Publications
2026
Schultheis, Alexander; Jilg, David; Traphöner, Ralph; Schander, Roman; Bergmann, Ralph
Applying Distributed Case-Based Reasoning in the Edge-Cloud Continuum Proceedings Article
In: Artificial Intelligence XLIII - 46th SGAI International Conference on Artificial Intelligence, AI 2026, Cambridge, UK, December 15-17, 2026, Proceedings, Springer, 2026.
Abstract | BibTeX | Tags: Distributed Case-Based Reasoning, Edge-Cloud Continuum, Load Balancing, ProCAKE
@inproceedings{SchultheisJTSB2026,
title = {Applying Distributed Case-Based Reasoning in the Edge-Cloud Continuum},
author = {Alexander Schultheis and David Jilg and Ralph Traphöner and Roman Schander and Ralph Bergmann},
year = {2026},
date = {2026-01-01},
booktitle = {Artificial Intelligence XLIII - 46th SGAI International Conference on Artificial Intelligence, AI 2026, Cambridge, UK, December 15-17, 2026, Proceedings},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {Case-Based Reasoning (CBR) is well suited for recurring but context-dependent industrial decisions and is therefore a promising artificial intelligence approach for the Edge-Cloud Continuum (ECC). The ECC denotes a distributed infrastructure in which tasks are placed dynamically across resource-constrained nodes near data sources and centralized cloud resources. However, the systematic transfer of CBR to distributed edge-cloud settings has received little attention. This paper presents a project-grounded approach for operationalizing CBR in the ECC. Based on experience from the EASY project and exchanges with industry and research partners, industrial application scenarios are structured, load balancing metrics are adopted, and an architecture for distributed CBR is introduced. The paper further discusses opportunities, challenges, and cross-organizational perspectives. To demonstrate technical feasibility, a ProCAKE-based prototype is implemented and investigated in a distributed case base scenario. The results demonstrate that distributed CBR in the ECC is technically feasible, while highlighting the need to assess potential runtime benefits in relation to case base characteristics, heterogeneous processing capabilities, and distribution overhead.},
keywords = {Distributed Case-Based Reasoning, Edge-Cloud Continuum, Load Balancing, ProCAKE},
pubstate = {published},
tppubtype = {inproceedings}
}
Case-Based Reasoning (CBR) is well suited for recurring but context-dependent industrial decisions and is therefore a promising artificial intelligence approach for the Edge-Cloud Continuum (ECC). The ECC denotes a distributed infrastructure in which tasks are placed dynamically across resource-constrained nodes near data sources and centralized cloud resources. However, the systematic transfer of CBR to distributed edge-cloud settings has received little attention. This paper presents a project-grounded approach for operationalizing CBR in the ECC. Based on experience from the EASY project and exchanges with industry and research partners, industrial application scenarios are structured, load balancing metrics are adopted, and an architecture for distributed CBR is introduced. The paper further discusses opportunities, challenges, and cross-organizational perspectives. To demonstrate technical feasibility, a ProCAKE-based prototype is implemented and investigated in a distributed case base scenario. The results demonstrate that distributed CBR in the ECC is technically feasible, while highlighting the need to assess potential runtime benefits in relation to case base characteristics, heterogeneous processing capabilities, and distribution overhead.
2023
Schultheis, Alexander; Zeyen, Christian; Bergmann, Ralph
An Overview and Comparison of Case-Based Reasoning Frameworks Proceedings Article
In: Case-Based Reasoning Research and Development - 31st International Conference, ICCBR 2023, Aberdeen, Scotland, July 17-20, 2023, Proceedings, pp. 327–343, Springer, 2023.
Abstract | Links | BibTeX | Tags: Case-Based Reasoning, CBR Applications, CBR Framework, CloodCBR, eXiT*CBR, jColibri, myCBR, ProCAKE
@inproceedings{SchultheisZB2023,
title = {An Overview and Comparison of Case-Based Reasoning Frameworks},
author = {Alexander Schultheis and Christian Zeyen and Ralph Bergmann},
url = {https://www.wi2.uni-trier.de/shared/publications/2023_ICCBR_SchultheisZB.pdf},
doi = {10.1007/978-3-031-40177-0_21},
year = {2023},
date = {2023-01-01},
booktitle = {Case-Based Reasoning Research and Development - 31st International Conference, ICCBR 2023, Aberdeen, Scotland, July 17-20, 2023, Proceedings},
volume = {14141},
pages = {327–343},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {Case-Based Reasoning (CBR) is a methodology with many applications in industrial and scientific domains. Over the past decades, various frameworks have been developed to facilitate the development of CBR applications. For practitioners and researchers, it is challenging to overview the landscape of existing frameworks with their specific scope and features. This makes it difficult to choose the most suitable framework for specific requirements. To address this issue, this work provides an overview and comparison of CBR frameworks, focusing on five recent, open-source CBR frameworks: CloodCBR, eXiT*CBR, jColibri, myCBR, and ProCAKE. They are compared by supported CBR types, knowledge containers, CBR phases, interfaces, and special features.},
keywords = {Case-Based Reasoning, CBR Applications, CBR Framework, CloodCBR, eXiT*CBR, jColibri, myCBR, ProCAKE},
pubstate = {published},
tppubtype = {inproceedings}
}
Case-Based Reasoning (CBR) is a methodology with many applications in industrial and scientific domains. Over the past decades, various frameworks have been developed to facilitate the development of CBR applications. For practitioners and researchers, it is challenging to overview the landscape of existing frameworks with their specific scope and features. This makes it difficult to choose the most suitable framework for specific requirements. To address this issue, this work provides an overview and comparison of CBR frameworks, focusing on five recent, open-source CBR frameworks: CloodCBR, eXiT*CBR, jColibri, myCBR, and ProCAKE. They are compared by supported CBR types, knowledge containers, CBR phases, interfaces, and special features.