[Response] Four kinds of oils (soybean oil, rapeseed oil, palm oil, and sunflower oil) were used for frying. the French fry samples were prepared in each frying oil at different frying time of 0.06, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, and 24 h. each spectrum of French fry samples were collected three times, so there are 4×13×3=156 sets of data.
15.line139 Testing dataset should be generated using a new batch of oil and potatoes that are subjected to the same experimental conditions under which the data was generated for building the model. This new set of data is used to predict the response from your model and then the accuracy and precision of those predictions are evaluated. Using a sub dataset from the same experiment is not acceptable as testing dataset.
[Response] Thanks for your comments,we have added the external validation in the Manuscript. Line 258-269.
16. line 145 No details were given about the development of the PLS model. Please clarify how the PLS model was created. Did the author use the full spectra of your samples?