- This topic has 1 reply, 2 voices, and was last updated 8 years, 1 month ago by
.
-
Posts
-
Hello everyone,
Maybe this was already asked but I couldn’t find an answer in the Guide. When using the Testing Model function from the ScioLab Dev app, what does the percentage value next to the classification result mean? Is it a level of confidence of the classification?
Also, when using this function it gives you the option of applying Processed, Normalization or Both to your spectra. If my models have been created using a preprocessing from the Expert Mode, are my models still been tested using this preprocessing or just Processed and/or Normalization?
Hi James,
I apologize for the delayed response.
The percentage value next to the classification result is the ‘Confidence Level’. When you test your model, you will see the model’s response and a number in brackets. That number is the confidence level of the answer – 0 means no confidence (theoretically should never happen), and 100 means full confidence.
In addition to the confidence level, you can train the model to disregard scans that look significantly different than the scans used to train the model (the response will be “null” in that case).
To activate the “outlier detection” feature, use the expert mode, click on the settings button (cog wheel on the right), and check the “outlier detection” option.
As for your second question, the models are still been tested using the pre-processing methods you have originally chosen.
Ayelet,
The Consumer Physics Team
- You must be logged in to reply to this topic.