On the Track to Application Architectures in Public Transport Service Companies
Round 1
Reviewer 1 Report
- Author did not address problem clearly, need to clearly mention research problem in abstract section.
- Table 1. AI Core and Sub-Domains add more attributes and details so, reader can easily understand.
- Figure 1. AI landscape in public transportation need more detail explanation.
- How can initial TRL1 proof of concept state to the final TRL9 deployment state need more detail explanation.
- how can author extracts taken from experiments during the development of the AI-based passenger
counter figure 4. need more detail explanation.
Author Response
please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
This paper is a general review of AI applications in public transportation. For a review paper, I think there are several weaknesses exists:
- Background introduction is insufficient, readers still don’t understand the necessity and importance of this investigation.
- In Introduction section, the authors claimed several contributions, however, it seems like a market investigation report rather than an academic review.
- In my opinion, this paper needs to be improved a lot in research method, statistical data and analysis and conclusions.
- Figures in this paper are too vague.
- Cases presented in this paper are not well explained and concluded.
Author Response
see document included.
Author Response File: Author Response.pdf
Reviewer 3 Report
The paper entitled “Towards AI-based Application Architectures in Public Transport Service Companies” proposes a framework for the public transport sector that relies on existing AI-domains and AI-categories defined by different technical reports of the European Commission. It collects use-cases from three different enterprises in the transportation sector and visualizes them on the proposed domain-specific AI landscape. It provides some insights into different maturity levels of different AI-based components and how the different machine learning and knowledge engineering-based components can be embedded into an AI-based software development life cycle.
In general, the topic invested in this paper is interesting and suitable for the scope of the AS journal. The paper is well written and organized. In support of this paper, the authors should revise the paper to further improve its quality before I vote for an acceptance. My comments are as follows:
- The Introduction is quite short, the authors should further discuss motivation and challenges in building AI-based components in the public transport service industry.
- Also, introduce the outline of the paper.
- Figures 1 and 2 are not in a good shape. Authors should revise these figures to make the text clearer, copiable, and not be broken when zooming out.
- In section 4, I suggest the authors illustrate use-cases by using UC diagrams in UML.
- Section 5, discuss how the proposed framework can be applied in real-life applications. An emerging problem is how to design Explainable Artificial Intelligence (XAI) system and improve the interpretability of the proposed framework. To this end, the authors should discuss the opportunity of using data-driven approaches in this field to improve the interpretability of the architectures. The authors refer to these works in the discussion [https://doi.org/10.3390/a15030076], [https://doi.org/10.1007/978-981-15-1209-4_1], [https://www.tandfonline.com/doi/abs/10.1080/16483840.2003.10414100]
- Carefully revise the paper to fix all typos and grammar mistakes.
Author Response
see document included.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
some of references is incomplete in reference list
Author Response
Fixed English language and style. (Changes done on May 10th, see final Latex zip file).
Fixed style issue of reference 23.
Since the purpose of the paper is not a comprehensive literature review, but developing new artefacts, which help to establish AI-based components in the transportation service sector and demonstrate it with the use-cases of the three organizations, we did not add further references. But we did add further remarks in the conclusion that points that explain these circumstances a little further.
Reviewer 3 Report
I think the paper reaches the level of acceptance
Author Response
Fixed English language and style. (Changes done on May 10th, see final Latex zip file).
Added more specific hints pointing to our results in the conclusion section and the aspect of creating a shared vision within transportation service organizations, that helps to speed up the implementation and sharing of AI-based components.