Date of Award

2026

Document Type

Thesis

Degree Name

Master of Science in Engineering (MSE)

Department

Electrical and Computer Engineering

Committee Chair

Laurie Joiner

Committee Member

David Pan

Committee Member

Adam Panagos

Research Advisor

Laurie Joiner

Subject(s)

Wireless communication systems, Image transmission, Deep learning (Machine learning), Combined source channel coding

Abstract

The growing use of AI-enabled applications has increased the demand for adaptive, efficient, and low-latency image transmission of large data volumes. This has created challenges for conventional separate source-channel coding that focuses on reliable bit sequence transmission without considering the contents or communication objectives. Deep joint source-channel coding (DeepJSCC) potentially solves this by combining source compression and error correction into a unified process. This thesis focuses on developing adaptive and computationally lightweight DeepJSCC-based transceivers for image transmission across heterogeneous channels. The framework further investigates DeepJSCC’s performance in OFDM with robust channel estimation and importance-based subcarrier allocation strategies. Comprehensive evaluation using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) across different channels and transmission conditions prove DeepJSCC’s ability in adaptation, efficiency, and robustness, establishing it as a promising alternative to traditional separation-based algorithms and a potential solution for next-generation wireless communication.

suvro 11295 suppl.pdf (16935 kB)
Presentation

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.