Statistics, Optimization & Information Computing — El Mehdi Bellfkih, Imrane Chemseddine Idrissi, El Mehdi Lamaizi

Maximum distance separable (MDS) matrices are central to the diffusion layers of symmetric-key primitives, and involutory MDS matrices are especially useful because the same circuit handles both encryption and decryption. Earlier work by the present authors and others identified involutory MDS matrices through row/colu...

Advances in Applied and Computational Mathematics — ICRAMCS 2025, Trends in Mathematics, Birkhauser, Cham — El Mehdi Bellfkih, Imrane Chemseddine Idrissi

This paper presents an in-depth study on the identification and transformation of MDS matrices into involutory using evolutionary algorithms, particularly Particle Swarm Optimization (PSO). MDS matrices are fundamental in coding theory and cryptography, notably in standards like AES. Involutory matrices, satisfying the...

IAES International Journal of Artificial Intelligence (IJ-AI) — El Mehdi Bellfkih, Said Nouh, Imrane Chemseddine Idrissi, Khalid Louartiti, Jamal Mouline

This paper introduces a novel error-correcting code (ECC) construction and decoding approach utilizing genetic algorithms (GAs). Our GA-based method optimizes generator vectors to maximize the minimum distance between codewords, enhancing error correction capabilities. We construct a new family of ECCs with code length...

Educational Process International Journal — Charaf Tilioui, El Mehdi Bellfkih, Imrane Chemseddine Idrissi, Khadija El Kababi, Mohamed Radid, Ghizlane Chemsi

This study develops a proactive, data-driven framework to forecast academic orientation for middle school students using Self-Organizing Maps (SOM) and a random forest classifier trained on data from 720 Moroccan middle school students, achieving 87% validated accuracy and enabling early, personalized orientation.

International Journal of Online and Biomedical Engineering (iJOE) — Hanan Sabbar, Hassan Silkan, Khalid Abbad, El Mehdi Bellfkih, Imrane Chemseddine Idrissi

The growing demand for automated classification of medical X-ray images has driven the development of efficient deep learning models. This study introduces YOLOv8n-cls, a lightweight and accurate solution for body part classification in radiographic images, achieving a top-1 accuracy of 99.4%, outperforming several sta...

Educational Process International Journal — Charaf Tilioui, El Mehdi Bellfkih, Imrane Chemseddine Idrissi, Khadija El Kababi, Mohamed Radid, Ghizlane Chemsi

Background/purpose. Mathematics education develops critical thinking and problem-solving skills, yet middle school students often face challenges, including didactical, epistemological, and ontogenic obstacles, that influence their academic orientation. This study investigates how Self-Organizing Maps (SOMs) can addres...

International Journal of Computing and Digital Systems — Hanan Sabbar, Hassan Silkan, Khalid Abbad, El Mehdi Bellfkih, Imrane Chemseddine Idrissi

Medical image segmentation is a crucial task in computer vision, playing a pivotal role in applications such as diagnostics, treatment planning, and medical research. This study explores a wide range of methodologies employed in medical image segmentation, from traditional thresholding and edge-detection approaches to...

Computational and Mathematical Methods — El Mehdi Bellfkih, Said Nouh, Imrane Chemseddine Idrissi, Khalid Louartiti, Jamal Mouline

We present an innovative approach for the discovery of involutory maximum distance separable (MDS) matrices over finite fields, derived from MDS self-dual codes, using genetic algorithms. Through comprehensive experiments, we demonstrate the effectiveness of our method and unveil essential insights into automorphism gr...

2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA) — El Mehdi Bellfkih, Said Nouh, Imrane Chemseddine Idrissi, Khalid Louartiti, Jamal Mouline

We provide an in-depth overview of error-correcting codes, including traditional techniques like Hamming, Reed-Solomon, Turbo, and Convolutional codes, then explore the integration of machine learning algorithms for adaptive, efficient, and dynamic error correction strategies, with applications in communication systems...

Journal of Theoretical and Applied Information Technology — El Mehdi Bellfkih, Said Nouh, Imrane Chemseddine Idrissi, Khalid Louartiti, Jamal Mouline

Error-correcting codes (ECCs) play a vital role in protecting data against corruption in storage systems and random errors due to noise in communication channels. In this paper, we propose improving our logistic regression-based decoder by utilizing two distinct models (2LRDec), which significantly enhances performance...

Proceedings - SITA 2023: 2023 14th International Conference on Intelligent Systems: Theories and Applications — El Mehdi Bellfkih, Said Nouh, Imrane Chemseddine Idrissi, Khalid Louartiti, Jamal Mouline

We present an innovative approach for the discovery of involutory Maximum Distance Separable (MDS) matrices over finite fields, derived from MDS self-dual codes, using a technique based on genetic algorithms. Our approach efficiently searches for involutory MDS matrices, ensuring their self-duality and maximization of...

Cakrawala Pendidikan

This study examines the importance of reflective practice (RP) in nursing education and its impact on the development of autonomy and academic success among nursing students, based on a validated questionnaire distributed to 200 nursing students from 21 Higher Institutes of Nursing Professions and Health Technologies a...

Indonesian Journal of Electrical Engineering and Computer Science — El Mehdi Bellfkih, Said Nouh, Imrane Chemseddine Idrissi, Khalid Louartiti, Jamal Mouline

An efficient method based on the genetic algorithm is proposed for computing the automorphism groups of low density parity check (LDPC) codes. Results show significant efficiency in finding an important set of automorphisms of LDPC codes.

Journal of Hunan University Natural Sciences — El Mehdi Bellfkih, Said Nouh, Imrane Chemseddine Idrissi, Khalid Louartiti, Jamal Mouline

This paper investigates the computation of the automorphism groups of some optimal codes, including linear circulant codes and the nonlinear Nordstrom-Robinson code, using a new genetic algorithm-based method with a detailed description of its fitness function, selection, crossover, and mutation.

Research Square

This study examines the development of reflective practice (RP) among 200 students from 21 Higher Institutes of Nursing Professions and Health Technologies (ISPITS) across Morocco, and its relationship with the development of autonomy and academic success among nursing students.

Indonesian Journal of Electrical Engineering and Computer Science — El Mehdi Bellfkih, Said Nouh, Imrane Chemseddine Idrissi, Khalid Louartiti, Jamal Mouline

We use multi-class logistic regression combined with the syndrome decoding algorithm to find errors from syndromes in linear codes such as BCH and quadratic residue codes. The proposed decoder — logistic regression decoder (LRDec) — reached a success percentage of 100% for correctable errors in the studied codes.