Next Article in Journal
Analysis and Ranking of IT Risk Factors Using Fuzzy TOPSIS-Based Approach
Next Article in Special Issue
Design of an In-Process Quality Monitoring Strategy for FDM-Type 3D Printer Using Deep Learning
Previous Article in Journal
Source Model and Seismogenic Environment of the Ms 6.4 Yangbi Earthquake in Yunnan, China—Based on InSAR Observation
Previous Article in Special Issue
Machine Learning-Based Highway Truck Commodity Classification Using Logo Data
 
 
Article
Peer-Review Record

Autonomous Temporal Pseudo-Labeling for Fish Detection

Appl. Sci. 2022, 12(12), 5910; https://doi.org/10.3390/app12125910
by Ricardo J. M. Veiga 1,2,*, Iñigo E. Ochoa 3,4, Adela Belackova 3, Luís Bentes 3, João P. Silva 1,2, Jorge Semião 1,5 and João M. F. Rodrigues 1,2
Reviewer 1:
Appl. Sci. 2022, 12(12), 5910; https://doi.org/10.3390/app12125910
Submission received: 5 May 2022 / Revised: 2 June 2022 / Accepted: 8 June 2022 / Published: 10 June 2022
(This article belongs to the Collection Machine Learning in Computer Engineering Applications)

Round 1

Reviewer 1 Report

There is a strange use of commas in the first three pages of the paper - need to run through a grammar check to validate the use of commas.

This paper is a very interesting approach and a good application of transfer learning. Overall metrics for the system are important since using DL to generate labels could insert a situation that is difficult to interpret. It may be good to have some type of feedback with the SME to validate the automated labeling if not all of the processing needs to be done inside the underwater station.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

The authors present an exciting application. The use of real data is also valuable. My comments are:

1. The recall values are low; this is not fatal; however, a detailed explanation of why it was impossible to obtain a more significant value will be insightful. Also, establish why this low value does not affect your application.

2. Would you consider providing a Github with the datasets and code to reply to your results?

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

Thanks for addressing all the comments.

Back to TopTop