Mohamed Benaddy | Ibn Zohr University, Agadir, Morocco (original) (raw)
Papers by Mohamed Benaddy
2017 International Conference on Engineering & MIS (ICEMIS), 2017
As an application of nanonotechnology, in this paper, we study a cell age-structured epidemic mod... more As an application of nanonotechnology, in this paper, we study a cell age-structured epidemic model. By the theory of semigroups and perturbation of linear operators we investigate the well-posedness of the system governed the model. Moreover, by the positivity, irreducibility and spectral theory we proof that the system converge to steady-state solution.
International Journal of Computer Applications, May 31, 2012
In this work we present a new and efficient recursive algorithm that enumerate all the s-t minima... more In this work we present a new and efficient recursive algorithm that enumerate all the s-t minimal cut sets (MCs) separating nodes s (source) and t (terminal) in a network system. The networks studied here are considered as the undirected graphs. Later enumerating all the MCs, the inclusion-exclusion principle is used to compute the network reliability based on the probabilities of the links.
Lecture notes in networks and systems, Aug 3, 2022
HAL (Le Centre pour la Communication Scientifique Directe), Jun 17, 2019
La réalisation d'un système précis de reconnaissance des langues de signes arabe (RLSAr) a un lar... more La réalisation d'un système précis de reconnaissance des langues de signes arabe (RLSAr) a un large impact social. Un tel système rendra la communication facile entre les sourds-muets et les citoyens ordinaires dans le monde arabe. Cependant, la réalisation d'un système (RLSAr) reste très difficile à réaliser puisque la (LSA) présente de nombreux détails et caractéristiques en raison des grandes variations dans les actions des mains. Dans ce travail, nous proposons un système de (RLSAr) basé sur les réseaux de neurones convolutionnels qui extrait automatiquement les caractéristiques discriminantes des signes représentant les chiffres et les caractères. Nous validons le système proposé sur un jeu de données réel et nous démontrons son efficacité par rapport aux approches traditionnelles basés sur les kplus proches voisins (KNN) machines à vecteurs de support (SVM). Mots clés : Langage de signes arabe, Apprentissage profond, réseaux de neurones convolutionnels (CNNs), reconnaissance des gestes.
Multimedia Tools and Applications
Displays
Video to text conversion is a vital activity in the field of computer vision. In recent years, de... more Video to text conversion is a vital activity in the field of computer vision. In recent years, deep learning algorithms have dominated automatic text generation in English, but there are a few research works available for other languages. In this paper, we propose a novel encoding-decoding system that generates character-level Arabic sentences from isolated RGB videos of Moroccan sign language. The video sequence was encoded by a spatiotemporal feature extraction using pose estimation models, while the label text of the video is transmitted to a sequence of representative vectors. Both the features and the label vector are joined and treated by a decoder layer to derive a final prediction. We trained the proposed system on an isolated Moroccan Sign Language dataset (MoSLD), composed of RGB videos from 125 MoSL signs. The experimental results reveal that the proposed model attains the best performance under several evaluation metrics. ✩ This paper was recommended for publication by G. Guangtao Zhai.
2017 International Conference on Engineering & MIS (ICEMIS)
Many applications of wireless sensor networks are critical such as, medical, crisis management, e... more Many applications of wireless sensor networks are critical such as, medical, crisis management, environmental, military, transportation, emergency, security applications. These applications require reliable data collection and achievement. Researchers have been investigated in this area proposing many techniques for WSN reliability meet, such as redundancy or retransmission mechanisms or multipaths routing protocols, some of these techniques dont care about the WSN limitation resources such as energy consumption. In this paper we propose a multipath routing algorithm for WSN for reliability data transmission, considering distance and energy consumption constraints.
International Journal of Engineering, Science and Mathematics, 2018
Signal, Image and Video Processing, 2022
2017 International Conference on Engineering & MIS (ICEMIS), 2017
His paper present a new Low Drop-Out Voltage Regulator (LDO) and highlight the topologies and the... more His paper present a new Low Drop-Out Voltage Regulator (LDO) and highlight the topologies and the advantages of the LDO for hardware security protection of Wireless Sensor Networks (WSNs), this integrated circuits are considered as an ideal solution in low power System on-chip applications (SOC) for their compact sizes and low cost. The advancement in lowpower design makes it possible that ubiquitous device can be powered by low-power energy source such as ambient energy or small size batteries. In many well supplied devices the problem related to power is essentially related to cost. However for lowpowered devices the problem of power is not only economics but also becomes very essential in terms of functionality. Due to the usual very small amount of energy or unstable energy available the way the engineer manages power becomes a key point in this area. Therefore, another focus of this dissertation is to try finding ways to improve the security of power management problems. Complementary metal oxide-semiconductor (CMOS) has become the predominant technology in integrated circuit design due to its high density, power savings and low manufacturing costs. The whole integrated circuit industry will still continue to benefit from the geometric downsizing that comes with every new generation of semiconductor manufacturing processes. Therefore, only several CMOS analog integrated circuit design techniques are proposed for low-powered ubiquitous device in this dissertation. This paper reviews the basics of LDO regulators and discusses the technology advances in the latest generation of LDOs that make them the preferred solution for many points of load power requirements. The paper will also introduce characteristics of CMOS LDO regulators and discuss their unique benefits in portable electronics applications. these new device offer a real advantages for the power management security of new applications mobile. Power efficiency and some practical issues for the CMOS implementation of these LDO structures are discussed.
2009 IEEE/ACS International Conference on Computer Systems and Applications, 2009
An evolutionary neural network modeling approach for software cumulative failure prediction based... more An evolutionary neural network modeling approach for software cumulative failure prediction based on feed-forward neural network is proposed. A real coded genetic algorithm is used to optimize the mean square of the error produced by training a neural network established by Aljahdali S. [3]. In this paper we present a real coded genetic algorithm that uses the appropriate operators for this encoding type to train feed-forward neural network. We describe the genetic algorithm and we also experimentally compare our approach with the back propagation learning algorithm for the regression model order 4. Numerical results show that both the goodness-offit and the next-step-predictability of our proposed approach have greater accuracy in predicting software cumulative failure compared to other approaches.
2011 Eighth International Conference on Information Technology: New Generations, 2011
In the past 35 years more than 100 software reliability models are proposed. Most of them are par... more In the past 35 years more than 100 software reliability models are proposed. Most of them are parametric models. In this paper we present a comparative study of different non-parametric models based on the neural networks and regression model learned by the real coded genetic algorithm to predict the cumulative failure in the software. Experimental results show that the training of different models by our real coded genetic algorithm have a good predictive capability across different projects.
Software failure occurs when the software runs in an operational profile. Controlling failures in... more Software failure occurs when the software runs in an operational profile. Controlling failures in software require that one can predict problems early enough to take preventive action. The prediction of software failures is done by using the historical failures collected previously when they occur. To predict software failures, several models are proposed by researchers. In this paper, we present a recurrent neural network (RNN) to predict software failure using historical failure data. The proposed RNN is trained and tested using collected data from the literature; the obtained results are compared with other models and show that our proposed model gives very attractive prediction rates.
2017 International Conference on Engineering & MIS (ICEMIS), 2017
The objective of low-resolution face recognition is to identify faces in an uncontrolled situatio... more The objective of low-resolution face recognition is to identify faces in an uncontrolled situations like from small size or poor quality images with varying pose, illumination, expression, etc. Most existing approaches use features of just one type. In this work, we propose a robust low face recognition technique based on unimodal features fusion, which is more discriminative than using only one feature modality. Features of each facial image are extracted using three steps: i) both Gabor filters and Histogram of Oriented Gradients (HOG) descriptor are calculated. ii) the size of these features is reduced using the Linear Discriminant Analysis (LDA) method in order to remove redundant information. iii) the reduced features are combined using Discriminant Correlation Analysis (DCA) method. To achieve the recognition task, a Support Vectors Machine Classifier, is used. Performance of the proposed method will be measured using the AR database.
International Journal of Computer Applications, 2012
In this work we present a new and efficient recursive algorithm that enumerate all the s-t minima... more In this work we present a new and efficient recursive algorithm that enumerate all the s-t minimal cut sets (MCs) separating nodes s (source) and t (terminal) in a network system. The networks studied here are considered as the undirected graphs. Later enumerating all the MCs, the inclusion-exclusion principle is used to compute the network reliability based on the probabilities of the links. General Terms Networked System Reliability, Algorithms, Optimisation and Modelling.
La realisation d'un systeme precis de reconnaissance des langues de signes arabe (RLSAr) a un... more La realisation d'un systeme precis de reconnaissance des langues de signes arabe (RLSAr) a un large impact social. Un tel systeme rendra la communication facile entre les sourds-muets et les citoyens ordinaires dans le monde arabe. Cependant, la realisation d'un systeme (RLSAr) reste tres difficile a realiser puisque la (LSA) presente de nombreux details et caracteristiques en raison des grandes variations dans les actions des mains. Dans ce travail, nous proposons un systeme de (RLSAr) base sur les reseaux de neurones convolutionnels qui extrait automatiquement les caracteristiques discriminantes des signes representant les chiffres et les caracteres. Nous validons le systeme propose sur un jeu de donnees reel et nous demontrons son efficacite par rapport aux approches traditionnelles bases sur les k-plus proches voisins (KNN) machines a vecteurs de support (SVM)
The international air transport association 2036 forecast reveals that air passenger will nearly ... more The international air transport association 2036 forecast reveals that air passenger will nearly double to 7.8 billion [1], which means that the rate of air traffic will increase exponentially. To keep these numbers of aircrafts at safe distances from each other, to direct them during takeoff and landing from airports, to direct them around bad weather and ensure that traffic flows smoothly with minimal delays; The optimization and automation of air traffic control has been the subject of several studies in the last decades. The objective of this paper is to review systematically current research in the literature about the automation and optimization of air traffic control system.
Ontologies have recently received popularity in the area of knowledge management and knowledge sh... more Ontologies have recently received popularity in the area of knowledge management and knowledge sharing, especially after the evolution of the Semantic Web and its supporting technologies. An ontology defines the terms and concepts (meaning) used to describe and represent an area of knowledge. The aim of this paper is to identify the basics notions of ontologies and ontology management tools specially protégé that are freely available and the process development of semantic web notions. The Semantic Web vision have lead to a number of standards such as OWL and Web Semantic Mining. While these standards provide a technical infrastructure, developers have little guidance on how to build real-world Semantic Web applications. We will start by some definitions of Semantic Web and the common points with Web Mining. We will illustrate how these notions can be put into practice using the modern Semantic Web development tool Protege, and indicate future possibilities;
2017 International Conference on Engineering & MIS (ICEMIS), 2017
As an application of nanonotechnology, in this paper, we study a cell age-structured epidemic mod... more As an application of nanonotechnology, in this paper, we study a cell age-structured epidemic model. By the theory of semigroups and perturbation of linear operators we investigate the well-posedness of the system governed the model. Moreover, by the positivity, irreducibility and spectral theory we proof that the system converge to steady-state solution.
International Journal of Computer Applications, May 31, 2012
In this work we present a new and efficient recursive algorithm that enumerate all the s-t minima... more In this work we present a new and efficient recursive algorithm that enumerate all the s-t minimal cut sets (MCs) separating nodes s (source) and t (terminal) in a network system. The networks studied here are considered as the undirected graphs. Later enumerating all the MCs, the inclusion-exclusion principle is used to compute the network reliability based on the probabilities of the links.
Lecture notes in networks and systems, Aug 3, 2022
HAL (Le Centre pour la Communication Scientifique Directe), Jun 17, 2019
La réalisation d'un système précis de reconnaissance des langues de signes arabe (RLSAr) a un lar... more La réalisation d'un système précis de reconnaissance des langues de signes arabe (RLSAr) a un large impact social. Un tel système rendra la communication facile entre les sourds-muets et les citoyens ordinaires dans le monde arabe. Cependant, la réalisation d'un système (RLSAr) reste très difficile à réaliser puisque la (LSA) présente de nombreux détails et caractéristiques en raison des grandes variations dans les actions des mains. Dans ce travail, nous proposons un système de (RLSAr) basé sur les réseaux de neurones convolutionnels qui extrait automatiquement les caractéristiques discriminantes des signes représentant les chiffres et les caractères. Nous validons le système proposé sur un jeu de données réel et nous démontrons son efficacité par rapport aux approches traditionnelles basés sur les kplus proches voisins (KNN) machines à vecteurs de support (SVM). Mots clés : Langage de signes arabe, Apprentissage profond, réseaux de neurones convolutionnels (CNNs), reconnaissance des gestes.
Multimedia Tools and Applications
Displays
Video to text conversion is a vital activity in the field of computer vision. In recent years, de... more Video to text conversion is a vital activity in the field of computer vision. In recent years, deep learning algorithms have dominated automatic text generation in English, but there are a few research works available for other languages. In this paper, we propose a novel encoding-decoding system that generates character-level Arabic sentences from isolated RGB videos of Moroccan sign language. The video sequence was encoded by a spatiotemporal feature extraction using pose estimation models, while the label text of the video is transmitted to a sequence of representative vectors. Both the features and the label vector are joined and treated by a decoder layer to derive a final prediction. We trained the proposed system on an isolated Moroccan Sign Language dataset (MoSLD), composed of RGB videos from 125 MoSL signs. The experimental results reveal that the proposed model attains the best performance under several evaluation metrics. ✩ This paper was recommended for publication by G. Guangtao Zhai.
2017 International Conference on Engineering & MIS (ICEMIS)
Many applications of wireless sensor networks are critical such as, medical, crisis management, e... more Many applications of wireless sensor networks are critical such as, medical, crisis management, environmental, military, transportation, emergency, security applications. These applications require reliable data collection and achievement. Researchers have been investigated in this area proposing many techniques for WSN reliability meet, such as redundancy or retransmission mechanisms or multipaths routing protocols, some of these techniques dont care about the WSN limitation resources such as energy consumption. In this paper we propose a multipath routing algorithm for WSN for reliability data transmission, considering distance and energy consumption constraints.
International Journal of Engineering, Science and Mathematics, 2018
Signal, Image and Video Processing, 2022
2017 International Conference on Engineering & MIS (ICEMIS), 2017
His paper present a new Low Drop-Out Voltage Regulator (LDO) and highlight the topologies and the... more His paper present a new Low Drop-Out Voltage Regulator (LDO) and highlight the topologies and the advantages of the LDO for hardware security protection of Wireless Sensor Networks (WSNs), this integrated circuits are considered as an ideal solution in low power System on-chip applications (SOC) for their compact sizes and low cost. The advancement in lowpower design makes it possible that ubiquitous device can be powered by low-power energy source such as ambient energy or small size batteries. In many well supplied devices the problem related to power is essentially related to cost. However for lowpowered devices the problem of power is not only economics but also becomes very essential in terms of functionality. Due to the usual very small amount of energy or unstable energy available the way the engineer manages power becomes a key point in this area. Therefore, another focus of this dissertation is to try finding ways to improve the security of power management problems. Complementary metal oxide-semiconductor (CMOS) has become the predominant technology in integrated circuit design due to its high density, power savings and low manufacturing costs. The whole integrated circuit industry will still continue to benefit from the geometric downsizing that comes with every new generation of semiconductor manufacturing processes. Therefore, only several CMOS analog integrated circuit design techniques are proposed for low-powered ubiquitous device in this dissertation. This paper reviews the basics of LDO regulators and discusses the technology advances in the latest generation of LDOs that make them the preferred solution for many points of load power requirements. The paper will also introduce characteristics of CMOS LDO regulators and discuss their unique benefits in portable electronics applications. these new device offer a real advantages for the power management security of new applications mobile. Power efficiency and some practical issues for the CMOS implementation of these LDO structures are discussed.
2009 IEEE/ACS International Conference on Computer Systems and Applications, 2009
An evolutionary neural network modeling approach for software cumulative failure prediction based... more An evolutionary neural network modeling approach for software cumulative failure prediction based on feed-forward neural network is proposed. A real coded genetic algorithm is used to optimize the mean square of the error produced by training a neural network established by Aljahdali S. [3]. In this paper we present a real coded genetic algorithm that uses the appropriate operators for this encoding type to train feed-forward neural network. We describe the genetic algorithm and we also experimentally compare our approach with the back propagation learning algorithm for the regression model order 4. Numerical results show that both the goodness-offit and the next-step-predictability of our proposed approach have greater accuracy in predicting software cumulative failure compared to other approaches.
2011 Eighth International Conference on Information Technology: New Generations, 2011
In the past 35 years more than 100 software reliability models are proposed. Most of them are par... more In the past 35 years more than 100 software reliability models are proposed. Most of them are parametric models. In this paper we present a comparative study of different non-parametric models based on the neural networks and regression model learned by the real coded genetic algorithm to predict the cumulative failure in the software. Experimental results show that the training of different models by our real coded genetic algorithm have a good predictive capability across different projects.
Software failure occurs when the software runs in an operational profile. Controlling failures in... more Software failure occurs when the software runs in an operational profile. Controlling failures in software require that one can predict problems early enough to take preventive action. The prediction of software failures is done by using the historical failures collected previously when they occur. To predict software failures, several models are proposed by researchers. In this paper, we present a recurrent neural network (RNN) to predict software failure using historical failure data. The proposed RNN is trained and tested using collected data from the literature; the obtained results are compared with other models and show that our proposed model gives very attractive prediction rates.
2017 International Conference on Engineering & MIS (ICEMIS), 2017
The objective of low-resolution face recognition is to identify faces in an uncontrolled situatio... more The objective of low-resolution face recognition is to identify faces in an uncontrolled situations like from small size or poor quality images with varying pose, illumination, expression, etc. Most existing approaches use features of just one type. In this work, we propose a robust low face recognition technique based on unimodal features fusion, which is more discriminative than using only one feature modality. Features of each facial image are extracted using three steps: i) both Gabor filters and Histogram of Oriented Gradients (HOG) descriptor are calculated. ii) the size of these features is reduced using the Linear Discriminant Analysis (LDA) method in order to remove redundant information. iii) the reduced features are combined using Discriminant Correlation Analysis (DCA) method. To achieve the recognition task, a Support Vectors Machine Classifier, is used. Performance of the proposed method will be measured using the AR database.
International Journal of Computer Applications, 2012
In this work we present a new and efficient recursive algorithm that enumerate all the s-t minima... more In this work we present a new and efficient recursive algorithm that enumerate all the s-t minimal cut sets (MCs) separating nodes s (source) and t (terminal) in a network system. The networks studied here are considered as the undirected graphs. Later enumerating all the MCs, the inclusion-exclusion principle is used to compute the network reliability based on the probabilities of the links. General Terms Networked System Reliability, Algorithms, Optimisation and Modelling.
La realisation d'un systeme precis de reconnaissance des langues de signes arabe (RLSAr) a un... more La realisation d'un systeme precis de reconnaissance des langues de signes arabe (RLSAr) a un large impact social. Un tel systeme rendra la communication facile entre les sourds-muets et les citoyens ordinaires dans le monde arabe. Cependant, la realisation d'un systeme (RLSAr) reste tres difficile a realiser puisque la (LSA) presente de nombreux details et caracteristiques en raison des grandes variations dans les actions des mains. Dans ce travail, nous proposons un systeme de (RLSAr) base sur les reseaux de neurones convolutionnels qui extrait automatiquement les caracteristiques discriminantes des signes representant les chiffres et les caracteres. Nous validons le systeme propose sur un jeu de donnees reel et nous demontrons son efficacite par rapport aux approches traditionnelles bases sur les k-plus proches voisins (KNN) machines a vecteurs de support (SVM)
The international air transport association 2036 forecast reveals that air passenger will nearly ... more The international air transport association 2036 forecast reveals that air passenger will nearly double to 7.8 billion [1], which means that the rate of air traffic will increase exponentially. To keep these numbers of aircrafts at safe distances from each other, to direct them during takeoff and landing from airports, to direct them around bad weather and ensure that traffic flows smoothly with minimal delays; The optimization and automation of air traffic control has been the subject of several studies in the last decades. The objective of this paper is to review systematically current research in the literature about the automation and optimization of air traffic control system.
Ontologies have recently received popularity in the area of knowledge management and knowledge sh... more Ontologies have recently received popularity in the area of knowledge management and knowledge sharing, especially after the evolution of the Semantic Web and its supporting technologies. An ontology defines the terms and concepts (meaning) used to describe and represent an area of knowledge. The aim of this paper is to identify the basics notions of ontologies and ontology management tools specially protégé that are freely available and the process development of semantic web notions. The Semantic Web vision have lead to a number of standards such as OWL and Web Semantic Mining. While these standards provide a technical infrastructure, developers have little guidance on how to build real-world Semantic Web applications. We will start by some definitions of Semantic Web and the common points with Web Mining. We will illustrate how these notions can be put into practice using the modern Semantic Web development tool Protege, and indicate future possibilities;