View Proposal


Proposer
Hadj Batatia
Title
Physics-informed neural networks for image reconstruction from WIFI data
Goal
Develop physics-informed deep learning models to reconstruct a scene from WiFi data
Description
WIFI data scattered from a 3D scene carries rich information that can be used to reconstruct the 3D space. This project investigates PINN to solve the reconstruction problem. The student first addresses the reconstruction of a static scene (3D cube). Depending on progress, the work can be extended to detection motion in the scene.
Resources
Background
Url
Difficulty Level
High
Ethical Approval
None
Number Of Students
1
Supervisor
Hadj Batatia
Keywords
deep learning, physics informed networks, inverse problems
Degrees
Bachelor of Science in Computer Science
Master of Science in Artificial Intelligence
Master of Science in Data Science
BSc Data Sciences