Introducing MOSA: Enhancing Traffic Event Analysis for Situational Awareness Services

This submission discusses the application of ontology systems for connected vehicles using techniques, such as knowledge graphs. This idea in general has the potential to provide a huge impact as it affects autonomous driving, intelligent transport, and traffic analyses in general.

The authors discuss their system at a fairly superficial level. Some logic rules are described. However, these seem overly simple. For example, the rule for hard braking is essentially detecting a large amount of negative acceleration. Similarly, the detection of speeding is essentially a measure of how fast a vehicle moves in excess of the speed limit. Again, this seems rather straightforward. But there is not much of a description of how all the pieces come together. There are references to OpenStreetMap but it is unclear how it is really used beyond serving as a data repository for speed limits.

The knowledge graph itself, which one would consider an essential component of this work, is described in three short paragraphs with mostly references to other elements but very little specificity.

A screenshot of the user interface is provided but with little to know explanation leaving the reader in the dark as to what data elements are included in the visualization.

The system was evaluated based on simulated data. However, there is no discussion on how this simulation was generated beyond its existence. This simulation is crucial in determining the relevance and functionality of the system. Without more description of how it was generated and how realistic the simulation effectively is, no conclusions can be drawn with respect to the system developed by the authors. The authors provide some plots for speeding and hard braking. But without the necessary context, these plots are fairly meaningless.

While I see potential value in what the authors are trying to do, the execution of this submission is lacking in both the description of the approach and its evaluation.

This manuscript was submitted as 'Application Report' and should be reviewed along the following dimensions: (1) Quality, importance, and impact of the described application (convincing evidence must be provided). (2) Clarity and readability of the describing paper, which shall convey to the reader the key ideas regarding the application of Semantic Web technologies in the application. Please also assess the data file provided by the authors under “Long-term stable URL for resources”. In particular, assess (A) whether the data file is well organized and in particular contains a README file which makes it easy for you to assess the data, (B) whether the provided resources appear to be complete for replication of experiments, and if not, why, (C) whether the chosen repository, if it is not GitHub, Figshare or Zenodo, is appropriate for long-term repository discoverability, and (4) whether the provided data artifacts are complete. Please refer to the reviewer instructions and the FAQ for further information.

Summary
The paper, "Introducing MOSA: Enhancing Traffic Event Analysis for Situational Awareness Services", explores the integration of intelligent transportation systems (ITS) and connected automated vehicles (CAVs) to improve situational awareness and traffic management. The authors propose the Mobility Ontology for Situational Awareness (MOSA), a novel ontology to formalize traffic scenarios, enable semantic inferencing, and enhance explainability in CAV systems. The paper discusses the development of MOSA, its integration with a knowledge graph (KG), and its application in a service architecture designed for real-time situational awareness. The study is supported by simulations and analyses, showcasing the potential of MOSA to improve traffic safety and decision-making.

Contribution -
The paper makes a valuable contribution to advancing situational awareness in ITS, particularly through the formalization of traffic scenarios using ontologies. It demonstrates strong technical depth and provides a clear path forward for integrating semantic technologies with CAV systems. However, the limited practical deployment and dense technical presentation slightly detract from its overall impact.

Strong Points -
1.Innovative Contribution:
The introduction of MOSA fills a significant gap in traffic scenario modeling by providing detailed semantic structures for events and actions. Its integration with a knowledge graph and semantic inference enhances the functionality of ITS.

2. Technical Depth:
Comprehensive development of MOSA with 185 classes, 20 object properties, and detailed rules for traffic scenarios. Simulation results demonstrate practical applicability and validate the proposed ontology.

3.Relevance and Impact:
Addressing situational awareness in ITS is highly relevant, aligning with current trends in smart mobility and autonomous systems. The focus on transparency and explainability builds trust in CAV systems.

4.Clear System Design:
The architecture is well-described, including data fusion, semantic inference, and visualization through a monitoring interface.

5. Open Challenges Acknowledged:
The paper identifies limitations and provides a roadmap for future work, including expanding MOSA and improving real-world applicability.

Weak Points -
1. Dense technical language and detailed descriptions may hinder accessibility for practitioners outside the ontology or ITS domain.
2. Limited discussion on how MOSA would scale with real-world data complexities and integrate seamlessly with existing ITS frameworks.
3. While simulations are detailed, the study lacks comprehensive metrics for evaluating the scalability, efficiency, or robustness of MOSA.

The paper presents a well-structured approach to improving traffic event analysis through the proposed Mobility Ontology for Situational Awareness (MOSA). The integration of knowledge graphs and semantic inference mechanisms is a notable contribution, as it enhances the interpretability and interoperability of traffic data for intelligent transportation systems (ITS). The discussion on Explainable AI (XAI) within Connected and Automated Vehicles (CAVs) is particularly relevant given the increasing need for transparency and trust in AI-driven decision-making. While the concept is relevant to the growing need for explainable AI (XAI) and improved traffic data processing, several aspects of the study weaken its practical impact.

The condition in Algorithm 1 seems wrong.
It can not be true that: if .... speed > 20 and speed = 20

- The framework is primarily evaluated through simulations, which, while useful, do not account for the complexities and unpredictability of real-world traffic scenarios. The absence of real-world implementation raises concerns about its scalability and robustness in practical ITS environments.

- One major issue with the paper is the lack of transparency regarding data availability. There is no clear reference to a publicly accessible dataset that would allow for independent verification or replication of the study. Given that the effectiveness of MOSA relies heavily on data-driven inference, the absence of dataset access significantly diminishes the reproducibility of the study.

- The proposed integration of semantic inference, knowledge graphs, and real-time data fusion is ambitious but does not sufficiently discuss performance constraints. Given the high computational overhead of semantic reasoning, practical deployment at scale could be a significant challenge.