Bulletin of Electrical Engineering and Informatics
The computation of network reliability for a system with many states is an NP-hard issue. Finding... more The computation of network reliability for a system with many states is an NP-hard issue. Finding all the minimum path vectors (d-MPs) lower boundary points for each level d is one of the few approaches for computing such dependability. This research proposed enhancements to the technique described in Chen's "Searching for d-MPs with rapid enumeration" paper. We propose additional adjustments to the method that creates the flow vector F in this enhancement. This decreases the number of required steps and the temporal complexity of the method. Comparing the newly suggested approach to the old algorithm reveals that the adjustment has increased the enumeration's efficiency and degree of complexity.
2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022
Detection of Parkinson's disease remains challenge for physicians, especially, in the clinica... more Detection of Parkinson's disease remains challenge for physicians, especially, in the clinical field due to the difficulty of cure. Thus, algorithms of classification have the main role in the assessment of this neurodegenerative disorder. In this paper, we focus on the analysis and the evaluation of nine Machine Learning Algorithms (MLA), namely Support Vector Machine (SVM), Logistic Regression, Discriminant Analysis, K-Nearest Neighbors (KNN), Decision tree, Random Forest, Bagging tree, Naïve Bayes, and AdaBoost. Classification algorithms were applied to a Parkinson's dataset of 240 speech measurements with 44 features using several evaluation parameters to establish the efficiency score of each classifier. We found that the KNN classifier yielded the highest accuracy rate of 97.22% and F1-score of 97.30%.
2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022
To compute system reliability, many approaches are available in the literature. One of the most u... more To compute system reliability, many approaches are available in the literature. One of the most used approaches is the enumeration method, minimal paths or minimal cuts. Most of these approaches enumerate the minimal paths to evaluate reliability, but few of them used minimal cuts. This paper proposes a new direct method that enumerates all the minimal cuts with nodes failure. Unlike the algorithms in the literature that use indirect methods based on finding minimal paths to extract the minimal cuts from them.
2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022
Many technological networks that execute their tasks with different levels of distinctive efficie... more Many technological networks that execute their tasks with different levels of distinctive efficiency are multi-state systems, and reliability is an essential predicate for their safe operation and optimal improvement. In this paper, a survey of recent progress of the evaluation of exact reliability for multi-state system is presented. A general method for the reliability evaluation of multi-state system is using d-minimal paths. Many methods have been proposed in the literature for the enumeration of the d-MPs, most of this works are based on the minimal paths (MPs). This article provides the most recent algorithms used for the evaluation of the exact reliability for multi-state systems, and discusses the basic idea of each algorithm.
La fraude aux examens scolaire a fait l’objet ces dernières années l’objet d’une forte médiatisat... more La fraude aux examens scolaire a fait l’objet ces dernières années l’objet d’une forte médiatisation, en particulier à l’approche des examens. Par ailleurs, les enseignants se plaignent de plus en plus des apprenants et des étudiants qui utilisent leur téléphone pendant les épreuves. Avec l’arrivée de la technologie dans les classes et l’utilisation courante d’Internet dans les activités scolaires, les apprenants et les étudiants ont davantage d’opportunités de plagier des documents ou de frauder lors des épreuves sur table. L’intégration des nouvelles technologies de l’information et de la communication dans l’ensemble de corps scolaire nous a amené à poser la question du mode d’évaluation. À travers ce travail, nous avons procédé à une recherche exploratoire, à travers un questionnaire élaboré par le logiciel Sphinx. L’analyse des données par Sphinx et par le test de confiance khideux, nous a permis de déterminer un aperçu sur l’ampleur de ce phénomène dans le milieu scolaire. Nou...
Le Centre Regional des Metiers de l'Education et de la Formation Casablanca - Settat (Section... more Le Centre Regional des Metiers de l'Education et de la Formation Casablanca - Settat (Section d'El Jadida), les departements des Mathematiques et d’Informatique CRMEF Casablanca - Settat ont organise la deuxieme edition du Colloque International CIFEM’2018 sur le theme : « Avenir de la formation et de l’enseignement des mathematiques et des sciences a l’ere du numerique» a El Jadida (Maroc), les 05 et 06 Avril 2018. Cet evenement montre la volonte des organisateurs de developper la qualite de l’enseignement des mathematiques au Maroc mais aussi en Afrique et la place importante que prend la formation dans ce developpement. Cette manifestation est d’autant plus pertinente que comme l’indique l’argumentaire accompagnant l’appel a communications les resultats d’evaluations internationales ou nationales (TIMSS) sont inquietants pour certains pays (le Maroc et la France notamment). L’amelioration des performances des eleves et des apprentissages est pour une part importante liee ...
Journal of Theoretical and Applied Information Technology
The hi-tech development has led great success in both scientific and technical fields. Therefore ... more The hi-tech development has led great success in both scientific and technical fields. Therefore we can obviously note that data processing takes less execution time and a smaller amount of human efforts. This is the advantage of the automatic line of work which aimed to reduce either physical or intellectual human effort. Furthermore it focused to let the painful and complex tasks to the machine including the computer. In our framework, the processing of medical images (brain MRI) is transferred to the computer so the setting up of processing algorithms becomes an axis of rich researches highly open to discussion and development in our work, and we know that MRI is an effective examination of disease diagnosis, In this paper, we present our own method of brain extraction inspired by different methods in the literature namely brain method (BET; BSE, MSPL; MCSTRIP; TMBE ...) and different segmentation algorithms. Then, we compare our own way to other methods with excellent results us...
In this paper, we intend to present a new method of data classification. An application of this m... more In this paper, we intend to present a new method of data classification. An application of this method to the segmentation of the MRI cerebral images will be made, to extract their different classes. The studied method is the one of the fuzzy c-means making intervene of the spatial information. The spatial information is the decision by focusing on the neighbourhood (DFN) for the pixels not having a strong degree of membership after the fuzzy partition. The introduction of the spatial information has been made in the goal to get more homogeneous regions, to reduce the spurious blobs and to have a less noise sensitive method. The convergence speed of the method has been improved considerably by avoiding a random initialization of the class centers for the FCM.
On se propose de présenter une nouvelle méthode de classification de données. Une application de ... more On se propose de présenter une nouvelle méthode de classification de données. Une application de cette méthode à la segmentation des images IRM cérébrales sera faite, pour extraire les différentes classes de tissus. La méthode étudiée est celle des c-moyennes floues faisant intervenir des informations spatiales. L’information spatiale proposée est la décision par focalisation sur le voisinage (DFV) pour les pixels n’ayant pas un fort degré d’appartenance après la partition floue. L’introduction des informations spatiales a été faite dans le but d’obtenir des régions plus homogènes, réduire les fausses tâches et avoir une méthode moins sensible au bruit.
RESUME : Dans cet article on se propose de présenter un algorithme parallèle de classification de... more RESUME : Dans cet article on se propose de présenter un algorithme parallèle de classification de données. Une application de cet algorithme à la segmentation des images IRM sera faite pour extraire leurs différentes classes. La méthode de classification étudiée est celle reconnue par la méthode des nuées dynamiques ou k-moyennes. L'introduction des ar-chitectures parallèles au niveau des algorithmes utilisés dans le domaine de classification est proposée dans le but d'améliorer leurs complexités et de les rendre sous formes de procédures de prétraitement. L'algorithme proposé est destiné à être implémenté dans une machine parallèle : la maille connexe reconfigurable (MCR). L'image (m x n) à traiter doit être stockée dans la MCR de même taille à raison d'un pixel par processeur élémentaire (PE).
In this paper, we present a method of data classification. An application of this method to the s... more In this paper, we present a method of data classification. An application of this method to the segmentation of the MRI cerebral images will be made, to extract their different classes. The studied method is the one of the fuzzy c-means making intervene of spatial information. The spatial information is the decision by focusing on the neighbourhood (DFN) for the pixels not having a strong degree of membership after the fuzzy partition. The introduction of the spatial information has been made in the goal to get more homogeneous regions, to reduce the spurious blobs and to have a less noise sensitive method. The convergence speed of the method has been considerably improved by avoiding a random initialization of the cluster centers for the FCM.
In the domain of medical imaging, accurate segmentation of brain MR images is of interest for man... more In the domain of medical imaging, accurate segmentation of brain MR images is of interest for many brain manipulations. However, due to several factors such noise, imaging artefacts, intrinsic tissue variation and partial volume effects, tissue segmentation remains a challenging task. So, in this paper, a full automatic method for segmentation of brain MR images is presented. The method consists of four steps segmentation procedure. First, noise removing by median filtering is done; second segmentation of brain/non-brain tissue is performed by using a Threshold Morphologic Brain Extraction method (TMBE). Then initial centroids estimation by gray level histogram analysis based is executed. Finally, Modified Fuzzy Cmeans Algorithm is used for MRI tissue segmentation. The TMBE efficiency is demonstrated by extensive segmentation experiments using simulated and real MR images and compared with three similar techniques through well known performance measure
In this paper we present the design of a parallel distributed computing middleware for high perfo... more In this paper we present the design of a parallel distributed computing middleware for high performance computing. The middleware allows each developer to create its specific applications. These applications are assigned to be implemented on a grid of computers linked by a local or a remote network. The designed software infrastructure of each node of the grid is based mainly on middleware, for data broadcasting and tasks distribution, and an application server that lets us deploy and launch the execution of parallel programs from any node of the Grid computing. The parallel application based in this middleware can be implemented in different languages. In this paper, we present the java implementation of this middleware. To valid the performance of this Middleware, the paper presents two examples of parallel filtering and segmentation c-means algorithms, using program code and flow sheet.
In medical imaging, accurate segmentation of brain MR images is of interest for many brain manipu... more In medical imaging, accurate segmentation of brain MR images is of interest for many brain manipulations. However, due to several factors such noise, imaging artefacts, intrinsic tissue variation and partial volume effects, tissue segmentation remains a challenging task. So, in this paper, a fast and accurate method for segmentation of brain MR images is presented. The method consists of five steps. First, noise removing by median filtering is done; second segmentation of brain/non-brain tissue is performed by a Threshold Morphologic Brain Extraction method (TMBE). Then initial centroids estimation by gray level histogram analysis is executed. This step leads to the proposition of a Modified Fuzzy C-means (MFCM) Algorithm that is used for brain MRI tissues segmentation. Finally transformation of the fuzzy partition realised by MFCM to crisp one (defuzzyfication) is done using function of Decision by Focusing on the Neighbourhood (DFN). The TMBE efficiency is demonstrated by extensiv...
Bulletin of Electrical Engineering and Informatics
The computation of network reliability for a system with many states is an NP-hard issue. Finding... more The computation of network reliability for a system with many states is an NP-hard issue. Finding all the minimum path vectors (d-MPs) lower boundary points for each level d is one of the few approaches for computing such dependability. This research proposed enhancements to the technique described in Chen's "Searching for d-MPs with rapid enumeration" paper. We propose additional adjustments to the method that creates the flow vector F in this enhancement. This decreases the number of required steps and the temporal complexity of the method. Comparing the newly suggested approach to the old algorithm reveals that the adjustment has increased the enumeration's efficiency and degree of complexity.
2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022
Detection of Parkinson's disease remains challenge for physicians, especially, in the clinica... more Detection of Parkinson's disease remains challenge for physicians, especially, in the clinical field due to the difficulty of cure. Thus, algorithms of classification have the main role in the assessment of this neurodegenerative disorder. In this paper, we focus on the analysis and the evaluation of nine Machine Learning Algorithms (MLA), namely Support Vector Machine (SVM), Logistic Regression, Discriminant Analysis, K-Nearest Neighbors (KNN), Decision tree, Random Forest, Bagging tree, Naïve Bayes, and AdaBoost. Classification algorithms were applied to a Parkinson's dataset of 240 speech measurements with 44 features using several evaluation parameters to establish the efficiency score of each classifier. We found that the KNN classifier yielded the highest accuracy rate of 97.22% and F1-score of 97.30%.
2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022
To compute system reliability, many approaches are available in the literature. One of the most u... more To compute system reliability, many approaches are available in the literature. One of the most used approaches is the enumeration method, minimal paths or minimal cuts. Most of these approaches enumerate the minimal paths to evaluate reliability, but few of them used minimal cuts. This paper proposes a new direct method that enumerates all the minimal cuts with nodes failure. Unlike the algorithms in the literature that use indirect methods based on finding minimal paths to extract the minimal cuts from them.
2022 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), 2022
Many technological networks that execute their tasks with different levels of distinctive efficie... more Many technological networks that execute their tasks with different levels of distinctive efficiency are multi-state systems, and reliability is an essential predicate for their safe operation and optimal improvement. In this paper, a survey of recent progress of the evaluation of exact reliability for multi-state system is presented. A general method for the reliability evaluation of multi-state system is using d-minimal paths. Many methods have been proposed in the literature for the enumeration of the d-MPs, most of this works are based on the minimal paths (MPs). This article provides the most recent algorithms used for the evaluation of the exact reliability for multi-state systems, and discusses the basic idea of each algorithm.
La fraude aux examens scolaire a fait l’objet ces dernières années l’objet d’une forte médiatisat... more La fraude aux examens scolaire a fait l’objet ces dernières années l’objet d’une forte médiatisation, en particulier à l’approche des examens. Par ailleurs, les enseignants se plaignent de plus en plus des apprenants et des étudiants qui utilisent leur téléphone pendant les épreuves. Avec l’arrivée de la technologie dans les classes et l’utilisation courante d’Internet dans les activités scolaires, les apprenants et les étudiants ont davantage d’opportunités de plagier des documents ou de frauder lors des épreuves sur table. L’intégration des nouvelles technologies de l’information et de la communication dans l’ensemble de corps scolaire nous a amené à poser la question du mode d’évaluation. À travers ce travail, nous avons procédé à une recherche exploratoire, à travers un questionnaire élaboré par le logiciel Sphinx. L’analyse des données par Sphinx et par le test de confiance khideux, nous a permis de déterminer un aperçu sur l’ampleur de ce phénomène dans le milieu scolaire. Nou...
Le Centre Regional des Metiers de l'Education et de la Formation Casablanca - Settat (Section... more Le Centre Regional des Metiers de l'Education et de la Formation Casablanca - Settat (Section d'El Jadida), les departements des Mathematiques et d’Informatique CRMEF Casablanca - Settat ont organise la deuxieme edition du Colloque International CIFEM’2018 sur le theme : « Avenir de la formation et de l’enseignement des mathematiques et des sciences a l’ere du numerique» a El Jadida (Maroc), les 05 et 06 Avril 2018. Cet evenement montre la volonte des organisateurs de developper la qualite de l’enseignement des mathematiques au Maroc mais aussi en Afrique et la place importante que prend la formation dans ce developpement. Cette manifestation est d’autant plus pertinente que comme l’indique l’argumentaire accompagnant l’appel a communications les resultats d’evaluations internationales ou nationales (TIMSS) sont inquietants pour certains pays (le Maroc et la France notamment). L’amelioration des performances des eleves et des apprentissages est pour une part importante liee ...
Journal of Theoretical and Applied Information Technology
The hi-tech development has led great success in both scientific and technical fields. Therefore ... more The hi-tech development has led great success in both scientific and technical fields. Therefore we can obviously note that data processing takes less execution time and a smaller amount of human efforts. This is the advantage of the automatic line of work which aimed to reduce either physical or intellectual human effort. Furthermore it focused to let the painful and complex tasks to the machine including the computer. In our framework, the processing of medical images (brain MRI) is transferred to the computer so the setting up of processing algorithms becomes an axis of rich researches highly open to discussion and development in our work, and we know that MRI is an effective examination of disease diagnosis, In this paper, we present our own method of brain extraction inspired by different methods in the literature namely brain method (BET; BSE, MSPL; MCSTRIP; TMBE ...) and different segmentation algorithms. Then, we compare our own way to other methods with excellent results us...
In this paper, we intend to present a new method of data classification. An application of this m... more In this paper, we intend to present a new method of data classification. An application of this method to the segmentation of the MRI cerebral images will be made, to extract their different classes. The studied method is the one of the fuzzy c-means making intervene of the spatial information. The spatial information is the decision by focusing on the neighbourhood (DFN) for the pixels not having a strong degree of membership after the fuzzy partition. The introduction of the spatial information has been made in the goal to get more homogeneous regions, to reduce the spurious blobs and to have a less noise sensitive method. The convergence speed of the method has been improved considerably by avoiding a random initialization of the class centers for the FCM.
On se propose de présenter une nouvelle méthode de classification de données. Une application de ... more On se propose de présenter une nouvelle méthode de classification de données. Une application de cette méthode à la segmentation des images IRM cérébrales sera faite, pour extraire les différentes classes de tissus. La méthode étudiée est celle des c-moyennes floues faisant intervenir des informations spatiales. L’information spatiale proposée est la décision par focalisation sur le voisinage (DFV) pour les pixels n’ayant pas un fort degré d’appartenance après la partition floue. L’introduction des informations spatiales a été faite dans le but d’obtenir des régions plus homogènes, réduire les fausses tâches et avoir une méthode moins sensible au bruit.
RESUME : Dans cet article on se propose de présenter un algorithme parallèle de classification de... more RESUME : Dans cet article on se propose de présenter un algorithme parallèle de classification de données. Une application de cet algorithme à la segmentation des images IRM sera faite pour extraire leurs différentes classes. La méthode de classification étudiée est celle reconnue par la méthode des nuées dynamiques ou k-moyennes. L'introduction des ar-chitectures parallèles au niveau des algorithmes utilisés dans le domaine de classification est proposée dans le but d'améliorer leurs complexités et de les rendre sous formes de procédures de prétraitement. L'algorithme proposé est destiné à être implémenté dans une machine parallèle : la maille connexe reconfigurable (MCR). L'image (m x n) à traiter doit être stockée dans la MCR de même taille à raison d'un pixel par processeur élémentaire (PE).
In this paper, we present a method of data classification. An application of this method to the s... more In this paper, we present a method of data classification. An application of this method to the segmentation of the MRI cerebral images will be made, to extract their different classes. The studied method is the one of the fuzzy c-means making intervene of spatial information. The spatial information is the decision by focusing on the neighbourhood (DFN) for the pixels not having a strong degree of membership after the fuzzy partition. The introduction of the spatial information has been made in the goal to get more homogeneous regions, to reduce the spurious blobs and to have a less noise sensitive method. The convergence speed of the method has been considerably improved by avoiding a random initialization of the cluster centers for the FCM.
In the domain of medical imaging, accurate segmentation of brain MR images is of interest for man... more In the domain of medical imaging, accurate segmentation of brain MR images is of interest for many brain manipulations. However, due to several factors such noise, imaging artefacts, intrinsic tissue variation and partial volume effects, tissue segmentation remains a challenging task. So, in this paper, a full automatic method for segmentation of brain MR images is presented. The method consists of four steps segmentation procedure. First, noise removing by median filtering is done; second segmentation of brain/non-brain tissue is performed by using a Threshold Morphologic Brain Extraction method (TMBE). Then initial centroids estimation by gray level histogram analysis based is executed. Finally, Modified Fuzzy Cmeans Algorithm is used for MRI tissue segmentation. The TMBE efficiency is demonstrated by extensive segmentation experiments using simulated and real MR images and compared with three similar techniques through well known performance measure
In this paper we present the design of a parallel distributed computing middleware for high perfo... more In this paper we present the design of a parallel distributed computing middleware for high performance computing. The middleware allows each developer to create its specific applications. These applications are assigned to be implemented on a grid of computers linked by a local or a remote network. The designed software infrastructure of each node of the grid is based mainly on middleware, for data broadcasting and tasks distribution, and an application server that lets us deploy and launch the execution of parallel programs from any node of the Grid computing. The parallel application based in this middleware can be implemented in different languages. In this paper, we present the java implementation of this middleware. To valid the performance of this Middleware, the paper presents two examples of parallel filtering and segmentation c-means algorithms, using program code and flow sheet.
In medical imaging, accurate segmentation of brain MR images is of interest for many brain manipu... more In medical imaging, accurate segmentation of brain MR images is of interest for many brain manipulations. However, due to several factors such noise, imaging artefacts, intrinsic tissue variation and partial volume effects, tissue segmentation remains a challenging task. So, in this paper, a fast and accurate method for segmentation of brain MR images is presented. The method consists of five steps. First, noise removing by median filtering is done; second segmentation of brain/non-brain tissue is performed by a Threshold Morphologic Brain Extraction method (TMBE). Then initial centroids estimation by gray level histogram analysis is executed. This step leads to the proposition of a Modified Fuzzy C-means (MFCM) Algorithm that is used for brain MRI tissues segmentation. Finally transformation of the fuzzy partition realised by MFCM to crisp one (defuzzyfication) is done using function of Decision by Focusing on the Neighbourhood (DFN). The TMBE efficiency is demonstrated by extensiv...
Uploads