Trajectory Compression with Spatio-Temporal Semantic Constraints

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Trajectory compression can reduce the size of data, and it is common in the processing of trajectory big data. Based on the spatial and temporal characteristics of trajectories and considering the semantic information of trajectories, a trajectory compression method based on spatial and temporal semantic constraints is proposed. This is an interesting study, but I still have a few suggestions for the paper.

1. Please clarify the POI data acquisition method, data processing process and detailed information. The most important thing is whether the time of the track information corresponds to the year of the POI data, namely 2009. If not, the experimental results will lack reliability.

2. Please describe in detail the criteria for selecting 13 types of POI in this paper. We know that there are many types of POI, and if some POI is applied to the study in this paper, the semantic expression of trajectory information is insufficient.

3. The description in the conclusion part of the paper is too simple, and the improvement of this study and the prospect of future research should be clarified.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

How to reduce the amount of data without reducing the trajectory accuracy is an important goal of trajectory compression. For the description of trajectory accuracy, this study introduces semantic trajectory constraints, which has certain innovation.

Question 1. There have been studies considering semantic trajectory compression, such as the reference [24] cited in this paper. Please explain the differences and advantages between semantic trajectory compression in this paper and the existing studies.

Question 2. In Table 1, please mark the units or make comments.

Question 3. The semantic annotation classification studied in this paper is more about functional or geospatial objects. In fact, semantic trajectories at different meta-semantic levels have different characteristics. Is the classification method proposed in this paper suitable for all semantic trajectories types, or is it just functional types of geospatial objects? Please add clarification to the discussion.

Question 4. In Figure 5, it is suggested to use a table or other graph to describe it, which is difficult to distinguish the difference.

Question 5. In Figure 7, it is suggested to add legend description, for example, what does the box represent?

Comments on the Quality of English Language

 the Quality of English Language is OK， Some sentences are difficult to understand. It is recommended to remove long sentences to increase readability.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

Dear Authors,

Thank you for your manuscript. The current manuscript provides an interesting approach but with certain limitations. I hope my comments and suggestions in the attached PDF can help improve your manuscript.

Thank you.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

The manuscript is overall well-written in English. However, there are a few minor errors and grammar issues in the current text. I hope my comments in the attached PDF can be useful.

Author Response

Please see the attachment.

Author Response File: Author Response.docx