Creating Occupant-Centered Digital Twins Using the Occupant Feedback Ontology Implemented in a Smartwatch App

Tracking #: 3158-4372

Alex Donkers
Bauke de Vries
Dujuan Yang

Responsible editor: 
Guest Editors SW for Industrial Engineering 2022

Submission type: 
Full Paper
Occupant feedback enables building managers to improve occupants’ health, comfort, and satisfaction. However, acquiring continuous occupant feedback and integrating this feedback with other building information is challenging. This paper presents a scalable method to acquire continuous occupant feedback and directly integrate this with other building information. Semantic web technologies were applied to solve data interoperability issues. The Occupant Feedback Ontology was developed to describe feedback semantically. Next to this, a smartwatch app – Mintal – was developed to acquire continuous feedback on indoor environmental quality. The app gathers location, medical information, and answers on short micro surveys. Mintal applied the Occupant Feedback Ontology to directly integrate the feedback with linked building data. A case study was performed to evaluate this method. A semantic digital twin was created by integrating linked building data, sensor data, and occupant feedback. Results from SPARQL queries gave more insight into an occupant's perceived comfort levels in the Open Flat. The case study shows how integrating feedback with building information allows for more occupant-centric decision support tools. The approach presented in this paper can be used in a wide range of use cases, both within and without the architecture, building, and construction domain.
Full PDF Version: 

Minor Revision

Solicited Reviews:
Click to Expand/Collapse
Review #1
Anonymous submitted on 07/Jul/2022
Review Comment:

The Authors answered all of my remarks and provided adequate changes to the manuscript.
In particular:
- Sect. 2.3 now details the novelty of the proposed solution wrt to existing ones;
- Abbreviations are now glossed
- Sect. 8 helps the readers in assessing the contribution of this paper.

The Authors also provided some details wrt the ontology engineering methodology adopted (Sect. 3). It is interesting to note that the ontology here proposed was developed by collaborating with industry partners (comment & answer 1005), therefore leveraging somehow on a collaborative approach. I suggest underlining this aspect of the engineering process, as it is fundamental (see e.g.: 10.1016/j.compind.2022.103690).

After reading answer 1006, I agree with the Authors' choice - removing the sentence.
Although the discussion regarding using one ontology instead of others is out of the scope of this work, the Authors properly addressed the alignment problem in Sect. 4.3.

Considering the answers provided and the modifications to the manuscript, I think this work is a solid contribution to the topic of integrating and exploiting building occupants' feedback leveraging a domain ontology.

Review #2
By Maxime Lefrançois submitted on 13/Jul/2022
Minor Revision
Review Comment:

I read attentively the other reviews and the exhaustive responses by the authors.
Overall I consider the paper has been greatly improved, and addresses the main comments by the reviewers.

The two new subsections 2.3 (Research gaps) and subsection 4.3 (Alignment) are on the right track.
However I consider they should be extended as follows:

Subsection 2.3 (Research gaps) lists features that different approaches have, or do not have, using long lists of citations to papers for each features. It would be a lot more more concise and readable to provide a simple table with the existing work as lines, the features as columns, and a simple tick in a cell to assert that an existing work implements an approach. Nuances can be provided with footnotes in the figure for example.

Subsection 4.3 (Alignment)
The alignment choices in the online alignment documents are fine with me. One minor comment:
should import
and not

However, the section is way too short. These alignments and the rationale are definitely of interest to the readers, and should be included as tables in the paper.

Note: I totally agree ssn:hasProperty would better be modeled as functional, to enforce that properties should be specific to features of interests. However former users of SSN defined generic properties such as :Temperature, :Humidity. Therefore, such an axiom would be too strong an ontological commitment, and make such legacy usage of SSN incompatible with the new version. See footnote 10, p.9 in the paper "The Modular SSN Ontology: A Joint W3C and OGC Standard Specifying the Semantics of Sensors, Observations, Sampling, and Actuation" published in this journal.

Review #3
By Georg Schneider submitted on 26/Jul/2022
Review Comment:

The content of the paper has significantly been improved. All my comments are now covered by the authors.

In particular, this includes the formal definition of alignments to existing ontologies as described in Section 4.3 and available on the web. Now it is clear and formally defined how the presented ontology relates to existing ones.

The newly added Section 2.3 largely improves the paper. The authors clarify now why the development of their ontology has been necessary and what distinguishes their work from others.

The long lists of citations in Section 2.3 are cumbersome to read. Putting the result of this analysis into a table where features/ requirements are mapped against previous contributions from literature would be much more easier for readers to read and grasp.

Some Minor comments

- This link seems to be broken:
- It might make sense to include the graphical notation used in Fig. 4 (arrow = rdf:type) or reference Fig. 3 in the title of Fig. 4 to make clear what is meant by the different arrows and line shapes.