Génie industriel - Rubrique Formation - 2022

UE Multi-criteria Decision Aiding and Artificial Intelligence - 5GUC4202

  • Volumes horaires

    • CM 27.0
    • Projet -
    • TD 27.0
    • Stage -
    • TP -
    • DS -

    Crédits ECTS

    Crédits ECTS 6.0

Objectif(s)

(This class will be in English)
Please read the required skills before enrolling in this class

The objective is that students will be able to :

A- implement some multi-criteria decision Aiding methods
B- understand how Artificial Intelligence (AI) techniques (specifically Machine Learning) can be used for decision aiding

Responsable(s)

Zakarya YAHOUNI

Contenu(s)

The class has two parts A and B. The order of classes depends on the availability of teachers. It means that we may start by part B then part A:

Part A: This part consists of studying some mutlti-criteria decision aiding methods, such as AHP, PARETO, etc. Sessions are proposed in lectures and exercices format (CM and TD). A real case study will be introduced for the AHP method. At the end of this part, the student will understand several multi-criteria decision support methods used operationally. The structure of this part is as follows:
• Introducing the key concepts of multi-criteria decision Aiding
• Describe the main steps of the implementation process of multi-criteria decision support
• Formalize a multi-criteria decision support problem
• Implement the AHP, PARETO, ELECTRE, and other methods….

Part B: This part tackles Artificial Intelligence (AI) in the context of multi-criteria decision aiding. We focus specifically on using machine learning as a decision aiding tool.
• In this part, we first, introduce machine learning techniques for solving multi-criteria decision support problems. The techniques studied are: supervised/unsupervised methods and reinforcement methods. We use these methods for solving case studies, but we do not discuss the details of programming development.
• One or several case studies will be conducted and literature review will be studied for the group work
• Some industrial partners will participate in the lecture by sharing industrial experiences

Prérequis

  • English is mandatory (understanding, reading and writing)
  • General knowledge of manufacturing and supply chain management: scheduling, inventory management
  • Know how to carry out a literature review: search and analyze scientific articles
  • Basic knowledge of statistics (correlation analysis, linear regression, etc.), Python (for using some packages), Simulation software (such as Arena).

Contrôle des connaissances

Evaluation of Part A: (Individual written exam + group report for the case study) -> ("A1")
Evaluation of Part B: (group report for case studies + group presentations) ->("B1")

Evaluation of session 1 (N1) = "A1" (50%) + "B1" (50%)
Evaluation of session 2 (N2) = Individual written exam for part A ("A2" 50%) + Synthesis of articles or interview for part B ("B2" 50%)

Repeated and unjustified absences will impact the final score and may lead to a score up to 0 for this class.

Using ChatGPT for writing reports is prohibited and lead you to a score of 0.

Evaluation of session 1 (N1) = 0.5 A1 + 0.5 B1

Evaluation of session 2 (N2) = 0.5 A2 + 0.5 B2

L'examen existe uniquement en anglais FR

Calendrier

Le cours est programmé dans ces filières :

  • Cursus ingénieur - Master 2 GI SIE SOM - Semestre 9 (ce cours est donné uniquement en anglais EN)
  • Cursus ingénieur - Master 2 GI GID DPD - Semestre 9 (ce cours est donné uniquement en anglais EN)
  • Cursus ingénieur - Ingénieur IdP - Semestre 9 (ce cours est donné uniquement en anglais EN)
  • Cursus ingénieur - Master 2 GI GID GOD - Semestre 9 (ce cours est donné uniquement en anglais EN)
  • Cursus ingénieur - Master 2 GI SIE SPD - Semestre 9 (ce cours est donné uniquement en anglais EN)
  • Cursus ingénieur - Ingénieur IPID - Semestre 9 (ce cours est donné uniquement en anglais EN)
  • Cursus ingénieur - Ingénieur ICL - Semestre 9 (ce cours est donné uniquement en anglais EN)
cf. l'emploi du temps 2023/2024

Informations complémentaires

Code de l'enseignement : 5GUC4202
Langue(s) d'enseignement : FR

Vous pouvez retrouver ce cours dans la liste de tous les cours.

Bibliographie

Part A :
• B. Roy. Multicriteria Methodology for Decision Aiding. Kluwer Academic (1996).
• Saaty, Thomas L. Relative Measurement and its Generalization in Decision Making. Review of the Royal Academy of Exact, Physical and Natural Sciences, Series A: Mathematics (RACSAM) 102 (2): 251–318 (2008)

Part B :
• Cadavid, J. P. U., Lamouri, S., Grabot, B., Pellerin, R., & Fortin, A. (2020). Machine learning applied in production planning and control: a state-of-the-art in the era of industry 4.0. Journal of Intelligent Manufacturing , 1-28
• Faustmann, G. (2019). Application of machine learning in production scheduling (Doctoral dissertation, Wien).
•Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems . O'Reilly Media.