the array of sensors. Evaluating the cross-covariance between ...

Classification des signaux EMG utérins afin de détecter les accouchements prématurés

pour avoir dirigé ce travail de recherche, pour m'avoir intégré dans son équipe de travail et m'a... more pour avoir dirigé ce travail de recherche, pour m'avoir intégré dans son équipe de travail et m'avoir fait confiance tout au long de ces années. Mes remerciements et ma sincère reconnaissance s'adressent à mon Codirecteur de thèse, Mr. Mohamad KHALIL, Chef du département de Génie Biomédical à l'Université Islamique du Liban pour m'avoir formé scientifiquement tout au long de ce travail de thèse. Je le remercie pour avoir crû en moi depuis le début de ma carrière scientifique. Je n'oublierai pas son enthousiasme, sa gaîté et son soutien moral dans les moments difficiles. En témoignage de mon profond respect, je remercie Mr.

Download

Theorie Des Ondelettes et La Statistique

On propose dans cet article une étude pour classifier les contractions utérines dans le signal él... more On propose dans cet article une étude pour classifier les contractions utérines dans le signal électromyographie (EMG) utérin. Comme le contenu fréquentiel dans la contraction change d’une femme à une autre et durant la grossesse, la décomposition par ondelette est utilisée pour l’extraction des paramètres de chaque contraction et une méthode de classification non supervisée basée sur le test de Fisher est utilisée pour classifier les évènements. Une projection par Analyse en Composantes Principales est utilisée pour la visualisation des groupes résultants de la méthode de classification. Les résultats ont montré que les contractions utérines peuvent être classifiées selon des groupes indépendants selon le continu fréquentiel, et selon le terme de grossesse. Mots clés: ondelette, EMG utérin, classification The purpose of this study is to classify the uterine contractions in the electromyography (EMG) signal. As the frequency content of the contraction changes from one woman to anoth...

Download

Usage of VGRF in Biometrics: Application on Healthy and Parkinson Gaits

Biometric systems use unique information about or from a person to identify that person. Investme... more Biometric systems use unique information about or from a person to identify that person. Investments and research in this era has increased more than ever before. However, such technology is facing major fraud risks and pitfalls. This paper examines the use of VGRF in biometrics as a tool to be fused with an existing biometric system for reliable person identification. Results ensure that the use of raw data of VGRF is trustworthy if extracted from a normal subject. However, the results deteriorated in the presence of an abnormal gait. For instance, Gait subjects affected with Parkinson decreases the accuracy of classification among subjects ending up in high bias among results.

A mother wavelet selection study for vertical ground reaction force signals

Wavelet transform (WT) is a recent mathematical tool widely used in biomedical field. Its applica... more Wavelet transform (WT) is a recent mathematical tool widely used in biomedical field. Its application enormously spans the field of signal and image processing. The first step in applying this transform is to select the appropriate mother wavelet (MW). However, there is no standard method in the literature that could be used to choose a convenient MW for the analysis of a given data. While few techniques have been proposed, the present work aims to select the optimum MW for Vertical Ground Reaction Force (VGRF) signals through the computation of the maximum compression ratio (CR). In this study, fifty-three orthogonal MWs have been analyzed using the discrete wavelet transform (DWT). Then, sequential steps have been applied on hundred signals extracted from participants walking at their usual speed. The obtained results show that sym1, db1, bior1.1 and rbio1.1 compress maximally the VGRF signals (50.56%). Therefore, the use of these MWs for VGRF signal analysis is recommended.

Artificial Neural Network Based on Ensemble Empirical Mode Decomposition Features for Human Gait Diagnosis and Classification

Human gait analysis has been widely used to assess the stage of disease affecting the walking abi... more Human gait analysis has been widely used to assess the stage of disease affecting the walking ability. The gait signals, namely vertical ground reaction force signals, become more unsteady and non-linear with the progress of the disease. This paper makes use of ground reaction force signals measured from both normal and subjects diagnosed with Parkinson. New features are then extracted from different intrinsic mode functions as a result of the ensemble mode decomposition. The extracted features are divided randomly into a training set of 60%, a validation set of 15% and testing set of 25%. The neural network is then employed which yield an interesting overall classification accuracy of 95.7 %. This paper will pave the way for better rehabilitative programs, understanding of gait biomechanics and fall prevention among the elderly.

Classification of multichannel uterine EMG signals by using a weighted majority voting decision fusion rule

Recording the bioelectrical signals by using multiple sensors has been the subject of considerabl... more Recording the bioelectrical signals by using multiple sensors has been the subject of considerable research effort in the recent years. The multisensor recordings have opened the way to the application of more advanced signal processing techniques and the extraction of new parameters. The focus of this paper is to demonstrate the importance of multisensor recordings for classifying multichannel uterine EMG

Classification of multichannel uterine EMG signals by using unsupervised competitive learning

Multichannel analysis is an innovative technique used for the analysis of bioelectrical signals. ... more Multichannel analysis is an innovative technique used for the analysis of bioelectrical signals. In this paper, we analyzed uterine Electromyogram (EMG) signals recorded by means of a 4x4 electrode matrix positioned on the woman's abdomen by using a multichannel approach. Relevant features were extracted from each channel and fed to a competitive neural network (CNN). First, we evaluated the classification performance of each channel. Then, we compared these performances to see which channel ranks better than the others. Finally, a decision fusion method based on the weighted sum of the individual decision of each channel was tested. The results showed that data can be grouped into 2 different groups. Furthermore, they showed that the classification performance varies according to the position of the electrode. Therefore, when a decision fusion rule was applied, the network yielded better classification accuracy than any individual channel could provide. These encouraging results prove that multichannel analysis can improve the classification of uterine EMG signals.

Download

Classification of multichannel uterine EMG signals

Download

Fall Risk Assessment Using Pressure Insole Sensors and Convolutional Neural Networks

2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), Dec 7, 2022

Design of Robotic Manipulator to Hollow Out Zucchini

Volume 6: Design, Systems, and Complexity

Robotics entered the food industry starting from packaging to cooking. Zucchini is an important d... more Robotics entered the food industry starting from packaging to cooking. Zucchini is an important dish in the Middle Eastern kitchen. The eventual challenge of hollowing out Zucchini is to avoid poking its bottom with the corer. This paper introduces a novel robotic mechanism for hollowing out zucchini tasks precisely and efficiently. The mobility of the robot arm ensured a smooth hollowing while the corer is put in motion. Moreover, frames are assigned to the tip of the corer, holder, zucchini and camera to avoid stabbing the zucchini bottom. Accordingly, the special Euclidean group of the homogenous transformation matrices derived between different links are discussed in the context of their properties. The kinematic analysis is based on Mozzi-Chasles’ theorem rather than using the traditional Denavit Hartenberg convention for better task-oriented planning of hollowing out zucchini mechanism. Results indicate a promising mechanism that is well designed, simple and easy to build, mai...

Identifying Elderly Patients at Risk of Falling using Time-Domain and Cyclostationarity Related Features

International Journal of Integrated Engineering, 2021

Falls are a prevalent and severe health problem in the elderly community, leading to unfortunate ... more Falls are a prevalent and severe health problem in the elderly community, leading to unfortunate and devastating consequences. Some falls can be prevented through interventions, proper management, and extra care. Therefore, studying and identifying elderly people with risk of falls is essential to minimize the falling risk and to minimize the severity of injuries that can occur from these falls. Besides, identifying at-risk patients can profoundly affect public health in a positive way. In this paper, we use classification techniques to identify at-risk patients using pressure signals of the innersoles of 520 elderly people. These people reported whether they had experienced previous falls or not. Two different types of feature sets were used as inputs to the classification models and were compared: The first feature set includes time-domain, physiological, and cyclostationary features, whereas the second includes a subset of those features chosen by Relief-F as the most important f...

Download

Murine Atherosclerosis Detection Using Machine Learning Under Magnetic Resonance Imaging

2020 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), 2021

Over the past few decades, the diagnosis of heart disease, namely atherosclerosis, has been of in... more Over the past few decades, the diagnosis of heart disease, namely atherosclerosis, has been of interest for many researchers. The use of electrocardiogram (ECG) triggered Magnetic Resonance Imaging (MRI) sequences, enables exploration of aortic arches with high-resolution images. Lately, implementation of numerous Machine Learning (ML) techniques improved the accuracy of diagnosing diseases especially cardiovascular ones. In this paper, we proposed a model to diagnose atherosclerosis in mice using features extracted from the electrocardiogram (ECG) and respiratory signals. We defined new variables, after adaptation to the altered nature of electrophysiological signals with superimposed MRI noise. Using the 5-fold cross validation test, we introduced the features into the Random Forest (RF) classifier and obtained an accuracy of 96.96%. Feature selection then took place using the Info Gain (IG) attribute evaluator, which increased our model's accuracy to 97.57%. This presents a first step towards a real-time MRI synchronous cardiovascular finding system.

Robotic Interface Controller for Minimally Invasive Surgery

2018 1st International Conference on Computer Applications & Information Security (ICCAIS), 2018

This study aims to assemble a touch screen controlled surgical robotic arm, with the ability to o... more This study aims to assemble a touch screen controlled surgical robotic arm, with the ability to overcome the lack of haptic feedback encountered during minimally invasive surgery (MIS). The objective is to advance feasibility of solutions for millimeter scale movement in critical surgery areas. We achieved a prototype integrating servo-motors, resistive screen, microcontroller and end-effector measurement sensor. We implemented calibration, command and feed-back processes using Arduino codes. We were able to deliver minimal motion of surgical alike tool in different directions. According to requirements, the detected output values allowed distinction between hard and soft materials that simulate various human tissues. However, the developed exploration will facilitate the completion of haptic feed-back system after implementing communication between sensors on both side of operation.

Synchrosqueezing Characterize Non-stationary Signals: Application on Gait-Vertical Ground Reaction Force

2016 Global Summit on Computer & Information Technology (GSCIT), 2016

Signal is a physical quantity we can measure like gait vertical ground reaction force. However, t... more Signal is a physical quantity we can measure like gait vertical ground reaction force. However, the latter are such non- stationary signals require a deep understanding of their instantaneous amplitude, phase and frequency. From this, one can model its stationary and non- stationary part and approximate the noise. In addition, one can practice such features for inter-subject classification of the vertical ground reaction force signals like between normal and pathological. Not to add, one objective could also concentrate in intra-subject classification like between usual gait and gait associated with cognitive tasks for the same subject as this paper mainly concerns. For that purpose, Synchrosqueezing of time-frequency representation is being used to spot its power in non-stationary signal analysis and classification. This technique also helped in developing an accurate detection of outliers within such time series signal like when subjects encounter turning points during walking. All this would help in a correct assessing treatment effectiveness and précising the stage of disease. In addition, this would be a starting point for having accurate parameters in elderly fall detection.

Bioinspired Approach to Inverse Kinematic Problem

Biomedical Engineering and Computational Intelligence, 2019

In robotics, inverse kinematics is mapping the end-effector location and orientation to joint ang... more In robotics, inverse kinematics is mapping the end-effector location and orientation to joint angles. In this paper, the challenge behind finding a solution in inverse kinematics is tackled through minimizing the energy introduced in joints and the energy required by the mechanism as a whole. Studying integrated energies in the joints found in the human arm can give a new approach in understanding and solving inverse kinematics problem constrained by following the optimized path. Results are based on screw motion theorem, introduced by Charles and Mozzi. Moreover, the proposed technique and the results are exposed through simulation of three-link redundant manipulators that resemble human arm.

A Graphical User Interface for an Automatic Rest-activity Cycle Detection and Dichotomy Index Computation

Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies, 2019

The success of chemotherapy treatment is achieved based on "Chronotherapy": the concept of admini... more The success of chemotherapy treatment is achieved based on "Chronotherapy": the concept of administering the correct drug at a precise time based on the circadian rhythm study. This paper aims to detect the rest/activity cycle and automatically calculate the dichotomy index (I<O), as both parameters have been proved to be reliable indices of the circadian rhythm. First, the DARC "Détection Automatique du Rythme Circadien" algorithm is used to segment the rest-activity phases automatically. Then, a Graphical User Interface (GUI) is used to calculate easily the I<O across several days of records and smooth the analysis. The outcome of this study provides an easy-to-use GUI that minimizes patients' intervention, facilitates user involvement, and reduces the time required for analysis.

Download

Prediction of Elderly Falls Using the Degree of Cyclostationarity of Walk Pressure Signals

2020 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), 2021

There is an increasing interest in developing older adult fall-risk prediction models that can be... more There is an increasing interest in developing older adult fall-risk prediction models that can be used as a preventive approach to predict future risk of falling in the elderly community. This study's primary objective is to implement and compare supervised machine-learning methods to classify elderly subjects as fallers or non-fallers. Features used for building the models were extracted from the pressure signals of the innersoles of 520 elderly people who reported whether they had experienced previous falls or not. Two different types of feature sets were used as inputs to the classification models and were compared. The first feature set includes ten time-domain features, while the second set includes a single cyclostationary property, which is the degree of cyclostationarity of the average walk pressure signal. Our study showed that the use of the degree of cyclostationarity as a single feature improved the model prediction accuracy by 6.58%, compared to the use of the time-...

Comparing Healthy Subjects and Alzheimer’s Disease Patients using Brain Network Similarity: a Preliminary Study

2021 Sixth International Conference on Advances in Biomedical Engineering (ICABME), 2021

Brain network analysis is an interdisciplinary field linking computational neuroscience with biom... more Brain network analysis is an interdisciplinary field linking computational neuroscience with biomedical data analytics, aiming for instance to map the brain into interconnected regions at different conditions, resting versus inactivity, and normal versus pathological. In our study, brain connectivity modeling and analysis are performed via graph theory. Several studies have revealed alterations in structural/functional brain networks of people diagnosed with several brain disorders. Most of the studies in the literature used graph theoretical approaches to characterize these disorders, however less attention was given for distance-based approaches (or network similarity). Our objective here is to compare the brain networks of normal versus Alzheimer’s disease (AD) patients by performing distance-based graph similarity analysis between their electrophysiological brain networks. The brain networks of a group of 10 healthy control subjects and 10 AD patients were constructed from Electroencephalography (EEG) signals recorded at rest, followed by the computation of intra- and inter-group network similarity via Siminet and DeltaCon algorithms at the EEG alpha and beta frequency bands. Results showed that AD networks have significantly lower similarity scores and tend to be more heterogenous with respect to the healthy networks. This work provides a preliminary foundation for the effective use of graph similarity in the computational assessment of pathological brain networks compared to healthy subjects.

Mohamad Diab

Uploads

Papers by Mohamad Diab

Log In