In major revision for publication of my paper, one of the points is " Identify the factors that make the accuracy reach 100% for both datasets. How to explain these points in the discussion. Kindly guide me.
An example of such point could be increasing in accuracy with increasing sample size, reaching accuracy at 100. The following paper talks about this sample size effects:
Effects of sample size on accuracy of species distribution models
DRB Stockwell, AT Peterson - Ecological modelling, 2002 - Elsevier
I am sending a paper, hoping it will be useful to you, it is a study of the influence of preprocessing, segmentation and optimization in the CNN.
Chapter Accurate Identification of Tomograms of Lung Nodules Using C...
You could write something like this: "the effect of preprocessing, and optimization (or whatever you have studied) were analyzed in both datasets, it was found that the factors that influence to have a better performance are ..."
I am deeply concerned about data sets with 100% accuracy. I was an Auditor for 5 years and know that one can approach perfect accuracy but it cannot be achieved in the real world.
Many of my fisheries models approach a statistical accuracy of unity, but the models reflected games being played by the fisheries managers -- If your statistics are at unity, you do not have a prediction model but an identity (i.e., the model being used by management to force out desirable outcomes).