Reviewer #1:
Reviewer: 1
In general, the paper is linguistically weak and hard to understand.
In addition, it needs to expand on details related to methodology,
results and discussion.
[Response] We appreciate Reviewer #1’scomments
and have revised as suggested.
2.
The
author did not provide a compelling reason for choosing ANN for this
spectroscopic application. In FTIR spectroscopy, the relationship
between absorbance and the concentration of the analyte of interest is a
linear one as established by Beer’s law. ANN is a powerful algorithm
used to model non-linear relationships between multiple predictors and
responses in big datasets. In this paper, the author used only three
FTIR peaks for 156
spectra,
as I understood it. This dataset does not qualify as big data and the
relationship between absorbance and concentration is already a linear
one.
[Response] Thanks for your comments.There is no one-to-one
correspondent relationship between these chemical indexes (polar
compounds, free fatty acids, hydroperoxide) and the selected peak areas,
therefore they may be not absolutely the linear relationships between
the chemical indexes and the selected peaks. Many researches also used
the ANN to calibrate the model with the spectra and other chemical index
indicating it is available for choosing ANN for this spectroscopic
application