The Final Results!!!

After training, validating and testing the models available in the Classification Learner app, the LSTM model, and the NPR tool model, it was seen that the Cubic Support Vector Machine provided the best test accuracy of 99.8% for 100% load.  

The table below shows the accuracies obtained for each of the models for 12.5% of the load.

Model
Test Accuracy
Train Accuracy
ROC (AUC)
LSTM
   
93.04%   
   
92.69%   
   
-   
SDNN
   
96.9%   
   
96.6%   
   
-   
Quadratic SVM
   
96.7%   
   
98.5%   
   
Class 1 – 0.9995   
   
Class 2 – 0.9999   
   
Class 3 – 0.9993   
   
Class 4 – 0.9994   
   
Class 5 – 0.9994   
Cubic SVM
   
96.6%   
   
98.7%   
   
Class 1 – 0.9993   
   
Class 2 – 0.9998   
   
Class 3 – 0.9986   
   
Class 4 – 0.9992   
   
Class 5 – 0.9995   
Medium Neural Network
   
96.4%   
   
98.4%   
   
Class 1 – 0.9985   
   
Class 2 – 0.9995   
   
Class 3 – 0.9980   
   
Class 4 – 0.9988   
   
Class 5 – 0.9990   
Bi-layered Neural Network
   
96.4%   
   
97.8%   
   
Class 1 – 0.9983   
   
Class 2 – 0.9996   
   
Class 3 – 0.9973   
   
Class 4 – 0.9982   
   
Class 5 – 0.9982   
Tri-layered Neural Network
   
96.0%   
   
97.7%   
   
Class 1 – 0.9981   
   
Class 2 – 0.9996   
   
Class 3 – 0.9975   
   
Class 4 – 0.9976   
   
Class 5 – 0.9979   

 The table below shows the accuracies obtained for each of the models for 100% of the load.

Model
Test Accuracy
Train Accuracy
ROC (AUC)
LSTM
   
98.18%   
   
98.72%   
   
-   
SDNN
   
98.6%   
   
98.5%   
   
-   
Cubic SVM
   
99.8%   
   
99.6%   
   
Class 1 – 0.9994   
   
Class 2 – 1.0   
   
Class 3 – 0.9998   
   
Class 4 – 0.9998   
   
Class 5 – 0.9997   
Wide Neural Network
   
99.7%   
   
99.5%   
   
Class 1 – 0.9999   
   
Class 2 – 0.9997   
   
Class 3 – 0.9987   
   
Class 4 – 0.9998   
   
Class 5 – 0.9998   
Quadratic SVM
   
99.6%   
   
99.3%   
   
Class 1 – 0.9998   
   
Class 2 – 1.0   
   
Class 3 – 0.9999   
   
Class 4 – 0.9996   
   
Class 5 – 0.9998   
Bi-layered Neural Network
   
99.4%   
   
99.3%   
   
Class 1 – 0.9998   
   
Class 2 – 0.9997   
   
Class 3 – 0.9995   
   
Class 4 – 0.9998   
   
Class 5 – 0.9988   

Medium Neural Network
   
99.4%   
   
99.4%   
   
Class 1 – 0.9999   
   
Class 2 – 0.9999   
   
Class 3 – 0.9997   
   
Class 4 – 0.9997   
   
Class 5 – 0.9997   

Comments

Popular posts from this blog

What are Broken Rotor bar Faults?!

The Induction Machine We Used...