@article{corcho2024maturity,
  title = {{A Maturity Model for Catalogues of Semantic Artefacts}},
  author = {Corcho, Oscar and Ekaputra, Fajar J and Heibi, Ivan and Jonquet, Clement and Micsik, Andras and Peroni, Silvio and Storti, Emanuele},
  journal = {Nature Scientific Data (to appear)},
  year = {2024}
}

@article{herwanto2024towards,
  title = {{Towards a Holistic Privacy Requirements Engineering Process: Insights from a Systematic Literature Review}},
  author = {Herwanto, Guntur Budi and Ekaputra, Fajar J. and Quirchmayr, Gerald and Tjoa, A Min},
  journal = {IEEE Access},
  doi = {10.1109/ACCESS.2024.3380888},
  year = {2024}
}

@article{breit2023combining,
  author = {Breit, Anna and Waltersdorfer, Laura and Ekaputra, Fajar J. and Sabou, Marta and Ekelhart, Andreas and Iana, Andreea and Paulheim, Heiko and Portisch, Jan and Revenko, Artem and ten Teije, Annette and van Harmelen, Frank},
  doi = {10.1145/3586163},
  issn = {0360-0300},
  journal = {ACM Computing Surveys},
  publisher = {ACM},
  title = {{Combining Machine Learning and Semantic Web: A Systematic Mapping Study}},
  year = {2023}
}

In line with the general trend in artificial intelligence research to create intelligent systems that combine learning and symbolic components, a new sub-area has emerged that focuses on combining machine learning (ML) components with techniques developed by the Semantic Web (SW) community – Semantic Web Machine Learning (SWeML for short). Due to its rapid growth and impact on several communities in the last two decades, there is a need to better understand the space of these SWeML Systems, their characteristics, and trends. Yet, surveys that adopt principled and unbiased approaches are missing. To fill this gap, we performed a systematic study and analyzed nearly 500 papers published in the last decade in this area, where we focused on evaluating architectural, and application-specific features. Our analysis identified a rapidly growing interest in SWeML Systems, with a high impact on several application domains and tasks. Catalysts for this rapid growth are the increased application of deep learning and knowledge graph technologies. By leveraging the in-depth understanding of this area acquired through this study, a further key contribution of this paper is a classification system for SWeML Systems which we publish as ontology.

@article{Miksa2023,
  author = {Miksa, Tomasz and Such{\'{a}}nek, Marek and Slifka, Jan and Knaisl, Vojtech and Ekaputra, Fajar J. and Kovacevic, Filip and Ningtyas, Annisa Maulida and El-Ebshihy, Alaa and Pergl, Robert},
  doi = {10.5334/dsj-2023-028},
  issn = {16831470},
  journal = {Data Science Journal},
  keywords = {FAIR,RDM,automation,evaluation,funder,maDMPs},
  number = {1},
  title = {{Towards a Toolbox for Automated Assessment of Machine-Actionable Data Management Plans}},
  volume = {22},
  year = {2023}
}

Most research funders require Data Management Plans (DMPs). The review process can be time consuming, since reviewers read text documents submitted by researchers and provide their feedback. Moreover, it requires specific expert knowledge in data stewardship, which is scarce. Machine-actionable Data Management Plans (maDMPs) and semantic technologies increase the potential for automatic assessment of information contained in DMPs. However, the level of automation and new possibilities are still not well-explored and leveraged. This paper discusses methods for the automation of DMP assessment. It goes beyond generating human-readable reports. It explores how the information contained in maDMPs can be used to provide automated pre-assessment or to fetch further information, allowing reviewers to better judge the content. We map the identified methods to various reviewer goals.

@article{Cardoso2022,
  author = {Cardoso, Jo{\~{a}}o and Castro, Leyla J and Ekaputra, Fajar J. and Jacquemot, Marie C and Such{\'{a}}nek, Marek and Miksa, Tomasz and Borbinha, Jos{\'{e}}},
  doi = {10.1186/s13326-022-00274-4},
  issn = {2041-1480},
  journal = {Journal of Biomedical Semantics},
  month = dec,
  number = {1},
  pages = {21},
  title = {{DCSO: towards an ontology for machine-actionable data management plans}},
  volume = {13},
  year = {2022}
}

The concept of Data Management Plan (DMP) has emerged as a fundamental tool to help researchers through the systematical management of data. The Research Data Alliance DMP Common Standard (DCS) working group developed a set of universal concepts characterising a DMP so it can be represented as a machine-actionable artefact, i.e., machine-actionable Data Management Plan (maDMP). The technology-agnostic approach of the current maDMP specification: (i) does not explicitly link to related data models or ontologies, (ii) has no standardised way to describe controlled vocabularies, and (iii) is extensible but has no clear mechanism to distinguish between the core specification and its extensions.This paper reports on a community effort to create the DMP Common Standard Ontology (DCSO) as a serialisation of the DCS core concepts, with a particular focus on a detailed description of the components of the ontology. Our initial result shows that the proposed DCSO can become a suitable candidate for a reference serialisation of the DMP Common Standard.

@article{Ekaputra2022,
  author = {Ekaputra, Fajar J. and Ekelhart, Andreas and Mayer, Rudolf and Miksa, Tomasz and {\v{S}}ar{\v{c}}evi{\'{c}}, Tanja and Tsepelakis, Sotirios and Waltersdorfer, Laura},
  doi = {10.3233/sw-212883},
  issn = {15700844},
  journal = {Semantic Web},
  pages = {1--34},
  title = {{Semantic-enabled architecture for auditable privacy-preserving data analysis}},
  year = {2022}
}

Small and medium-sized organisations face challenges in acquiring, storing and analysing personal data, particularly sensitive data (e.g., data of medical nature), due to data protection regulations, such as the GDPR in the EU, which stipulates high standards in data protection. Consequently, these organisations often refrain from collecting data centrally, which means losing the potential of data analytics and learning from aggregated user data. To enable organisations to leverage the full-potential of the collected personal data, two main technical challenges need to be addressed: (i) organisations must preserve the privacy of individual users and honour their consent, while (ii) being able to provide data and algorithmic governance, e.g., in the form of audit trails, to increase trust in the result and support reproducibility of the data analysis tasks performed on the collected data. Such an auditable, privacy-preserving data analysis is currently challenging to achieve, as existing methods and tools only offer partial solutions to this problem, e.g., data representation of audit trails and user consent, automatic checking of usage policies or data anonymisation. To the best of our knowledge, there exists no approach providing an integrated architecture for auditable, privacy-preserving data analysis. To address these gaps, as the main contribution of this paper, we propose the WellFort approach, a semantic-enabled architecture for auditable, privacy-preserving data analysis which provides secure storage for users’ sensitive data with explicit consent, and delivers a trusted, auditable analysis environment for executing data analytic processes in a privacy-preserving manner. Additional contributions include the adaptation of Semantic Web technologies as an integral part of the WellFort architecture, and the demonstration of the approach through a feasibility study with a prototype supporting use cases from the medical domain. Our evaluation shows that WellFort enables privacy preserving analysis of data, and collects sufficient information in an automated way to support its auditability at the same time.

@article{Fernandez2020,
  author = {Fern{\'{a}}ndez, Javier D. and Sabou, Marta and Kirrane, Sabrina and Kiesling, Elmar and Ekaputra, Fajar J. and Azzam, Amr and Wenning, Rigo},
  doi = {10.1007/s00779-019-01330-0},
  issn = {1617-4909},
  journal = {Personal and Ubiquitous Computing},
  keywords = {Cyber physical (social) systems,GDPR,Linked data,Privacy,Smart mobility,User consent modeling},
  mendeley-groups = {[_MartaSabou_],_projects_/[report] 2020 CitySPIN,[ SemSysGroup  ],Slovak,_papers_/[paper] 2021 SWJ},
  month = aug,
  number = {4},
  pages = {465--486},
  title = {{User consent modeling for ensuring transparency and compliance in smart cities}},
  volume = {24},
  year = {2020}
}

Smart city infrastructures such as transportation and energy networks are evolving into so-called cyber physical social systems (CPSSs), which collect and leverage citizens’ data in order to adapt services to citizens’ needs. The privacy implications of such systems are, however, significant and need to be addressed. Current systems either try to escape the privacy challenge via anonymization or use very rigid, hard-coded workflows that have been agreed with a data protection authority. In the case of the latter, there is a severe impact on data quality and richness, whereas in the former, only these hard-coded flows are permitted resulting in diminished functionality and potential. We address these limitations via user modeling in terms of investigating how to model and semantically represent user consent, preferences, and data usage policies that will guide the processing of said data in the data lake. Data protection is a horizontal field and consequently very wide. Therefore, we focus on a concrete setting where we extend the domain-agnostic SPECIAL policy language for a smart mobility use case supplied by Vienna’s largest utility provider. To that end, (1) we create an extension of SPECIAL in terms of a core CPSS vocabulary that lowers the semantic gap between the domain agnostic terms of SPECIAL and the vocabulary of the use case; (2) we propose a workflow that supports defining domain-specific vocabularies for complex CPSSs; and (3) show that these two contributions allow successfully achieving the goals of our setting.

@article{Sabou2020,
  author = {Sabou, Marta and Biffl, Stefan and Einfalt, Alfred and Krammer, Lukas and Kastner, Wolfgang and Ekaputra, Fajar J.},
  doi = {10.3233/SW-190381},
  editor = {Hitzler, Pascal and Janowicz, Krzysztof},
  issn = {22104968},
  journal = {Semantic Web},
  keywords = {0,cyber-physical systems,industrie4,semantic web technologies,smart buildings,smart energy networks},
  mendeley-groups = {[_MartaSabou_],[ SemSysGroup  ],[_TO_READ_!!!_]},
  month = jan,
  number = {1},
  pages = {115--124},
  title = {{Semantics for Cyber-Physical Systems: A cross-domain perspective}},
  volume = {11},
  year = {2020}
}

@article{OJIS_Ekaputra_2017,
  author = {Ekaputra, Fajar J. and Sabou, Marta and Serral, Estefan{\'{i}}a and Kiesling, Elmar and Biffl, Stefan},
  journal = {Open Journal of Information Systems (OJIS)},
  mendeley-groups = {[_MartaSabou_],_projects_/[project] 2019 OBARIS,PhD_thesis,_projects_/[report] 2020 CitySPIN,[ SemSysGroup  ],_papers_/[paper] 2019 SWJ,_projects_/[project] 2019 VasQua,_projects_/[project] 2019 SIEMENS},
  number = {1},
  pages = {1--26},
  publisher = {RonPub},
  title = {{Ontology-Based Data Integration in Multi-Disciplinary Engineering Environments: A Review}},
  url = {http://rebrand.ly/v5k2x9},
  volume = {4},
  year = {2017}
}

Today’s industrial production plants are complex mechatronic systems. In the course of the production plant lifecycle, engineers from a variety of disciplines (e.g., mechanics, electronics, automation) need to collaborate in multi-disciplinary settings that are characterized by heterogeneity in terminology, methods, and tools. This collaboration yields a variety of engineering artifacts that need to be linked and integrated, which on the technical level is reflected in the need to integrate heterogeneous data. Semantic Web technologies, in particular ontology-based data integration (OBDI), are promising to tackle this challenge that has attracted strong interest from the engineering research community. This interest has resulted in a growing body of literature that is dispersed across the Semantic Web and Automation System Engineering research communities and has not been systematically reviewed so far. We address this gap with a survey reflecting on OBDI applications in the context of Multi-Disciplinary Engineering Environment (MDEE). To this end, we analyze and compare 23 OBDI applications from both the Semantic Web and the Automation System Engineering research communities. Based on this analysis, we (i) categorize OBDI variants used in MDEE, (ii) identify key problem context characteristics, (iii) compare strengths and limitations of OBDI variants as a function of problem context, and (iv) provide recommendation guidelines for the selection of OBDI variants and technologies for OBDI in MDEE.

@article{DBLP:journals/ijseke/BifflKREW14,
  author = {Biffl, Stefan and Kalinowski, Marcos and Rabiser, Rick and Ekaputra, Fajar and Winkler, Dietmar},
  doi = {10.1142/S021819401440018X},
  isbn = {0218194014400},
  issn = {0218-1940},
  journal = {International Journal of Software Engineering and Knowledge Engineering},
  keywords = {Empirical software engineering,body of knowledge,software inspection,software product lines,systematic knowledge engineering,systematic review},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  month = dec,
  number = {10},
  pages = {1533--1571},
  title = {{Systematic Knowledge Engineering: Building Bodies of Knowledge from Published Research}},
  volume = {24},
  year = {2014}
}

Context. Software engineering researchers conduct systematic literature reviews (SLRs) to build bodies of knowledge (BoKs). Unfortunately, relevant knowledge collected in the SLR process is not publicly available, which considerably slows down building BoKs incrementally.

@inproceedings{flicker2024factors,
  title = {Factors influencing perceptions of trust in data infrastructures},
  author = {Flicker, Katharina and Rauber, Andreas and Kern, Bettina and Ekaputra, Fajar J.},
  booktitle = {The 18th International Digital Curation Conference (IDCC) 2024 (to appear)},
  year = {2024}
}

@inproceedings{tufek2024validating,
  title = {Validating Semantic Artifacts With Large Language Models},
  author = {Tufek, Nilay and Thuluva, Aparna Saisree and Bandyopadhyay, Tathagata and Just, Valentin Philipp and Sabou, Marta and Ekaputra, Fajar J. and Hanbury, Allan},
  booktitle = {ESWC 2024 Special Track on Large Language Models for Knowledge Engineering (to appear)},
  year = {2024}
}

@inproceedings{llugiqi2024leveraging,
  title = {Leveraging Knowledge Graphs for Enhancing Machine Learning-based Heart Disease Prediction},
  author = {Llugiqi, Majlinda and Ekaputra, Fajar J. and Sabou, Marta},
  booktitle = {The Knowledge Graphs and Neurosymbolic AI (KG-NeSy) 2024 Workshop co-located with AIRoV -- The First Austrian Symposium on AI, Robotics, and Vision},
  url = {https://semantic-systems.org/sites/KG-NeSy/papers/P28.pdf},
  year = {2024}
}

@inproceedings{Schreiberhuber2023,
  author = {Schreiberhuber, Katrin and Sabou, Marta and Ekaputra, Fajar J. and Knees, Peter and Aryan, Peb Ruswono and Einfalt, Alfred and Mosshammer, Ralf},
  booktitle = {Proceedings of the 17th International Workshop on Neural-Symbolic Learning and Reasoning},
  issn = {16130073},
  keywords = {Causality,Explainability,Knowledge Graph,Knowledge Graph Embedding,Smart Grid},
  pages = {336--347},
  title = {{Causality Prediction with Neural-Symbolic Systems: A Case Study in Smart Grids}},
  volume = {3432},
  url = {https://ceur-ws.org/Vol-3432/paper29.pdf},
  year = {2023}
}

In complex systems, such as smart grids, explanations of system events benefit both system operators and users. Deriving causality knowledge as a basis for explanations has been addressed with rule-based, symbolic AI systems. However, these systems are limited in their scope to discovering causalities that can be inferred by their rule base. To address this gap, we propose a neural-symbolic architecture that augments symbolic approaches with sub-symbolic components, in order to broaden the scope of the identified causalities. Concretely, we use Knowledge Graph Embeddings (KGE) to solve causality knowledge derivation as a link prediction problem. Experimental results show that the neural-symbolic approach can predict causality knowledge with a good performance and has the potential to predict causalities that were not present in the symbolic system, thus broadening the causality knowledge scope of symbolic approaches.

@inproceedings{Herwanto2023,
  author = {Herwanto, Guntur B. and Ekaputra, Fajar J. and Piroi, Florina and Sabou, Marta},
  booktitle = {Proceedings of the 8th International Workshop on the Visualization and Interaction for Ontologies, Linked Data and Knowledge Graphs co-located with the 22nd International Semantic Web Conference (ISWC 2023)},
  title = {{Towards A Knowledge Graph-based Exploratory Search for Privacy Engineering}},
  url = {https://ceur-ws.org/Vol-3508/paper5.pdf},
  year = {2023}
}

@inproceedings{Li2023,
  author = {Li, Xue and Hughes, Anthony and Llugiqi, Majlinda and Polat, Fina and Groth, Paul and Ekaputra, Fajar J.},
  booktitle = {Joint proceedings of the KBC-LM workshop and the LM-KBC challenge @ ISWC 2023},
  title = {{Knowledge-centric Prompt Composition for Knowledge Base Construction from Pre-trained Language Models}},
  url = {https://ceur-ws.org/Vol-3577/paper3.pdf},
  year = {2023}
}

@inproceedings{Ekaputra2023,
  author = {Ekaputra, Fajar J. and Fabianek, Christoph and Unterholzer, Gabriel and Gringinger, Eduard},
  doi = {10.1109/ICoDSE59534.2023.10291689},
  booktitle = {Proceedings of the 2023 International Conference on Data and Software Engineering (ICoDSE)},
  title = {{The Semantic Overlay Architecture for Data Interoperability and Exchange}},
  year = {2023}
}

@inproceedings{Tchat2023,
  author = {Tchat, Gary P. and Anjomshoaa, Amin and Dobriy, Daniil and Ekaputra, Fajar J. and Kiesling, Elmar and Polleres, Axel and Sabou, Marta},
  booktitle = {Proceedings of the Next 20 Years Track - ESWC 2023},
  doi = {10.5281/zenodo.8147588},
  title = {{From Semantic Web to Wisdom Web: A Retrospective on the Journey to 2043}},
  year = {2023}
}

@inproceedings{ekaputra2023describing,
  author = {Ekaputra, Fajar J and Llugiqi, Majlinda and Sabou, Marta and Ekelhart, Andreas and Paulheim, Heiko and Breit, Anna and Revenko, Artem and Waltersdorfer, Laura and Farfar, Kheir Eddine and Auer, S{\"{o}}ren},
  doi = {10.1007/978-3-031-33455-9_22},
  booktitle = {Proceedings of the 20th International Conference, ESWC 2023, Hersonissos, Crete, Greece, May 28–June 1, 2023)},
  title = {{Describing and Organizing Semantic Web and Machine Learning Systems in the SWeMLS-KG}},
  year = {2023}
}

@inproceedings{breit2023combiningESWC,
  author = {Breit, Anna and Waltersdorfer, Laura and Ekaputra, Fajar J and Karampatakis, Sotiris and Miksa, Tomasz and K{\"{a}}fer, Gregor},
  doi = {10.1007/978-3-031-33455-9_36},
  booktitle = {Proceedings of the 20th International Conference, ESWC 2023, Hersonissos, Crete, Greece, May 28–June 1, 2023)},
  title = {{Combining Semantic Web and Machine Learning for Auditable Legal Key Element Extraction}},
  year = {2023}
}

@inproceedings{Ekaputra2022a,
  author = {Ekaputra, Fajar J and Waltersdorfer, Laura and Breit, Anna and Sabou, Marta},
  booktitle = {Proceedings of Poster and Demo Track and Workshop Track of the 18th International Conference on Semantic Systems co-located with 18th International Conference on Semantic Systems (SEMANTiCS 2022)},
  title = {Towards a Standardized Description of Semantic Web Machine Learning Systems},
  year = {2022},
  url = {https://ceur-ws.org/Vol-3235/paper23.pdf}
}

@inproceedings{Breit2022,
  author = {Breit, Anna and Waltersdorfer, Laura and Ekaputra, Fajar J. and Miksa, Tomasz and Sabou, Marta},
  booktitle = {The 4th International Workshop on Machine Learning and Knowledge Graphs, MLKgraphs 2022},
  doi = {10.1007/978-3-031-14343-4_33},
  pages = {359--368},
  title = {{A Lifecycle Framework for Semantic Web Machine Learning Systems}},
  year = {2022}
}

@inproceedings{Josephine2021,
  author = {Josephine, Deborah Aprilia and Purwarianti, Ayu and Ekaputra, Fajar J.},
  booktitle = {Proceedings of the 8th International Conference on Advanced Informatics: Concepts, Theory, and Application, ICAICTA 2021},
  doi = {10.1109/ICAICTA53211.2021.9640251},
  isbn = {9781665417433},
  keywords = {entity,information extraction,knowledge graph,mapping,model},
  title = {{Knowledge Graph Construction using Information Extraction of Indonesia Cosmetic Product Text in Bahasa Indonesia}},
  year = {2021}
}

Knowledge graphs can be used for entity recognition in text, graph visualization, and to improve business processes, e.g. information retrieval in E-commerce. One of the information sources for building knowledge graphs is text data available in many digital system, such as E-commerce platform. In this paper, we proposed an approach to extract knowledge graph entities from product text available from E-commerce platforms. We utilize transfer learning technique with full-fine tuning from an existing trained model in order to recognize the entities due to the limitation of labeled data. Since some English terms are expressed in product texts, we used multilingual pretrained models with the Transformer Architecture, i.e. multilingual-BERT-base-cased (mBERT) and XLM-RoBERTa-base (XLMR) in our approach. The extracted entities were then mapped into a knowledge graph by adopting Text to Knowledge Graph (T2KG) framework components, i.e. using entity mapping and triple integration. The training data contains 1.500 labeled texts, while the test data contains 216 labeled texts conducted in three versions of data and four scenarios. Our evaluation result showed that the XLMR model performed better than mBERT for entity extraction task with an average F1-score of 0,895. Furthermore, we manually evaluate the knowledge graph mapping and construction using 1.445 product texts from two E-commerce platforms, which resulted in 338 entities formed in the knowledge graph with mapping precision 0,94.

@inproceedings{Raissya2021,
  author = {Raissya, Hana and Darari, Fariz and Ekaputra, Fajar J.},
  booktitle = {Proceedings of the Sixth International Workshop on the Visualization and Interaction for Ontologies and Linked Data co-located with the 20th International Semantic Web Conference (ISWC 2021)},
  issn = {16130073},
  keywords = {Insights,Knowledge graphs,SPARQL,Visualization},
  pages = {95--102},
  title = {{VizKG: A framework for visualizing SPARQL query results over knowledge graphs}},
  url = {http://ceur-ws.org/Vol-3023/paper3.pdf},
  volume = {3023},
  year = {2021}
}

Despite the rise of the knowledge graph (KG) popularity, understanding SPARQL query results from a KG can be challenging for users. The use of data visualization tools, e.g., Wikidata Query Service and YASGUI, can help address this challenge. However, existing tools are either focused just on a specific KG or only provided as a web interface. This paper proposes VizKG, a framework that provides a wide range of visualizations for SPARQL query results over KGs. VizKG aims to assist users in extracting patterns and insights from data in KGs, and hence supporting further KG analysis. VizKG features a wrapper that links SPARQL query results and external visualization libraries by mapping query result variables to the required visualization components, currently allowing for 24 types of visualizations. Not only that, VizKG also includes visualization recommendations for arbitrary SPARQL query results as well as extension mechanisms for additional visualization types. In our evaluation, the visualization recommendation feature of VizKG achieves an accuracy of 87.8%. To demonstrate the usefulness of VizKG in practical settings, this paper also reports on use case evaluation over various domains and KGs. A Python-based, Jupyter Notebook friendly implementation of VizKG is openly available at https://pypi.org/project/VizKG/.

@inproceedings{Aryan2021,
  author = {Aryan, Peb Ruswono and Ekaputra, Fajar Juang and Sabou, Marta and Hauer, Daniel and Mosshammer, Ralf and Einfalt, Alfred and Miksa, Tomasz and Rauber, Andreas},
  booktitle = {9th Workshop on Modeling and Simulation of Cyber-Physical Energy Systems, MSCPES 2021, Held as part of the Cyber-Physical Systems and Internet-of-Things Week, Proceedings},
  doi = {10.1145/3470481.3472704},
  isbn = {9781450386081},
  keywords = {Explainability,Knowledge Graphs,Ontologies,Smart Grid Simulation,Smart grids},
  title = {{Explainable cyber-physical energy systems based on knowledge graph}},
  year = {2021}
}

Explainability can help cyber-physical systems alleviating risk in automating decisions that are affecting our life. Building an explainable cyber-physical system requires deriving explanations from system events and causality between the system elements. Cyber-physical energy systems such as smart grids involve cyber and physical aspects of energy systems and other elements, namely social and economic. Moreover, a smart-grid scale can range from a small village to a large region across countries. Therefore, integrating these varieties of data and knowledge is a fundamental challenge to build an explainable cyber-physical energy system. This paper aims to use knowledge graph based framework to solve this challenge. The framework consists of an ontology to model and link data from various sources and graph-based algorithm to derive explanations from the events. A simulated demand response scenario covering the above aspects further demonstrates the applicability of this framework.

@inproceedings{Aryan2021a,
  author = {Aryan, Peb R. and Deimel, Matthias and Ekaputra, Fajar J. and Sabou, Marta},
  booktitle = {Proceedings - 2021 8th International Conference on Advanced Informatics: Concepts, Theory, and Application, ICAICTA 2021},
  doi = {10.1109/ICAICTA53211.2021.9640268},
  isbn = {9781665417433},
  keywords = {causality,cyber physical systems,explainability,knowledge graph,sparql},
  title = {{Using SPARQL to express Causality in Explainable Cyber-Physical Systems}},
  year = {2021}
}

Causality knowledge is an essential component of an explainable cyber-physical systems. Since this knowledge mainly come from domain experts, manual annotation of causality is prone to errors especially if the system is large and complex. This paper describes how SPARQL queries can minimize domain expert work by (1)partitioning causality as two level of abstraction: abstract and concrete causality, and (2)inferring concrete causality from query result. We illustrate the usefulness of this method by showing the use of SPARQL in a smart grid scenario.

@inproceedings{Waltersdorfer2021,
  author = {Waltersdorfer, Laura and Breit, Anna and Ekaputra, Fajar J. and Sabou, Marta},
  booktitle = {Communications in Computer and Information Science},
  doi = {10.1007/978-3-030-87101-7_9},
  isbn = {9783030871000},
  issn = {18650937},
  keywords = {Knowledge engineering,Machine learning,Semantic web,Systematic mapping study},
  pages = {81--90},
  title = {{Bridging Semantic Web and Machine Learning: First Results of a Systematic Mapping Study}},
  volume = {1479 CCIS},
  year = {2021}
}

Both symbolic and subsymbolic AI research have seen a recent surge driven by innovative approaches, such as neural networks and knowledge graphs. Further opportunities lie in the combined use of these two paradigms in ways that benefit from their complementary strengths. Accordingly, there is much research at the confluence of these two research areas and a number of efforts were already made to survey and analyze the resulting research area. However, to our knowledge, none of these surveys rely on methodologies that aim to capture an evidence-based characterization of the area while at the same time being reproducible. To fill in this gap, in this paper we report on our ongoing work to apply a systematic mapping study methodology to better characterise systems in this area. Given the breadth of the area, we scope the study to focus on systems that combine semantic web technologies and machine learning, which we call SWeML Systems. While the study is still ongoing, we hereby report on its design and the first results obtained.

@inproceedings{Ekelhart2021,
  author = {Ekelhart, Andreas and Ekaputra, Fajar J. and Kiesling, Elmar},
  booktitle = {Proceedings of the 18th International Conference, ESWC 2021, Virtual Event, June 6–10, 2021)},
  doi = {10.1007/978-3-030-77385-4_38},
  isbn = {9783030773847},
  issn = {16113349},
  keywords = {Graph modelling patterns,Knowledge graphs,Log analysis,Log vocabularies},
  mendeley-tags = {Graph modelling patterns,Knowledge graphs,Log analysis,Log vocabularies},
  pages = {631--646},
  title = {{The SLOGERT Framework for Automated Log Knowledge Graph Construction}},
  volume = {12731 LNCS},
  year = {2021}
}

Log files are a vital source of information for keeping systems running and healthy. However, analyzing raw log data, i.e., textual records of system events, typically involves tedious searching for and inspecting clues, as well as tracing and correlating them across log sources. Existing log management solutions ease this process with efficient data collection, storage, and normalization mechanisms, but identifying and linking entities across log sources and enriching them with background knowledge is largely an unresolved challenge. To facilitate a knowledge-based approach to log analysis, this paper introduces SLOGERT, a flexible framework and workflow for automated construction of knowledge graphs from arbitrary raw log messages. At its core, it automatically identifies rich RDF graph modelling patterns to represent types of events and extracted parameters that appear in a log stream. We present the workflow, the developed vocabularies for log integration, and our prototypical implementation. To demonstrate the viability of this approach, we conduct a performance analysis and illustrate its application on a large public log dataset in the security domain.

@inproceedings{Breit2020,
  author = {Breit, Anna and Waltersdorfer, Laura and Ekaputra, Fajar J. and Sabou, Marta},
  booktitle = {Proceedings of the 2020 IEEE International Conference on Big Data, Big Data 2020},
  doi = {10.1109/BigData50022.2020.9378375},
  isbn = {9781728162515},
  keywords = {auditability,environmental law,knowledge graphs,legal information extraction,legal permits,machine learning},
  pages = {2105--2110},
  title = {{An Architecture for Extracting Key Elements from Legal Permits}},
  year = {2020}
}

In many countries worldwide, including Austria, the environmental impact of production facilities is strongly regulated leading to authorities issuing a large number of legal permits on this topic. The access of interested parties to these permits is typically supported by search systems that present a structured view of the permits along their key elements, such as issuing authority or their legal basis. In this paper, we present a real-life use case from Austria’s Environment Agency, where the extraction of such key elements represents a non-trivial task for laypersons with limited legal knowledge: the heterogeneity of data, complex language, and implicit information hinder the manual data extraction process and can lead to poor quality in data management. Based on an analysis of the use case’s main requirements, we propose an architecture for a system to support the extraction of key elements from legal permits by laypersons. The system combines methods and techniques based on Knowledge Graphs / Semantic Web and Machine Learning technologies and aims to be auditable in terms of its operation.

@inproceedings{Kurniawan2020,
  author = {Kurniawan, Kabul and Ekelhart, Andreas and Ekaputra, Fajar and Kiesling, Elmar},
  booktitle = {Proceedings of the 35th IFIP TC 11 International Conference, SEC 2020},
  doi = {10.1007/978-3-030-58201-2_26},
  isbn = {9783030582005},
  issn = {1868422X},
  keywords = {Digital forensics,Exfiltration detection,File system monitoring,Semantic log analysis},
  pages = {384--397},
  title = {{Cross-Platform File System Activity Monitoring and Forensics – A Semantic Approach}},
  volume = {580 IFIP},
  year = {2020}
}

Ensuring data confidentiality and integrity are key concerns for information security professionals, who typically have to obtain and integrate information from multiple sources to detect unauthorized data modifications and transmissions. The instrumentation that operating systems provide for the monitoring of file system level activity can yield important clues on possible data tampering and exfiltration activity but the raw data that these tools provide is difficult to interpret, contextualize and query. In this paper, we propose and implement an architecture for file system activity log acquisition, extraction, linking and storage that leverages semantic techniques to tackle limitations of existing monitoring approaches in terms of integration, contextualization, and cross-platform interoperability. We illustrate the applicability of the proposed approach in both forensic and monitoring scenarios and conduct a performance evaluation in a virtual setting.

@inproceedings{Aryan2020,
  author = {Aryan, Peb R. and Ekaputra, Fajar J. and Sabou, Marta and Hauer, Daniel and Mosshammer, Ralf and Einfalt, Alfred and Miksa, Tomasz and Rauber, Andreas},
  booktitle = {2020 8th Workshop on Modeling and Simulation of Cyber-Physical Energy Systems},
  doi = {10.1109/MSCPES49613.2020.9133700},
  isbn = {978-1-7281-8721-1},
  mendeley-groups = {[_MartaSabou_],[ SemSysGroup  ],Slovak,[_PebAryan_]},
  pages = {1--6},
  title = {{Simulation Support for Explainable Cyber-Physical Energy Systems}},
  year = {2020}
}

Smart energy grids are evolving from static infrastructures to dynamic systems where Distributed Energy Resources (PV, eCars) are joining or leaving the system randomly. Cyber-Physical (Energy) Systems (CP(E)S) are therefore increasingly complex and dynamic, with several stakeholders (end users, system operators) requiring explanations of the system status/behaviour. The development of solutions for explainable CP(E)S algorithms is however challenging because the deployment and testing in vivo of these solutions is restricted, if not impossible, in terms of the risks of modifying a critical infrastructure. In this paper, we present a semantics based solution to explainable CP(E)S and show how its development is supported by being able to test it in in vitro settings enabled by the BIFROST simulation engine. We validate the proposed solution in a simulated e-mobility use case.

@inproceedings{DBLP:conf/semweb/KieslingEKE19,
  author = {Kiesling, Elmar and Ekelhart, Andreas and Kurniawan, Kabul and Ekaputra, Fajar},
  booktitle = {The Semantic Web - {ISWC} 2019 - 18th International Semantic Web Conference, Auckland, New Zealand, October 26-30, 2019, Proceedings, Part {II}},
  doi = {10.1007/978-3-030-30796-7_13},
  editor = {Ghidini, Chiara and Hartig, Olaf and Maleshkova, Maria and Sv{\'{a}}tek, Vojtech and Cruz, Isabel F and Hogan, Aidan and Song, Jie and Lefran{\c{c}}ois, Maxime and Gandon, Fabien},
  mendeley-groups = {[ SemSysGroup  ]},
  pages = {198--214},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {{The SEPSES Knowledge Graph: An Integrated Resource for Cybersecurity}},
  volume = {11779},
  year = {2019}
}

@inproceedings{DBLP:conf/iot/AzzamACCEFKKMSS19,
  author = {Azzam, Amr and Aryan, P.R. Peb Ruswono and Cecconi, Alessio and Ciccio, Claudio Di and Ekaputra, Fajar J and Fern{\'{a}}ndez, Javier D and Karampatakis, Sotiris and Kiesling, Elmar and Musil, Angelika and Sabou, Marta and Shadlau, Pujan and Thurner, Thomas and {Di Ciccio}, C. and Ekaputra, Fajar J and Fern{\'{a}}ndez, Javier D and Karampatakis, Sotiris and Kiesling, Elmar and Musil, Angelika and Sabou, Marta and Shadlau, Pujan and Thurner, Thomas},
  booktitle = {Proceedings of the 1st Workshop on Cyber-Physical Social Systems co-located with the 9th International Conference on the Internet of Things (IoT 2019), Bilbao, Spain, October 22, 2019},
  editor = {Longo, Antonella and Fazio, Maria and Ranjan, Rajiv and Zappatore, Marco},
  issn = {16130073},
  keywords = {CPSS,Knowledge Graphs,Linked Data,Publict Transport,Smart City},
  mendeley-groups = {[_MartaSabou_],[ SemSysGroup  ],[_PebAryan_]},
  pages = {57--64},
  publisher = {CEUR-WS.org},
  series = {{CEUR} Workshop Proceedings},
  title = {{The CitySPIN Platform: A CPSS Environment for City-Wide Infrastructures}},
  url = {http://ceur-ws.org/Vol-2530/paper8.pdf},
  volume = {2530},
  year = {2019}
}

Copyright \textcopyright 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). Cyber-physical Social System (CPSS) are complex systems that span the boundaries of the cyber, physical and social spheres. They play an important role in a variety of domains ranging from industry to smart city applications. As such, these systems necessarily need to take into account, combine and make sense of heterogeneous data sources from legacy systems, from the physical layer and also the social groups that are part of/use the system. The collection, cleansing and integration of these data sources represents a major effort not only during the operation of the system, but also during its engineering and design. Indeed, while ongoing efforts are concerned primarily with the operation of such systems, limited focus has been put on supporting the engineering phase of CPSS. To address this shortcoming, within the CitySPIN project we aim to create a platform that supports stakeholders involved in the design of these systems especially in terms of support for data management. To that end, we develop methods and techniques based on Semantic Web and Linked Data technologies for the acquisition and integration of heterogeneous data from disparate structured, semi-structured and unstructured sources, including open data and social data. In this paper we present the overall system architecturewith a core focus on data acquisition and integration.We demon-strate our approach through a prototypical implementation of an adaptive planning use case for public transportation scheduling.

@inproceedings{Fernandez2019d,
  address = {New York, New York, USA},
  author = {Fern{\'{a}}ndez, Javier D and Ekaputra, Fajar J. and Aryan, Peb Ruswono and Azzam, Amr and Kiesling, Elmar},
  booktitle = {Companion Proceedings of The 2019 World Wide Web Conference on - WWW '19},
  doi = {10.1145/3308560.3317591},
  editor = {Amer-Yahia, Sihem and Mahdian, Mohammad and Goel, Ashish and Houben, Geert-Jan and Lerman, Kristina and McAuley, Julian J and Baeza-Yates, Ricardo and Zia, Leila},
  isbn = {9781450366755},
  keywords = {Compliance,GDPR,Linked Data,Privacy,accepted},
  mendeley-groups = {_projects_/CDL-2019,_projects_/[report] 2020 CitySPIN,[ SemSysGroup  ],Slovak,_papers_/[paper] 2019 SWJ,_papers_/[paper] 2021 SWJ,[_PebAryan_]},
  mendeley-tags = {accepted},
  pages = {508--514},
  publisher = {ACM Press},
  title = {{Privacy-aware Linked Widgets}},
  year = {2019}
}

The European General Data Protection Regulation (GDPR) bringsnew challenges for companies, who must demonstrate that theirsystems and business processes comply with usage constraintsspecified by data subjects. However, due to the lack of standards,tools, and best practices, many organizations struggle to adapt theirinfrastructure and processes to ensure and demonstrate that alldata processing is in compliance with users’ given consent. TheSPECIAL EU H2020 project has developed vocabularies that canformally describe data subjects’ given consent as well as meth-ods that use this description to automatically determine whetherprocessing of the data according to a given policy is compliantwith the given consent. Whereas this makes it possible to deter-mine whether processing was compliant or not, integration of theapproach into existing line of business applications and ex-antecompliance checking remains an open challenge. In this short paper,we demonstrate how the SPECIAL consent and compliance frame-work can be integrated into Linked Widgets, a mashup platform, inorder to support privacy-aware ad-hoc integration of personal data.The resulting environment makes it possible to create data integra-tion and processing workflows out of components that inherentlyrespect usage policies of the data that is being processed and areable to demonstrate compliance. We provide an overview of thenecessary meta data and orchestration towards a privacy-awarelinked data mashup platform that automatically respects subjects’given consents. The evaluation results show the potential of ourapproach for ex-ante usage policy compliance checking within theLinked Widgets Platforms and beyond

@inproceedings{DBLP:conf/otm/PanditPBBBEFHKL19,
  author = {Pandit, Harshvardhan J and Polleres, Axel and Bos, Bert and Brennan, Rob and Bruegger, Bud P and Ekaputra, Fajar J and Fern{\'{a}}ndez, Javier D and Hamed, Roghaiyeh Gachpaz and Kiesling, Elmar and Lizar, Mark and Schlehahn, Eva and Steyskal, Simon and Wenning, Rigo},
  booktitle = {On the Move to Meaningful Internet Systems: {OTM} 2019 Conferences - Confederated International Conferences: CoopIS, ODBASE, C\&TC 2019, Rhodes, Greece, October 21-25, 2019, Proceedings},
  doi = {10.1007/978-3-030-33246-4_44},
  editor = {Panetto, Herv{\'{e}} and Debruyne, Christophe and Hepp, Martin and Lewis, Dave and Ardagna, Claudio Agostino and Meersman, Robert},
  mendeley-groups = {[ SemSysGroup  ],Slovak},
  pages = {714--730},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {{Creating a Vocabulary for Data Privacy - The First-Year Report of Data Privacy Vocabularies and Controls Community Group {(DPVCG)}}},
  volume = {11877},
  year = {2019}
}

@inproceedings{DBLP:conf/euromicro/BifflELPRW019,
  author = {Biffl, Stefan and Ekaputra, Fajar J and L{\"{u}}der, Arndt and Pauly, Johanna-Lisa and Rinker, Felix and Waltersdorfer, Laura and Winkler, Dietmar},
  booktitle = {45th Euromicro Conference on Software Engineering and Advanced Applications, {SEAA} 2019, Kallithea-Chalkidiki, Greece, August 28-30, 2019},
  doi = {10.1109/SEAA.2019.00059},
  editor = {Staron, Miroslaw and Capilla, Rafael and Skavhaug, Amund},
  mendeley-groups = {[ SemSysGroup  ]},
  pages = {342--346},
  publisher = {IEEE},
  title = {{Technical Debt Analysis in Parallel Multi-Disciplinary Systems Engineering}},
  year = {2019}
}

@inproceedings{DiCiccio2019,
  author = {{Di Ciccio}, Claudio and Ekaputra, Fajar J. and Cecconi, Alessio and Ekelhart, Andreas and Kiesling, Elmar},
  booktitle = {Proceedings of the CAiSE Forum 2019},
  doi = {10.1007/978-3-030-21297-1_6},
  isbn = {9783030212964},
  issn = {18651348},
  keywords = {Compliance checking,Process mining,RDF,SHACL,SPARQL},
  mendeley-groups = {_projects_/[report] 2020 CitySPIN,[ SemSysGroup  ]},
  pages = {60--74},
  title = {{Finding Non-compliances with Declarative Process Constraints Through Semantic Technologies}},
  volume = {350},
  year = {2019}
}

Business process compliance checking enables organisations to assess whether their processes fulfil a given set of constraints, such as regulations, laws, or guidelines. Whilst many process analysts still rely on ad-hoc, often handcrafted per-case checks, a variety of constraint languages and approaches have been developed in recent years to provide automated compliance checking. A salient example is DECLARE , a well-established declarative process specification language based on temporal logics. DECLARE specifies the behaviour of processes through temporal rules that constrain the execution of tasks. So far, however, automated compliance checking approaches typically report compliance only at the aggregate level, using binary evaluations of constraints on execution traces. Consequently, their results lack gran-ular information on violations and their context, which hampers auditability of process data for analytic and forensic purposes. To address this challenge, we propose a novel approach that leverages semantic technologies for compliance checking. Our approach proceeds in two stages. First, we translate DECLARE templates into statements in SHACL, a graph-based constraint language. Then, we evaluate the resulting constraints on the graph-based, semantic representation of process execution logs. We demonstrate the feasibility of our approach by testing its implementation on real-world event logs. Finally, we discuss its implications and future research directions.

@inproceedings{Kurniawan2018,
  author = {Kurniawan, Kabul and Ekaputra, Fajar J. and Aryan, Peb R.},
  booktitle = {2018 2nd International Conference on Informatics and Computational Sciences (ICICoS)},
  doi = {10.1109/ICICOS.2018.8621686},
  isbn = {978-1-5386-7440-6},
  keywords = {semantic APIs,semantic service composition,semantic service description,semantic web services},
  mendeley-groups = {[ SemSysGroup  ]},
  month = oct,
  pages = {1--6},
  publisher = {IEEE},
  title = {{Semantic Service Description and Compositions: A Systematic Literature Review}},
  year = {2018}
}

@inproceedings{Ahmeti2017CitySPIN,
  author = {Ahmeti, Aljbin and Bala, Saimir and Belk, Stefan and Ekaputra, Fajar J. and Fern{\'{a}}ndez, Javier D. and Kiesling, Elmar and Koller, Andreas and Mendling, Jan and Musil, Angelika and Musil, Juergen and Polleres, Axel and Aryan, Peb R. and Sabou, Marta and Solti, Andreas},
  booktitle = {Proceedings of the Posters and Demos Track of the 13th International Conference on Semantic Systems - SEMANTiCS2017 co-located with the 13th International Conference on Semantic Systems (SEMANTiCS 2017)},
  issn = {16130073},
  keywords = {Cyber-physical,Linked Data,Smart City,Social systems},
  mendeley-groups = {PhD_thesis,_projects_/[report] 2020 CitySPIN,[ SemSysGroup  ]},
  title = {{CitySPIN: Cyber-physical social systems for city-wide infrastructures}},
  url = {http://ceur-ws.org/Vol-2044/paper21/paper21.pdf},
  volume = {2044},
  year = {2018}
}

CitySpin is an Austrian research project funded by the Austrian Federal Ministry of Transport, Innovation and Technology (BMVIT) and the Austrian Research Promotion Agency (FFG) under the program " ICT of the Future " . The CitySPIN project aims to create a platform for cyber-physical social systems in order to facilitate innovative Smart City infrastructure services. The project is at the forefront of cyber-physical systems research and aims to extend those systems with a social dimension (i.e., cyber-physical social systems).

@inproceedings{Sabou2018,
  author = {Sabou, Marta and Ekaputra, Fajar J. and Ionescu, Tudor and Musil, Juergen and Schall, Daniel and Haller, Kevin and Friedl, Armin and Biffl, Stefan},
  booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)},
  doi = {10.1007/978-3-319-93417-4_36},
  isbn = {9783319934167},
  issn = {16113349},
  keywords = {Enterprise knowledge graph,Exploratory search,Software architectural knowledge,Software engineering},
  mendeley-groups = {[_MartaSabou_],[ SemSysGroup  ],[_KevinHaller_]},
  pages = {560--575},
  title = {{Exploring Enterprise Knowledge Graphs: A Use Case in Software Engineering}},
  volume = {10843 LNCS},
  year = {2018}
}

When reusing software architectural knowledge, such as design patterns or design decisions, software architects need support for exploring architectural knowledge collections, e.g., for finding related items. While semantic-based architectural knowledge management tools are limited to supporting lookup-based tasks through faceted search and fall short of enabling exploration, semantic-based exploratory search systems primarily focus on web-scale knowledge graphs without having been adapted to enterprise-scale knowledge graphs (EKG). We investigate how and to what extent exploratory search can be supported on EKGs of architectural knowledge. We propose an approach for building exploratory search systems on EKGs and demonstrate its use within Siemens, which resulted in the STAR system used in practice by 200–300 software architects. We found that the EKG’s ontology allows making previously implicit organisational knowledge explicit and this knowledge informs the design of suitable relatedness metrics to support exploration. Yet, the performance of these metrics heavily depends on the characteristics of the EKG’s data. Therefore both statistical and user-based evaluations can be used to select the right metric before system implementation.

@inproceedings{Aryan2017,
  author = {Aryan, Peb R. and Ekaputra, Fajar J. and Kiesling, Elmar and Tjoa, A. Min and Kurniawan, Kabul},
  booktitle = {2017 1st International Conference on Informatics and Computational Sciences (ICICoS)},
  doi = {10.1109/ICICOS.2017.8276347},
  isbn = {978-1-5386-0903-3},
  mendeley-groups = {[ SemSysGroup  ]},
  month = nov,
  pages = {113--118},
  publisher = {IEEE},
  title = {{RMLx: Mapping interface for integrating open data with linked data exploration environment}},
  year = {2017}
}

Recent advances in linked data generation through mapping such as RML (RDF mapping language) allows for providing large-scale RDF data in a more automatic way. However, considerable amount of data in open data portals remain inaccessible as linked data. This is due to the nature of data portals having large number of small-size dataset which makes writing mapping description becomes tedious and error-prone. Moreover, these data sources requires additional preprocessing before To solve this challenge, We introduce extensions to RML to support required tasks and developed RMLx, a visual web-interface to create RML mappings. Using this interface, the process of creating mapping description can become faster and less error-prone. Furthermore, the process of linked data generation can be wrapped as to enable integration with other data in a linked data exploration environment. We explore on four different use cases to identify the requirements followed by describing how these are solved.

@inproceedings{Musil2017Continuous,
  author = {Musil, Juergen and Ekaputra, Fajar J. and Sabou, Marta and Ionescu, Tudor and Schall, Daniel and Musil, Angelika and Biffl, Stefan},
  booktitle = {Proceedings of the 2017 IEEE International Conference on Software Architecture, ICSA 2017},
  doi = {10.1109/ICSA.2017.28},
  isbn = {9781509057290},
  keywords = {Architectural knowledge management,continuous software architecture,semantic integration},
  mendeley-groups = {[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  pages = {189--192},
  title = {{Continuous Architectural Knowledge Integration: Making Heterogeneous Architectural Knowledge Available in Large-Scale Organizations}},
  year = {2017}
}

The timely discovery, sharing and integration of architectural knowledge (AK) have become critical aspects in enabling the software architects to make meaningful conceptual and technical design decisions and trade-offs. In large-scale organizations particular obstacles in making AK available to architects are a heterogeneous pool of internal and external knowledge sources, poor interoperability between AK management tools and limited support of computational AK reasoning. Therefore we introduce the Continuous Architectural Knowledge Integration (CAKI) approach that combines the continuous integration of internal and external AK sources together with enhanced semantic reasoning and personalization capabilities dedicated to large organizations. Preliminary evaluation results show that CAKI potentially reduces AK search effort by concurrently yielding more diverse and relevant results.

@inproceedings{DBLP:conf/webi/TrinhADEKRWT17,
  author = {Trinh, Tuan-Dat and Aryan, Peb Ruswono and Do, Ba-Lam and Ekaputra, Fajar J and Kiesling, Elmar and Rauber, Andreas and Wetz, Peter and Tjoa, A Min},
  booktitle = {Proceedings of the International Conference on Web Intelligence, Leipzig, Germany, August 23-26, 2017},
  doi = {10.1145/3106426.3106495},
  editor = {Sheth, Amit P and Ngonga, Axel and Wang, Yin and Chang, Elizabeth and Slezak, Dominik and Franczyk, Bogdan and Alt, Rainer and Tao, Xiaohui and Unland, Rainer},
  mendeley-groups = {[ SemSysGroup  ],[_PebAryan_]},
  pages = {88--96},
  publisher = {ACM},
  title = {{Linked data processing provenance: towards transparent and reusable linked data integration}},
  year = {2017}
}

@inproceedings{Novak2017Generation,
  author = {Nov{\'{a}}k, Petr and Ekaputra, Fajar J. and Biffl, Stefan},
  booktitle = {Proceedings of the International Federation of Automatic Control (IFAC) World Congress 2017},
  doi = {10.1016/j.ifacol.2017.08.1027},
  issn = {24058963},
  keywords = {Application of mechatronic principles,Design methodologies,Mechatronic systems,Modeling,Simulation,Virtual environments},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  number = {1},
  pages = {7613--7620},
  title = {{Generation of Simulation Models in MATLAB-Simulink Based on AutomationML Plant Description}},
  volume = {50},
  year = {2017}
}

Process simulations are useful test-beds for experiments and optimizations along the entire industrial plant life-cycle. Shifting testing and tuning of industrial plants and their automation systems from the real world to simulated environments is a part of a virtualization, which is one of the key movements in emerging areas of Industry 4.0 and factories of the future. Although simulations bring a large variety of benefits, they suffer from a time-consuming and error-prone design phase, which limits their use in industrial practice. This paper proposes a new design method called AML2SIM, which transforms the real plant description represented in AutomationML (AML) and generates a dynamic simulation model (SIM). The proposed method signifcantly improves the engineering and re-design of simulation models in terms of saving time and effort of experts as the models can be easily re-generated based on a given AutomationML plant model. Simulations are assembled from simulation blocks that are shared among various projects in simulation libraries, hence the method contributes to reuse of simulation artifacts.

@inproceedings{SabouEKB16,
  author = {Sabou, Marta and Ekaputra, Fajar and Kovalenko, Olga and Biffl, Stefan},
  booktitle = {Proceedings of the 1st International Workshop on Cyber-Physical Production Systems (CPPS)},
  doi = {10.1109/CPPS.2016.7483919},
  mendeley-groups = {_papers_/[survey] OBDI in MDEE/SLR-Lite (2a-abstract_intro)/refs,[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_papers_/[paper] 2019 SWJ,_papers_/[paper] 2016 KCM@SWT4IEA,_papers_/[survey] OBDI in MDEE/SLR-Lite (2-abstract_intro)/References},
  month = apr,
  pages = {1--8},
  publisher = {IEEE},
  title = {{Supporting the engineering of cyber-physical production systems with the AutomationML analyzer}},
  year = {2016}
}

\textcopyright 2016 IEEE. The engineering phase of Cyber-Physical Production Systems (CPPS) is a multi-disciplinary process in which representatives of diverse engineering disciplines collaborate to deliver a complex CPPS. To ensure optimal project management as well as to avoid risks of inconsistencies between engineering models created by engineers from different disciplines, support is needed for integrating and subsequently analyzing diverse engineering data. AutomationML is an emerging data exchange format for engineering data which makes the first step towards the easier exchange of engineering data. Yet, there is a lack of tool support for integrating, making sense of and analyzing AML files. In this paper, we explore the use of Semantic Web and Linked Data technologies to provide extended functionality on top of AML that allows advanced data analytics on engineering data such as intuitive browsing of interlinked engineering models and queries for project-wide verification and validation activities. As a result of these investigations, we present the AutomationML Analyzer prototypical implementation to showcase some of the functionalities made possible by Semantic Web and Linked Data technologies in this context.

@inproceedings{Winkler2016AutomationML,
  author = {Winkler, Dietmar and Ekaputra, Fajar J. and Biffl, Stefan},
  booktitle = {2016 IEEE 21th Conference on Emerging Technologies and Factory Automation (ETFA)},
  doi = {10.1109/ETFA.2016.7733555},
  isbn = {9781509013142},
  issn = {19460759},
  keywords = {Automation Systems,AutomationML,Defect Detection,Multi-disciplinary Engineering,Quality Assurance,Reviews,Risk Management,inspection},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  title = {{AutomationML Review Support in Multi-Disciplinary Engineering Environments}},
  volume = {2016-Novem},
  year = {2016}
}

\textcopyright 2016 IEEE. [Context] In Multi-Disciplinary Engineering (MDE) environments, the engineering of industrial production systems requires the collaboration of engineers coming from different disciplines. Engineers typically apply discipline specific tools and data models with limited collaboration capabilities. These loosely coupled tools and heterogeneous data models hinder efficient change management and defect detection, which makes MDE projects unnecessarily risky and error prone. [Objective] This paper presents an adapted review approach, AML-Review, for multi-disciplinary engineering (MDE) projects based on best practices for reviews in software engineering. [Method] Software reviews have been successfully used for early defect detection in Software Engineering. However, adaptations are needed for defect detection in MDE environments. We focus on production systems models according to the emerging AutomationML standard. [Results] We evaluated the feasibility of the AML-Review process with requirements and an AutomationML model from a real-world application scenario. The AML-Review process provides the benefits of systematic and traceable review results for MDE projects based on AutomationML. [Conclusion] The prototype results imply that systematic and structured review processes help to improve traceability of requirements and defects and increase defect detection performance.

@inproceedings{Ekaputra2016Knowledge,
  address = {New York, New York, USA},
  author = {Ekaputra, Fajar J. and Sabou, Marta and Serral, Estefan{\'{i}}a and Biffl, Stefan},
  booktitle = {Proceedings of the 12th International Conference on Semantic Systems - SEMANTiCS 2016},
  doi = {10.1145/2993318.2993325},
  isbn = {9781450347525},
  keywords = {Cyber-physical production system,Knowledge change management and analysis,Multi-disciplinary Engineering,Ontology based information integration},
  mendeley-groups = {_papers_/[survey] OBDI in MDEE/SLR-Lite (2a-abstract_intro)/_definite,_papers_/[survey] OBDI in MDEE/SLR-Lite (1-title_abstract)/SEMANTiCS,_papers_/[paper] 2017 OJIS,_papers_/[survey] OBDI in MDEE/SLR-Lite (0-scopus),[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE,_projects_/[project] 2017 CitySPIN,_projects_/[project] 2017 ODILIA/ODILIA - LD-Lab,_papers_/[survey] OBDI in MDEE/SLR-Lite (2-abstract_intro),_papers_/[survey] OBDI in MDEE/SLR-Lite (2-abstract_intro)/Definite},
  organization = {ACM},
  pages = {105--112},
  publisher = {ACM Press},
  title = {{Knowledge change management and analysis during the engineering of cyber physical production systems: A use case of hydro power plants}},
  year = {2016}
}

\textcopyright 2016 ACM. The process of designing Cyber Physical Production Systems (CPPS), e.g., modern power plants or steel mills, typically takes place in a multi-disciplinary engineering environment, in which experts from various engineering domains and organizations work together towards creating complex engineering artifacts. The process of designing such complex engineering artifacts requires iterations and redesign phases, which lead to continuous changes of the data and knowledge. To manage changes in such environment, we have previously proposed a generic reference process for conducting Knowledge Change Management and Analysis (KCMA). This paper implements this process for the case study of a modern Hydro Power Plant by adapting the proposed generic reference process into a scientific prototype developed using Semantic Web Technologies. Finally, we conduct an evaluation to evaluate the feasibility of the proposed reference process and the developed prototype. Thus, the contribution of this paper is twofolds: (1) A tool-supported prototype for KCMA of a hydro power plant, and (2) A feasibility evaluation of this prototype that reports feedback and lessons learned for achieving KCMA in real-world case studies.

@inproceedings{Ekaputra2016SHACL4P,
  author = {Ekaputra, Fajar J. and Lin, Xiashuo},
  booktitle = {Proceedings of 2016 International Conference on Data and Software Engineering, ICoDSE 2016},
  doi = {10.1109/ICODSE.2016.7936162},
  isbn = {9781509056712},
  keywords = {Constraint Validation,Prot{\'{e}}g{\'{e}} Plugin,RDF Graph,SHACL},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  title = {{SHACL4P: SHACL constraints validation within Prot{\'{e}}g{\'{e}} ontology editor}},
  year = {2016}
}

\textcopyright 2016 IEEE. Recently, Semantic Web Technologies (SWT) have been introduced and adopted to address the problem of enterprise data integration (e.g., to solve the problem of terms and concepts heterogeneity within large organizations). One of the challenges of adopting SWT for enterprise data integration is to provide the means to define and validate structural constraints over Resource Description Framework (RDF) graphs. This is difficult since RDF graph axioms behave like implications instead of structural constraints. SWT researchers and practitioners have proposed several solutions to address this challenge (e.g., SPIN and Shape Expression). However, to the best of our knowledge, none of them provide an integrated solution within open source ontology editors (e.g., Protégé). We identified this absence of the integrated solution and developed SHACL4P, a Protégé plugin for defining and validating Shapes Constraint Language (SHACL), the upcoming W3C standard for constraint validation within Protégé ontology editor.

@inproceedings{Mordinyi2016Investigating,
  author = {Mordinyi, Richard and Winkler, Dietmar and Ekaputra, Fajar J. and Wimmer, Manuel and Biffl, Stefan},
  booktitle = {Proceedings of the 21st International Conference on Emerging Technologies and Factory Automation (ETFA)},
  doi = {10.1109/ETFA.2016.7733556},
  isbn = {9781509013142},
  issn = {19460759},
  keywords = {AutomationML,Model Slicing,Multi-Disciplinary Engineering,Software Architecture},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  title = {{Investigating model slicing capabilities on integrated plant models with AutomationML}},
  volume = {2016-Novem},
  year = {2016}
}

\textcopyright 2016 IEEE. Typical large-scale systems engineering projects depend on seamless cooperation and data exchange of experts from various engineering domains and organizations that work in a heterogeneous engineering environment. Available software tools support individual engineering disciplines quite well, but they only represent a discipline-specific view on the engineering plant. Consequently, a so-called integrated plant model captures and combines all different views into one representation in order to provide an overarching, discipline-independent view on the engineering plant. However, in order to support effective engineering processes, like change management, stakeholders need to be able to (a) define the scope of their changes they want to merge into the integrated plant model rather than the latest status of their view with various fragile adaptations, and (b) extract only engineering information from integrated plant model which is in the scope of the stakeholders’s discipline and interest. In this paper, we describe requirements identified in industrial use cases regarding filtering capabilities on (integrated) engineering plant models and model-driven engineering techniques for model-slicing applied on AutomationML models. The approach contributes to quality assurance and fault-prevention in engineering data since it helps to focus on parts of the engineering plant model relevant in certain engineering processes.

@inproceedings{Ekaputra2015Ontology,
  author = {Ekaputra, Fajar J.},
  booktitle = {Proceedings of the 12th European Semantic Web Conference (ESWC 2015)},
  doi = {10.1007/978-3-319-18818-8_44},
  institution = {Springer International Publishing},
  isbn = {9783319188171},
  issn = {16113349},
  keywords = {Model-Driven engineering,Ontology change,Ontology evolution,Ontology versioning,Ontology-Based information integration},
  mendeley-groups = {_papers_/[survey] OBDI in MDEE/SLR-Lite (0-scopus),PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE,_papers_/[survey] OBDI in MDEE/SLR-Lite (1-title_abstract)/ESWC},
  pages = {711--720},
  title = {{Ontology change in ontology-based information integration systems}},
  volume = {9088},
  year = {2015}
}

\textcopyright Springer International Publishing Switzerland 2015. Ontology change is an important part of the Semantic Web field that helps researchers and practitioners to deal with changes performed in ontologies. Ontology change is especially important in Ontology-Based Information Integration (OBII) systems, where several ontologies are interrelated and therefore, changes raise various complexities and implications, such as modifications of ontology mappings and change propagation. Current approaches to ontology change mainly focus on a single ontology and therefore do not properly address the constraints specific to OBII systems. To address the challenge of ontology change in OBII contexts, we plan to adapt successful techniques proposed both by Semantic Web and Model-Driven Engineering communities. We discuss the research goals, methods, and evaluation options to address this challenge. Real-world case studies are used for the development and evaluation of the proposed methods.

@inproceedings{Kovalenko2015Modeling,
  author = {Kovalenko, Olga and Wimmer, Manuel and Sabou, Marta and L{\"{u}}der, Arndt and Ekaputra, Fajar J. and Biffl, Stefan},
  booktitle = {Prodeedings of the 20th Conference on Emerging Technologies and Factory Automation (ETFA)},
  doi = {10.1109/ETFA.2015.7301643},
  isbn = {9781467379298},
  issn = {19460759},
  keywords = {AutomationML,enterprise models,manufacturing,model driven engineering,modeling engineering knowledge,ontology,ontology engineering},
  mendeley-groups = {_papers_/[survey] OBDI in MDEE/SLR-Lite (0-scopus),[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  organization = {IEEE},
  pages = {1--4},
  title = {{Modeling automationml: Semantic web technologies vs. model-driven engineering}},
  year = {2015}
}

\textcopyright 2015 IEEE. Modeling engineering knowledge explicitly and representing it by means of standardized modeling languages and in machine-understandable form enables advanced engineering processes in industrial and factory automation. This affects positively both process and product quality. In this paper we explore how the AutomationML format, an emerging data exchange standard, that supports the Industry 4.0 vision, can be represented by means of two established modeling approaches - Model-Driven Engineering (MDE) and Semantic Web. We report observed differences w.r.t. resulting model features and model creation process and, additionally, present the application possibilities of the developed models for engineering process improvement in a production system engineering context.

@inproceedings{Ekaputra2014semantic,
  author = {Ekaputra, Fajar J. and Serral, Estefan{\'{i}}a and Winkler, Dietmar and Biffl, Stefan},
  booktitle = {Proceedings of 2014 International Conference on Data and Software Engineering, ICODSE 2014},
  doi = {10.1109/ICODSE.2014.7062487},
  isbn = {9781479979967},
  keywords = {Project consortia,communication,data integration,heterogeneous data environments},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE,_projects_/[project] 2017 ODILIA/ODILIA - LD-Lab},
  month = nov,
  organization = {IEEE},
  pages = {1--6},
  publisher = {IEEE},
  title = {{A semantic framework for data integration and communication in project consortia}},
  year = {2014}
}

\textcopyright 2014 IEEE. Engineering project consortia represents the collaboration of different groups of partners to achieve a common goal, e.g., developing innovative products. This collaboration may be challenging because of different terminologies and different tools and data models used by the project partners. In this work, we present the concept of a Project Consortia Knowledge Base (PC-KB), an integration framework based on semantic knowledge that facilitates project-level communication as well as access to and querying of project data across tool and partner boundaries. The PC-KB allows establishing common data models on different abstraction layers within the consortia organization. Using these common models, the PC-KB integrates partner data to provide (a) a common terminology for facilitating communication among project partners and (b) a common consistent view for efficient data integration. The PC-KB has been successfully applied in the automation systems domain to improve collaboration and data exchange in heterogeneous engineering environments.

@inproceedings{aryan2014fostering,
  author = {Aryan, Peb R. and Ekaputra, Fajar J. and Sunindyo, Wikan D. and Akbar, Saiful},
  booktitle = {2014 International Conference on Data and Software Engineering (ICODSE)},
  doi = {10.1109/ICODSE.2014.7062655},
  isbn = {978-1-4799-8175-5},
  keywords = {Data models,Education,Government,Indonesian government,Internet,Joining processes,LOGD,Portals,Resource description framework,Standards,conceptual framework,government data processing,government transparency,linked data,linked open government data,open data,open government data,open systems,public administration,public participation},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE,_projects_/[report] ITB-TUWien/Informatics/PRA},
  month = nov,
  organization = {IEEE},
  pages = {1--6},
  publisher = {IEEE},
  title = {{Fostering government transparency and public participation through linked open government data: Case study: Indonesian public information service}},
  year = {2014}
}

Open data refers to data that is freely available in the Internet and can be used, reused, and redistributed without restrictions from copyright or patent. This paper describes our approach to fostering government transparency and public participation through linked open government data (LOGD). We have analyzed how Indonesian Government deals with the open government data issues, and we define its maturity level based on the existing maturity framework. Then, we proposed a conceptual framework advance the Indonesian open government data maturity level to encourage further improvement on the government transparency and public participation. To show the feasibility of our approach, we developed a case study to show how the open data advancement could support the government transparency and public participation. Our case study shows promising result and we are eager to continue working in the area in a bigger scale.

@inproceedings{Winkler2014Efficient,
  address = {New York, New York, USA},
  author = {Winkler, Dietmar and Ekaputra, Fajar J. and Serral, Estefan{\'{i}}a and Biffl, Stefan},
  booktitle = {Proceedings of the 14th International Conference on Knowledge Technologies and Data-driven Business - i-KNOW '14},
  doi = {10.1145/2637748.2638442},
  isbn = {9781450327695},
  keywords = {communication,data integration,heterogeneous data environments,project consortium},
  mendeley-groups = {_papers_/[survey] OBDI in MDEE/SLR-Lite (0-scopus),PhD_thesis,[ SemSysGroup  ],_papers_/[survey] OBDI in MDEE/SLR-Lite (1-title_abstract)/i-KNOW},
  month = sep,
  pages = {1--4},
  publisher = {ACM Press},
  title = {{Efficient data integration and communication issues in distributed engineering projects and project consortia}},
  year = {2014}
}

\textcopyright Copyright 2014 ACM. An engineering project consortium represents the collaboration of different groups of partners to achieve a common goal, e.g., developing innovative products. This collaboration may be challenging because of different terminologies and different tools and data models used by the project partners. In this work, we present the concept of a Project Consortia Knowledge Base (PC-KB), an integration framework based on semantic knowledge that facilitates project-level communication as well as access to and querying of project data across tool and partner boundaries. The PC-KB allows establishing common data models on different abstraction layers within the consortium organization. Using these common models, the PC-KB integrates partner data to provide (a) a common terminology for facilitating communication among project partners and (b) a common consistent view for efficient data integration. The PC-KB has been successfully applied in the automation systems domain to improve collaboration and data exchange in heterogeneous engineering environments.

@inproceedings{Ekaputra2014Building,
  address = {New York, New York, USA},
  author = {Ekaputra, Fajar J. and Serral, Estefan{\'{i}}a and Biffl, Stefan},
  booktitle = {Proceedings of the 14th International Conference on Knowledge Technologies and Data-driven Business - i-KNOW '14},
  doi = {10.1145/2637748.2638408},
  isbn = {9781450327695},
  keywords = {Design and architecture of data sharing facilities,Digital research libraries,Empirical software engineering,Metadata representation,Science 2.0,Systematic knowledge engineering process},
  mendeley-groups = {_papers_/[survey] OBDI in MDEE/SLR-Lite (0-scopus),PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  pages = {1--8},
  publisher = {ACM Press},
  title = {{Building an empirical software engineering research knowledge base from heterogeneous data sources}},
  year = {2014}
}

\textcopyright Copyright 2014 ACM. Recently, the Systematic Knowledge Engineering (SKE) process has been introduced to help researchers build up an empirical software engineering (EMSE) Body of Knowledge (BoK) based on a systematic literature review process. However, the SKE process does not explain how to effectively capture and represent the EMSE knowledge to enable efficient data analysis. In this paper, we introduce the EMSE Research Knowledge Base Building (RKB) process, which guides knowledge engineers in developing and using a knowledge base (KB) for the SKE process based on contributions from heterogeneous data sources. We evaluate the RKB process in the context of three research topics from the EMSE domain: software inspection experiments, theory construct identification, and threats to validity. Major results are that the RKB process is effective in guiding the knowledge engineer to build a KB that allows answering the EMSE-specific queries. The RKB process shows promising results in the EMSE research context and should be investigated in other research contexts as well.

@inproceedings{Biffl2014Towards,
  address = {New York, New York, USA},
  author = {Biffl, Stefan and Kalinowski, Marcos and Ekaputra, Fajar J. and Neto, Amadeu Anderlin and Conte, Tayana and Winkler, Dietmar},
  booktitle = {Proceedings of the 8th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement - ESEM '14},
  doi = {10.1145/2652524.2652568},
  isbn = {9781450327749},
  issn = {19493789},
  keywords = {body of knowledge,controlled experiment,knowledge engineering,systematic review,threats to validity},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  number = {August},
  pages = {1--4},
  publisher = {ACM Press},
  title = {{Towards a semantic knowledge base on threats to validity and control actions in controlled experiments}},
  year = {2014}
}

[Context] Experiment planners need to be aware of relevant Threats to Validity (TTVs), so they can devise effective control actions or accept the risk. [Objective] The aim of this paper is to introduce a TTV knowledge base (KB) that supports experiment planners in identifying relevant TTVs in their research context and actions to control these TTVs. [Method] We identified requirements, designed and populated a TTV KB with data extracted during a systematic review: 63 TTVs and 149 control actions from 206 peer-reviewed published software engineering experiments. We conducted an initial proof of concept on the feasibility of using the TTV KB and analyzed its content. [Results] The proof of concept and content analysis provided indications that experiment planners can benefit from an extensible TTV KB for identifying relevant TTVs and control actions in their specific context. [Conclusions] The TTV KB should be further evaluated and evolved in a variety of software engineering contexts.

@inproceedings{Ekaputra2014Supporting,
  author = {Ekaputra, Fajar J. and Sabou, Marta and Serral, Estefan{\'{i}}a and Biffl, Stefan},
  booktitle = {Proceedings of the 4th Workshop on Semantic Publishing (SePublica 2014)},
  issn = {16130073},
  keywords = {And ontology,Empirical research,Empirical software engineering,Publication database},
  mendeley-groups = {[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  publisher = {CEUR-WS},
  title = {{Supporting Information Sharing for Reuse and Analysis of Scientific Research Publication Data}},
  url = {https://ceur-ws.org/Vol-1155/paper-06.pdf},
  volume = {1155},
  year = {2014}
}

Effective and efficient information sharing for reuse and analysis of scientific data from published research papers is an important challenge for researchers working within the empirical software engineering (EMSE) domain. Currently, there is only limited support for storing empirical research data and results in a way that is easy to access and reuse for other researchers. In this paper, we propose the Systematic Knowledge Engineering Tool (SKET), an ontologybased tool to provide researchers in the EMSE domain with capabilities for storing, sharing, and verifying results within their research community. The initial evaluation results show that SKET can address relevant needs in the EMSE community and can be considered as a foundation for advanced tool capabilities.

@inproceedings{Kovalenko2014238,
  author = {Kovalenko, Olga and Serral, Estefan{\'{i}}a and Sabou, Marta and Ekaputra, Fajar J. and Winkler, Dietmar and Biffl, Stefan},
  booktitle = {Knowledge Engineering and Knowledge Management: 19th International Conference, EKAW 2014, Link{\"o}ping, Sweden, November 24-28, 2014. Proceedings},
  doi = {10.1007/978-3-319-13704-9_19},
  mendeley-groups = {_papers_/[survey] OBDI in MDEE/SLR-Lite (2a-abstract_intro)/_definite,_papers_/[survey] OBDI in MDEE/SLR-Lite (0-scopus),[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_papers_/[paper] 2019 SWJ,_projects_/[report] ITB-TUWien/Informatics/FJE,_papers_/[paper] 2016 ICoDSE,_papers_/[survey] OBDI in MDEE/SLR-Lite (2-abstract_intro),_papers_/[survey] OBDI in MDEE/SLR-Lite (2-abstract_intro)/Definite,_papers_/[survey] OBDI in MDEE/SLR-Lite (1-title_abstract)/EKAW},
  pages = {238--249},
  title = {{Automating Cross-Disciplinary Defect Detection in Multi-disciplinary Engineering Environments}},
  year = {2014}
}

Multi-disciplinary engineering (ME) projects are conducted in complex heterogeneous environments, where participants, originating from different disciplines, e.g., mechanical, electrical, and software engineering, collaborate to satisfy project and product quality as well as time constraints. Detecting defects across discipline boundaries early and efficiently in the engineering process is a challenging task due to heterogeneous data sources. In this paper we explore how Semantic Web technologies can address this challenge and present the Ontology-based Cross-Disciplinary Defect Detection (OCDD) approach that supports automated cross-disciplinary defect detection in ME environments, while allowing engineers to keep their well-known tools, data models, and their customary engineering workflows. We evaluate the approach in a case study at an industry partner, a large-scale industrial automation software provider, and report on our experiences and lessons learned. Major result was that the OCDD approach was found useful in the evaluation context and more efficient than manual defect detection, if cross-disciplinary defects had to be handled.

@inproceedings{Biffl2014Building,
  author = {Biffl, Stefan and Kalinowski, Marcos and Ekaputra, Fajar J. and Serral, Estefan{\'{i}}a and Winkler, Dietmar},
  booktitle = {Proceedings of the 26th International Conference on Software Engineering & Knowledge Engineering (SEKE 2014)},
  issn = {23259086},
  keywords = {-empirical software engineering,considerably less efficient than,gineering,meta-anal-,moreover,necessary,not allowing,software inspection,systematic knowledge en-,systematic review,the presented research synthesis,yses are limited to},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE,_papers_/[paper] 2016 KCM@SWT4IEA},
  title = {{Building Empirical Software Engineering Bodies of Knowledge with Systematic Knowledge Engineering}},
  url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-84938367623&partnerID=MN8TOARS},
  year = {2014}
}

[Context] Empirical software engineering (EMSE) researchers conduct systematic literature reviews (SLRs) to build bodies of knowledge (BoKs). Unfortunately, valuable knowledge collected in the SLR process is publicly available only to a limited extent, which considerably slows down building BoKs incrementally. [Objective] In this paper, we introduce the Systematic Knowledge Engineering (SKE) process to support building up BoKs from empirical studies efficiently. [Method] SKE is based on the SLR process and on Knowledge Engineering (KE) practices to provide a Knowledge Base (KB) with semantic technologies that enable reusing intermediate data extraction results and querying of empirical evidence. We evaluated SKE by building a software inspection EMSE BoK KB from knowledge acquired by controlled experiments. We elicited relevant queries from EMSE researchers and systematically integrated information from 30 representative research papers into the KB. [Results] The resulting KB was effective in answering the queries, enabling knowledge reuse for analyses beyond the results from the SLR process. [Conclusion] SKE showed promising results in the software inspection context and should be evaluated in other contexts for building EMSE BoKs faster.

@inproceedings{sunindyo2013osmf,
  author = {Sunindyo, Wikan D. and Ekaputra, Fajar J.},
  booktitle = {Proceedings of the ICT-EurAsia 2013: Information and Communication Technology},
  doi = {10.1007/978-3-642-36818-9_8},
  isbn = {9783642368172},
  issn = {03029743},
  keywords = {Open Source Software,process observation,project management,software quality},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/WDS},
  organization = {Springer Berlin Heidelberg},
  pages = {71--80},
  title = {{OSMF: A framework for OSS process measurement}},
  volume = {7804 LNCS},
  year = {2013}
}

An Open Source Software (OSS) project can be considered as a new type of business entity involving various roles and stakeholders, e.g., project managers, developers, and users, who apply individual methods. The project managers have the responsibility to manage the OSS development in a way that the OSS product can be delivered to the customers in time and with good quality. This responsibility is challenging, because the heterogeneity of the data collected and analyzed from different stakeholders leads to the complexity of efforts of the project managers to measure and manage OSS projects. In this paper, we propose a measurement framework (OSMF) to enable the project managers to collect and analyze process data from OSS projects efficiently. Initial results show that OSMF can help project managers to manage OSS business processes more efficient, hence improve the decision on OSS project quality. \textcopyright 2013 Springer-Verlag.

@inproceedings{Ekaputra2013analysis,
  address = {New York, New York, USA},
  archiveprefix = {arXiv},
  arxivid = {1306.1723},
  author = {Ekaputra, Fajar J. and Serral, Estefan{\'{i}}a and Winkler, Dietmar and Biffl, Stefan},
  booktitle = {Proceedings of the 9th International Conference on Semantic Systems - I-SEMANTICS '13},
  doi = {10.1145/2506182.2506183},
  eprint = {1306.1723},
  isbn = {9781450319720},
  keywords = {analysis framework,ontology querying,ontology tools,user interaction},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE,_projects_/[project] 2017 ODILIA/ODILIA - LD-Lab,_papers_/[paper] 2016 KCM@SWT4IEA},
  pages = {1},
  publisher = {ACM Press},
  title = {{An analysis framework for ontology querying tools}},
  year = {2013}
}

While knowledge querying is a key capability of ontologies, the query language recommended by W3C, SPARQL, is not easy to use for some user types, e.g., casual users and domain experts. To improve this drawback, user-friendly Ontology Query Tools (OQTs) have been introduced. However, there is, to our knowledge, no comprehensive framework for researchers and practitioners to compare the capabilities of the wide range of available OQTs. In this paper we introduce, based on a systematic literature review, a framework that allows researchers and practitioners to classify and compare OQTs regarding their capabilities and their support for relevant user types and scenarios. We evaluate the framework based on a real-world use case. Major result of the evaluation was that the framework was found useful and usable by users from the target audience to identify the most suitable OQTs for their context.

@inbook{Waltersdorfer2023,
  author = {Waltersdorfer, Laura and Breit, Anna and Ekaputra, Fajar J and Sabou, Marta and Ekelhart, Andreas and Iana, Andreea and Paulheim, Heiko and Portisch, Jan and Revenko, Artem and ten Teije, Annette and van Harmelen, Frank},
  booktitle = {Compendium of Neurosymbolic Artificial Intelligence},
  doi = {10.3233/FAIA230136},
  pages = {77--99},
  publisher = {IOS Press},
  title = {{Semantic web machine learning systems: An analysis of system patterns}},
  year = {2023}
}

@inbook{Sabou2017Semantic,
  author = {Sabou, Marta and Ekaputra, Fajar J. and Biffl, Stefan},
  booktitle = {Multi-Disciplinary Engineering for Cyber-Physical Production Systems},
  doi = {10.1007/978-3-319-56345-9_12},
  editor = {Biffl, Stefan and Gerhard, Detlef and L{\"{u}}der, Arndt},
  isbn = {9780262527811},
  mendeley-groups = {[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  pages = {301--329},
  title = {{Semantic Web Technologies for Data Integration in Multi-Disciplinary Engineering}},
  year = {2017}
}

@inbook{sabou2015beitrage,
  address = {Berlin, Heidelberg},
  author = {Sabou, Marta and Kovalenko, Olga and Ekaputra, Fajar J. and Biffl, Stefan},
  booktitle = {Handbuch Industrie 4.0 Bd.2},
  doi = {10.1007/978-3-662-45537-1_90-1},
  mendeley-groups = {[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  pages = {293--313},
  publisher = {Springer Berlin Heidelberg},
  title = {{Beitr{\"{a}}ge des Semantic Web zum Engineering f{\"{u}}r Industrie 4.0}},
  year = {2017}
}

Ein wesentlicher Aspekt f€ ur die Umsetzung der Vision von Industrie 4.0 ist die Verbesserung des Engineering-Prozesses von Produktionssystemen. Dieses Kapitel untersucht, welche Beiträge Semantic Web Technologien zu Engineering-Prozessen von Industrie 4.0 einbringen können. Dazu wird ein Analyse-Framework entwickelt, in dem die hauptsächlichen Fähigkeiten von Semantic Web Technologien dargestellt werden, und werden diejenigen tech- nischen Aufgaben diskutiert, die in Industrie 4.0 spezifischen mechatronischen Engineering Szenarien den größten Vorteil aus Verbesserungen ziehen könnten. Dieses Framework wird einer fokussierten Review aktueller Ansätze zugrunde gelegt, die Semantic Web Technologien im Kontext des Engineerings von Produktionssystemen verwenden. So soll ein besseres Verständnis erlangt werden, welche Fähigkeiten der Technologien welche technischen Aufgaben gut unterstützen. Die Analyse zeigt, dass Semantic Web Technologien vor allem für die Integration und das Management von Unternehmensdaten in verschiedenen Aspekten des Engineerings, vom Anforderungsmanagement bis hin zur Simulation und zu Projektmanagement, verwendet werden. Durch den Fokus auf Datenintegration und Konsistenzmanagement wird das Potential der Web- orientierten Fähigkeiten des Semantic Web vorerst nicht ausgeschöpft.

@inbook{Mordinyi2016Semantic,
  author = {Mordinyi, Richard and Serral, Estefan{\'{i}}a and Ekaputra, Fajar J.},
  booktitle = {Semantic Web Technologies for Intelligent Engineering Applications},
  doi = {10.1007/978-3-319-41490-4_8},
  isbn = {978-3-319-41488-1},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  pages = {181--217},
  title = {{Semantic Data Integration: Tools and Architectures}},
  year = {2016}
}

This chapter is focused on the technical aspects of semantic data inte-gration that provides solutions for bridging semantic gaps between common project-level concepts and the local tool concepts as identified in the Engineering Knowledge Base (EKB). Based on the elicitation of use case requirements from automation systems engineering, the chapter identifies required capabilities an EKB software architecture has to consider. The chapter describes four EKB software architecture variants and their components, and discusses identified drawbacks and advantages regarding the utilization of ontologies. A benchmark is defined to evaluate the efficiency of the EKB software architecture variants in the context of selected quality attributes, like performance and scalability. Main results suggest that architectures relying on a relational database still outperform traditional ontology storages while NoSQL databases outperforms for query execution. In large-scale systems engineering projects, like power plants, steel mills, or car manufactures, the seamless cooperation and data exchange of expert knowledge from various engineering domains and organizations is a crucial success factor (Biffl et al. 2009a). This environment consists of a wide range of engineering systems and tools that differ in the underlying technical platforms and the used data models. Each domain or organization usually prefers using their own well-known models, from now on referred as local tool models. In order to successfully develop projects, it is essential to integrate important knowledge of different domain experts. However, these experts usually prefer using their well-known local tool models. In addition, they want to access data from other tools within their local data repre-sentation approach (Moser and Biffl 2012). The standardization of data interchange is one of the most promising approaches (Wiesner et al. 2011) to enable efficient data integration that allows experts to continue using their familiar data models and formats. This approach is based on agreeing on a minimal common model for data exchange that represents the common concepts shared among different disciplines on project level. Chapter 2 presented main use cases with typical process steps during the engineering phase within the life cycle of production systems. Selected scenarios focused on the capability to interact appropriately within a multidisciplinary engineering network while pointing out the need for a common vocabulary over all engineering disciplines involved in an engineering organization. The described challenges in the context of engineering data integration referred to a consistent production system plant model in order to support quality-assured parallel engi-neering, and the ability to access and analyze integrated data, e.g., for project progress and project quality reports. Versioning of exchanged information helps to improve change management and team collaboration over the course of the engi-neering project. As part of an efficient data management it is essential for process observations, project monitoring, and control across engineering disciplines (Moser et al. 2011b). As a common baseline it can be concluded that it is necessary to clearly dis-tinguish between local concepts of engineering tools and common concepts (Moser and Biffl 2010) (i.e., data sets representing heterogeneous but semantically corre-sponding local data elements) at project level. Consequently, interoperability between heterogeneous engineering environments is only supported if the semantic gap between local tool concepts and common project-level concepts can be prop-erly bridged. The Engineering Knowledge Base (EKB) (Moser and Biffl 2010) (see Chap. 4) provides the means for semantic integration of the heterogeneous models of each discipline using ontologies, and thus facilitates seamless communication, interaction, and data exchange. Semantic technologies are capable of linking cor-responding local concepts of engineering tools with each other via common project-level concepts representing the data integration needs of engineering dis-ciplines at their interfaces. 182 R. Mordinyi et al.

@inbook{SWBook_Ch11,
  address = {Cham},
  author = {Sabou, Marta and Kovalenko, Olga and Ekaputra, Fajar Juang and Biffl, Stefan},
  booktitle = {Semantic Web Technologies for Intelligent Engineering Applications},
  chapter = {11},
  doi = {10.1007/978-3-319-41490-4_11},
  editor = {Biffl, Stefan and Sabou, Marta},
  mendeley-groups = {_papers_/[paper] 2017 OJIS,[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_papers_/[paper] 2019 SWJ,_projects_/[report] ITB-TUWien/Informatics/FJE},
  pages = {281--296},
  publisher = {Springer International Publishing},
  title = {{Semantic Web Solutions in Engineering}},
  year = {2016}
}

@inbook{Ekaputra2016KnowledgeChapter,
  address = {Cham},
  author = {Ekaputra, Fajar J.},
  booktitle = {Semantic Web Technologies for Intelligent Engineering Applications},
  chapter = {7},
  doi = {10.1007/978-3-319-41490-4_7},
  editor = {Biffl, Stefan and Sabou, Marta},
  mendeley-groups = {_papers_/[paper] 2017 OJIS,PhD_thesis,[ SemSysGroup  ],_projects_/[report] ITB-TUWien/Informatics/FJE},
  pages = {159--178},
  publisher = {Springer International Publishing},
  title = {{Knowledge Change Management and Analysis in Engineering}},
  year = {2016}
}

@unpublished{auge2024challenges,
  title = {{Challenges of Tracking Provenance in Marine Data}},
  author = {Auge, Tanja and Ekaputra, Fajar J. and Feistel, Susanne and J{\"u}rgensmann, Susanne and Klettke, Meike and Waltersdorfer, Laura},
  booktitle = {International Conference on Marine Data and Information Systems (IMDIS) 2024 (to appear)},
  year = {2024}
}

@unpublished{reiz2024semantic,
  title = {Semantic Tool Hub: Towards A Sustainable Community-Driven Documentation of Semantic Web Tools},
  author = {Reiz, Achim and Ekaputra, Fajar J. and Mihindukulasooriya, Nandana},
  booktitle = {ESWC 2024 Satellite Events (to appear)},
  year = {2024}
}

@unpublished{Ekelhart2020,
  author = {Ekelhart, Andreas and Ekaputra, Fajar J. and Kiesling, Elmar},
  booktitle = {Proceedings of the ISWC 2020 Demos and Industry Tracks: From Novel Ideas to Industrial Practice co-located with 19th International Semantic Web Conference (ISWC 2020)},
  issn = {16130073},
  url = {http://ceur-ws.org/Vol-2721/paper552.pdf},
  pages = {205--209},
  title = {{Automated knowledge graph construction from raw log data}},
  volume = {2721},
  year = {2020}
}

Logs are a crucial source of information to diagnose the health and status of systems, but their manual investigation typically does not scale well and often leads to a lack of awareness and incomplete transparency about issues. To tackle this challenge, we introduce SLOGERT, a flexible framework and workflow for automated construction of knowledge graphs from arbitrary raw log messages. To this end, we combine a variety of techniques to facilitate a knowledge-based approach to log analysis.

@unpublished{DBLP:conf/i-semantics/EkaputraAKFG19,
  author = {Ekaputra, Fajar J and Aryan, Peb Ruswono and Kiesling, Elmar and Fabianek, Christoph and Gringinger, Eduard},
  booktitle = {Proceedings of the Posters and Demo Track of the 15th International Conference on Semantic Systems co-located with 15th International Conference on Semantic Systems (SEMANTiCS 2019), Karlsruhe, Germany, September 9th - to - 12th, 2019},
  editor = {Alam, Mehwish and Usbeck, Ricardo and Pellegrini, Tassilo and Sack, Harald and Sure-Vetter, York},
  mendeley-groups = {[ SemSysGroup  ],[_PebAryan_]},
  publisher = {CEUR-WS.org},
  series = {{CEUR} Workshop Proceedings},
  title = {{Semantic Containers for Data Mobility: {A} Seismic Activity Use Case}},
  url = {http://ceur-ws.org/Vol-2451/paper-11.pdf},
  volume = {2451},
  year = {2019}
}

@unpublished{DBLP:conf/i-semantics/KurniawanEKFE19,
  author = {Kurniawan, Kabul and Ekelhart, Andreas and Kiesling, Elmar and Froschl, Agnes and Ekaputra, Fajar J and Fr{\"{o}}schl, A. and Ekaputra, Fajar J},
  booktitle = {Proceedings of the Posters and Demo Track of the 15th International Conference on Semantic Systems co-located with 15th International Conference on Semantic Systems (SEMANTiCS 2019), Karlsruhe, Germany, September 9th - to - 12th, 2019},
  editor = {Alam, Mehwish and Usbeck, Ricardo and Pellegrini, Tassilo and Sack, Harald and Sure-Vetter, York},
  issn = {16130073},
  mendeley-groups = {[ SemSysGroup  ]},
  publisher = {CEUR-WS.org},
  series = {{CEUR} Workshop Proceedings},
  title = {{Semantic Integration and Monitoring of File System Activity}},
  url = {http://ceur-ws.org/Vol-2451/paper-17.pdf},
  volume = {2451},
  year = {2019}
}

Copyright \textcopyright 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). File access activity information is an important source for identifying unauthorized data transmissions. In this paper, we present a semantic approach for the monitoring of file system activity in the context of information security. We thereby tackle limitations of existing monitoring approaches in terms of semantic integration, contextualization, and cross-system interoperability. In particular, we present a vocabulary for file activity logs and outline an architecture for log file collection, extraction, linking, and storage. We demonstrate the applicability of this approach by means of an application scenario. Finally, we show how analysts can inspect the life-cycle of files in a context-rich manner by means of SPARQL queries and a graph visualization of the results.

@unpublished{DBLP:conf/i-semantics/MorzingerSES18,
  author = {M{\"{o}}rzinger, Benjamin and Sabou, Marta and Ekaputra, Fajar J. and Sindelar, Nikolaus},
  booktitle = {Proceedings of the Posters and Demos Track of the 14th International Conference on Semantic Systems co-located with the 14th International Conference on Semantic Systems (SEMANTiCS 2018), Vienna, Austria, September 10-13, 2018},
  editor = {Khalili, Ali and Koutraki, Maria},
  issn = {16130073},
  keywords = {Manufacturing,Ontology-based data access,Simulation},
  mendeley-groups = {[_MartaSabou_],[ SemSysGroup  ]},
  publisher = {CEUR-WS.org},
  series = {{CEUR} Workshop Proceedings},
  title = {{Improving Simulations-based Industrial Optimization with Semantic Web Technologies}},
  url = {http://ceur-ws.org/Vol-2198/paper_113.pdf},
  volume = {2198},
  year = {2018}
}

Time-series based simulations of industrial processes are instrumental to optimizing a variety of industrial settings. In this paper, we describe a use case, developed together with Infineon Technologies Austria AG. Monitoring data stored in relational databases was used to build process models of industrial chillers. Optimization algorithms were then applied to find optimal strategies for operating the chillers. Even though the results from this approach were convincing, the access to the necessary data was a labor-intensive and error-prone task. Therefore, in this paper, we investigate how Semantic Web technologies can help to improve data access for time-series data and under which circumstances they would be helpful for the domain experts performing the simulation.

@unpublished{Ekaputra2017Towards,
  author = {Ekaputra, Fajar J. and Do, Ba-Lam and Kiesling, Elmar and Novak, Niina Maarit and Trinh, Tuan-Dat and Tjoa, A Min and Aryan, Peb R.},
  booktitle = {Proceedings of the Posters and Demos Track of the 13th International Conference on Semantic Systems (SEMANTiCS '17)},
  mendeley-groups = {PhD_thesis,[ SemSysGroup  ],[_PebAryan_]},
  title = {{Towards Open Data Mashups for Data Journalism}},
  url = {http://ceur-ws.org/Vol-2044/paper17/paper17.html},
  year = {2017}
}

@unpublished{ekaputra2015knowledge,
  author = {Ekaputra, Fajar J. and Serral, Estefan{\'{i}}a and Sabou, Marta and Biffl, Stefan},
  booktitle = {Joint Proceedings of the Posters and Demos Track of 11th International Conference on Semantic Systems - SEMANTiCS2015 and 1st Workshop on Data Science: Methods, Technology and Applications (DSci15)},
  mendeley-groups = {[_MartaSabou_],PhD_thesis,[ SemSysGroup  ],_papers_/[paper] 2016 KCM@SWT4IEA},
  pages = {13--17},
  title = {{Knowledge Change Management and Analysis for Multi-Disciplinary Engineering Environments}},
  url = {https://ceur-ws.org/Vol-1481/paper5.pdf},
  volume = {1481},
  year = {2015}
}

\textcopyright Copyright 2015 for the individual papers by the papers’ authors. Multi-Disciplinary Engineering (MDEng) environments involve a wide range of models, processes and tools that were not designed to cooperate together. The Ontology-Based Information Integra-tion (OBII) approach has been proposed to address the integration issue within such environments. However, knowledge changes management and analysis (KCMA) process within the environ-ment are not covered within the OBII approach. While the tradi-tional ontology change management approach has been investi-gated to the general problem, it remains unclear how to use the available solutions within MDEng context. In this paper, we ex-tend the OBII approach to enable the KCMA process. We have identified the main KCMA requirements within MDEng projects and studied the related work of Ontology Change Management to propose a suitable solution, as well as suggesting further works.

@unpublished{DBLP:conf/www/EkaputraSSB15,
  author = {Ekaputra, Fajar J and Sabou, Marta and Serral, Estefania and Biffl, Stefan},
  booktitle = {Proceedings of the 24th International Conference on World Wide Web Companion, {WWW} 2015, Florence, Italy, May 18-22, 2015 - Companion Volume},
  doi = {10.1145/2740908.2742027},
  editor = {Gangemi, Aldo and Leonardi, Stefano and Panconesi, Alessandro},
  mendeley-groups = {[_MartaSabou_],[ SemSysGroup  ]},
  pages = {1055--1056},
  publisher = {ACM},
  title = {{Collaborative Exchange of Systematic Literature Review Results: The Case of Empirical Software Engineering}},
  year = {2015}
}