@inproceedings{58763,
  abstract     = {{Utilizing data is crucial for economic success, but a lack of interoperability and concerns about the misuse of ones own data are hindering the cross-organizational use of data. Dataspaces provide the infrastructure necessary to integrate heterogeneous data sources within an organization or ecosystem, enabling seamless data interaction and interoperability. In addition, data spaces strengthen data sovereignty through their decentralized nature, which enables organizations to effectively control and manage their data. However, challenges persist in managing the complexity and dynamic nature of dataspaces, requiring significant resources and technical expertise. The decentralized nature leads to a large and diverse number of stakeholders, who need to agree on the use and scope of a dataspace. Modeling is a common approach to cope with technical complexity and heterogeneous stakeholders. In this paper, we propose a version of SysML and a corresponding method that focus on the modelling of data spaces. We provide a dataspace modelling method to unify the understanding of dataspaces and scope among all stakeholders to simplify the design and development process.}},
  author       = {{Kulkarni, Pranav Jayant and Zerbin, Julian and Koldewey, Christian and Bernijazov, Ruslan and Dumitrescu, Roman}},
  booktitle    = {{2024 IEEE International Conference on Technology Management, Operations and Decisions (ICTMOD)}},
  keywords     = {{Dataspaces, Modelling, SysML, Gaia-X, System Specification}},
  location     = {{Sharjah, United Arab Emirates }},
  publisher    = {{IEEE}},
  title        = {{{Using SysML as a Modelling Language for Dataspaces}}},
  doi          = {{10.1109/ictmod63116.2024.10878227}},
  year         = {{2025}},
}

@inproceedings{65038,
  abstract     = {{The rapid advancements in digital transformation have led to the emergence of dataspaces as a pivotal element for industry-wide and cross-industry data integration and interoperability across various businesses. Despite their potential, the adoption and effective utilization of dataspaces by business stakeholders remain challenging. This paper aims to address this gap by developing a comprehensive learning environment tailored for business stakeholders. Through an interview study and an analysis of the current state of research, we identify problem fields and derive key requirements for the development of the learning environment. The proposed environment includes a demonstrator and a training concept designed to enhance stakeholders' understanding and capabilities in managing and leveraging dataspaces. Our findings contribute to the body of knowledge by providing practical guidance through learning environments for the deployment of dataspaces in business contexts and highlighting areas for future research.}},
  author       = {{Lick, Jonas and Lamarz, Jessica and Dohmann, Friederike and Kulkarni, Pranav Jayant and Zerbin, Julian and Koldewey, Christian}},
  booktitle    = {{2024 6th International Conference on Control and Robotics (ICCR)}},
  location     = {{Yokohama, Japan }},
  publisher    = {{IEEE}},
  title        = {{{Guidance on Dataspaces: Development of a Learning Environment for Industrial SMEs}}},
  doi          = {{10.1109/iccr64365.2024.10927580}},
  year         = {{2025}},
}

@inproceedings{56166,
  abstract     = {{Developing Intelligent Technical Systems (ITS) involves a complex process encompassing planning, analysis, design, production, and maintenance. Model-Based Systems Engineering (MBSE) is a key methodology for systematic systems engineering. Designing models for ITS requires harmonious interaction of various elements, posing a challenge in MBSE. Leveraging Generative Artificial Intelligence, we generated a dataset for modeling, using prompt engineering on large language models. The generated artifacts can aid engineers in MBSE design or serve as synthetic training data for AI assistants.}},
  author       = {{Kulkarni, Pranav Jayant and Tissen, Denis and Bernijazov, Ruslan and Dumitrescu, Roman}},
  booktitle    = {{DS 130: Proceedings of NordDesign 2024}},
  editor       = {{Malmqvist, J. and Candi, M. and Saemundsson, R. and Bystrom, F. and Isaksson, O.}},
  keywords     = {{Data Driven Design, Design Automation, Systems Engineering (SE), Artificial Intelligence (AI)}},
  location     = {{Reykjavik}},
  pages        = {{617--625}},
  title        = {{{Towards Automated Design: Automatically Generating Modeling Elements with Prompt Engineering and Generative Artificial Intelligence}}},
  doi          = {{10.35199/NORDDESIGN2024.66}},
  year         = {{2024}},
}

@inproceedings{58479,
  author       = {{Kulkarni, Pranav Jayant and Tissen, Denis and Bernijazov, Ruslan and Dumitrescu, Roman}},
  booktitle    = {{Proceedings of NordDesign 2024}},
  publisher    = {{The Design Society}},
  title        = {{{Towards Automated Design: Automatically Generating Modeling Elements with Prompt Engineering and Generative Artificial Intelligence}}},
  doi          = {{10.35199/norddesign2024.66}},
  year         = {{2024}},
}