Next Article in Journal
Machine Learning Model Based on Radiomic Features for Differentiation between COVID-19 and Pneumonia on Chest X-ray
Previous Article in Journal
Development and Validation of a Tunable Diode Laser Absorption Spectroscopy System for Hot Gas Flow and Small-Scale Flame Measurement
 
 
Article
Peer-Review Record

Transportation Mode Detection Using Temporal Convolutional Networks Based on Sensors Integrated into Smartphones

Sensors 2022, 22(17), 6712; https://doi.org/10.3390/s22176712
by Pu Wang * and Yongguo Jiang
Reviewer 1: Anonymous
Reviewer 2:
Reviewer 3:
Sensors 2022, 22(17), 6712; https://doi.org/10.3390/s22176712
Submission received: 16 August 2022 / Revised: 1 September 2022 / Accepted: 1 September 2022 / Published: 5 September 2022
(This article belongs to the Section Sensor Networks)

Round 1

Reviewer 1 Report

This paper proposed deep learning algorithms to identify the transportation mode of road users carrying a smartphone. The data used are from the IMU sensor, including accelerometers, gyroscopes, magnetometers, and barometers, in contrast to the previous studies using GPS traces for cellular vehicle probes. The model prediction results outperform the previous models.

 

 

However, it is unclear the application of the presented study. How can the proposed methodology be applied to detect the modes of travelers in the road system? IMU data is not to be collected by the mobile service provider. Or if the algorithm is to be installed on the smartphone? The smartphone user knows the transportation mode they are using, and it seems there is no need to detect the mode automatically. Please clarify the potential application of this methodology.

Author Response

We have uploaded our response letter as a PDF file, please refer to it. Thank you.

Author Response File: Author Response.pdf

Reviewer 2 Report

Refer to the attached file, Review_R1_Trans_mode, please.

Comments for author File: Comments.pdf

Author Response

We have uploaded our response letter as a PDF file, please refer to it. Thank you.

Author Response File: Author Response.pdf

Reviewer 3 Report

The paper with title, ‘Transportation Mode Detection Using Temporal Convolutional  Networks Based on Sensors Integrated in Smartphones’ transportation mode detection algorithm has been proposed, which is namely as T2Trans. The model is based on temporal convolutional networks, such as TCN by using myriad lightweight sensors being integrated with phone.  Furthermore, results of F1-score of 86.42% on the real world SHL dataset and 88.37% on the HTC dataset are achieved. The carried out work is interesting and quite comprehensive. However, before acceptance following comments must be incorporated.

1.       The abstract and Conclusion could be improved by adding more quantitative data (results).

2.       More recent works should be added in the citations.

3.       Very brief captions are given to all figures, authors should add little details in each figure.

4.       There are various grammatical mistakes, which should be corrected in the revised manuscript.

5.       The variable in equation (1) need explanation.

6.       Authors should add a comparison table which shows the standing of their achieved results in comparison to the recently reported studies.

7.       It would be better, if authors add a paragraph before conclusion about the future work (as this algorithm still needs improved to be at mature level).

 

 

Author Response

We have uploaded our response letter as a PDF file, please refer to it. Thank you.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Refer to the attached file, please.

Comments for author File: Comments.pdf

Author Response

We have uploaded our response letter as a PDF file, please refer to it. Thank you.

Author Response File: Author Response.pdf

Reviewer 3 Report

All of my comments are well addressed. So I recommend its acceptance.

Author Response

Thanks for your insightful comments.

Back to TopTop