On July 1, the first Aqsone Lab Keynote took place, in the presence of our customers. An opportunity for us to present the activities of the Lab and its achievements over the last three 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.
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 first topic addressed during the Keynote gives an example of the use of Data Science and Computer Vision techniques in the service of the environment and biodiversity. The aim here was to detect in images the presence of a proliferating starfish species threatening the balance of the Great Barrier Reef.
In this video, Hugo Naya shows you how to boost object detection algorithms like YOLO, using Image Augmentation methods.
The second subject traces the participation of our teams in the 2022 edition of the BirdClef Challenge.
A challenge under the theme of biodiversity, which is looking for data science solutions to classify bird species through recordings of their song.
Léa Besnard and Nicolas CHEIFETZ explain to you what are the main stages of audio signal processing and the results obtained in the challenge thanks to the convolutional neural network (CNN).
Our teams studied the automation of the Bechdel test, which measures female (under) representation in cinema and audiovisual.
To do this, they combined computer vision techniques for detecting the gender of characters on the screen with speech-to-text techniques to script the dialogues of the scenes and finally NLP (Natural Language Processing) techniques to analyze the topics covered in the dialogues.
Matthieu Vinette and Vincent Gargasson show you their results in this video:
The exceptional temperatures of this summer 2022 brought to the forefront of the news our need to optimize our energy consumption, both in terms of cooling (air conditioning) and heating. Our teams have developed a reinforcement learning model to optimize the operation of the heating and air conditioning system in an office building. The model seeks a balance between consumption and occupants' comfort.
Evan Graïne and Colombe Becquart present the results in this video:
Dental health is a problem that every person faces during their lifetime. In collaboration with the RESTORE laboratory, our teams designed a model for predicting the risk of receding teeth using machine learning techniques. In particular, clustering techniques have been used to highlight the characteristics of groups of patients at risk.
Adrien Schaffner presents his work in the video below:
The Aqsone teams continue to strengthen their expertise by working on projects around the themes of the environment, biodiversity, health and social issues. The next Keynote will take place at the end of 2022.
