Michael Heider

Research Assistant
Lehrstuhl für Organic Computing
Phone: +49 821 598 69261
Email:
Room: 1031 (W)
Address: Am Technologiezentrum 8, 86159 Augsburg

Research foci

My main research project aims to automate parameter optimization of industrial machinery by including existing expert knowledge into advanced machine learning algorithms, such as Learning Classifier Systems, a family of evolutionary learning methods. Therefore, I am developing a new way of creating LCS models (that can be thought of as generalisations of decision trees) with the Supervised Rule-based Learning System (SupRB). In our case study, we try to implement our concepts in the context of plastic extrusion manufacturing. An important role in finding optimal parameter settings plays predicting the quality, that results from applying a given setting. However, operators, supervisors, process engineers and management do all request that these predictive models offer explainability, interpretability and transparency (ergo, be somewhat understandable to a human user).

 

  • evolutionary rule-based learning (supervised and reinforcement learning)
  • unsupervised deep learning for feature extraction (e.g. Autoencoders)
  • explainable AI (XAI)
  • socio-technical assistance systems
  • extrusion-based manufacturing
  • 3D printing / additive manufacturing

Publications

2023 | 2022 | 2021 | 2020 | 2019 | 2016

2023

Markus Görlich-Bucher, Michael Heider, Tobias Ciemala and Jörg Hähner. 2023. A decision-theoretic approach for prioritizing maintenance activities in organic computing systems. DOI: 10.1007/978-3-031-42785-5_3
BibTeX | RIS | DOI

Helena Stegherr, Leopold Luley, Jonathan Wurth, Michael Heider and Jörg Hähner. 2023. A framework for modular construction and evaluation of metaheuristics.
PDF | BibTeX | RIS

Michael Heider, David Pätzel, Helena Stegherr and Jörg Hähner. 2023. A metaheuristic perspective on learning classifier systems. DOI: 10.1007/978-981-19-3888-7_3
BibTeX | RIS | DOI

Michael Heider, Helena Stegherr, Richard Nordsieck and Jörg Hähner. 2023. Assessing model requirements for explainable AI: a template and exemplary case study. DOI: 10.1162/artl_a_00414
PDF | BibTeX | RIS | DOI

Helena Stegherr, Michael Heider and Jörg Hähner. 2023. Assisting convergence behaviour characterisation with unsupervised clustering. DOI: 10.5220/0012202100003595
PDF | BibTeX | RIS | DOI

Michael Heider, Helena Stegherr, David Pätzel, Roman Sraj, Jonathan Wurth, Benedikt Volger and Jörg Hähner. 2023. Discovering rules for rule-based machine learning with the help of novelty search. DOI: 10.1007/s42979-023-02198-x
PDF | BibTeX | RIS | DOI

Jonathan Wurth, Helena Stegherr, Michael Heider, Leopold Luley and Jörg Hähner. 2023. Fast, flexible, and fearless: a rust framework for the modular construction of metaheuristics. DOI: 10.1145/3583133.3596335
BibTeX | RIS | DOI

Neele Kemper, Michael Heider, Dirk Pietruschka and Jörg Hähner. in press. Forecasting of residential unit's heat demands: a comparison of machine learning techniques in a real-world case study. DOI: 10.1007/s12667-023-00579-y
BibTeX | RIS | DOI

Lukas Meitz, Michael Heider, Thorsten Schöler and Jörg Hähner. 2023. On data-preprocessing for effective predictive maintenance on multi-purpose machines. DOI: 10.5220/0012146700003541
PDF | BibTeX | RIS | DOI

Markus Görlich-Bucher, Michael Heider and Jörg Hähner. 2023. Predicting physical disturbances in organic computing systems using automated machine learning. DOI: 10.1007/978-3-031-42785-5_4
BibTeX | RIS | DOI

Michael Heider, Helena Stegherr, Roman Sraj, David Pätzel, Jonathan Wurth and Jörg Hähner. 2023. SupRB in the context of rule-based machine learning methods: a comparative study. DOI: 10.1016/j.asoc.2023.110706
BibTeX | RIS | DOI

David Pätzel, Michael Heider and Jörg Hähner. 2023. Towards principled synthetic benchmarks for explainable rule set learning algorithms. DOI: 10.1145/3583133.3596416
BibTeX | RIS | DOI

Tobias Wittmeir, Michael Heider, André Schweiger, Michaela Krä, Jörg Hähner, Johannes Schilp and Joachim Berlak. 2023. Towards robustness of production planning and control against supply chain disruptions. DOI: 10.15488/13425
PDF | BibTeX | RIS | DOI

Henning Cui, Andreas Margraf, Michael Heider and Jörg Hähner. 2023. Towards understanding crossover for Cartesian Genetic Programming. DOI: 10.5220/0012231400003595
PDF | BibTeX | RIS | DOI

2022

Richard Nordsieck, Michael Heider, Anton Hummel and Jörg Hähner. 2022. A closer look at sum-based embeddings for knowledge graphs containing procedural knowledge.
PDF | BibTeX | RIS | URL

Michael Heider, David Pätzel and Alexander R. M. Wagner. 2022. An overview of LCS research from 2021 to 2022. DOI: 10.1145/3520304.3533985
PDF | BibTeX | RIS | DOI

Michael Heider, Helena Stegherr, David Pätzel, Roman Sraj, Jonathan Wurth, Benedikt Volger and Jörg Hähner. 2022. Approaches for rule discovery in a learning classifier system. DOI: 10.5220/0011542000003332
PDF | BibTeX | RIS | DOI

Helena Stegherr, Michael Heider and Jörg Hähner. 2022. Classifying metaheuristics: towards a unified multi-level classification system. DOI: 10.1007/s11047-020-09824-0
PDF | BibTeX | RIS | DOI

Jonathan Wurth, Michael Heider, Helena Stegherr, Roman Sraj and Jörg Hähner. 2022. Comparing different metaheuristics for model selection in a supervised learning classifier system. DOI: 10.1145/3520304.3529015
PDF | BibTeX | RIS | DOI

Michael Heider, Helena Stegherr, Jonathan Wurth, Roman Sraj and Jörg Hähner. 2022. Investigating the impact of independent rule fitnesses in a learning classifier system. DOI: 10.1007/978-3-031-21094-5_11
PDF | BibTeX | RIS | DOI

Richard Nordsieck, Michael Heider, Alwin Hoffmann and Jörg Hähner. 2022. Reliability-based aggregation of heterogeneous knowledge to assist operators in manufacturing. DOI: 10.1109/icsc52841.2022.00027
PDF | BibTeX | RIS | DOI

Michael Heider, Helena Stegherr, Jonathan Wurth, Roman Sraj and Jörg Hähner. 2022. Separating rule discovery and global solution composition in a learning classifier system. DOI: 10.1145/3520304.3529014
PDF | BibTeX | RIS | DOI

Richard Nordsieck, Michael Heider, Anton Hummel, Alwin Hoffmann and Jörg Hähner. 2022. Towards models of conceptual and procedural operator knowledge.
PDF | BibTeX | RIS | URL

2021

David Pätzel, Michael Heider and Alexander R. M. Wagner. 2021. An overview of LCS research from 2020 to 2021. DOI: 10.1145/3449726.3463173
PDF | BibTeX | RIS | DOI

Andreas Wiedholz, Michael Heider, Richard Nordsieck, Andreas Angerer, Simon Dietrich and Jörg Hähner. 2021. CAD-based grasp and motion planning for process automation in fused deposition modelling. DOI: 10.5220/0010571204500458
PDF | BibTeX | RIS | DOI

Helena Stegherr, Michael Heider, Leopold Luley and Jörg Hähner. 2021. Design of large-scale metaheuristic component studies. DOI: 10.1145/3449726.3463168
PDF | BibTeX | RIS | DOI

Richard Nordsieck, Michael Heider, Anton Winschel and Jörg Hähner. 2021. Knowledge extraction via decentralized knowledge graph aggregation. DOI: 10.1109/icsc50631.2021.00024
PDF | BibTeX | RIS | DOI

Michael Heider, Richard Nordsieck and Jörg Hähner. 2021. Learning classifier systems for self-explaining socio-technical-systems.
PDF | BibTeX | RIS | URL

2020

Richard Nordsieck, Michael Heider, Andreas Angerer and Jörg Hähner. 2020. Evaluating the effect of user-given guiding attention on the learning process. DOI: 10.1109/acsos49614.2020.00044
PDF | BibTeX | RIS | DOI

Michael Heider, David Pätzel and Jörg Hähner. 2020. SupRB: a supervised rule-based learning system for continuous problems.
BibTeX | RIS | URL

Michael Heider, David Pätzel and Jörg Hähner. 2020. Towards a Pittsburgh-style LCS for learning manufacturing machinery parametrizations. DOI: 10.1145/3377929.3389963
PDF | BibTeX | RIS | DOI

2019

Michael Heider. 2019. Increasing reliability in FDM manufacturing. DOI: 10.18420/inf2019_ws52
PDF | BibTeX | RIS | DOI

Richard Nordsieck, Michael Heider, Andreas Angerer and Jörg Hähner. 2019. Towards automated parameter optimisation of machinery by persisting expert knowledge. DOI: 10.5220/0007953204060413
PDF | BibTeX | RIS | DOI

2016

Sebastian von Mammen, Heiko Hamann and Michael Heider. 2016. Robot gardens: an augmented reality prototype for plant-robot biohybrid systems. DOI: 10.1145/2993369.2993400
BibTeX | RIS | DOI

Curriculum/Vitae

since 2019 Research Assistant with the chair for Organic Computing
2015–2018 Master programme Computer Science and Information-oriented Business Management at the University of Augsburg
2012–2016 Bachelor programme Computer Science at the University of Augsburg

Courses / teaching

(applied filters: semester: current | institute: Organic Computing | lecturers: Michael Heider | course types: all)
name semester type
Studentische Arbeiten am Lehrstuhl Organic Computing winter semester 2023/24 sonstige
Seminar Organic Computing (Bachelor) winter semester 2023/24 Seminar
Seminar Organic Computing (Master) winter semester 2023/24 Seminar

Search