TBRm: A Time Representation Method for Industrial Knowledge Graph

Round 1

Reviewer 1 Report

The authors proposed a time representation method for industrial knowledge graph. The idea is interesting and novelty. nice work.

Author Response

Thank you very much for your encouragement and affirmation. We will continue to seriously improve the shortcomings in the research and make the paper more perfect.

Reviewer 2 Report

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

 

The paper deals with the usage od temporal knowledge graph to represent and process information gathered by IoT and IIoT (industrial Intenet of Things). The approach has been tested on four datasets.

Compared to traditional knowledge graph, the author has shown that the addition of temporal factor leads to better model. The Model structure and the mapping mechanism are correctly explained. However the section 4.1 dealing with datasets is not in adequation with the abstract and the introduction. The chosen datasets “ICEWS”, a political time repository, has no relation with IoT nor IIoT. The three other datasets are also with no significance when we speak about IoT and IIoT. This section should be reconducted on significant Datasets dealing with IIoT or at Least IoT. At the same time, the author should justify how he choose the datasets among those found.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

The paper deals with the usage od temporal knowledge graph to represent and process information gathered by IoT and IIoT (industrial Intenet of Things). The approach has been tested on some datasets having no relation with IIoT. The use of Edge-IIoTset is good but not enough.

The section Dataset should be enforced by other datasets representing another context of IoT and IIoT. And suppress datasets having no sense with IoT and IIoT.

For example, ICEWS is a political time repository containing timestamps and has no relation to the semantic and specificities of Internet of Things and their subset IIoT. ICEWS has no place in this paper. Even the explanation of the approach should be based on IoT and IIoT and not political context.

If this task will be correctly done, the paper could be accepted.

Author Response

Please see the attachment.

Author Response File: Author Response.docx