About
Hi I'm Lucas. I have had a passion for computers since childhood and have had the chance to study in this field until today. From web programming to artificial intelligence, including network architectures, I was able to study many of the exciting subjects this field has to offer.
Doctor in computer science
I did my PhD at INSA Lyon within the INRIA Agora team of the CITI laboratory, and finished it in February 2024. My PhD thesis was named "Learning algorithms for urban cycling: implicit models and dynamic infrastructure." and was at the frontier of artificial intelligence and transportation studies.
- Birthday: 8 july 1997
- Website: perso.citi-lab.fr/lmagnana
- City: Villeurbanne, France
- Age: 26
- Degree: PhD
- Email: lucas.magnana@gmail.com
Some stats
Here are some stats about my thesis that I am proud of, this list is obviously not exhaustive.
Happy Students to whom I teach the basics of Python.
Publication in a journal.
Hours Of Teaching at INSA Lyon.
Hours of scientific mediation for the radio of the Urban School of Lyon.
Skills
My first lines of code date back to middle school. I then expanded my knowledge throughout my schooling and am now able to code in Python, Java and C++. During my last year of master, I specialized in artificial intelligence which allowed me to learn and practice the different aspects of this fascinating field of research.
Resume
Sumary
Lucas Magnana
PhD student in his last year, my thesis consists in applying learning algorithms on cycling data in order to model and predict cyclists' behaviors and to try to design a new type of cycling infrastructure.
- 56 boulevard Niels Bohr, Villeurbanne
- lucas.magnana@inria.fr
Education
PhD in Computer Science
October 2020 - February 2024
INSA Lyon
I did an internship in the CITI laboratory at the end of my master's degree. Following this, I obtained funding for a PhD at INSA Lyon in this laboratory.
Master of Computer Science
2018 - 2020
University of Lyon
I was accepted into the master's program after my bachelor's degree. I specialized in Artificial Intelligence during the second year of the master.
Bachelor of Computer Science
2017 - 2018
University of Lyon
Once I obtained my two-year technical degree, I decided to aim for a master's degree and went for a bachelor.
UIT in Computer Science
2015 - 2017
University of Lyon
After highschool I immediatly started studying computer science.
Professional Experience
PhD Project
2022 - 2023
CITI Laboratory, Villeurbanne
- Tools used : Python, PyTorch, SUMO, Deep Reinforcement Learning (3DQN, PPO)
- I imagined a new way of making a road segment attractive to cyclists using the dynamic properties of traffic lights.
- Using SUMO (Simulation of Urban MObility) and real vehicle counter data, I simulated a traffic light with green phases added specifically for cyclists. This trafic light allows cyclists to securely cross an intersection by separating their flows from the motorized vehicles.
- Naively added, these green phases for cyclists explode the waiting time of all vehicles at the intersection.
- I trained deep reinforcement learning agents to control this traffic light while minimizing vehicle waiting time. The agent trained using the Dueling Dual Deep Q-Network (3DQN) outperforms other tested traffic light control methods.
PhD Project
2020 - 2022
CITI Laboratory, Villeurbanne
- Tools used : Python, PyTorch, Sklearn, Jupyter Notebook, Recurrent Neural Networks (LSTM), Clustering algorithms (DBSCAN, K-means)
- developped a method to create implicit route choice models for cyclists using GPS tracks. Given an origin and a destination, the models are capable of generating a route that approximates cyclists’ behavior.
- The first part of this work was to find datasets of GPS tracks and to analyse them both quantitatibvely and qualitatively.
- A clustering algorithm is then applied to the GPS tracks in order to find cyclists' preferred road segments.
- A LSTM network is trained to find the relevant preferred road segments from a shortest path between any pair of origin/destination.
- The relevant preferred road segments are then used to weight a road graph which is used to generate routes approximating cyclists’ behavior.
Web developer (intern)
APRIL 2017 - JUNE 2017
Viveris, Villeurbanne
- Tools used : Angular, HTML, CSS, Typescript , Bootstrap, JEE
- I did a 3 months intership in Viveris during which I worked on a web application.
- My mission was to code a model of an old application to present it at a client to propose a reworking.
- The application, developed by Viveris in 2008, is used by Schneider and enable them to optimize the working time of employees and machines.
Contact
If you want any information about my work you can contact me by my professional or my personal email address.
Location:
56 boulevard Niels Bohr, Villeurbanne, 69100
Email:
lucas.magnana@gmail.com
Email:
lucas.magnana@inria.fr