ESR11 - Sophie Noiret

ESR photo
Sophie Noiret
Research project
Algorithmic fairness in AI for active assisted living
About the project

Algorithmic decision-making has become deeply embedded in daily life. In the field of AAL, data is analysed and interpreted with the aim of supporting individuals in various ways, such as recognising behaviours, events, emotions, and needs; creating ambient intelligence; predicting activities; and proposing treatment strategies. Machine learning, as a prerequisite for achieving this form of intelligence, is extensively applied. Given recent advancements, it is evident that the successful implementation of machine learning methods requires not only a set of specific algorithms but also a substantial amount of example data to train them effectively.


However, significant challenges remain. Typically, those developing these algorithms are not trained in law or the social sciences, while experts in discrimination law often lack the technical expertise needed to audit modern machine learning systems. Further complicating matters, even specialists in computer science and mathematics frequently find it difficult to interpret the outputs of contemporary machine learning algorithms. As a result, assessing and ensuring fairness and transparency in machine learning remains an open and critical area of research. Addressing these challenges forms the central focus of this project.

Start date: April 2021

End date: March 2024

Progress of the project

The first part of the project was dedicated to education in the subject of machine learning, AI fairness, bias, and transparency, as well as interviews with developers at TU Wien and a review of the use of explainable AI in audio and video-based AAL applications. The completion of the review of the state of the art, led to the decision of examining several AAL systems (fall detection system and automatic speech recognition systems) by using a pre-processing, in-processing, post-processing framework. Pre-processing experiments with fall detection include creating synthetic data to improve the human diversity in fall detection data and testing state-of-the-art solution on a more diverse dataset.


In parallel, experiments on fair privacy were conducted with ESR13. Collaborations were also undertaken with ESR3, participating as an AI expert in their studies.
 

Scientific publications

State of the Art of Audio- and Video-Based Solutions for AAL

Aleksic, Slavisa; Atanasov, Michael; Calleja Agius, Jean; Camilleri, Kenneth; Čartolovni, Anto; Climent-Pérez, Pau; Colantonio, Sara; Cristina, Stefania; Despotovic, Vladimir; Ekenel, Hazım Kemal; Erakin, Ekrem; Florez-Revuelta, Francisco; Germanese, Danila; Grech, Nicole; Sigurðardóttir, Steinunn Gróa; Emirzeoğlu, Murat; Iliev, Ivo; Jovanovic, Mladjan; Kampel, Martin; Kearns, William; Klimczuk, Andrzej; Lambrinos, Lambros; Lumetzberger, Jennifer; Mucha, Wiktor; Noiret, Sophie; Pajalic, Zada; Pérez, Rodrigo Rodriguez; Petrova, Galidiya; Petrovica, Sintija; Pocta, Peter; Poli, Angelica; Pudane, Mara; Spinsante, Susanna; Ali Salah, Albert; Santofimia, Maria Jose; Islind, Anna Sigríður; Stoicu-Tivadar, Lacramioara; Tellioğlu, Hilda; Zgank, Andrej

GoodBrother COST Action, Technical Report, 2022

About the ESR

Sophie received her Master's Degree in Engineering from the Ecole Centrale de Nantes (France) in 2018, with a specialty in Robotics and Embedded Systems. She has since worked in the aeronautics industry, developing software for the Rafale plane.

Contact information

Sophie Noiret

Vienna University of Technology

Computer Vision Lab
Favoritenstr. 9/193-1
A-1040 Vienna, Austria

Email address: snoiret@cvl.tuwien.ac.at