A
Akrem Sellami
Researcher at University of Lorraine
Publications - 26
Citations - 466
Akrem Sellami is an academic researcher from University of Lorraine. The author has contributed to research in topics: Hyperspectral imaging & Dimensionality reduction. The author has an hindex of 7, co-authored 22 publications receiving 246 citations. Previous affiliations of Akrem Sellami include Manouba University & École Normale Supérieure.
Papers
More filters
Journal ArticleDOI
Hyperspectral imagery classification based on semi-supervised 3-D deep neural network and adaptive band selection
TL;DR: A novel approach based on adaptive dimensionality reduction (ADR) and a semi-supervised 3-D convolutional neural network (3-D CNN) for the spectro-spatial classification of hyperspectral images (HSIs) and significantly improves the classification accuracy of HSIs.
Journal ArticleDOI
Bringing Deep Learning at the Edge of Information-Centric Internet of Things
Hakima Khelifi,Senlin Luo,Boubakr Nour,Akrem Sellami,Hassine Moungla,Syed Hassan Ahmed,Mohsen Guizani +6 more
TL;DR: This letter study and discuss the applicability of merging deep learning (DL) models, i.e., convolutional neural network (CNN), recurrent neural network and reinforcement learning (RL), with IoT and information-centric networking which is a promising future Internet architecture, combined all together with the EC concept.
Proceedings ArticleDOI
An Optimized Proactive Caching Scheme Based on Mobility Prediction for Vehicular Networks
TL;DR: This work focuses in this paper on the content delivery issue and proposes an optimized caching scheme that proactively predicts the moving direction of a vehicle and brings into the next encountered RSU cache only the required content of interest to that vehicle.
Journal ArticleDOI
Deep neural networks-based relevant latent representation learning for hyperspectral image classification
Akrem Sellami,Salvatore Tabbone +1 more
TL;DR: In this article, a multi-view deep autoencoder model is proposed to fuse the spectral and spatial features extracted from the hyperspectral image into a joint latent representation space.
Journal ArticleDOI
Fused 3-D spectral-spatial deep neural networks and spectral clustering for hyperspectral image classification
TL;DR: An unsupervised band selection method to avoid the problem of redundancy between spectral bands and automatically find a set of groups each one containing similar spectral bands, which improves the classification of HSI using a low number of labeled samples.