Design and modelling of sustainable, autonomous, smart and energy-efficient connected systems for precision beekeeping

Supervisor: Dr Doreid AMMAR

A research project as part of Hugo Hadjur’s PhD thesis, conducted under a joint supervision arrangement with the ENS de Lyon and co-supervised by Doreid Ammar, Professor and Academic Director of aivancity, and Laurent Lefùvre, Professor and Research Fellow at INRIA/ENS Lyon
With pollinating insects threatened with extinction due to the intensity of current agricultural and industrial practices – including the use of pesticides, urbanisation, pollution and global warming. This PhD project aims to develop an innovative beekeeping system capable of automatically assessing the health of a hive using the Internet of Things and Artificial Intelligence (AI), whilst ensuring compliance with the practical constraints of beekeeping and design (maximising resource use, minimising energy costs). The development of machine learning algorithms capable of managing multiple data streams generated by a connected hive will be essential to helping protect bees and preserve their role in maintaining ecological balance and biodiversity.

ANR SKYDATA Project: A project investigating the minimal properties of a distributed system for federated learning

Project Leader: Dr Etienne MAUFFRET

The aim of this research project, funded by the French National Research Agency (ANR) in collaboration with ENS Lyon, is to study and implement an autonomous and intelligent data system. The data within such a system are capable of evolving, migrating and replicating themselves, without the intervention of a file management system. Drawing on the current state of the art in large-scale data management systems, distributed systems and multi-agent systems incorporating federated learning will facilitate the development of this new data management paradigm.

Fully Distributed Federated Learning in Asynchronous Dynamic Distributed Systems

Principal Investigator(s): Dr Etienne MAUFFRET, in partnership with: Eddy Caron, Elise Jeanneau, Aurélie Beynier

This project aims to understand and develop efficient federated learning algorithms within a fully distributed system. In particular, we will seek to identify the minimum properties required for such systems and to determine the performance that can be expected from minimal systems.

Formalisation of the Difference-in-Discontinuities methodology

Principal Investigators: Dr Yacine ALLAM and André MIRANDA ACEVEDO

As part of an exploratory research project, the aim is to develop and formalise a causal inference methodology to address the lack of unbiased and robust methodologies in the field of regional public policy. The model is constructed in a similar way to a geographical RDD but with a temporal dimension, a sort of hybrid of Difference-in-Differences and Regression in Discontinuity. More specifically, we seek to isolate the treatment effect and estimate it by performing a locally linear regression in the vicinity of a threshold of our explanatory variable.

NLP to identify gender bias in court decisions

Project leader: Dr Yacine ALLAM

This project aims to utilise natural language processing (NLP) to analyse potential biases in court rulings. Through the collection of data on court rulings dating from 1990 onwards (legal databases, archives, websites), the research will first involve extracting key information such as the names of judges, penalties and final judgements, and then developing methods to process and organise this data for an analysis of potential gender-related biases in sentencing: do sentences differ according to the judge’s gender in cases of sexual and gender-based violence? Do sentences differ according to the defendant’s background?

Diff-in-Disc: A robust method for identifying causality in a spatial context

Principal Investigator: Dr Yacine ALLAM

This project aims to develop a causal inference methodology, specifically the ‘diff-in-disc’ (difference-in-discontinuity) method. The main objective is to establish a rigorous methodological framework for the diff-in-disc method in a spatial context, and to develop a dedicated software package.

From sharing to value creation

Assessing the impact of Airbnb’s growth on property prices through an analysis of property transaction data from 2018 to 2020

Principal Investigator: Dr Yacine ALLAM, in partnership with: Julie Le Gallo (Institut Agro Dijon), Marie Breuillé (INRAE)

This research examines the impact of the density of short-term rental (STR) listings on property transaction prices in mainland France. Using data on Airbnb listings and property transaction prices for the period 2018–2020, covering the whole country and thus providing robust external validity, this research focuses on spatial variations within different areas, including major cities, secondary towns, suburbs and rural areas.

A causal study of discrimination in France, identifying differences in voting patterns for lists headed by candidates of North African origin in the 2014 French municipal elections

Principal Investigator: Dr Yacine ALLAM
Assessment of the existence and extent of racial discrimination in French municipal elections, by conducting a causal analysis of the difference in the percentage of votes received by a list between 2008 and 2014 following a change in the list leader from a non-North African candidate to a North African candidate.

ANR Project: Digital Demonstrators in Higher Education (DemoES)

Project Leader: Dr Doreid AMMAR

aivancity is a partner in the PEIA (Platform for Immersive Learning Experiences) project, led by the Université Polytechnique des Hauts-de-France, which is one of the 14 universities and three schools selected under the PIA4 DemoES call for proposals. This project aims to tackle new challenges, both in teaching and research, for higher education, and continues the transformation towards more inclusive digital teaching practices through collaborative, realistic virtual environments.
The PEIA (Platform for Immersive Learning Experiences) project, led by the UniversitĂ© Polytechnique des Hauts-de-France (UPHF) and the UniversitĂ© Catholique de Lille (ICL), proposes the creation of an open-source Immersive Learning Management System (I-LMS). It aims to support an immersive and learning-focused community, to offer learning experiences in persistent worlds, and to facilitate the publication of immersive resources. See: http://peia-demo.com/home aivancity’s involvement in the PEIA project is to contribute to the creation of intelligent chatbots within the framework of the I-LMS. This project is being developed as part of the AI Clinic.

Approximating sparse semi-non-negative matrix factorisation for X-ray COVID-19 image classification

Project lead: Dr Amel MHAMDI

This project was developed in response to the challenges posed by the COVID-19 health crisis and its impact on the healthcare system. The main aim is to develop an analysis of reliable digital data to ensure the accurate diagnosis of patients with the condition. The analysis is based on medical imaging data, particularly from chest radiology, which was used extensively during the health crisis. The aim of this project is to create a new algorithm, more reliable than current ones, enabling the automatic detection of affected patients based on their imaging results. It is within this framework that R&D work has been undertaken.