9 papers
LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learning
Said Ohamouddou, Hanaa El Afia, Abdellatif El Afia +1
Three-dimensional (3D) point cloud analysis has become central to applications ranging from autonomous driving and robotics to forestry and ecological monitoring. Although numerous…
MS-DGCNN++: Multi-Scale Dynamic Graph Convolution with Scale-Dependent Normalization for Robust LiDAR Tree Species Classification
Said Ohamouddou, Hanaa El Afia, Mohamed Hamza Boulaich +2
Graph-based deep learning on LiDAR point clouds encodes geometry through edge features, yet standard implementations use the same encoding at every scale. In tree species classific…
ATMS-KD: Adaptive Temperature and Mixed Sample Knowledge Distillation for a Lightweight Residual CNN in Agricultural Embedded Systems
Mohamed Ohamouddou, Said Ohamouddou, Abdellatif El Afia +1
This study proposes ATMS-KD (Adaptive Temperature and Mixed-Sample Knowledge Distillation), a novel framework for developing lightweight CNN models suitable for resource-constraine…
Dynamic Graph CNN with Jacobi Kolmogorov-Arnold Networks for 3D Classification of Point Sets
Hanaa El Afia, Said Ohamouddou, Raddouane Chiheb +1
We introduce Jacobi-KAN-DGCNN, a framework that integrates Dynamic Graph Convolutional Neural Network (DGCNN) with Jacobi Kolmogorov-Arnold Networks (KAN) for the classification of…
An Introduction to the Hausdorff Measure and Its Applications in Fractal Geometry
Mohammed Nechba, Mustapha Ouyaaz, Abdellatif El Afia +1
This paper presents a comprehensive introduction to the Hausdorff measure, a fundamental tool in fractal geometry and geometric measure theory. We begin by defining the Hausdorff o…
Random Normed k-Means: A Paradigm-Shift in Clustering within Probabilistic Metric Spaces
Abderrafik Laakel Hemdanou, Youssef Achtoun, Mohammed Lamarti Sefian +2
Existing approaches remain largely constrained by traditional distance metrics, limiting their effectiveness in handling random data. In this work, we introduce the first k-means v…