DSTN Scholars

DSTN > Scholars > Lionel AFFOGNON

Affiliated project: IoT-SDC

Affiliated CEAs:

CEA SMIA, University of Abomey-Calavi

CEA MITIC Gaston Berger University

Thesis supervisor : Prof. Eugène C. EZIN, ACE SMIA, Institut de Mathématiques et de Sciences Physiques, Université d'Abomey-Calavi, Benin, eugene.ezin@gmail.com

Thesis co-supervisor Prof. Chérif DIALLO, ACE MITIC, UFR des Sciences Appliquées et de Technologies, Université Gaston Berger, Senegal, cherif.diallo@ugb.edu.sn

Other contributors to thesis supervision : Abdoulaye DIALLO, UFR des Sciences Appliquées et de Technologies, Université Gaston Berger, Saint-Louis, Senegal, diallo.abdoulaye8@ugb.edu.sn

DSTN > Scholars > Lionel AFFOGNON

Start date: 01/08/2021
Anticipated date of thesis defense: December 2024
ORCID profile
: 0000-0003-2811-0466

Project title: Sensory characterization of local products using an electronic robot and an intelligent data classifier

Summary of the scientific project:
It is important to know what we are able to produce and to understand their economic, nutritional and sensory benefits. This is supported by the theory that a person's nutritional and sensory needs should be satisfied by the resources also present in their environment.
The main objective of this thesis is the implementation of an electronic nose in the context of food safety. Thanks to this technology, combined with machine learning algorithms, we will be able to make decisions concerning the condition of local produce (the case of tomatoes).

Summary of results:

  • Development of an electronic nose.
  • Data collection on two local tomato varieties (Tounvi and Akikon) during their lifetime.
  • 4 scientific publications: a literature review on the different methods associated with e-nose technology for accessing the quality of various products [2]. This was an opportunity to highlight the research work to be carried out in this thesis project. Two articles highlighted the electronic nose and its effectiveness in collecting data on various local products [1] and on two local tomato varieties [3]. The latter data collection enabled the creation of a dataset accessible on gitlab: https://gitlab.com/liooonel/tomato-tounvi-and-akikon-pictures-and-e-nose-data.git. This dataset was used to train different supervised learning models [4], after which the best one was chosen.

Prospects for the end of the thesis:

  • Implement tomato condition prediction using machine learning models.
  • Present results in scientific publications.

Prospects after completion of thesis:

  • Generalize to other local products

Scientific publications :

  1. Affognon, L., Diallo, A., Diallo, C., & Ezin, E. C. (2023). Design of an Experimental Electronic Nose for Data Collection for Food Quality. IEEE EUROCON 2023 - 20th International Conference on Smart Technologies, Torino, Italy, 2023, pp. 406-411, https://doi.org/10.1109/EUROCON56442.2023.10199067
  2. Affognon, L., Diallo, A., Diallo, C. and Ezin, E., C. A Survey on Statistical and Machine Learning Algorithms Used in Electronic Noses for Food Quality Assessment. SN COMPUT. SCI. 4, 590 (2023), https://doi.org/10.1007/s42979-023-02052-0
  3. Affognon, L., Diallo, A., Diallo, C., Ezin, E.C. (2023). Electronic Nose Architecture for Tomato Data Collection. In: Arai, K. (eds) Proceedings of the Future Technologies Conference (FTC) 2023, Volume 3. FTC 2023. Lecture Notes in Networks and Systems, vol 815. Springer, Cham, https://doi.org/10.1007/978-3-031-47457-6_9
  4. Affognon, A. Diallo, C. Diallo and E. C. Ezin, "Supervised Learning Models for Tomato Quality Prediction Using Electronic Nose Data," 2023 International Conference on Electrical, Computer and Energy Technologies (ICECET), Cape Town, South Africa, 2023, https://doi.org/10.1109/ICECET58911.2023.10389485

Contribution / added value to the affiliated project :

The other major innovation is the introduction of an electronic nose for sensory qualification of local products.