Abdessamad Belangour

Abdessamad Belangour

Auto-generated profile, based on publicly available information

Abdessamad Belangour

Hassan II University of Casablanca

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019
Verified
Conference Paper
Closed access
AEAllae Erraissi
Allae Erraissi
MBMouad BANANE
Mouad BANANE
ABAbdessamad Belangour
Abdessamad Belangour
The evolution and democratization of technologies have created a veritable explosion of information, this, of course, gives rise to an urgent need to analyze and deal with the huge masses of data. In fact, the problems raised by the accumulation of data (storage, processing time, heterogeneity, capture rate/generation, etc.) become stronger because the data are massive, complex and varied. It is clear that the representation of information has the capacity to synthesize and condense data, and constitutes an efficient approach for analysis. Nevertheless, it remains ineffective and does not solve these problems. Besides that, conventional visualization techniques are rarely adapted to manage and process this mass of information. To face the complex big data challenges, various types of technologies have been developed. This paper talks about the visualization layer. This layer is located just above the Data Sources, Ingestion, Hadoop storage and Hadoop Platform Management layers for which we have already proposed a meta-modeling. It has a very important role at the level of Big Data Structure. In a continuous effort, we shall present in this paper a universal meta-modeling for the visualization layer and its relationship with the other layers of a Big Data system.

1 October 2024 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
SBSara Bouraya
Sara Bouraya
ABAbdessamad Belangour
Abdessamad Belangour
Activation functions (AFs) play a critical role in artificial neural networks, allowing for the modeling of complex, non-linear relationships in data. In this review paper, we provide an overview of the most commonly used AFs in deep learning. In this comparative study, we survey and compare the different AFs in deep learning and artificial neural networks. Our aim is to provide insights into the strengths and weaknesses of each AF and to provide guidance on the appropriate selection of AFs for different types of problems. We evaluate the most commonly used AFs, including sigmoid, tanh, rectified linear units (ReLUs) and its variants, exponential linear unit (ELU), and SoftMax. For each activation category, we discuss its properties, mathematical formulation (MF), and the benefits and drawbacks in terms of its ability to model complex, non-linear relationships in data. In conclusion, this comparative study provides a comprehensive overview of the properties and performance of different AFs, and serves as a valuable resource for researchers and practitioners in deep learning and artificial neural networks.

1 January 2019 in Advances in Science, Technology and Engineering Systems Journal
Verified
Journal Article
Open access
AEAllae Erraissi
Allae Erraissi
ABAbdessamad Belangour
Abdessamad Belangour


15 May 2018
Verified
Book Chapter
Closed access
PDF file
MBMouad BANANE
Mouad BANANE
ABAbdessamad Belangour
Abdessamad Belangour
LHLabriji El Houssine
Labriji El Houssine

30 October 2019 in International Journal of Innovative Technology and Exploring Engineering
Verified
Journal Article
Closed access
FKFatima Kalna
Fatima Kalna
AEAllae Erraissi
Allae Erraissi
MBMouad BANANE
Mouad BANANE
ABAbdessamad Belangour
Abdessamad Belangour
Transformation presents the second step in the ETL process that is responsible for extracting, transforming and loading data into a data warehouse. The role of transformation is to set up several operations to clean, to format and to unify types and data coming from multiple and different data sources. The goal is to get data to conform to the schema of the data warehouse to avoid any ambiguity problems during the data storage and analytical operations. Transforming data coming from structured, semi-structured and unstructured data sources need two levels of treatments: the first one is transformation schema to schema to get a unified schema for all selected data sources and the second treatment is transformation data to data to unify all types and data gathered. To ensure the setting up of these steps we propose in this paper a process switch from one database schema to another as a part of transformation schema to schema, and a meta-model based on MDA approach to describe the main operations of transformation data to data. The results of our transformations propose a data loading in one of the four schemas of NoSQL to best meet the constraints and requirements of Big Data.