This thesis explores ML applied to wireless technologies in two different contexts: 5G cellular networks and radar systems. In the case of 5G, classification ML models are used to identify fundamental scheduling algorithms that a simulated network is using based on a several types of data (UE performance metrics and spectrogram data). As for radar systems, a monostatic radar simulation was built, opening opportunities for future cognitive radar experiments involving adaptive NLFM waveforms via optimization. This thesis exemplifies the importance of ML applied to wireless emissions and sets up future research in the two domains considered.

Creator

• Tames, Donovan

Contributors

• Wyglinski, Alexander

Degree

• MS

Unit

• Electrical & Computer Engineering

Publisher

• Worcester Polytechnic Institute

Identifier

• etd-107931

Keyword

• Scheduling Algorithm
• 5G
• Radar
• Waveform Optimization
• Cognitive Radio

Advisor

• Wyglinski, Alexander

Defense date

• 2023-04-25

Year

• 2023

Sponsor

• MIT Lincoln Laboratory (G65)
• MIT Lincoln Laboratory (G33)

Date created

• 2023-05-02

Resource type

• Thesis

Source

• etd-107931

Rights statement

• In Copyright

Last modified

• 2023-06-07