Overview
Integrated Sensing and Communication (ISAC) uses wireless signals themselves to sense the environment — inferring position, identity, and activity from how people perturb a multi-antenna channel, a promising direction for 6G. The challenge is the communication cost of transmitting all that sensing data for processing.
This thesis analyzes ISAC data and applies deep learning-based semantic compression to reduce the communication footprint of sensing tasks such as gait-based identification, while preserving performance.
Prerequisites
Neural Networks and Reinforcement Learning