Machine Learning Methodologies for Beyond 5G and 6G Heterogeneous Networks: Prediction, Automation, and Performance Analysis

The rapid evolution of technologies has led to a profound shift, creating a complex landscape of heterogeneous networks that integrate cellular, smart sensors, IoT, edge computing devices, and security endpoints, enabling new forms of communication and data exchange. This dissertation unlocks the potential of novel machine learning method- ologies in heterogeneous networks, tackling the complex challenges of prediction, automation, and performance analysis. For instance, to address communication network limitations, supervised learning methods are employed, achieving high accuracy rates of 95% for stationary and 90% for mobile signal level prediction, alongside multi-stage autonomous fault management. From communication networks, the focus is generalized to UAV-based networks, where object detection is enhanced with Phantom Convolution, a novel technique that builds on YOLO, enabling detection across RGB and infrared modalities. YOLO Phantom achieves a 43% reduction in parameters and model size, and up to 17% increase in speed. Furthermore, the development of secure and efficient authentication methods is crucial for these expanding network ecosystems. The connected ecosystem is expanded through the development of a privacy-preserving biometric authentication system. This system utilizes trustworthy AI and template obfuscation to ensure secure and confidential authentication, with excellent performance (ROC up to 0.99) and fast processing (1.47 seconds on average). Finally, a novel Energy Optimized Semantic Loss (EOSL) function is introduced that revolutionizes the concept of futuristic semantic communication to turn into green semantic communication, enabling sustainable and energy-efficient networks of the future. In essence, this dissertation pioneers a pioneering approach for heterogeneous networks, where AI-driven innovations harmonize human, machine, and environmental needs, shaping a resilient and thriving digital ecosystem.

Name thesis:degree_name

Ph.D. (Doctor of Philosophy)

Level thesis:degree_level

Doctoral

Discipline thesis:degree_discipline

Computer Networking and Communication Systems (UMKC)

Grantor

University of Missouri--Kansas City

Year dc:date.issued

2024

Author dc:creator

• Mukherjee, Shubhabrata

Advisors dc:contributor.advisor

• Beard, Cory
• Derakhshani, Reza

Handle dc:identifier.uri

https://hdl.handle.net/10355/101867

OAI identifier oai:identifier

oai:mospace.umsystem.edu:10355/101867