Using Sensor Fusion and ML to Navigate Underground When GPS Fails

Étienne Tremblay

Machine Learning & Deep Learning & Statistics
Python Skill Intermediate
Domain Expertise Intermediate

Attendees will gain from the lessons learned developing a sensor fusion ML system for offline use in smartphones

Data Collection & Annotation

Strategies for gathering high-quality, labeled "ground truth", especially in cases where the labels can't be inferred by human annotators after the fact

The ML Pipeline

Hyperparameter tuning of a convolutional neural network (CNN) Building a multi-stage training regimen, to leverage different datasets

UX

Presenting predictions to users in a way that expresses uncertainty when necessary, and inspires confidence when justified. We want users to forget GPS doesn't work underground.

Étienne Tremblay

Hi, I'm Étienne! I am responsible for developing machine learning solutions to rider problems, and turning them into features that help Transit users in their journeys. Before working at Transit, I was building databases and analysis tools for the aerospace industry. I was also been involved in the mobility professorship at Polytechnique Montréal. I hold a B. Eng. in Aerospace from Polytechnique Montréal.