Department of Engineering and Communication
Unit
Department of Engineering and Communication
Research fields
- Computer Aided Ideation
- Evolutionary Multi-Solution Optimization, Quality Diversity
- Machine Learning
- Gaussian Process regression
- Neuroevolution
- Generative Deep Learning
- Computer Vision
- Robotics
Location
Sankt Augustin
Address
Grantham-Allee 20
53757 Sankt Augustin
Profile
Dutch researcher with international experience in both teaching and research. Strong background in evolutionary optimization and generative and efficient machine learning in various domains, such as fluid dynamics, urban planning, computational chemistry, robotics and computer vision.
My primary interest is in efficient computer aided ideation algorithms that help us understand, early on, what good solutions to a problem might look like.
I get my inspiration from real world applications and nature, and am guided by the need to adapt to the climate catastrophy.
I received my PhD at the LIACS institute of the Leiden University in The Netherlands, where I created a framework and algorithms to interactively discover and incorporate user preferences in complicated computational domains. I use AI as a co-creator - to work together to explore extremely large optimization domains.
Personal webpage: https://alexander-hagg.github.io/
Profile Researchgate: https://www.researchgate.net/profile/Alexander-Hagg
Research Projects
OpenSKIZZE: Open source development tools for urban development: climate impact adaptation with cooperative AI-supported decision-making processes. As an open source AI assistant, OpenSKIZZE is intended to transfer the findings from climate models into concrete construction projects. This system is intended to involve all stakeholders in the process at an early stage and inform them about the effects of their decisions on the local urban climate.
Project management at the H-BRS
Dr Alexander Hagg
The "Digital Twin-4-Multiphysics Lab" (DT4MP) focuses on urban digital twins (UDTs) and multiphysics twins for industry, treating both areas equally and synergistically. By integrating real-time data and advanced simulations, DT4MP enhances urban processes, infrastructures, and industrial production efficiency. Combining AI and machine learning, the lab provides services like data analysis and virtual testing for SMEs and larger companies. Founded by leading institutes, DT4MP drives digitalization research in urban and industrial contexts.
Project management at the H-BRS
Prof. Dr Sebastian Houben Prof. Dr Dirk Reith Dr Alexander Hagg
Artificial intelligence methods can efficiently help us understand aftermath requirements, constraints, and decision-making processes at an early stage. Algorithms are typically used in late stages of engineering development projects. We want to reverse this and show engineers early on which types of solutions meet their requirements.
Project management at the H-BRS
Dr Alexander Hagg
The goal of this project was to develop a strategy in order to extend the infrastructure of car charging stations in Bonn and the Rhein-Sieg-Kreis. Based on goals set by the government and information about the distribution of the car density in the area of interest, scenarios for the extension between 2016 and 2020 have been identified. In order to achieve these goals, the number of charging stations has to be raised successively from 256 (in 2016) to a number of 935 in 2020. Therefore, a grid map for the distribution of charging stations for electronic cars and bicycles had to be created. Also so called "points of interest" (POIs) (tourist attractions, leisure time facilities, etc.) as well as park-and-ride stations have been taken into account. All those options have been ranked according to their priority and their individual traffic data. The current distribution of charging stations has been investigated beforehand. With the help of an algorithm, the best positions and distributions for charging stations have been determined. Though, further analysis is necessary in order to bring these proposals into practise. Therefore, a guildeline has been developed and tested in a workshop for the locations "Königswinter" and "Bonn City Centre".
Project management at the H-BRS
Prof. Dr Stefanie Meilinger
Publications
Dr. Alexander Hagg
2024
Robin Strickstrock, Alexander Hagg, Marco Hülsmann, Karl Kirschner, Dirk Reith:
Fine-Tuning Property Domain Weighting Factors and the Objective Function in Force Field Parameter Optimization.
doi:10.26434/chemrxiv-2024-vfzx8-v2
BibTeX | RIS
2023
Alexander Hagg, Karl N. Kirschner:
Open-Source Machine Learning in Computational Chemistry.
PDF Download (CC BY-NC-ND 4.0) doi:10.1021/acs.jcim.3c00643 PMID urn:nbn:de:hbz:1044-opus-74406
BibTeX | RIS
Ludovico Scarton, Alexander Hagg:
On the Suitability of Representations for Quality Diversity Optimization of Shapes.
doi:10.1145/3583131.3590381
BibTeX | RIS
Ludovico Scarton, Alexander Hagg:
On the Suitability of Representations for Quality Diversity Optimization of Shapes.
arXiv doi:10.48550/arXiv.2304.03520
BibTeX | RIS
Alexander Hagg, Martin L. Kliemank, Alexander Asteroth, Dominik Wilde, Mario C. Bedrunka, Holger Foysi, Dirk Reith:
Efficient Quality Diversity Optimization of 3D Buildings through 2D Pre-optimization.
doi:10.1162/evco_a_00326 PMID
BibTeX | RIS
Max Müller, Alexander Hagg, Robin Strickstrock, Marco Hülsmann, Alexander Asteroth, Karl N. Kirschner, Dirk Reith:
Determining Lennard-Jones Parameters Using Multiscale Target Data through Presampling-Enhanced, Surrogate-Assisted Global Optimization.
doi:10.1021/acs.jcim.2c01231 PMID
BibTeX | RIS
2022
Alexander Hagg, Alexander Asteroth, Christian Rasche, Kevin Bach, Mark Pfeiffer:
Künstliche Intelligenz für den Spitzensport im Spannungsfeld zwischen Big und Small Data: (KISs-BiS).
URL
BibTeX | RIS
Fabian Hammes, Alexander Hagg, Alexander Asteroth, Daniel Link:
Artificial Intelligence in Elite Sports-A Narrative Review of Success Stories and Challenges.
PDF Download (CC BY 4.0) doi:10.3389/fspor.2022.861466 PMID urn:nbn:de:hbz:1044-opus-63714
BibTeX | RIS
2021
Alexander Hagg:
Discovering the preference hypervolume: an interactive model for real world computational co-creativity.
URL
BibTeX | RIS
Alexander Hagg, Sebastian Berns, Alexander Asteroth, Simon Colton, Thomas Bäck:
Expressivity of parameterized and data-driven representations in quality diversity search.
doi:10.1145/3449639.3459287 arXiv
BibTeX | RIS
Alexander Hagg:
Phenotypic Niching Using Quality Diversity Algorithms.
doi:10.1007/978-3-030-79553-5_12
BibTeX | RIS
2020
Alexander Hagg, Alexander Asteroth, Thomas Bäck:
A Deep Dive Into Exploring the Preference Hypervolume.
PDF Download (CC BY 4.0) URL urn:nbn:de:hbz:1044-opus-64423
BibTeX | RIS
Fabian Hammes, Daniel Link, Martin Lames, Alexander Hagg, Alexander Asteroth, Mark Pfeiffer:
Einsatz von Künstlicher Intelligenz im internationalen Spitzensport – Eine Erhebung des Status Quo.
BibTeX | RIS
Alexander Hagg, Alexander Asteroth, Mark Pfeiffer, Fabian Hammes, Daniel Link:
Einsatzmöglichkeiten und Transfer von Künstlicher Intelligenz im internationalen Spitzensport – zwischen Small und Big Data.
BibTeX | RIS
Alexander Hagg, Mike Preuss, Alexander Asteroth, Thomas Bäck:
An Analysis of Phenotypic Diversity in Multi-solution Optimization.
doi:10.1007/978-3-030-63710-1_4
BibTeX | RIS
Alexander Hagg, Dominik Wilde, Alexander Asteroth, Thomas Bäck:
Designing Air Flow with Surrogate-Assisted Phenotypic Niching.
doi:10.1007/978-3-030-58112-1_10
BibTeX | RIS
Alexander Asteroth, Adam Gaier, Alexander Hagg, Jakob Meng, Andreas Priesnitz, Lea Prochnau, Dirk Reith:
AErOmAt Abschlussbericht.
PDF Download doi:10.18418/opus-4850 urn:nbn:de:hbz:1044-opus-48506
BibTeX | RIS
2019
Alexander Hagg, Martin Zaefferer, Jörg Stork, Adam Gaier:
Prediction of neural network performance by phenotypic modeling.
doi:10.1145/3319619.3326815 arXiv
BibTeX | RIS
Alexander Hagg, Alexander Asteroth, Thomas Bäck:
Modeling User Selection in Quality Diversity.
doi:10.1145/3321707.3321823 arXiv
BibTeX | RIS
2018
Alexander Hagg, Alexander Asteroth, Thomas Bäck:
Prototype Discovery Using Quality-Diversity.
doi:10.1007/978-3-319-99253-2_40 arXiv
BibTeX | RIS
2017
Alexander Hagg:
Hierarchical Surrogate Modeling for Illumination Algorithms.
doi:10.1145/3067695.3082495 arXiv
BibTeX | RIS
Alexander Hagg, Maximilian Mensing, Alexander Asteroth:
Evolving Parsimonious Networks by Mixing Activation Functions.
doi:10.1145/3071178.3071275 arXiv
BibTeX | RIS
Helge Spieker, Alexander Hagg, Adam Gaier, Stefanie Meilinger, Alexander Asteroth:
Multi-stage evolution of single- and multi-objective MCLP: Successive placement of charging stations.
doi:10.1007/s00500-016-2374-9
BibTeX | RIS
Alexander Hagg, Frederik Hegger, Paul Plöger:
On Recognizing Transparent Objects in Domestic Environments Using Fusion of Multiple Sensor Modalities.
arXiv doi:10.1007/978-3-319-68792-6_1
BibTeX | RIS
2015
Alexander Hagg, Helge Spieker, Alexander Oslislo, Volker Jacobs, Alexander Asteroth, Stefanie Meilinger:
Methodische Grundlegung für eine Strategie zum sukzessiven Ausbau der Ladeinfrastruktur für Elektromobilität in Bonn und dem Rhein-Sieg-Kreis: Studie zur Strategie für den Ausbau der Ladeinfrastruktur im Hinblick auf E-Autos und E-Zweiräder.
URL
BibTeX | RIS
Helge Spieker, Alexander Hagg, Alexander Asteroth, Stefanie Meilinger, Volker Jacobs, Alexander Oslislo:
Successive evolution of charging station placement.
doi:10.1109/INISTA.2015.7276733
BibTeX | RIS
Alexander Asteroth, Alexander Hagg:
How to successfully apply genetic algorithms in practice: Representation and parametrization.
doi:10.1109/INISTA.2015.7276778
BibTeX | RIS