Marvin Kastner, M.Sc.
Address
Hamburg University of Technology
Institute of Maritime Logistics
Am Schwarzenberg-Campus 4 (D)
21073 Hamburg
Contact Details & Profiles
Office: building D room 5.007
Phone: +49 40 42878 4793
E-mail: marvin.kastner(at)tuhh(dot)de
ORCiD: 0000-0001-8289-2943
LinkedIn: https://www.linkedin.com/in/marvin-kastner/
ResearchGate: https://www.researchgate.net/profile/Marvin-Kastner
Google scholar: https://scholar.google.de/citations?user=lAR-oVAAAAAJ&hl=de&oi=ao
Scopus: https://www.scopus.com/authid/detail.uri?authorId=57221938031
Research Focus
- Simulation-based Design of Container Terminals
- Optimization of Yard Operations at Container Terminals
- Data-driven Improvement of Maritime Security
- Machine Learning in Maritime Logistic
- Optimization of Multivariate Black-box Functions
Presentations and workshops (Excerpt)
- 25.01.2023 a talk at the 7. Suderburger Logistics Forum: "AI-assisted planning of cargo handling facilities with the example of container terminals" (title translated)
- 15.09.2022 a talk at the MLE-Days 2022: "Synthetic data for reinforcement learning in container terminal control systems."
- 28.06.2022 a workshop at the Graduate Academy of TUHH: "Introduction to Jupyter Notebooks" (title translated) [more]
- 02.07.2021 a workshop at the MLE-Days 2021: "Machine Learning in Maritime Logistics" (title translated) [zip]
- 16.03.2021 a workshop at the Graduate Academy of TUHH: "Introduction to Jupyter Notebooks" (title translated) [more]
- 30.11.2020 in the lecture series "Train Your Engineering Network" of the MLE initiative: "How to Talk About Machine Learning with Jupyter Notebooks"
- 22.11.2019 at DISRUPT NOW! AI for Hamburg: "Artificial Intelligence in Maritime Economy" (title translated) [more]
- 29.10.2019 in the context of forschungsbörse: "Maritime Logistics - an all-round cover" (title translated) [more]
- 23.10.2019 at the Open Access Week 2019 at TUHH: "Data Analysis - Describe and Visualize Data with Jupyter Notebooks" (title translated) [more] [git]
- 16.11.2018 at the GI DevCamp Hamburg: "Mobility Research and GDPR"
- 27.09.2018 at SGKV WG regarding truck arrivals: "Forecasting and Neural Networks – What is possible?" (title translated)
2024
| [182407] |
| Title: Model-based Optimisation with Tree-structured Parzen Estimation for Discrete Event Simulation at Container Terminals: Modellbasierte Optimierung mit baumstrukturierter Kerndichteschätzung für ereignisdiskrete Simulation auf Container-Terminals. <em>Simulation in Produktion und Logistik</em> |
| Written by: Kastner, Marvin and Nellen, Nicole and Jahn, Carlos |
| in: <em>ASIM 2019</em>. (2019). |
| Volume: Number: |
| on pages: 489-498 |
| Chapter: |
| Editor: In Putz, Matthias and Schlegel, Andreas (Eds.) |
| Publisher: Wissenschaftliche Scripten: |
| Series: |
| Address: Auerbach /Vogtl. |
| Edition: 1 |
| ISBN: 9783957351135 |
| how published: |
| Organization: |
| School: |
| Institution: |
| Type: |
| DOI: |
| URL: http://www.asim-fachtagung-spl.de/asim2019/papers/47_Proof_164.pdf |
| ARXIVID: |
| PMID: |
Note:
Abstract: Traditionally discrete event simulation serves as a tool for estimating the impact of managerial decisions at container terminals. For complex situations, simulation-based optimisation can be employed to lower the amount of executed simulation experiments and therefore reduce the time to obtain results. The search is guided by the already run experiments. This paper examines the applicability of the Tree-structured Parzen Estimator for optimizing simulation models of container terminals. The reasoning is based both on prior literature in the field of simulation and machine learning, as well as a numerical study. Within the experiments, the performance of the Tree-structured Parzen Estimator is compared with Simulated Annealing and Random Search. The Tree-structured Parzen Estimator displays a more explorative and robust search behaviour than Simulated Annealing
2023
| [182407] |
| Title: Model-based Optimisation with Tree-structured Parzen Estimation for Discrete Event Simulation at Container Terminals: Modellbasierte Optimierung mit baumstrukturierter Kerndichteschätzung für ereignisdiskrete Simulation auf Container-Terminals. <em>Simulation in Produktion und Logistik</em> |
| Written by: Kastner, Marvin and Nellen, Nicole and Jahn, Carlos |
| in: <em>ASIM 2019</em>. (2019). |
| Volume: Number: |
| on pages: 489-498 |
| Chapter: |
| Editor: In Putz, Matthias and Schlegel, Andreas (Eds.) |
| Publisher: Wissenschaftliche Scripten: |
| Series: |
| Address: Auerbach /Vogtl. |
| Edition: 1 |
| ISBN: 9783957351135 |
| how published: |
| Organization: |
| School: |
| Institution: |
| Type: |
| DOI: |
| URL: http://www.asim-fachtagung-spl.de/asim2019/papers/47_Proof_164.pdf |
| ARXIVID: |
| PMID: |
Note:
Abstract: Traditionally discrete event simulation serves as a tool for estimating the impact of managerial decisions at container terminals. For complex situations, simulation-based optimisation can be employed to lower the amount of executed simulation experiments and therefore reduce the time to obtain results. The search is guided by the already run experiments. This paper examines the applicability of the Tree-structured Parzen Estimator for optimizing simulation models of container terminals. The reasoning is based both on prior literature in the field of simulation and machine learning, as well as a numerical study. Within the experiments, the performance of the Tree-structured Parzen Estimator is compared with Simulated Annealing and Random Search. The Tree-structured Parzen Estimator displays a more explorative and robust search behaviour than Simulated Annealing
2022
| [182407] |
| Title: Model-based Optimisation with Tree-structured Parzen Estimation for Discrete Event Simulation at Container Terminals: Modellbasierte Optimierung mit baumstrukturierter Kerndichteschätzung für ereignisdiskrete Simulation auf Container-Terminals. <em>Simulation in Produktion und Logistik</em> |
| Written by: Kastner, Marvin and Nellen, Nicole and Jahn, Carlos |
| in: <em>ASIM 2019</em>. (2019). |
| Volume: Number: |
| on pages: 489-498 |
| Chapter: |
| Editor: In Putz, Matthias and Schlegel, Andreas (Eds.) |
| Publisher: Wissenschaftliche Scripten: |
| Series: |
| Address: Auerbach /Vogtl. |
| Edition: 1 |
| ISBN: 9783957351135 |
| how published: |
| Organization: |
| School: |
| Institution: |
| Type: |
| DOI: |
| URL: http://www.asim-fachtagung-spl.de/asim2019/papers/47_Proof_164.pdf |
| ARXIVID: |
| PMID: |
Note:
Abstract: Traditionally discrete event simulation serves as a tool for estimating the impact of managerial decisions at container terminals. For complex situations, simulation-based optimisation can be employed to lower the amount of executed simulation experiments and therefore reduce the time to obtain results. The search is guided by the already run experiments. This paper examines the applicability of the Tree-structured Parzen Estimator for optimizing simulation models of container terminals. The reasoning is based both on prior literature in the field of simulation and machine learning, as well as a numerical study. Within the experiments, the performance of the Tree-structured Parzen Estimator is compared with Simulated Annealing and Random Search. The Tree-structured Parzen Estimator displays a more explorative and robust search behaviour than Simulated Annealing
2021
| [182407] |
| Title: Model-based Optimisation with Tree-structured Parzen Estimation for Discrete Event Simulation at Container Terminals: Modellbasierte Optimierung mit baumstrukturierter Kerndichteschätzung für ereignisdiskrete Simulation auf Container-Terminals. <em>Simulation in Produktion und Logistik</em> |
| Written by: Kastner, Marvin and Nellen, Nicole and Jahn, Carlos |
| in: <em>ASIM 2019</em>. (2019). |
| Volume: Number: |
| on pages: 489-498 |
| Chapter: |
| Editor: In Putz, Matthias and Schlegel, Andreas (Eds.) |
| Publisher: Wissenschaftliche Scripten: |
| Series: |
| Address: Auerbach /Vogtl. |
| Edition: 1 |
| ISBN: 9783957351135 |
| how published: |
| Organization: |
| School: |
| Institution: |
| Type: |
| DOI: |
| URL: http://www.asim-fachtagung-spl.de/asim2019/papers/47_Proof_164.pdf |
| ARXIVID: |
| PMID: |
Note:
Abstract: Traditionally discrete event simulation serves as a tool for estimating the impact of managerial decisions at container terminals. For complex situations, simulation-based optimisation can be employed to lower the amount of executed simulation experiments and therefore reduce the time to obtain results. The search is guided by the already run experiments. This paper examines the applicability of the Tree-structured Parzen Estimator for optimizing simulation models of container terminals. The reasoning is based both on prior literature in the field of simulation and machine learning, as well as a numerical study. Within the experiments, the performance of the Tree-structured Parzen Estimator is compared with Simulated Annealing and Random Search. The Tree-structured Parzen Estimator displays a more explorative and robust search behaviour than Simulated Annealing
2020
| [182407] |
| Title: Model-based Optimisation with Tree-structured Parzen Estimation for Discrete Event Simulation at Container Terminals: Modellbasierte Optimierung mit baumstrukturierter Kerndichteschätzung für ereignisdiskrete Simulation auf Container-Terminals. <em>Simulation in Produktion und Logistik</em> |
| Written by: Kastner, Marvin and Nellen, Nicole and Jahn, Carlos |
| in: <em>ASIM 2019</em>. (2019). |
| Volume: Number: |
| on pages: 489-498 |
| Chapter: |
| Editor: In Putz, Matthias and Schlegel, Andreas (Eds.) |
| Publisher: Wissenschaftliche Scripten: |
| Series: |
| Address: Auerbach /Vogtl. |
| Edition: 1 |
| ISBN: 9783957351135 |
| how published: |
| Organization: |
| School: |
| Institution: |
| Type: |
| DOI: |
| URL: http://www.asim-fachtagung-spl.de/asim2019/papers/47_Proof_164.pdf |
| ARXIVID: |
| PMID: |
Note:
Abstract: Traditionally discrete event simulation serves as a tool for estimating the impact of managerial decisions at container terminals. For complex situations, simulation-based optimisation can be employed to lower the amount of executed simulation experiments and therefore reduce the time to obtain results. The search is guided by the already run experiments. This paper examines the applicability of the Tree-structured Parzen Estimator for optimizing simulation models of container terminals. The reasoning is based both on prior literature in the field of simulation and machine learning, as well as a numerical study. Within the experiments, the performance of the Tree-structured Parzen Estimator is compared with Simulated Annealing and Random Search. The Tree-structured Parzen Estimator displays a more explorative and robust search behaviour than Simulated Annealing
2019
| [182407] |
| Title: Model-based Optimisation with Tree-structured Parzen Estimation for Discrete Event Simulation at Container Terminals: Modellbasierte Optimierung mit baumstrukturierter Kerndichteschätzung für ereignisdiskrete Simulation auf Container-Terminals. <em>Simulation in Produktion und Logistik</em> |
| Written by: Kastner, Marvin and Nellen, Nicole and Jahn, Carlos |
| in: <em>ASIM 2019</em>. (2019). |
| Volume: Number: |
| on pages: 489-498 |
| Chapter: |
| Editor: In Putz, Matthias and Schlegel, Andreas (Eds.) |
| Publisher: Wissenschaftliche Scripten: |
| Series: |
| Address: Auerbach /Vogtl. |
| Edition: 1 |
| ISBN: 9783957351135 |
| how published: |
| Organization: |
| School: |
| Institution: |
| Type: |
| DOI: |
| URL: http://www.asim-fachtagung-spl.de/asim2019/papers/47_Proof_164.pdf |
| ARXIVID: |
| PMID: |
Note:
Abstract: Traditionally discrete event simulation serves as a tool for estimating the impact of managerial decisions at container terminals. For complex situations, simulation-based optimisation can be employed to lower the amount of executed simulation experiments and therefore reduce the time to obtain results. The search is guided by the already run experiments. This paper examines the applicability of the Tree-structured Parzen Estimator for optimizing simulation models of container terminals. The reasoning is based both on prior literature in the field of simulation and machine learning, as well as a numerical study. Within the experiments, the performance of the Tree-structured Parzen Estimator is compared with Simulated Annealing and Random Search. The Tree-structured Parzen Estimator displays a more explorative and robust search behaviour than Simulated Annealing