Next Article in Journal
Titanium(III) Oxide Doped with meta-Aminophenol Formaldehyde Magnetic Microspheres: Enhancing Dye Adsorption toward Methyl Violet
Previous Article in Journal
A Three-Phase Relative Permeability Model for Heavy Oil Emulsion System
 
 
Article
Peer-Review Record

The Application of Hyperspectral Images in the Classification of Fresh Leaves’ Maturity for Flue-Curing Tobacco

Processes 2023, 11(4), 1249; https://doi.org/10.3390/pr11041249
by Xiaochong Lu 1, Chen Zhao 1, Yanqing Qin 2, Liangwen Xie 2, Tao Wang 3, Zhiyong Wu 1 and Zicheng Xu 1,*
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3:
Processes 2023, 11(4), 1249; https://doi.org/10.3390/pr11041249
Submission received: 8 March 2023 / Revised: 4 April 2023 / Accepted: 17 April 2023 / Published: 18 April 2023

Round 1

Reviewer 1 Report

The author applied hyperspectral imaging combined with machine learnings for classing the fresh leaves' maturity. Here are some comments:

1 Please improve Figure 4, I can't get difference among the samples, maybe you can use average spectral of each stage?

2 Table2 there are only 6 samples in "Unripe" stage. Please add samples

3There are 11 filtered methods for original data, please the effective methods. (There are 7 methods with lower accuracy than original data)

4PSO select 70 or 66 important  wavelenghts, too much, you just using SPA and PSO, please add other helpful selective algorithm.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

This is an interesting work presenting an interesting research on the application of Hyperspectral images in the Classification of tobacco leaves. Some comments:

- Highlight all assumptions and limitations of your work.

- Conclusions should provide some lessons learnt.

 

- Related works section does not mention recent research efforts in related fields on classification and predicition on highly correlated and scarce sequential data. Authors are advised to refer to the following related articles to add some discussions: [1] Novel Data-Driven Models Applied to Short-Term Electric Load Forecasting, Applied Sciences, 2021 [2] Additive Ensemble Neural Network with Constrained Weighted Quantile Loss for Probabilistic Electric-Load Forecasting, sensors, 2021 [3] Plant Species Classification Based on Hyperspectral Imaging via a Lightweight Convolutional Neural Network Model. Frontiers in Plant Science. 2022  [4] Bloodstain Identification Based on Visible/Near-Infrared Hyperspectral Imaging With Convolutional Neural Network, IEEE Access, 2022 [5]Hyperspectral Image Classification Based on Expansion Convolution Network, IEEE Transactions on Geoscience and Remote Sensing , 2022

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report


Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Back to TopTop