Week 1 (5/28 - 5/30)

We installed and familiarized ourselves with GNU Radio.

We also explored the architecture of the Orbit test bed.

Reviewed several papers to gain insights into the current state of 5G networks and the interference mitigation techniques used across different frequency ranges.

Week 2 (6/03 - 6/06)

We delved into the context of HyPhyLearn and conducted an in-depth exploration of Domain Adversarial Neural Networks (DANN).

Ran reference code for DANN and examined the source, target, and domain accuracies.

Analyzed graphs that demonstrated the model's ability to learn from domain-invariant features.

Week 3 (6/03 - 6/06)

We explored the TensorFlow implementation of the HyPhyLearn model, which classifies 2D Gaussian datasets.

Augmented the code from TensorFlow 1.0 to PyTorch and validated the experimentation.

Additionally, we explored how Dynamic Exclusion Zones apply to our mitigation objective. We weighed various approaches, debating whether the satellite receiver should autonomously localize interference sources or instead initiate a centralized algorithm for optimizing resource allocation.

Week 4 (6/17 - 6/20)

Emulated a DVB Satellite Transmitter in GNU Radio for the ORBIT Sandbox 1 - ran into some issues with existing implementations.

Formulated specific plans for our data collection experiments:

Experiment 1 SAT Reception

• SAT Transmitter
• SAT Receiver
• 4 sensors that compute the FFT of the received signal

Experiment 2 5G Interference

• 5G Terrestrial Transmitter
• SAT Receiver
• 4 sensors that compute the FFT of the received signal

Experiment 3 Network Coexistence

• SAT Transmitter
• SAT Receiver
• 5G Terrestrial Transmitter
• 4 sensors that compute the FFT of the received signal

Designed the neural network's input/output formatting.