[Response] Thanks for your comments. We have added more details as suggested. Each recorded spectrum was obtained by averaging 16 scans at a resolution of 4 cm-1. Each sample was measured three times. The average of the three spectra obtained from each same sample was used in subsequent analysis. The spectra file of samples was pretreated through normalization to reduce measurement error. Each spectrum was aligned to the baseline using instrumentation software. Line 139-143
12. line 126 Do ”oil extracts” refer to oil extracted from the French fries? What does ”extracts” refer to?
[Response] The oil extracts refer tooil extracted from the French fries. Line 144
13.line 132 The author did not provide enough details about how he/she developed the ANN model. The description is very general. For example, what were the settings that he/she used for the construction of the hidden layer? Did he/she use a specific random seed for the validation? Did he/she use boosting? Did he/she apply any penalty method?
[Response] Thanks for your comments. We have added more details as suggested.Through parameter optimization in the pre-experiment, the best BP-ANN model was obtained with the neuron number of 10 in hidden layer, the training function of trainlm, and the transfer functions of tansig and purelin in hidden layer and output layer, respectively, without using the boosting and penalty method. Line 154-157
14. line 147 It is not clear what the author means with 156 sets of data. Does each dataset represent spectra of extracted oil from French fries fried in a specific oil for 3 days? Please, clarify this point thoroughly.