ExeKG: Executable Knowledge Graph System for User-friendly Data Analytics

Zheng, Zhuoxun; Zhou, Baifan; Zhou, Dongzhuoran; Soylu, Ahmet; Kharlamov, Evgeny

doi:10.1145/3511808.3557195

Cited by 6 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic Web technologies are a set of technologies for representing and exchanging knowledge on the Web in standardised formats and they allow data integration and reasoning (Hitzler, 2021). This vision has for the most part not come to pass yet, although the technologies developed are useful in developing data intensive applications (Kleppmann, 2017), including industrial and public data integration scenarios (e.g., Soylu et al, 2022;Zheng et al, 2022b). A core Semantic Web technology is the Resource Description Framework (RDF); it is a graphbased data model and associates Uniform Resource Identifiers (URI) with entities in a domain of interest, and describe these resources and their relationships using triples.…”

Section: Semantic Web Technologiesmentioning

confidence: 99%

Chrontext: Portable Sparql Queries Over Contextualised Time Series Data in Industrial Settings

Bakken

Soylu

2022

SSRN Journal

View full text Add to dashboard Cite

Section: Semantic Web Technologiesmentioning

confidence: 99%

Chrontext: Portable Sparql Queries Over Contextualised Time Series Data in Industrial Settings

Bakken

Soylu

2022

SSRN Journal

View full text Add to dashboard Cite

“…Our Contribution. To address these challenges, we propose to combine semantic technologies and ML, to encode ML solutions in knowledge graphs (KG), which is named as executable KG and helps in describing ML knowledge and solutions in a standardised way and increase the transparency via graphic user interface (GUI)based system and visualisation of KGs [3]. In addition, executable KGs can be translated to modularised executable ML scripts that can be modified and reused for new data and new questions [4].…”

Section: Talk Descriptionmentioning

confidence: 99%

Executable Knowledge Graph for Transparent Machine Learning in Welding Monitoring at Bosch

Zheng

Zhou

et al. 2022

Proceedings of the 31st ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

With the development of Industry 4.0 technology, modern industries such as Bosch's welding monitoring witnessed the rapid widespread of machine learning (ML) based data analytical applications, which in the case of welding monitoring has led to more efficient and accurate welding monitoring quality. However, industrial ML is affected by the low transparency of ML towards non-ML experts needs. The lack of understanding by domain experts of ML methods hampers the application of ML methods in industry and the reuse of developed ML pipelines, as ML methods are often developed in an ad hoc manner for specific problems. To address these challenges, we propose the concept and a system of executable Knowledge Graph (KG), which formally encode ML knowledge and solutions in KGs, which serve as common language between ML experts and non-ML experts, thus facilitate their communication and increase the transparency of ML methods. We evaluated our system extensively with an industrial use case at Bosch, showing promising results.Speaker's Bio: Zhuoxun Zheng is a Data Scientist and Doctoral Researcher at Bosch Center for Artificial Intelligence. He obtained his Master's degree in Mechanical Engineering at Karlsruhe Institute of Technology. Currently, he is working on knowledge enhanced machine learning and neuro-symbolic reasoning to increase transparency, trust, and performance of ML.Relevancy to CIKM: Knowledge enhanced ML in the industry.

show abstract

“…The shift towards Semantic Web and linked data technologies highlights their crucial role in representing, capturing, and integrating industrial data. These technologies, embodying a range of methodologies for articulating and disseminating knowledge across the World Wide Web in standardized formats, promise to enhance data integration and support reasoning processes [10,11]. Nevertheless, challenges persist, such as data retention issues in Resource Description Framework (RDF) stores, when dealing with high sample rates or extended durations.…”

Section: Introduction and State Of The Artmentioning

confidence: 99%

Enabling Federated Learning Services Using OPC UA, Linked Data and GAIA-X in Cognitive Production

Friedrich,

Vogt,

Rudolph

et al. 2024

Journal of Machine Engineering

View full text Add to dashboard Cite

Value creation in production is based on collaboration of different stakeholders and requires the secure and sovereign exchange of knowledge. Today, knowledge has mostly been built up individually and is only exchanged in a proprietary manner. This paper presents an exemplary pipeline for federated services in cross-domain and cross-company value creation networks for cognitive production. On the example of collaboratively training of a federated machine learning model, machine tool lifetime is predicted in industrial manufacturing for high-end operating resources (high-quality cutting tools). From the shop floor to the cloud, all service relevant information is structured using existing digital twin standards and a linked data approach. In particular, the Industry 4.0 Asset Administration Shell (AAS) and OPC UA are used for collecting and referencing operational and engineering data. GAIA-X connectors transfer the service relevant data through a shared data space. The solution enables intelligent analysis and decision-making under the prioritization of data sovereignty and transparency and, therefore, acts as an enabler for future collaborative, data-driven manufacturing applications.

show abstract

ExeKG: Executable Knowledge Graph System for User-friendly Data Analytics

Cited by 6 publications

References 19 publications

Chrontext: Portable Sparql Queries Over Contextualised Time Series Data in Industrial Settings

Chrontext: Portable Sparql Queries Over Contextualised Time Series Data in Industrial Settings

Executable Knowledge Graph for Transparent Machine Learning in Welding Monitoring at Bosch

Enabling Federated Learning Services Using OPC UA, Linked Data and GAIA-X in Cognitive Production

Contact Info

Product

Resources

About