Publications

2025

1. Vortrag

   Einsatz eines Autograders in der universitären Programmierausbildung zur Verbesserung des digital gestützten Lernens und Prüfens für Ingenieure

   Jonas Genath and Daniel Fischer

   DigiTeLL – Digital Teaching and Learning Lab, Frankfurt, Vortrag und Poster , 2025

   Abs

   As part of the redesign of a course on operational digitization, the desire was expressed to also digitize teaching itself to a greater extent. The aim is to give students a basic understanding of programming so that they can better understand digital possibilities. The autograder CodeOcean was used as a suitable tool—a web-based open-source platform with a development environment, collaboration functions, and LMS integration. In the “examING” project, funded by the Foundation for Innovation in Higher Education, new digital teaching and examination formats for Python training were developed and tested with CodeOcean. So far, around 270 students have participated in the courses, and around 120 have taken digital exams. Feedback and observations accompanied the implementation. Automated assessment by CodeOcean facilitates individual learning and promotes targeted skills development. The article reflects on the experiences, identifies challenges, and outlines further developments, in particular the planned integration of generative AI such as ChatGPT to further improve feedback for students.

2024

1. Vortrag

   ChatGPT meets CodeOcean: Integeration KI-basierten Feedbacks in Autograder-Systeme

   Gunther Kreuzberger, Jonas Genath, and Daniel Fischer

   TURN Conference, Berlin, Vortrag und Poster , 2024

   Abs

   The examING project – digitization of competency-based testing for bachelor’s degree programs in engineering – is investigating how feedback on programming tasks can be improved through generative AI. The aim is to make feedback more individualized, differentiated, constructive, and linguistically variable. The approach developed motivates learners through practical tasks, extensive practice opportunities, and integrated programming tools. To implement this, ChatGPT was integrated into the web-based autograder system CodeOcean via an API. Structured prompts are used to generate factual feedback that specifically addresses the submitted solutions. Initial results show that AI integration can be used to generate high-quality, customizable feedback along defined dimensions. The next steps include the user-friendly presentation of feedback, an evaluation of acceptance, and expansion to other use cases such as comment requests, note creation, and task clarification. The project is funded by the Foundation for Innovation in Higher Education as part of the federal-state program “Strengthening Universities through Digitization.”

2023

1. Paper

   How Not to Visualize your Simulation Output Data

   Jonas Genath and Steffen Strassburger

   In Proceedings of the 2023 Winter Simulation Conference, 2023

   Abs Bib

   Hybrid modeling and simulation studies combine well-defined methods from other disciplines with a simulation technique. Especially in the area of output data analysis of simulation studies, there is great potential for hybrid approaches that incorporate methods from machine learning and AI. For their successful application, the analytical capabilities of machine learning and AI must be combined with the interpretive capabilities of humans. In most cases, this connection is achieved through visualizations. As methods become more complicated, the demands on visualizations are increasing. In this paper, we conduct a data farming study and delve into the analysis of the output data. In doing so, we uncover typical errors in visualizations making the interpretation and evaluation of the data difficult or misleading. We then apply concepts of visual analytics to these visualizations and derive general guidelines to help simulation users to analyze their simulation studies and present results unambiguously and clearly.

   @inproceedings{genath2023wsc,
     author = {Genath, Jonas and Strassburger, Steffen},
     title = {How Not to Visualize your Simulation Output Data},
     booktitle = {Proceedings of the 2023 Winter Simulation Conference},
     address = {San Antonio, TX, USA},
     year = {2023},
   }

2. Paper

   Erfahrungen bei der Integration des Autograding-Systems CodeOcean in die universitäre Programmierausbildung

   Jonas Genath, Peter Amthor, Ulf Döring, and 2 more authors

   In Proceedings of the sixth workshop "Automatische Bewertung von Programmieraufgaben", 2023

   Abs Bib

   Effective and efficient university programming education increasingly requires the use of automated assessment systems. As part of the examING2 project, the AutoPING subproject is testing the use of the open-source autograding system CodeOcean for comprehensive courses and exams at the Technical University of Ilmenau with the aim of enabling and promoting self-directed and competence-oriented learning. This article provides an overview of initial project experiences in adapting didactic scenarios in programming education to test-driven software development and the generation of feedback. It discusses key findings from the perspective of students and teachers, challenges and approaches to integrating and expanding CodeOcean for new fields of application, and opens up future perspectives.

   @inproceedings{amthor2023codeocean,
     author = {Genath, Jonas and Amthor, Peter and Döring, Ulf and Fischer, Daniel and Kreuzberger, Gunther},
     title = {Erfahrungen bei der Integration des Autograding-Systems CodeOcean in die universitäre Programmierausbildung},
     booktitle = {Proceedings of the sixth workshop "Automatische Bewertung von Programmieraufgaben"},
     publisher = {Gesellschaft für Informatik e. V.},
     year = {2023},
   }

2022

1. Article

   Data Farming und Wissensentdeckung in Simulationsdaten - Entwicklung einer integrierten Lösung

   Jonas Genath, Soeren Bergmann, Steffen Straßburger, and 2 more authors

   Zeitschrift für wirtschaftlichen Fabrikbetrieb, 2022

   Abs Bib

   Simulation as a method of digital factory has long been established to support the planning of production and logistics systems. In addition to the simulation studies that have prevailed to date, the method of knowledge discovery in simulation data presented here uses a simulation model as a data generator. This allows data mining and visual analytics methods to be used to uncover hidden and potentially useful cause-and-effect relationships in the generated data. Until now, however, there has been a lack of integrated software solutions for practical use.

   @article{genath2022zfwf,
     author = {Genath, Jonas and Bergmann, Soeren and Straßburger, Steffen and Spieckermann, Sven and Stauber, Stephan},
     title = {Data Farming und Wissensentdeckung in Simulationsdaten - Entwicklung einer integrierten Lösung},
     journal = {Zeitschrift für wirtschaftlichen Fabrikbetrieb},
     number = {3},
     year = {2022},
   }

2. Article

   Development of an Integrated Solution for Data Farming and Knowledge Discovery in Simulation Data

   Jonas Genath, Sören Bergmann, Sven Spieckermann, and 2 more authors

   Simulation Notes Europe, 2022

   Abs Bib

   Simulation is an established methodology for planning and evaluating manufacturing and logistics systems. In contrast to classical simulation studies, the method of knowledge discovery in simulation data uses a simulation model as a data generator (data farming). Subsequently, hidden, previously unknown and potentially useful cause-effect relationships can be uncovered on the generated data using data mining and visual analytics methods. So far, however, there was a lack of integrated, easy-to-use software solutions for the application of the data farming in operational practice. This paper presents such an integrated solution, which allows generating experiment designs, implements a method to distribute the necessary experiment runs, and provides the user with tools to analyze and visualize the result data.

   @article{genath2022sne,
     author = {Genath, Jonas and Bergmann, Sören and Spieckermann, Sven and Stauber, Stephan and Feldkamp, Niclas},
     title = {Development of an Integrated Solution for Data Farming and Knowledge Discovery in Simulation Data},
     journal = {Simulation Notes Europe},
     volume = {32},
     number = {2},
     year = {2022},
   }

3. Paper

   Explainable AI for Data Farming Output Analysis: A Use Case for Knowledge Generation through Black-Box Classifiers

   Niclas Feldkamp, Jonas Genath, and Steffen Strassburger

   In Proceedings of the 2022 Winter Simulation Conference, 2022

   Abs Bib

   Data farming combines large-scale simulation experiments with high performance computing and sophisticated big data analysis methods. The portfolio of analysis methods for those large amounts of simulation data still yields potential to further development, and new methods emerge frequently. Among the most interesting are methods of explainable artificial intelligence (XAI). Those methods enable the use of black-box-classifiers for data farming output analysis, which has been shown in a previous paper. In this paper, we apply the concept for XAI-based data farming analysis on a complex, real world case study to investigate the suitability of such concept in a real world application, and we also elaborate on which blackbox classifiers are actually the most suitable for large-scale simulation data that accumulates in a data farming project.

   @inproceedings{feldkamp2022wsc,
     author = {Feldkamp, Niclas and Genath, Jonas and Strassburger, Steffen},
     title = {Explainable AI for Data Farming Output Analysis: A Use Case for Knowledge Generation through Black-Box Classifiers},
     booktitle = {Proceedings of the 2022 Winter Simulation Conference},
     address = {Singapur, SGP},
     year = {2022},
   }

2021

1. Paper

   Entwicklung einer integrierten Lösung für das Data Farming und die Wissensentdeckung in Simulationsdaten

   Jonas Genath, Sören Bergmann, Sven Spieckermann, and 2 more authors

   In Proceedings der ASIM Fachtagung „Simulation in Produktion und Logistik“, 2021

   Abs Bib

   Simulation is an established methodology for planning and evaluating manufacturing and logistics systems. In contrast to classical simulation studies, the method of knowledge discovery in simulation data uses a simulation model as a data generator (data farming). Subsequently, hidden, previously unknown and potentially useful cause-effect relationships can be uncovered on the generated data using data mining and visual analytics methods. So far, however, there is a lack of integrated, easy-to-use software solutions for the application of the data farming in operational practice. This paper presents such an integrated solution, which allows for generating experiment designs, implements a method to distribute the necessary experiment runs, and provides the user with tools to analyze and visualize the result data.

   @inproceedings{genath2021asim1,
     author = {Genath, Jonas and Bergmann, Sören and Spieckermann, Sven and Stauber, Stephan and Feldkamp, Niclas},
     title = {Entwicklung einer integrierten Lösung für das Data Farming und die Wissensentdeckung in Simulationsdaten},
     booktitle = {Proceedings der ASIM Fachtagung „Simulation in Produktion und Logistik“},
     year = {2021},
     pages = {377--386},
   }

2. Paper

   Automatisierung im Prozess der Wissensentdeckung in Simulationsdaten - Charakterisierung der Ergebnisdaten

   Jonas Genath, Sören Bergmann, Niclas Feldkamp, and 1 more author

   In Proceedings der ASIM Fachtagung „Simulation in Produktion und Logistik“, 2021

   Abs Bib

   The traditional application of simulation in production and logistics is usually aimed at changing certain parameters in order to answer clearly defined objectives or questions. In contrast to this approach, the method of knowledge discovery in simulation data (KDS) uses a simulation model as a data generator (data farming). Subsequently using data mining methods, hidden, previously unknown and potentially useful cause-effect relationships can be uncovered. So far, however, there is a lack of guidelines and automatization-tools for non-experts or novices in KDS, which leads to a more difficult use in industrial applications and prevents a broader utilization. This paper presents a concept for automating the first step of the KDS, which is the process of characterization of the result data, using meta learning and validates it on small case study.

   @inproceedings{genath2021asim2,
     author = {Genath, Jonas and Bergmann, Sören and Feldkamp, Niclas and Straßburger, Steffen},
     title = {Automatisierung im Prozess der Wissensentdeckung in Simulationsdaten - Charakterisierung der Ergebnisdaten},
     booktitle = {Proceedings der ASIM Fachtagung „Simulation in Produktion und Logistik“},
     year = {2021},
     pages = {367--376},
   }

3. Paper

   An Integrated Solution for Data Farming and Knowledge Discovery in Simulation Data: A Case Study of the Battery Supply of a Vehicle Manufacturer

   Jonas Genath, Soeren Bergmann, Steffen Strassburger, and 2 more authors

   In Proceedings of the 2021 Winter Simulation Conference, 2021

   Abs Bib

   The development of logistics concepts, here for supplying an automobile production with batteries, is a major challenge, especially when there are uncertainties. In order to mitigate this, the method of knowledge discovery in simulation data is to be applied here. In order to enable the planners to easily use the method, a tool that can be easily integrated into practical use (SimAssist-4farm) was developed.

   @inproceedings{genath2021wsc1,
     author = {Genath, Jonas and Bergmann, Soeren and Strassburger, Steffen and Stauber, Stephan and Spieckermann, Sven},
     title = {An Integrated Solution for Data Farming and Knowledge Discovery in Simulation Data: A Case Study of the Battery Supply of a Vehicle Manufacturer},
     booktitle = {Proceedings of the 2021 Winter Simulation Conference},
     address = {Phoenix, AZ, USA},
     year = {2021},
   }

4. Vortrag

   Automation in the Process of Knowledge Discovery in Simulation Data

   Jonas Genath

   Winter Simulation Conference, Phoenix, AZ, USA, Vortrag und Poster , 2021

   Abs

   In contrast to classical simulation studies, the method of knowledge discovery in simulation data uses a simulation model as a data generator (data farming). Subsequently using data mining methods, hidden, previously unknown and potentially useful cause-effect relationships can be uncovered. So far, however, there is a lack of support and automatization tools for non-experts or novices in knowledge discovery in simulation data, which leads to a more difficult use in industrial applications and prevents a broader utilization. In this work, we propose a concept which provides an approach for automating and supporting knowledge discovery in simulation data.