Changes between Version 65 and Version 66 of Other/Summer/2025/mlCoexist

Timestamp:

Jul 15, 2025, 6:47:10 PM (4 weeks ago)

Author:

aw1086

Comment:

—

Other/Summer/2025/mlCoexist

@@ -89 +89 @@
 
 **Progress:** 
- * Machine learning models: 
-   * Developed a CNN for RFI detection using pre-trained model (ResNet18) with the last classification layer modified and retrained  
-   * Developed SVM as a baseline to assess the efficiency of the CNN approach (underutilization of the neural network)  
+- Machine learning models: 
+ 1. Trained a CNN for RFI detection using pre-trained model (ResNet18) with the last classification layer modified   
+ 2. Developed an SVM baseline to assess the efficiency of the CNN approach (address potential underutilization of the neural network) 
       * Performed cross-validation to ensure the models were not overfitting 
-      * Both the CNN and the SVM reached >95% accuracy
- * Continued obtaining data from transition band (100 additional rows: 1413.5mHz(fc0), 1453.5mHz(fc4)
- * Identified Friis Transmission Formula & Stefan-Boltzmann Law which will be used to find beam efficiency
+      * Both the CNN and SVM achieved over 95% accuracy
+- Continued obtaining data from transition band (100 additional rows: 1413.5mHz(fc0), 1453.5mHz(fc4)
+- Created a mathematical pipeline to estimate brightness temperature(K) based on total transmitting power(W)
+- Identified the unknown variable ηB (beam efficiency) within the Friis Transmission and Brightness Temperature Formulas 
 
 \\