Next Article in Journal
Analysis of Feature Dimension Reduction Techniques Applied on the Prediction of Impact Force in Sports Climbing Based on IMU Data
Previous Article in Journal
User Identity Protection in Automatic Emotion Recognition through Disguised Speech
 
 
Article
Peer-Review Record

Traffic Speed Prediction Based on Heterogeneous Graph Attention Residual Time Series Convolutional Networks

AI 2021, 2(4), 650-661; https://doi.org/10.3390/ai2040039
by Yan Du, Xizhong Qin *, Zhenhong Jia, Kun Yu and Mengmeng Lin
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
AI 2021, 2(4), 650-661; https://doi.org/10.3390/ai2040039
Submission received: 27 August 2021 / Revised: 26 October 2021 / Accepted: 16 November 2021 / Published: 26 November 2021

Round 1

Reviewer 1 Report

The paper looks well done, though:

  1. The introductory bibliography should be improved
  2. The text in the yellow rectangles of Figure 1 does not read, increase the font size
  3. Figure 2 must be modified to assume a horizontal shape in order to be inserted on page 7 without leaving spaces
  4. The experiment should be expanded and better described

Author Response

This article has been substantially revised according to your requirements. The revised content has been marked in red font. In addition, there are some annotations to explain the original meaning, and the experimental part has also been expanded. Thanks for the guidance.

Author Response File: Author Response.docx

Reviewer 2 Report

Please see attachment.

Comments for author File: Comments.pdf

Author Response

This article has been substantially revised according to your requirements. The revised content has been marked in red font. In addition, there are some annotations to explain the original meaning, and the experimental part has also been expanded. Thanks for the guidance.

Author Response File: Author Response.docx

Reviewer 3 Report

In this paper, the authors try to predict traffic speed using neural networks. There is some effort in comparing different prediction techniques. However, the paper is terribly written which made the review quite challenging. This paper needs a complete overhaul, in consultation with a native speaker.

There are several statements that made absolutely no sense. 

What is the meaning of "realization of urban smart traffic", "social events such as traffic accidents", "clear traffic tasks", "development of society", "European data"? These are just a few phrases that don't make any sense. There are several of them throughout the paper.

There are several long sentences. For example, Lines 13-16, 78-82. Again, these are just some examples.

There are also several incomplete sentences. For example, lines 41-42, 76-77.

The authors should proofread the document thoroughly before submitting the paper to a journal as this wastes our precious time.

The introduction and literature review needs to be separated. A clear gap in the past studies needs to be identified. The objectives of the current study are not clear.

What exactly is the meaning of "changing the relation between nodes", 
"relation between changes in roads"? These do not make any sense at all.

You mentioned "accidents" several times, but accident data was not analysed.

 

Author Response

This article has been substantially revised according to your requirements. The revised content has been marked in red font. In addition, there are some annotations to explain the original meaning, and the experimental part has also been expanded. Thanks for the guidance.

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

The paper has been not revised sufficiently. Several issues found in the original submission still exist. 

Back to TopTop