Abderraouf Boussif

Abderraouf Boussif

Auto-generated profile, based on publicly available information

Abderraouf Boussif

Technological Research Institute Railenium, Valenciennes, France

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
7 September 2020 in Discrete Event Dynamic Systems
Verified
Journal Article
Closed access
PDF file
ABAbderraouf Boussif
Abderraouf Boussif
MGMohamed Ghazel
Mohamed Ghazel
JBJoão Carlos Basilio
João Carlos Basilio

8 November 2022 in Reliability Engineering & System Safety
Verified
Journal Article
Closed access
MCMohammed Chelouati
Mohammed Chelouati
ABAbderraouf Boussif
Abderraouf Boussif
JBJulie Beugin
Julie Beugin
EKEl-Miloudi El Koursi
El-Miloudi El Koursi

10 June 2024 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
FBFateh Boudardara
Fateh Boudardara
ABAbderraouf Boussif
Abderraouf Boussif
PMPierre-Jean Meyer
Pierre-Jean Meyer
MGMohamed Ghazel
Mohamed Ghazel
Neural networks as a machine learning technique are increasingly deployed in various domains. Despite their performance and their continuous improvement, the deployment of neural networks in safety-critical systems, in particular for autonomous mobility, remains restricted. This is mainly due to the lack of (formal) specifications and verification methods and tools that allow for having sufficient confidence in the behavior of the neural-network-based functions. Recent years have seen neural network verification getting more attention; many verification methods were proposed, yet the practical applicability of these methods to real-world neural network models remains limited. The main challenge of neural network verification methods is related to the computational complexity and the large size of neural networks pertaining to complex functions. As a consequence, applying abstraction methods for neural network verification purposes is seen as a promising mean to cope with such issues. The aim of abstraction is to build an model by omitting some irrelevant details or some details that are not highly impacting w.r.t some considered features. Thus, the verification process is made faster and easier while preserving, to some extent, the relevant behavior regarding the properties to be examined on the original model. In this article, we review both the abstraction techniques for activation functions and model size reduction approaches, with a particular focus on the latter. The review primarily discusses the application of abstraction techniques on feed-forward neural networks and explores the potential for applying abstraction to other types of neural networks. Throughout the article, we present the main idea of each approach and then discuss its respective advantages and limitations in detail. Finally, we provide some insights and guidelines to improve the discussed methods.

23 September 2019 in International Journal of Control, Automation, and Systems
Verified
Journal Article
Closed access
PDF file
ABAbderraouf Boussif
Abderraouf Boussif
MGMohamed Ghazel
Mohamed Ghazel

17 July 2024 in IEEE Access
Verified
Journal Article
Open access
ATAbhimanyu Tonk
Abhimanyu Tonk
ABAbderraouf Boussif
Abderraouf Boussif
This paper provides a bibliometric analysis and literature review to explore the current application landscape of the Systems Theoretic Accident Model and Processes (STAMP) principles and techniques in the railway transportation domain. Following PRISMA guidelines, we systematically reviewed 118 research documents retrieved from prominent bibliographic databases, covering the period from 2008 to September 2023. The investigated research works, involving STAMP, mainly focus on two topics: 1) applications of STAMP to railway accident modeling/analysis and 2) applications of Systems Theoretic Process Analysis (STPA) to railway hazard analysis and risk assessment. In this paper, while the STAMP related studies are discussed with respect to the considered railway accidents, the studies related to STPA analysis are discussed with respect to three subjects, STPA applications, STPA comparative studies, and STPA extensions and improvements. Ultimately, this review aims to provide academic researchers and railway practitioners with a comprehensive exploration and analysis of the current state of knowledge on STAMP within the railway sector.

1 January 2021
Verified
Conference Paper
Closed access
ATAbhimanyu Tonk
Abhimanyu Tonk
ABAbderraouf Boussif
Abderraouf Boussif
JBJulie Beugin
Julie Beugin
SCSimon Collart-Dutilleul
Simon Collart-Dutilleul