Changes between Version 112 and Version 113 of Other/Summer/2025/mlCoexist

Timestamp:

Jul 28, 2025, 3:17:49 PM (5 days ago)

Author:

aw1086

Comment:

—

Other/Summer/2025/mlCoexist

@@ -144 +144 @@
 **Progress:** 
 - Tested the accuracy of the two formulas for estimating brightness temperature by comparing the calculated values with the physically measured Tb values provided in the testbed dataset
- - Issue: the calculated Tb only matches the measured Tb when the variables are adjusted to reflect real-life scenarios (e.g., setting the distance between the transmitter and the radiometer to 800 km instead of the testbed value of 5 m)
+ - Problem: the calculated Tb only matches the measured Tb when the variables are adjusted to reflect real-life scenarios (e.g., setting the distance between the transmitter and the radiometer to 800 km instead of the testbed value of 5 m)
 - Generated spectrograms of the transmitted signals using MATLAB's 5G Toolbox, replicating the exact transmission settings described in the referenced research paper (Link to [https://www.orbit-lab.org/attachment/wiki/Other/Summer/2025/mlCoexist/graph_w%3Ao_cropping.m code]) 
+ - Centered the graphs around the transmitted central frequency values on the y-axis, and marked the L-band range with blue dashed lines
 [[Image(https://www.orbit-lab.org/raw-attachment/wiki/Other/Summer/2025/mlCoexist/matlab.png, 60%)]]
 \\
@@ -154 +155 @@
 
 **Progress:** 
-
+- MATLAB code modification: 
+ - Added a variability margin to the signal gains to simulate the uncertainty in physical transmissions and obtain multiple samples from a single scenario
+ - Edited the y-axis (frequency range: 1400 MHz–1427 MHz) to illustrate only the section of signals that leaked into the L-band, in order to prevent the CNN model from picking up insignificant details during training
 \\
 \\