| 160 | - Problem: found impracticality in using binary classification (with/without RFI) on transmitting signal spectrograms. As they are pre-RFI and contain no features that reveal the impact of signal interference, Tx graphs are not suitable as input for training CNN, since the model would become a simple color detector (hue of spectrograms based on intensity of power, e.g., orange = RFI, blue = no RFI), which reduces the entire purpose of using ML for RFI detection |
| 161 | - Solution: pivoted to using cropped Tx spectrograms (only signals leaked into L-band) to estimate brightness temperature, and changed the model from classification to regression |
| 162 | - Force the model to extract more graphical features than just color (ex. using the area of the brighter color in graphs to approximate total Tb when leaked signal reaches the receiving site) |
| 163 | - New data table for model training: |
| 164 | |