by Joanna Georgiou, Chrysovalantis Christodoulou, George Pallis and Marios Dikaiakos (University of Cyprus)
A key challenge in the aviation industry is managing aviation data, which are complex and often derived from heterogeneous data sources. ICARUS Ontology is a domain-specific ontology that addresses this challenge by enhancing the semantic description and integration of the various ICARUS platform assets.
The current digital revolution has heavily influenced the way we manage data. For the past few years every human activity, process, and interaction has been digitised, resulting in an exponential increase in the amount of data produced. There is huge potential for useful information to be extracted from this data, perhaps enabling us to discover new ways of optimising processes, find innovative solutions, and improve decision-making. However, managing enormous amounts of data from numerous, heterogeneous sources that do not share common schemas or standards poses many challenges: data integration and linking remains a major concern.
The procedure of integrating and linking data can be expensive and is often underrated, especially for small and medium-sized enterprises (SMEs), which may lack the required expertise and be unable to invest the necessary time and resources to understand and share the digital information derived from their operational systems. Usually, data models are created in a manner that can handle information by encoding the structure, format, constraints, and relationships with real-world entities.
The challenge of managing big data is apparent in various industry domains, including the aviation industry. Unfortunately, aviation data providers use very distinct data models that can vary across different dimensions [1], like data encoding format, data field naming, data semantics, spatial and temporal resolution, and measurement unit conventions. To enhance the integration of data in a data platform for the aviation industry, we designed and introduced the ICARUS ontology [2].
The ICARUS [L1] platform helps stakeholders that are connected to the aviation industry by providing them with a system to share, collect or exchange datasets, knowledge, and skills. Through these services, the ICARUS project seeks to help stakeholders gain better perspectives, optimise operations, and increase customer safety and satisfaction. Additionally, it aims to offer a variety of user-friendly assets, such as datasets, algorithms, usage analytics and tools. To manage the complex and dynamic evolution of these assets, we sought to develop an ontology to describe various information resources that could be integrated and managed by the ICARUS platform. Ontologies can act as valuable tools to describe and define, in a formal and explicit manner, relationships and constraints, and for knowledge representation, data integration, and decision making.
The ICARUS ontology, as is depicted in Figure 1, enables: (i) the integration and description of numerous sources of heterogeneous aviation data; (ii) the semantic representation of the metadata generated by the ICARUS platform and the knowledge-based storage, which is dynamically updated and accessed through queries. More specifically, the ICARUS ontology extracts, stores, and represents semantically in the knowledge-based storage all of the platform’s datasets and operations. It represents other modules of the ICARUS platform semantically, like deployed algorithms, user interactions, service assets, and their popularity. In addition, the ontology keeps the ICARUS data model and knowledge-based storage up-to-date, while facilitating the ongoing integration of new datasets and services. In this way, it also enables searches and queries of various heterogeneous data sources that are available on the ICARUS platform. Lastly, the ontology provides an application-programming interface to feed valuable knowledge into the ICARUS recommendation engine algorithms.
Figure 1: Ontology and knowledge-base extension of the ICARUS platform architecture.
The ontology can be applied in various scenarios, including the management of epidemic data. Epidemics, such as the COVID-19 pandemic, present a significant challenge for health organisations when it comes to as locating, collecting and integrating accurate airline and human mobility data with adequate geographical coverage and resolution. If such challenges are addressed well, this can lead to improved epidemic forecasts [3] and potentially enable better estimates of anticipated relative losses of revenue under various scenarios by estimating the reduction of passengers in the airline mobility network. The ICARUS ontology can semantically combine epidemic and aviation-related data for data analytics and epidemic predictions. These analytics and predictions can be extracted from the ontology by completing three key stages: (i) using the ontology to collect aviation and health related data based on concepts / entities stored in the ontology; (ii) combining the datasets based on their relationships as described in the ontology; and (iii) using SPARQL queries to derive new information and insights from the combined datasets.
The main innovative aspects of the ICARUS ontology are: (i) the reuse of existing domain ontologies while adding new concepts, definitions, and relations in order to create a new integrated domain ontology for aviation; and (ii) the use of multiple layers to represent both metadata and aviation-specific concepts. With this approach, the ontology's domain can also be used for other purposes, for instance, general data marketplaces.
The ICARUS ontology can be utilised to perform various analytic SPARQL queries and extract knowledge. It can be found in our github repository [L2] and it is intended to be used by:
• data providers and consumers, who can be stakeholders that are directly or indirectly connected in the aviation value chain industry;
• people from the IT industry who are supporting the aviation value chain. (e.g., IT companies, web entrepreneurs, and software engineers);
• research organisations and universities studying the aviation ecosystem;
• the general public (e.g., passengers);
• other data marketplaces.
ICARUS is a three-and-a-half year project (started 1 January 2018), funded by the European Union’s Horizon 2020 research and innovation programme. This work is partially supported by the EU Commission in terms of ICARUS 780792 (H2020-ICT-2016-2017) project and by the Cyprus Research Promotion Foundation in terms of COMPLEMENTARY/0916/0010 project. The authors are solely responsible for the contents of this publication and can in no way be taken to reflect the views of the European Commission.
Links:
[L1] https://www.icarus2020.aero/
[L2] https://github.com/UCY-LINC-LAB/icarus-ontology
References:
[1] R. M Keller: “Ontologies for aviation data management”, in 2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC), pages 1–9. IEEE, 2016.
[2] D. Stefanidis, et al.: “The ICARUS Ontology: A general aviation ontology developed using a multi-layer approach”, in Proc. of the 10th International Conference on Web Intelligence, Mining and Semantics (WIMS), 2020.
[3] C. Nicolaides, et al.: “Hand‐Hygiene Mitigation Strategies Against Global Disease Spreading through the Air Transportation Network”, Risk Analysis, vol. 40, no. 4, pp. 723–40, 2020.
Please contact:
George Pallis, University of Cyprus, Cyprus
