Abdelkarim EL MOUATASIM

Abdelkarim EL MOUATASIM

Université Ibn Zohr

H-index: 11

Africa-Morocco

Abdelkarim EL MOUATASIM Information

University

Université Ibn Zohr

Position

- FPO

Citations(all)

333

Citations(since 2020)

214

Cited By

135

hIndex(all)

11

hIndex(since 2020)

9

i10Index(all)

13

i10Index(since 2020)

8

Email

University Profile Page

Université Ibn Zohr

Abdelkarim EL MOUATASIM Skills & Research Interests

Applied Mathematics

Top articles of Abdelkarim EL MOUATASIM

Digital handwriting characteristics for dysgraphia detection using artificial neural network

Despite all of the technical advancements in writing and text editing with keyboards on numerous devices, writing with a pen remains a fundamental ability in modern human existence. Handwriting disabilities are referred to as dysgraphia. Nonetheless, how well they are taught to write in school, 10-30% of children never attain a respectable level of handwriting. Early identification is critical because it can help children avoid difficulties in their behavioral and academic development. On blank papers attached to digital tablets, 280 individuals were asked to complete the concise evaluation scale for children’s handwriting (BHK), with 218 having typical handwriting and 62 having dysgraphia. In addition to their age and BHK quality and speed scores, 12 variables identifying digital handwriting across several domains (static, kinematic, pressure, and tilt) were collected. In this paper, we provided a rapid and automated dysgraphia classification approach using an artificial neural network (ANN) model. Using digital handwriting traits as an input to the ANN approach, the prediction findings were encouraging and very accurate, reaching 96% accuracy, and they could lead to the development of a new self-administered dysgraphia screening tool.

Authors

Mohamed Ikermane,Abdelkrim El Mouatasim

Journal

Bulletin of Electrical Engineering and Informatics

Published Date

2023/6/1

Deep Speech Recognition System Based on AutoEncoder-GAN for Biometric Access Control.

Speech recognition-based biometric access control systems are promising solutions that have resolved many issues related to security and convenience. Speech recognition, as a biometric modality, offers unique advantages such as user-friendliness and non-intrusiveness, etc. However, developing robust and accurate speaker identification and authentication systems pose challenges due to variations in speech patterns and environmental factors. Integrating deep learning techniques, especially AutoEncoder and Generative Adversarial Network models, has shown promising results in addressing these challenges. This article presents a novel approach based on the combination of two deep learning models, namely, AE and GAN for speech recognition-based biometric access control. In the model architecture, the AutoEncoder takes the MFCC coefficients as input, and the encoder converts the latter to the latent …

Authors

Oussama Mounnan,Otman Manad,Abdelkrim El Mouatasim,Larbi Boubchir,Boubaker Daachi

Journal

International Journal of Advanced Computer Science & Applications

Published Date

2023/11/1

Web-based autism screening using facial images and convolutional neural network

Developmental disabilities such as autism spectrum disorder (ASD) affect a person’s ability to interact socially, and communicate effectively and also cause behavioral issues. Children with ASD cannot be cured but they might benefit from early intervention to enhance their cognitive abilities, favorite their growth, and affect their lives and families in a positive way. Multiple standard ASD screening tools are used such as the autism diagnostic observational schedule (ADOS) and the autism diagnostic interview (ADI), which are known to be lengthy and challenging without specialist training to administrate and score. The process of ASD assessment can be time-consuming and costly, and the growing number of autistic cases worldwide indicates an urgent need for a quick, simple, and dependable self-administered autism screening tool that may be used if a child displays some of the common signs of autism, and to ensure whether or not he should seek professional full ASD diagnosis. According to a number of studies, ASD individuals exhibit facial phenotypes that are distinct from those of normally developing children. Furthermore, convolutional neural networks (CNN) have mostly found utility in image classification applications due to their high classification accuracy. Using facial images, a dense convolutional network (Densenet) model, and cloud-based advantages, in this paper we proposed a practical, fast, and easy-to-use ASD online screening approach. Easily available through the internet via the link “https://asd-detector. herokuapp. com/”, our suggested web-based screening instrument may be a practical and trustworthy tool for …

Authors

Mohamed Ikermane,AE Mouatasim

Journal

Indones. J. Electr. Eng. Comput. Sci

Published Date

2023/2

Control learning rate for autism facial detection via deep transfer learning

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects social interaction and communication. Early detection of ASD can significantly improve outcomes for individuals with the disorder, and there has been increasing interest in using machine learning techniques to aid in the diagnosis of ASD. One promising approach is the use of deep learning techniques, particularly convolutional neural networks (CNNs), to classify facial images as indicative of ASD or not. However, choosing a learning rate for optimizing the performance of these deep CNNs can be tedious and may not always result in optimal convergence. In this paper, we propose a novel approach called the control subgradient algorithm (CSA) for tackling ASD diagnosis based on facial images using deep CNNs. CSA is a variation of the subgradient method in which the learning rate is updated by a control step in each iteration of …

Authors

Abdelkrim El Mouatasim,Mohamed Ikermane

Journal

Signal, Image and Video Processing

Published Date

2023/10

Hilbert Basis Activation Function for Neural Network

Artificial neural networks (NNs) have shown remarkable success in a wide range of machine learning tasks. The activation function is a crucial component of NNs, as it introduces non-linearity and enables the network to learn complex representations. In this paper, we propose a novel activation function based on Hilbert basis, a mathematical concept from algebraic geometry. We formulate the Hilbert basis activation function and investigate its properties. We also compare its performance with popular activation functions such as ReLU and sigmoid through experiments on MNIST dataset under LeNet architecture. Our results show that the Hilbert basis activation function can improve the performance of NNs, achieving competitive accuracy and robustness via probability analysis.

Authors

JE Souza de Cursi,A El Mouatasim,T Berroug,R Ellaia

Published Date

2023/7/30

RPCGB Method for Large-Scale Global Optimization Problems

In this paper, we propose a new approach for optimizing a large-scale non-convex differentiable function subject to linear equality constraints. The proposed method, RPCGB (random perturbation of the conditional gradient method with bisection algorithm), computes a search direction by the conditional gradient, and an optimal line search is found by a bisection algorithm, which results in a decrease of the cost function. The RPCGB method is designed to guarantee global convergence of the algorithm. An implementation and testing of the method are given, with numerical results of large-scale problems that demonstrate its efficiency.

Authors

Abderrahmane Ettahiri,Abdelkrim El Mouatasim

Journal

Axioms

Published Date

2023/6/18

Stochastic perturbation of subgradient algorithm for nonconvex deep neural networks

Choosing a learning rate is a necessary part of any subgradient method optimization. With deeper models such as convolutional neural networks of image classification, fine-tuning the learning rate can quickly become tedious, and it does not always result in optimal convergence. In this work, we suggest a variation of the subgradient method in which the learning rate is updated by a control step in each iteration of each epoch. Stochastic Perturbation Subgradient Algorithm (SPSA) is our approach for tackling image classification issues with deep neural networks including convolutional neural networks. Used MNIST dataset, the numerical results reveal that our SPSA method is faster than Stochastic Gradient Descent and its variants with a fixed learning rate. However SPSA and convolutional neural network model improve the results of image classification including loss and accuracy.

Authors

Abdelkrim El Mouatasim,JE Souza de Cursi,Rachid Ellaia

Journal

Computational and Applied Mathematics

Published Date

2023/6

Web-Based Dyscalculia Screening with Unsupervised Clustering: Moroccan Fourth Grade Students

The interest in learning disability (LD) is relatively new in Morocco, not only in research but also in student detection techniques. The purpose of this study is to provide a novel dyscalculia screening method. It comprised 56 fourth-grade students (aged 8 to 11,5 years, SD = 0.74, 48% females) from two Moroccan primary public schools in Guelmim, Rabouate Assahrij, and Al Massira. The identification is based on a web-based tool that uses the nonverbal intelligence Raven’s Colored Progressive Matrices test (CPM), and The Trends in International Mathematics and Science Study (TIMSS) assessment. As a consequence, it was shown that 46 pupils evaluated had a significant probability of having dyscalculia and needs more diagnosis. They are characterized by weak nonverbal intelligence as well as a low TIMSS score respectively an average of 25,87 and 6,63 while having a long Answering duration when …

Authors

Mohamed Ikermane,A El Mouatasim

Published Date

2022/3/30

Existence, Uniqueness of Weak Solution to the Thermoelastic Plates

In this paper, we study a model of dynamic von Karman equation coupled to the thermoelastic equation, with rotational forces and not clamped boundary conditions. Our fundamental goal is to establish the existence as well as the uniqueness of a weak solution for the so-called global energy. In the end, we display a numerical simulation.

Authors

B El-Aqqad,J Oudaani,A El Mouatasim

Journal

Nonlinear Dynamics and Systems Theory

Published Date

2022

Deep Learning-Based Speech Recognition System using Blockchain for Biometric Access Control

Deep learning-based automatic speech recognition is a promising technology that has witnessed high interest from academics and industrials and proved its efficiency in several fields, including biometric access control systems. In such systems, the use of biometric data is challenging, namely in the centralized environment. It represents several risks, including information leakage, unreliability, security, privacy, etc. To tackle these issues, several approaches are proposed based on blockchain technology, which has recently gained popularity in various areas. Given the risks related to data security and many others to the technologies involved, it is essential today to have specific protection, particularly for authentication, access control, authorization, secure transfer, traceability, etc. To this end, this project aims to provide secure and intrusion-tolerant intelligent infrastructure and platform, combining the …

Authors

Oussama Mounnan,Otman Manad,Larbi Boubchir,Abdelkrim El Mouatasim,Boubaker Daachi

Published Date

2022/12/12

Conditional gradient and bisection algorithms for non-convex optimization problem with random perturbation

In this paper, we propose an implementation of stochastic perturbation of conditional gradient and bisection (SPCGB) method (aka Frank-Wolfe method) for solving non-convex differentiable programming under linear constraints. The goal is to attempt to avoid getting stuck in local optimum solutions. Theoretical results guarantee the convergence of the proposed method towards a global minimizer. To demonstrate the effectiveness of our method, some numerical results of small and medium scale problems are given.

Authors

Abdelkrim El Mouatasim,Abderrahmane Ettahiri

Journal

Appl. Math. E-Notes

Published Date

2022

Autism spectrum disorder screening using artificial neural network

Autism spectrum disorders, a neuro-developmental illness marked by deficits in social, communication, and behavioral development and associated with high healthcare expenses. Autism has no cure, and the purpose of treatment is to enhance your child’s functional abilities by lowering autism spectrum disorder symptoms. As a result, early diagnosis can significantly reduce its symptoms and promote the child’s growth and learning. The process of diagnosing autism can be lengthy and expensive, and the increasing number of Autistic cases around the world shows an urgent need for a rapid, easy, and reliable self-administered Autism screening tool that can be used by professionals, parents, and caregivers to ensure if the subject exhibits some of the typical symptoms of autism, and whether they should pursue formal clinical diagnosis or not. This paper presented an Autism spectrum disorders (ASD) screening …

Authors

Mohamed Ikermane,Abdelkrim El Mouatasim

Published Date

2022/11/24

Structural acoustic problem and dynamic nonlinear plate equations

The purpose of this paper is to investigate a structural interaction model coupled with dynamic von Karman equations, without neither rotational inertia nor clamped boundary conditions. Our fundamental goal is to establish the existence and the uniqueness of the weak solution for the so-called global functional energy. The stability is also discussed. At the end, a numerical study based on the finite difference method is presented as well.

Authors

Jaouad Oudaani,Mustapha Raïssouli,Abdelkrim El Mouatasim

Journal

Applicable Analysis

Published Date

2022/6/13

ICRAMCS 2021

ICRAMCS 2021 Page 1 ICRAMCS 2021 | Faculty of Sciences Ben M'sik, Hassan II University of Casablanca, Morocco ICRAMCS 2021 INTERNATIONAL CONFERENCE ON RESEARCH IN APPLIED MATHEMATICS AND COMPUTER SCIENCE March 26-27, 2021 | Casablanca, Morocco Implementation of Frank-Wolfe method for non-convex optimization problem via stochastic perturbation Communication Info Abstract Authors: Abderrahmane ETTAHIRI1 Abdelkrim El MOUATASIM 2 1Faculty of Polydisciplinary Ouarzazate (FPO), Ibn Zohr University, BP 284, Ouarzazate 45800, Morocco. 2Faculty of Polydisciplinary Ouarzazate (FPO), Ibn Zohr University, BP 284, Ouarzazate 45800, Morocco. Keywords: (1) Non-convex optimization (2) Linear constraints (3) Frank-Wolfe algorithm (4) Stochastic perturbation The Frank-Wolfe method (aka conditional gradient method) for smooth optimization has been of great interest in …

Authors

Abderrahmane ETTAHIRI,Abdelkrim El MOUATASIM

Published Date

2021

Accelerated diagonal steepest descent method for unconstrained multiobjective optimization

In this paper, we propose two methods for solving unconstrained multiobjective optimization problems. First, we present a diagonal steepest descent method, in which, at each iteration, a common diagonal matrix is used to approximate the Hessian of every objective function. This method works directly with the objective functions, without using any kind of a priori chosen parameters. It is proved that accumulation points of the sequence generated by the method are Pareto-critical points under standard assumptions. Based on this approach and on the Nesterov step strategy, an improved version of the method is proposed and its convergence rate is analyzed. Finally, computational experiments are presented in order to analyze the performance of the proposed methods.

Authors

Mustapha El Moudden,Abdelkrim El Mouatasim

Journal

Journal of Optimization Theory and Applications

Published Date

2021/1

A novel approach based on blockchain to enhance security with dynamic policy updating

The cipher-text policy attribute-based encryption is a promising technique to ensure the security in the third trust parties environment and offers opportunities to their users. However, the policy updating becomes a challenging issue when we use CP-ABE to construct access control schemes. The traditional method consists of presenting a huge work to the data owners, data retrieving, its re-encryption under the new access policy, and the re-sending back to the cloud. These interactions incur a heavy computation burden and a high communication on the data owner. In this paper, we propose a novel approach, in one hand, to enhance the security by using Blockchain technology, and in the other hand to update the access policy dynamically. We use Blockchain to deploy a policy in a manner that preserves security. We use also the cloud to store the data with CP-ABE, and especially, we focus on the delegation of the …

Authors

Oussama Mounnan,Abdelkrim El Mouatasim,Otman Manad,Aissam Outchakoucht,Hamza Es-Samaali,Larbi Boubchir

Published Date

2020/12/14

Uniqueness of Solution to the von Karman Equations with Free Boundary Conditions

The purpose of this paper is to give some theoretical results, under weaker hypotheses imposed on the external, internal, linear potential loads and three measurable portions with non null area of the boundary of the shallow shell, for the local existence and uniqueness of solution to the stationary von Karman equations, with free-type boundary conditions of the elastic shallow shell. Finally, in some theoretical results, we describe an iterative method for constructing a unique weak solution for the problem.

Authors

J Oudaani,A El Mouatasim,B El-Aqqad

Journal

Nonlinear Dynamics and Systems Theory

Published Date

2020

Fast gradient descent algorithm for image classification with neural networks

Any optimization of gradient descent methods involves selecting a learning rate. Tuning the learning rate can quickly become repetitive with deeper models of image classification, does not necessarily lead to optimal convergence. We proposed in this paper, a modification of the gradient descent algorithm in which the Nestrove step is added, and the learning rate is update in each epoch. Instead, we learn learning rate itself, either by Armijo rule, or by control step. Our algorithm called fast gradient descent (FGD) for solving image classification with neural networks problems, the quadratic convergence rate of FGD algorithm are proved. FGD algorithm are applicate to a MNIST dataset. The numerical experiment, show that our approach FGD algorithm is faster than gradient descent algorithms.

Authors

Abdelkrim El Mouatasim

Journal

Signal, Image and Video Processing

Published Date

2020/11

Stochastic perturbation of Frank-Wolfe method for nonconvex programming problems

In this paper, we present a random perturbation of Frank-Wolfe method (aka Conditional gradient method) for solving nonconvex differentiable programming under linear differentiable constraints. The perturbation avoids convergence to local minima. Theoretical results guarantee the convergence of the proposed method towards a global minimizer. Some numerical results of medium and large size problems are provided to show the effectiveness of our approach.

Authors

Abdelkrim El Mouatasim,Abderrahmane Ettahiri

Journal

Annals of the University of Craiova-Mathematics and Computer Science Series

Published Date

2020

Cyberspace

Cyberspace is the geographies made possible by the adoption of computer technologies into everyday life. At first, this broad description and its emphasis on plural geographies may not seem intuitive. Yet, the breadth of this description is helpful when considering the massive variety of ways that computer-related technologies are unevenly incorporated into human life. The incorporation of these technologies is altering the scales and rates at which people can organize, intervene in, and understand human and nonhuman worlds (Hayles, 1996). Yet these processes are not universal. They differ from place to place and matter in different ways for different people as individuals and collective groups. Thus, cyberspace crosses numerous social, political, economic, and cultural boundaries (Haraway, 1991, 1997). The term cyberspace was first used by novelist William Gibson (1984), but the phenomena now described …

Authors

Josh Lepawsky,Kyonghwan Park

Published Date

2006

Nesterov step reduced gradient algorithm for convex programming problems

In this paper, we proposed an implementation of method of speed reduced gradient algorithm for optimizing a convex differentiable function subject to linear equality constraints and nonnegativity bounds on the variables. In particular, at each iteration, we compute a search direction by reduced gradient, and line search by bisection algorithm or Armijo rule. Under some assumption, the convergence rate of speed reduced gradient (SRG) algorithm is proven to be significantly better, both theoretically and practically. The algorithm of SRG are programmed by Matlab, and comparing by Frank-Wolfe algorithm some problems, the numerical results which show the efficient of our approach, we give also an application to ODE, optimal control, image and video co-localization and learning machine.

Authors

Abdelkrim El Mouatasim,Yousef Farhaoui

Published Date

2020

Privacy-aware and authentication based on blockchain with fault tolerance for IoT enabled fog computing

Fog computing is a new distributed computing paradigm that extends the cloud to the network edge. Fog computing aims at improving quality of service, data access, networking, computation and storage. However, the security and privacy issues persist, even if many cloud solutions were proposed. Indeed, Fog computing introduces new challenges in terms of security and privacy, due to its specific features such as mobility, geo-distribution and heterogeneity etc. Blockchain is an emergent concept bringing efficiency in many fields. In this paper, we propose a new access control scheme based on blockchain technology for the fog computing with fault tolerance in the context of the Internet of Things. Blockchain is used to provide secure management authentication and access process to IoT devices. Each network entity authenticates in the blockchain via the wallet, which allows a secure communication in …

Authors

Oussama Mounnan,Abdelkrim El Mouatasim,Otman Manad,Tarik Hidar,Anas Abou El Kalam,Noureddine Idboufker

Published Date

2020/4/20

2020 7TH INTERNATIONAL CONFERENCE ON INTERNET OF THINGS: SYSTEMS, MANAGEMENT AND SECURITY, IOTSMS 2020

2020 7th International Conference on Internet of Things: Systems, Management and Security (IOTSMS) - Archive ouverte HAL Accéder directement au contenu Documentation FR Français (FR) Anglais (EN) Se connecter HAL science ouverte Recherche Loading... Recherche avancée Information de documents Titres Titres Sous-titre Titre de l'ouvrage Titre du volume (Série) Champ de recherche par défaut (multicritères) + texte intégral des PDF Résumé Texte intégral indexé des documents PDF Mots-clés Type de document Sous-type de document Tous les identifiants du document Identifiant HAL du dépôt Langue du document (texte) Pays (Texte) Ville À paraître (true ou false) Ajouter Auteur Auteur (multicritères) Auteur (multicritères) Auteur : Nom complet Auteur : Nom de famille Auteur : Prénom Auteur : Complément de nom, deuxième prénom Auteur : Organisme payeur Auteur : IdHal (chaîne de caractères) …

Authors

Larbi Boubchir,Elhadj Benkhelifa,Yaser Jararweh,Imad Saleh

Published Date

2020

See List of Professors in Abdelkarim EL MOUATASIM University(Université Ibn Zohr)

Abdelkarim EL MOUATASIM FAQs

What is Abdelkarim EL MOUATASIM's h-index at Université Ibn Zohr?

The h-index of Abdelkarim EL MOUATASIM has been 9 since 2020 and 11 in total.

What are Abdelkarim EL MOUATASIM's top articles?

The articles with the titles of

Digital handwriting characteristics for dysgraphia detection using artificial neural network

Deep Speech Recognition System Based on AutoEncoder-GAN for Biometric Access Control.

Web-based autism screening using facial images and convolutional neural network

Control learning rate for autism facial detection via deep transfer learning

Hilbert Basis Activation Function for Neural Network

RPCGB Method for Large-Scale Global Optimization Problems

Stochastic perturbation of subgradient algorithm for nonconvex deep neural networks

Web-Based Dyscalculia Screening with Unsupervised Clustering: Moroccan Fourth Grade Students

...

are the top articles of Abdelkarim EL MOUATASIM at Université Ibn Zohr.

What are Abdelkarim EL MOUATASIM's research interests?

The research interests of Abdelkarim EL MOUATASIM are: Applied Mathematics

What is Abdelkarim EL MOUATASIM's total number of citations?

Abdelkarim EL MOUATASIM has 333 citations in total.

    academic-engine

    Useful Links