On December 9, Keynote #2 took place forAqsone Lab, in the presence of our customers. An opportunity for us to present the activities of the Lab and its achievements over the last 6 months.
The Aqsone Lab is a time dedicated for our employees to explore, innovate and learn about issues that are important to us such as the environment, health or social issues, but also to master the latest technologies that respond to them.
For two periods of three months, employees worked in teams on various projects, the results of which are as follows.
The first topic addressed during this keynote is a health project. The objective is to predict the effects of a drug on pathologies based on its molecular compound. This would speed up the drug discovery process.
To do this, Nicolas Cheifetz shows you how to approach this subject using machine learning and the fine analysis of undocumented data:
The environment is a strong subject and is often highlighted by Aqsone. This is why this project, initiated by Veolia, aims to predict the level of sulfur dioxide in the air near factories to prevent olfactory pollution.
Nicolas Le Gall introduces you to the various algorithms used for the analysis and forecasting of time series and which one is most suitable for this case:
This project addresses a well-known problem: optimizing data allocation. Our teams have developed a model of Reinforcement learning allowing to optimize the allocation of orders in the purchasing sector.
Nicolas Cheifetz and Thomas Framery present their results and the comparison with other optimization models:
The project focuses on health and aims to predict the number of cases of dengue in a city based on environmental and governmental data. Dengue, also known as “tropical flu,” is a viral disease transmitted to humans by mosquitoes, with around 50 million estimated cases worldwide. Machine learning will be used to achieve the goals of the project.
Léa Besnard and Hugo Naya show you their results in this video:
Due to numerous economic, political and social factors in the context of the health crisis, transport prices are increasing sharply. The two projects presented were initially launched during an online challenge organized by Renault and Roadef.
The first project, called “Logistic 4.0 — Truck Fleet Planning Performance”, aims to optimize parcel allocation with different trucks between two warehouses at a given time.
Houcem Chaabane explains how this problem was solved by detailing the different steps of the optimization algorithm:
The second project, called “3D Truck Loading Optimization”, aims to optimize the layout of packages in a trailer by using a 3D layout to better visualize the scientific approach.
Vincent Gargasson explains the various difficulties encountered in this project and how they were overcome to offer an efficient solution:
Our employees want to offer innovative and relevant solutions to our customers, and the Lab is an excellent way for them to self-train and discover new technologies in order to continue to strengthen their expertise.
The Lab is also a way for us to propose projects around the themes of the environment, biodiversity, health and social issues to our employees.
The next Keynote will take place in June 2023, all the information will be announced on LinkedIn.
