Khadija Bousselmi, née ARFAOUI

Lecturer, University of Savoie Mont Blanc, Annecy University Institute of Technology

Contact:

Email: khadija.arfaoui –@– univ-smb.fr

Phone: +1 404-509-6559

Office: A 222

Address: LISTIC – Polytech Annecy-Chambéry, PO Box 80439 – Annecy le Vieux – 74944 ANNECY Cedex, France

Research topics:

My research interests focus on parallel computing, distributed computing, and computer communications. I have mainly worked on optimizing the performance of data-intensive systems, such as scheduling scientific workflows in the cloud and designing and processing big data warehouses. I am currently working on optimizing the architecture of convolutional neural networks (CNNs) to reduce energy consumption and improve performance.

Frames:

Theses:

2021-2024: Asma Dhaouadi (defended on 12/11/2024)
Topic: Modeling Data Warehousing in the Context of Big Data

Subject: CONTRIBUTION TO BIG DATA STORAGE: GENERIC ARCHITECTURE, METHODOLOGY, AND IMPLEMENTATION
Abstract:

In the era of Big Data, rapid technological advances make it difficult for experts to choose the right tools for their needs. Existing studies on Big Data storage and analysis are often limited and specific. To overcome these limitations, this thesis proposes a generic modeling approach, inspired by model-driven architecture, to guide technology choices at each stage. An interactive framework helps model a customized pipeline and verify the interoperability of tools, with connector recommendations. This framework has been validated through case studies on COVID-19 and the 2022 World Cup. User feedback is satisfactory (85% satisfaction).

Internships:

2023: William Paccoud, M2 internship, analysis of the performance of Big Data warehousing tools

2022: Moenes Ben Soussia, M2 internship, Dynamic load balancing of cloud servers based on machine learning techniques


2021: EZ-ZAROUALY AZIZA M1 internship, Study and extension of mechanisms for orchestrating scientific data stream processing pipelines for the MUST platform .

Keywords:

Cloud Computing, load balancing, Reinforcement Learning, MUST, Scheduling, scientific workflows, distributed environments, Data Warehousing, Big Data, Decision Support, Machine Learning, Interoperability, Green Computing, CNN, Neural Networks.

Publications:

Here is the link to my publications on HAL: here

Here is the link to my current publications from Google Scholar: here

Reading committees:

International journals:

  • IEEE Transactions on Industrial Informatics
  • Intelligent Decision Technologies
  • International Journal of Computing
  • IEEE Transactions on Neural Networks and Learning Systems
  • Journal of King Saud University – Computer and Information Sciences
  • Jordanian Journal of Computers and Information Technology

International conferences:

  • International Conference on Software Engineering Advances (ICSEA 2024, 2022)

  • International Conference on Control, Decisionand Information Technologies(CoDIT 2024, 2023)

  • International Conference on the Sciences of Electronics, Technologies of Information and Telecommunications
    (SETIT’18)
  • International Conference on Sciences and Techniques of Automatic Control and Computer Engineering
    (STA’19)

Education:

Module Information Description
Name: Optimization methods for decision support

Hours per week: 15

Level: GOAL 3 – all courses

 This module aims to introduce students to the fundamental principles of optimization methods used in decision-making and resource management. The courses will cover techniques such as linear programming, nonlinear programming, as well as heuristic and meta-heuristic approaches adapted to complex problems. Applications include various fields such as logistics, project planning, and business scenario analysis.
Name: Optimization Methods: Introduction to Machine Learning

Hours per week: 15

Level: GOAL 2

 

 This module provides an introduction to the fundamental concepts and tools of machine learning for second-year BUT students. The main objectives are:

· Understand the basics of machine learning, including classification, regression, and clustering.

· Discover the links between optimization and machine learning, such as cost function optimization and hyperparameter tuning.
Low-level communication and operation

Hours per week: 50

Level GOAL 1

 This module introduces students to the basics of machine-to-machine communication. It covers:

  • The fundamental principles of digital communication (binary coding, synchronization, modulation).
  • Low-level transmission protocols (RS232, UART, SPI, I2C).
  • Understanding the physical layers and bonding of the OSI model.
Name: Network Architecture

Hours per week: 50

Level: GOAL 2, semester 3

 This module explores the concepts of structuring and organizing computer networks in greater depth. It includes:

  • The basics of IP networks: addressing, subnets, and routing.
  • Discovering the network and transport layers (TCP/IP, UDP).
  • Implementation of communication protocols (DHCP, DNS, HTTP).
Name: Advanced Networks

Hours per week: 18

Level: GOAL 2, semester 4

 This module explores advanced technologies and issues in modern networks:

  • Wireless networks (Wi-Fi, Bluetooth, ZigBee) and IoT networks.
  • Management of complex networks, including virtualization (VLAN, VPN) and cloud networking.
Name: Graph theory

Hours per week: 22

Level: GOAL 1
  • Modeling complex problems using graphs (directed/undirected, weighted graphs).
  • Study the fundamental properties of graphs: connectivity, traversal (DFS/BFS), minimum spanning tree.
  • Applications: networks, planning, and optimization.
Name: Automata and Languages

Hours per week: 22

Level: BUT2, semester 4
  • Understanding deterministic finite automata (DFA) and non-deterministic finite automata (NFA).
  • Model computer processes with automata and link them to regular expressions.
  • Applications in compiler design and pattern recognition.
  • Introduction to formal grammars (type 0 to type 3 according to Chomsky).
  • Study of the relationships between languages, automata, and Turing machines.
  • Applications to programming languages, syntax analysis, and interpreter development.

Professional background:

Since 2020: Lecturer at the Annecy University Institute of Technology

  • University: University of Savoie Mont Blanc
  • Laboratory: LISTIC, Annecy Polytechnic School
  • Research team: Representation, Management, and Processing of Data for Humans (ReGaRD)

2019–2020: Postdoctoral fellowship at LAMSADE

  • Subject: Multi-objective optimization of scheduling intensive scientific workflows in a cloud computing environment, guided by data localization.
  • Location: LAMSADE, Paris Dauphine University, Paris, France

2018–2020: Temporary Teaching and Research Assistant (ATER), University of Paris Nanterre, SEGMI Faculty.

2013–2017: Doctoral thesis, RIADI-GDL Laboratory, La Mannouba, Tunisia

  • Subject: Scalable approach for scheduling scientific workflows in a cloud computing environment, guided by quality of service (QoS) and energy consumption.
  • Location: Faculty of Sciences of Tunis, University of Tunis El Manar
  • Research laboratory: RIADI-GDL, University of Manouba, Tunisia
  • Supported in 2017

2010–2013: C/C++ design and development engineer

  • Company: EUROGICIEL Engineering, Tunisia
  • Mission: Design and development of embedded applications in C/C++.
  • Clients: SAGEM Defense, THALES, EURODOC

2009–2010: C/C++ Design and Development Engineer

  • Company: SAGEM COMMUNICATION
  • Mission: Development of embedded applications in C/C++.
  • Clients: SAGEM COMMUNICATION, Bouygues Telecom

2011: Master's degree in computer science, software engineering, and decision support

    • Research laboratory: RIADI-GDL, University of Manouba, Tunisia.

2008: Degree in Computer Engineering

    • Institution: National School of Computer Science (ENSI), Tunisia.

2003: High school diploma, mathematics major