---
_id: '12445'
author:
- first_name: Colin
full_name: Behrens, Colin
id: '73022'
last_name: Behrens
citation:
ama: 'Behrens C. Splatman : Automatisierte Erstellung von optimierten Datensets
aus digitalen Szenen für Gaussian Splatting. Technische Hochschule Ostwestfalen-Lippe'
apa: 'Behrens, C. (n.d.). Splatman : Automatisierte Erstellung von optimierten
Datensets aus digitalen Szenen für Gaussian Splatting. Technische Hochschule
Ostwestfalen-Lippe.'
bjps: 'Behrens C (n.d.) Splatman : Automatisierte Erstellung von optimierten
Datensets aus digitalen Szenen für Gaussian Splatting. Lemgo: Technische Hochschule
Ostwestfalen-Lippe.'
chicago: 'Behrens, Colin. Splatman : Automatisierte Erstellung von optimierten
Datensets aus digitalen Szenen für Gaussian Splatting. Lemgo: Technische Hochschule
Ostwestfalen-Lippe, n.d.'
chicago-de: 'Behrens, Colin. Splatman : Automatisierte Erstellung von optimierten
Datensets aus digitalen Szenen für Gaussian Splatting. Lemgo: Technische Hochschule
Ostwestfalen-Lippe.'
din1505-2-1: 'Behrens, Colin: Splatman :
Automatisierte Erstellung von optimierten Datensets aus digitalen Szenen für Gaussian
Splatting. Lemgo : Technische Hochschule Ostwestfalen-Lippe'
havard: 'C. Behrens, Splatman : Automatisierte Erstellung von optimierten Datensets
aus digitalen Szenen für Gaussian Splatting, Technische Hochschule Ostwestfalen-Lippe,
Lemgo, n.d.'
ieee: 'C. Behrens, Splatman : Automatisierte Erstellung von optimierten Datensets
aus digitalen Szenen für Gaussian Splatting. Lemgo: Technische Hochschule
Ostwestfalen-Lippe.'
mla: 'Behrens, Colin. Splatman : Automatisierte Erstellung von optimierten Datensets
aus digitalen Szenen für Gaussian Splatting. Technische Hochschule Ostwestfalen-Lippe.'
short: 'C. Behrens, Splatman : Automatisierte Erstellung von optimierten Datensets
aus digitalen Szenen für Gaussian Splatting, Technische Hochschule Ostwestfalen-Lippe,
Lemgo, n.d.'
ufg: 'Behrens, Colin: Splatman : Automatisierte Erstellung von optimierten
Datensets aus digitalen Szenen für Gaussian Splatting, Lemgo o. J.'
van: 'Behrens C. Splatman : Automatisierte Erstellung von optimierten Datensets
aus digitalen Szenen für Gaussian Splatting. Lemgo: Technische Hochschule Ostwestfalen-Lippe;
69 p.'
date_created: 2025-02-17T10:13:31Z
date_updated: 2025-02-24T13:00:02Z
ddc:
- '004'
department:
- _id: DEP2001
file:
- access_level: local
content_type: application/pdf
creator: mhd-u1u
date_created: 2025-02-24T12:08:03Z
date_updated: 2025-02-24T13:00:01Z
file_id: '12492'
file_name: Masterarbeit_Colin_Behrens.pdf
file_size: 10558536
relation: main_file
file_date_updated: 2025-02-24T13:00:01Z
has_accepted_license: '1'
keyword:
- Gaussian
- Splatting
- Computergraphics
- Scanning
- 3D
- NeRF
- Datensätze
language:
- iso: ger
page: '69'
place: Lemgo
publication_status: submitted
publisher: Technische Hochschule Ostwestfalen-Lippe
status: public
supervisor:
- first_name: Alexander
full_name: Kutter, Alexander
id: '83513'
last_name: Kutter
title: 'Splatman : Automatisierte Erstellung von optimierten Datensets aus digitalen
Szenen für Gaussian Splatting'
type: master_thesis
user_id: '83781'
year: '2025'
...
---
_id: '12646'
abstract:
- lang: ger
text: "Die präzise und kosteneffiziente 3D-Rekonstruktion industrieller Umgebungen
gewinnt zu-nehmend an Bedeutung, insbesondere für digitale Zwillinge und automatisierte
Inspektions-prozesse. Diese Arbeit untersucht die Entwicklung und Evaluierung
eines multisensorischen Kamera-Setups, das mit Gaussian Splatting eine speichereffiziente
und schnelle Modellierung von Produktionsumgebungen ermöglicht. Dafür wurde ein
mobiles, autonomes System auf Basis eines MiR-Roboters entwickelt, das Bilddaten
von verschiedenen USB-Kameras (Lo-gitech Brio, Anker C200), einer DSLR und iPhone
Kamera sowie Raspberry Pi Kameras er-fasst und verarbeitet. \r\nDie zentrale Forschungsfrage
adressiert die Effizienz, Bildqualität und Wirtschaftlichkeit von Gaussian Splatting
im Vergleich zu etablierten Verfahren wie Photogrammetrie und LiDAR. Erste Testläufe
mit DSLR-Aufnahmen und einer manuell rekonstruierten Pipeline zeigen, dass Gaussian
Splatting hochdetaillierte Punktwolken generieren kann, jedoch mit Herausfor-derungen
hinsichtlich Kameraausrichtung, Überlappung der Bilder und automatisierter Missi-onsplanung
des Roboters konfrontiert ist. \r\nDie Ergebnisse zeigen, dass das System eine
schnelle und speichereffiziente 3D-Rekonstruk-tion ermöglicht, jedoch in seiner
aktuellen Form noch Optimierungspotenzial aufweist. Be-sonders die genaue Kalibrierung
der Kameras, eine verbesserte Synchronisation der Bilder so-wie eine präzisere
Steuerung des Roboters sind entscheidend für die Qualität der Punktwol-ken. Während
Gaussian Splatting eine überzeugende Alternative zu klassischen Verfahren darstellt,
ist die Systemstabilität derzeit noch abhängig von manuellen Eingriffen und Justie-rungen.
\r\nZukünftige Arbeiten sollten sich darauf konzentrieren, die Automatisierung
des gesamten Workflows weiter voranzutreiben, insbesondere durch den Einsatz verbesserter
Kamera-A-lignment-Algorithmen, Hardware-Trigger für synchrone Bildaufnahme und
Machine-Learn-ing-gestützte Bildoptimierung. Zudem könnte eine Erweiterung des
Systems um zusätzliche Sensortechnologien wie Time-of-Flight-Sensoren oder LiDAR-Module
helfen, die Detailge-nauigkeit weiter zu verbessern und eine robuste Echtzeit-Rekonstruktion
zu ermöglichen. "
author:
- first_name: Sam
full_name: Wiemann, Sam
id: '78421'
last_name: Wiemann
citation:
ama: Wiemann S. Entwicklung und Evaluierung eines multisensorischen Kamera-Setups
zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung mittels Gaussian
Splatting auf einem autonomen Robotersystem. Technische Hochschule Ostwestfalen-Lippe;
2025.
apa: Wiemann, S. (2025). Entwicklung und Evaluierung eines multisensorischen
Kamera-Setups zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung
mittels Gaussian Splatting auf einem autonomen Robotersystem. Technische Hochschule
Ostwestfalen-Lippe.
bjps: 'Wiemann S (2025) Entwicklung und Evaluierung eines multisensorischen
Kamera-Setups zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung
mittels Gaussian Splatting auf einem autonomen Robotersystem. Detmold: Technische
Hochschule Ostwestfalen-Lippe.'
chicago: 'Wiemann, Sam. Entwicklung und Evaluierung eines multisensorischen Kamera-Setups
zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung mittels Gaussian
Splatting auf einem autonomen Robotersystem. Detmold: Technische Hochschule
Ostwestfalen-Lippe, 2025.'
chicago-de: 'Wiemann, Sam. 2025. Entwicklung und Evaluierung eines multisensorischen
Kamera-Setups zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung
mittels Gaussian Splatting auf einem autonomen Robotersystem. Detmold: Technische
Hochschule Ostwestfalen-Lippe.'
din1505-2-1: 'Wiemann, Sam: Entwicklung
und Evaluierung eines multisensorischen Kamera-Setups zur 3D-Raumrekonstruktion
in einer dynamischen Industrieumgebung mittels Gaussian Splatting auf einem autonomen
Robotersystem. Detmold : Technische Hochschule Ostwestfalen-Lippe, 2025'
havard: S. Wiemann, Entwicklung und Evaluierung eines multisensorischen Kamera-Setups
zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung mittels Gaussian
Splatting auf einem autonomen Robotersystem, Technische Hochschule Ostwestfalen-Lippe,
Detmold, 2025.
ieee: 'S. Wiemann, Entwicklung und Evaluierung eines multisensorischen Kamera-Setups
zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung mittels Gaussian
Splatting auf einem autonomen Robotersystem. Detmold: Technische Hochschule
Ostwestfalen-Lippe, 2025.'
mla: Wiemann, Sam. Entwicklung und Evaluierung eines multisensorischen Kamera-Setups
zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung mittels Gaussian
Splatting auf einem autonomen Robotersystem. Technische Hochschule Ostwestfalen-Lippe,
2025.
short: S. Wiemann, Entwicklung und Evaluierung eines multisensorischen Kamera-Setups
zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung mittels Gaussian
Splatting auf einem autonomen Robotersystem, Technische Hochschule Ostwestfalen-Lippe,
Detmold, 2025.
ufg: 'Wiemann, Sam: Entwicklung und Evaluierung eines multisensorischen Kamera-Setups
zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung mittels Gaussian
Splatting auf einem autonomen Robotersystem, Detmold 2025.'
van: 'Wiemann S. Entwicklung und Evaluierung eines multisensorischen Kamera-Setups
zur 3D-Raumrekonstruktion in einer dynamischen Industrieumgebung mittels Gaussian
Splatting auf einem autonomen Robotersystem. Detmold: Technische Hochschule Ostwestfalen-Lippe;
2025.'
date_created: 2025-03-04T09:49:19Z
date_updated: 2025-03-04T15:29:49Z
ddc:
- '000'
department:
- _id: DEP2001
file:
- access_level: open_access
content_type: application/pdf
creator: sa3-8ag
date_created: 2025-03-04T09:48:08Z
date_updated: 2025-03-04T09:48:08Z
file_id: '12647'
file_name: Bachelorarbeit_Sam-Wiemann_15457078_ELSA.pdf
file_size: 40444229
relation: main_file
success: 1
file_date_updated: 2025-03-04T09:48:08Z
has_accepted_license: '1'
keyword:
- 3D-Rekonstruktion
- Gaussian Splatting
- Photogrammetrie
- LiDAR
- autonome Robotik
- digitale Zwillinge
- Industrie 4.0
language:
- iso: ger
oa: '1'
place: Detmold
publication_status: published
publisher: Technische Hochschule Ostwestfalen-Lippe
status: public
supervisor:
- first_name: Alexander
full_name: Kutter, Alexander
id: '83513'
last_name: Kutter
- first_name: Colin
full_name: Behrens, Colin
id: '77083'
last_name: Behrens
title: Entwicklung und Evaluierung eines multisensorischen Kamera-Setups zur 3D-Raumrekonstruktion
in einer dynamischen Industrieumgebung mittels Gaussian Splatting auf einem autonomen
Robotersystem
type: bachelor_thesis
user_id: '83781'
year: '2025'
...
---
_id: '11377'
abstract:
- lang: eng
text: consuming and often performed rather empirically. Efficient optimization
of multiple objectives such as process time, viable cell density, number of operating
steps & cultivation scales, required medium, amount of product as well as
product quality depicts a promising approach. This contribution presents a workflow
which couples uncertainty-based upstream simulation and Bayes optimization using
Gaussian processes. Its application is demonstrated in a simulation case study
for a relevant industrial task in process development, the design of a robust
cell culture expansion process (seed train), meaning that despite uncertainties
and variabilities concerning cell growth, low variations of viable cell density
during the seed train are obtained. Compared to a non-optimized reference seed
train, the optimized process showed much lower deviation rates regarding viable
cell densities (<10% instead of 41.7%) using five or four shake flask scales
and seed train duration could be reduced by 56 h from 576 h to 520 h. Overall,
it is shown that applying Bayes optimization allows for optimization of a multi-objective
optimization function with several optimizable input variables and under a considerable
amount of constraints with a low computational effort. This approach provides
the potential to be used in the form of a decision tool, e.g., for the choice
of an optimal and robust seed train design or for further optimization tasks within
process development.
article_number: '883'
author:
- first_name: Tanja
full_name: Hernández Rodriguez, Tanja
id: '52466'
last_name: Hernández Rodriguez
- first_name: Anton
full_name: Sekulic, Anton
last_name: Sekulic
- first_name: Markus
full_name: Lange-Hegermann, Markus
id: '71761'
last_name: Lange-Hegermann
- first_name: Björn
full_name: Frahm, Björn
id: '45666'
last_name: Frahm
citation:
ama: Hernández Rodriguez T, Sekulic A, Lange-Hegermann M, Frahm B. Designing Robust
Biotechnological Processes Regarding Variabilities Using Multi-Objective Optimization
Applied to a Biopharmaceutical Seed Train Design. Processes. 2022;10(5).
doi:10.3390/pr10050883
apa: Hernández Rodriguez, T., Sekulic, A., Lange-Hegermann, M., & Frahm, B.
(2022). Designing Robust Biotechnological Processes Regarding Variabilities Using
Multi-Objective Optimization Applied to a Biopharmaceutical Seed Train Design.
Processes, 10(5), Article 883. https://doi.org/10.3390/pr10050883
bjps: Hernández Rodriguez T et al. (2022) Designing Robust Biotechnological
Processes Regarding Variabilities Using Multi-Objective Optimization Applied to
a Biopharmaceutical Seed Train Design. Processes 10.
chicago: Hernández Rodriguez, Tanja, Anton Sekulic, Markus Lange-Hegermann, and
Björn Frahm. “Designing Robust Biotechnological Processes Regarding Variabilities
Using Multi-Objective Optimization Applied to a Biopharmaceutical Seed Train Design.”
Processes 10, no. 5 (2022). https://doi.org/10.3390/pr10050883.
chicago-de: Hernández Rodriguez, Tanja, Anton Sekulic, Markus Lange-Hegermann und
Björn Frahm. 2022. Designing Robust Biotechnological Processes Regarding Variabilities
Using Multi-Objective Optimization Applied to a Biopharmaceutical Seed Train Design.
Processes 10, Nr. 5. doi:10.3390/pr10050883,
.
din1505-2-1: 'Hernández Rodriguez, Tanja
; Sekulic, Anton ; Lange-Hegermann,
Markus ; Frahm, Björn: Designing
Robust Biotechnological Processes Regarding Variabilities Using Multi-Objective
Optimization Applied to a Biopharmaceutical Seed Train Design. In: Processes
Bd. 10. Basel, MDPI AG (2022), Nr. 5'
havard: T. Hernández Rodriguez, A. Sekulic, M. Lange-Hegermann, B. Frahm, Designing
Robust Biotechnological Processes Regarding Variabilities Using Multi-Objective
Optimization Applied to a Biopharmaceutical Seed Train Design, Processes. 10 (2022).
ieee: 'T. Hernández Rodriguez, A. Sekulic, M. Lange-Hegermann, and B. Frahm, “Designing
Robust Biotechnological Processes Regarding Variabilities Using Multi-Objective
Optimization Applied to a Biopharmaceutical Seed Train Design,” Processes,
vol. 10, no. 5, Art. no. 883, 2022, doi: 10.3390/pr10050883.'
mla: Hernández Rodriguez, Tanja, et al. “Designing Robust Biotechnological Processes
Regarding Variabilities Using Multi-Objective Optimization Applied to a Biopharmaceutical
Seed Train Design.” Processes, vol. 10, no. 5, 883, 2022, https://doi.org/10.3390/pr10050883.
short: T. Hernández Rodriguez, A. Sekulic, M. Lange-Hegermann, B. Frahm, Processes
10 (2022).
ufg: 'Hernández Rodriguez, Tanja u. a.: Designing Robust Biotechnological
Processes Regarding Variabilities Using Multi-Objective Optimization Applied to
a Biopharmaceutical Seed Train Design, in: Processes 10 (2022), H. 5.'
van: Hernández Rodriguez T, Sekulic A, Lange-Hegermann M, Frahm B. Designing Robust
Biotechnological Processes Regarding Variabilities Using Multi-Objective Optimization
Applied to a Biopharmaceutical Seed Train Design. Processes. 2022;10(5).
date_created: 2024-04-25T13:35:04Z
date_updated: 2024-05-21T09:30:15Z
department:
- _id: DEP4000
doi: 10.3390/pr10050883
intvolume: ' 10'
issue: '5'
keyword:
- Gaussian processes
- Bayes optimization
- Pareto optimization
- multi-objective
- cell culture
- seed train
language:
- iso: eng
place: Basel
publication: Processes
publication_identifier:
eissn:
- 2227-9717
publication_status: published
publisher: MDPI AG
status: public
title: Designing Robust Biotechnological Processes Regarding Variabilities Using Multi-Objective
Optimization Applied to a Biopharmaceutical Seed Train Design
type: scientific_journal_article
user_id: '83781'
volume: 10
year: '2022'
...
---
_id: '10193'
abstract:
- lang: eng
text: Development and optimization of biopharmaceutical production processes with
cell cultures is cost- and time-consuming and often performed rather empirically.
Efficient optimization of multiple objectives such as process time, viable cell
density, number of operating steps & cultivation scales, required medium, amount
of product as well as product quality depicts a promising approach. This contribution
presents a workflow which couples uncertainty-based upstream simulation and Bayes
optimization using Gaussian processes. Its application is demonstrated in a simulation
case study for a relevant industrial task in process development, the design of
a robust cell culture expansion process (seed train), meaning that despite uncertainties
and variabilities concerning cell growth, low variations of viable cell density
during the seed train are obtained. Compared to a non-optimized reference seed
train, the optimized process showed much lower deviation rates regarding viable
cell densities (<10% instead of 41.7%) using five or four shake flask scales and
seed train duration could be reduced by 56 h from 576 h to 520 h. Overall, it
is shown that applying Bayes optimization allows for optimization of a multi-objective
optimization function with several optimizable input variables and under a considerable
amount of constraints with a low computational effort. This approach provides
the potential to be used in the form of a decision tool, e.g., for the choice
of an optimal and robust seed train design or for further optimization tasks within
process development.
author:
- first_name: Tanja
full_name: Hernández Rodriguez, Tanja
id: '52466'
last_name: Hernández Rodriguez
- first_name: Anton
full_name: Sekulic, Anton
last_name: Sekulic
- first_name: Markus
full_name: Lange-Hegermann, Markus
id: '71761'
last_name: Lange-Hegermann
- first_name: Björn
full_name: Frahm, Björn
id: '45666'
last_name: Frahm
citation:
ama: 'Hernández Rodriguez T, Sekulic A, Lange-Hegermann M, Frahm B. Designing robust
biotechnological processes regarding variabilities using multi-objective optimization
applied to a biopharmaceutical seed train design. In: Pörtner R, Möller J, eds.
Bioprocess Systems Engineering Applications in Pharmaceutical Manufacturing.
Vol special issue. Processes : open access journal. MDPI; 2022:21-48. doi:https://doi.org/10.3390/pr10050883'
apa: 'Hernández Rodriguez, T., Sekulic, A., Lange-Hegermann, M., & Frahm, B.
(2022). Designing robust biotechnological processes regarding variabilities using
multi-objective optimization applied to a biopharmaceutical seed train design.
In R. Pörtner & J. Möller (Eds.), Bioprocess Systems Engineering Applications
in Pharmaceutical Manufacturing: Vol. special issue (pp. 21–48). MDPI. https://doi.org/10.3390/pr10050883'
bjps: 'Hernández Rodriguez T et al. (2022) Designing Robust Biotechnological
Processes Regarding Variabilities Using Multi-Objective Optimization Applied to
a Biopharmaceutical Seed Train Design. In Pörtner R and Möller J (eds), Bioprocess
Systems Engineering Applications in Pharmaceutical Manufacturing, vol. special
issue. Basel: MDPI, pp. 21–48.'
chicago: 'Hernández Rodriguez, Tanja, Anton Sekulic, Markus Lange-Hegermann, and
Björn Frahm. “Designing Robust Biotechnological Processes Regarding Variabilities
Using Multi-Objective Optimization Applied to a Biopharmaceutical Seed Train Design.”
In Bioprocess Systems Engineering Applications in Pharmaceutical Manufacturing,
edited by Ralf Pörtner and Johannes Möller, special issue:21–48. Processes : Open
Access Journal. Basel: MDPI, 2022. https://doi.org/10.3390/pr10050883.'
chicago-de: 'Hernández Rodriguez, Tanja, Anton Sekulic, Markus Lange-Hegermann und
Björn Frahm. 2022. Designing robust biotechnological processes regarding variabilities
using multi-objective optimization applied to a biopharmaceutical seed train design.
In: Bioprocess Systems Engineering Applications in Pharmaceutical Manufacturing,
hg. von Ralf Pörtner und Johannes Möller, special issue:21–48. Processes : open
access journal. Basel: MDPI. doi:https://doi.org/10.3390/pr10050883,
.'
din1505-2-1: 'Hernández Rodriguez, Tanja
; Sekulic, Anton ; Lange-Hegermann,
Markus ; Frahm, Björn: Designing
robust biotechnological processes regarding variabilities using multi-objective
optimization applied to a biopharmaceutical seed train design. In: Pörtner,
R. ; Möller, J. (Hrsg.):
Bioprocess Systems Engineering Applications in Pharmaceutical Manufacturing,
Processes : open access journal. Bd. special issue. Basel : MDPI, 2022,
S. 21–48'
havard: 'T. Hernández Rodriguez, A. Sekulic, M. Lange-Hegermann, B. Frahm, Designing
robust biotechnological processes regarding variabilities using multi-objective
optimization applied to a biopharmaceutical seed train design, in: R. Pörtner,
J. Möller (Eds.), Bioprocess Systems Engineering Applications in Pharmaceutical
Manufacturing, MDPI, Basel, 2022: pp. 21–48.'
ieee: 'T. Hernández Rodriguez, A. Sekulic, M. Lange-Hegermann, and B. Frahm, “Designing
robust biotechnological processes regarding variabilities using multi-objective
optimization applied to a biopharmaceutical seed train design,” in Bioprocess
Systems Engineering Applications in Pharmaceutical Manufacturing, vol. special
issue, R. Pörtner and J. Möller, Eds. Basel: MDPI, 2022, pp. 21–48. doi: https://doi.org/10.3390/pr10050883.'
mla: Hernández Rodriguez, Tanja, et al. “Designing Robust Biotechnological Processes
Regarding Variabilities Using Multi-Objective Optimization Applied to a Biopharmaceutical
Seed Train Design.” Bioprocess Systems Engineering Applications in Pharmaceutical
Manufacturing, edited by Ralf Pörtner and Johannes Möller, vol. special issue,
MDPI, 2022, pp. 21–48, https://doi.org/10.3390/pr10050883.
short: 'T. Hernández Rodriguez, A. Sekulic, M. Lange-Hegermann, B. Frahm, in: R.
Pörtner, J. Möller (Eds.), Bioprocess Systems Engineering Applications in Pharmaceutical
Manufacturing, MDPI, Basel, 2022, pp. 21–48.'
ufg: 'Hernández Rodriguez, Tanja u. a.: Designing robust biotechnological
processes regarding variabilities using multi-objective optimization applied to
a biopharmaceutical seed train design, in: Pörtner, Ralf/Möller, Johannes (Hgg.):
Bioprocess Systems Engineering Applications in Pharmaceutical Manufacturing, Band
special issue, Basel 2022 (Processes : open access journal), S. 21–48.'
van: 'Hernández Rodriguez T, Sekulic A, Lange-Hegermann M, Frahm B. Designing robust
biotechnological processes regarding variabilities using multi-objective optimization
applied to a biopharmaceutical seed train design. In: Pörtner R, Möller J, editors.
Bioprocess Systems Engineering Applications in Pharmaceutical Manufacturing. Basel:
MDPI; 2022. p. 21–48. (Processes : open access journal; vol. special issue).'
date_created: 2023-08-08T12:58:36Z
date_updated: 2023-08-16T09:24:16Z
department:
- _id: DEP4000
doi: https://doi.org/10.3390/pr10050883
editor:
- first_name: Ralf
full_name: Pörtner, Ralf
last_name: Pörtner
- first_name: Johannes
full_name: Möller, Johannes
last_name: Möller
keyword:
- Gaussian processes
- Bayes optimization
- Pareto optimization
- multi-objective
- cell culture
- seed train
language:
- iso: eng
page: 21-48
place: Basel
publication: Bioprocess Systems Engineering Applications in Pharmaceutical Manufacturing
publication_identifier:
eisbn:
- 978-3-0365-5209-5
eissn:
- 2227-9717
isbn:
- 978-3-0365-5210-1
publication_status: published
publisher: MDPI
quality_controlled: '1'
series_title: 'Processes : open access journal'
status: public
title: Designing robust biotechnological processes regarding variabilities using multi-objective
optimization applied to a biopharmaceutical seed train design
type: book_chapter
user_id: '83781'
volume: special issue
year: '2022'
...
---
_id: '12812'
abstract:
- lang: eng
text: Discerning unexpected from expected data patterns is the key challenge of
anomaly detection. Although a multitude of solutions has been applied to this
modern Industry 4.0 problem, it remains an open research issue to identify the
key characteristics subjacent to an anomaly, sc. generate hypothesis as to why
they appear. In recent years, machine learning models have been regarded as universal
solution for a wide range of problems. While most of them suffer from non-self-explanatory
representations, Gaussian Processes (GPs) deliver interpretable and robust statistical
data models, which are able to cope with unreliable, noisy, or partially missing
data. Thus, we regard them as a suitable solution for detecting and appropriately
representing anomalies and their respective characteristics. In this position
paper, we discuss the problem of automatic and interpretable anomaly detection
by means of GPs. That is, we elaborate on why GPs are well suited for anomaly
detection and what the current challenges are when applying these probabilistic
models to large-scale production data.
author:
- first_name: Fabian
full_name: Berns, Fabian
last_name: Berns
- first_name: Markus
full_name: Lange-Hegermann, Markus
id: '71761'
last_name: Lange-Hegermann
- first_name: Christian
full_name: Beecks, Christian
last_name: Beecks
citation:
ama: Berns F, Lange-Hegermann M, Beecks C. Towards Gaussian Processes for Automatic
and Interpretable Anomaly Detection in Industry 4.0. (Panetto H, Madani K,
Smirnov A, eds.). SCITEPRESS - Science and Technology Publications; 2020:87-92.
doi:10.5220/0010130300870092
apa: Berns, F., Lange-Hegermann, M., & Beecks, C. (2020). Towards Gaussian Processes
for Automatic and Interpretable Anomaly Detection in Industry 4.0. In H. Panetto,
K. Madani, & A. Smirnov (Eds.), Proceedings of the International Conference
on Innovative Intelligent Industrial Production and Logistics IN4PL - Volume 1
(pp. 87–92). SCITEPRESS - Science and Technology Publications. https://doi.org/10.5220/0010130300870092
bjps: Berns F, Lange-Hegermann M and Beecks C (2020) Towards Gaussian
Processes for Automatic and Interpretable Anomaly Detection in Industry 4.0,
Panetto H, Madani K and Smirnov A (eds). SCITEPRESS - Science and Technology Publications.
chicago: Berns, Fabian, Markus Lange-Hegermann, and Christian Beecks. Towards
Gaussian Processes for Automatic and Interpretable Anomaly Detection in Industry
4.0. Edited by H. Panetto, K. Madani, and A. Smirnov. Proceedings of the
International Conference on Innovative Intelligent Industrial Production and Logistics
IN4PL - Volume 1. SCITEPRESS - Science and Technology Publications, 2020.
https://doi.org/10.5220/0010130300870092.
chicago-de: Berns, Fabian, Markus Lange-Hegermann und Christian Beecks. 2020. Towards
Gaussian Processes for Automatic and Interpretable Anomaly Detection in Industry
4.0. Hg. von H. Panetto, K. Madani, und A. Smirnov. Proceedings of the
International Conference on Innovative Intelligent Industrial Production and Logistics
IN4PL - Volume 1. SCITEPRESS - Science and Technology Publications. doi:10.5220/0010130300870092,
.
din1505-2-1: 'Berns, Fabian ; Lange-Hegermann, Markus ; Beecks,
Christian ; Panetto, H. ;
Madani, K. ; Smirnov,
A. (Hrsg.): Towards Gaussian Processes for Automatic and Interpretable
Anomaly Detection in Industry 4.0 : SCITEPRESS - Science and Technology Publications,
2020'
havard: F. Berns, M. Lange-Hegermann, C. Beecks, Towards Gaussian Processes for
Automatic and Interpretable Anomaly Detection in Industry 4.0, SCITEPRESS - Science
and Technology Publications, 2020.
ieee: 'F. Berns, M. Lange-Hegermann, and C. Beecks, Towards Gaussian Processes
for Automatic and Interpretable Anomaly Detection in Industry 4.0. SCITEPRESS
- Science and Technology Publications, 2020, pp. 87–92. doi: 10.5220/0010130300870092.'
mla: Berns, Fabian, et al. “Towards Gaussian Processes for Automatic and Interpretable
Anomaly Detection in Industry 4.0.” Proceedings of the International Conference
on Innovative Intelligent Industrial Production and Logistics IN4PL - Volume 1,
edited by H. Panetto et al., SCITEPRESS - Science and Technology Publications,
2020, pp. 87–92, https://doi.org/10.5220/0010130300870092.
short: F. Berns, M. Lange-Hegermann, C. Beecks, Towards Gaussian Processes for Automatic
and Interpretable Anomaly Detection in Industry 4.0, SCITEPRESS - Science and
Technology Publications, 2020.
ufg: 'Berns, Fabian/Lange-Hegermann, Markus/Beecks, Christian: Towards Gaussian
Processes for Automatic and Interpretable Anomaly Detection in Industry 4.0, hg.
von Panetto, H./Madani, K./Smirnov, A., o. O. 2020.'
van: Berns F, Lange-Hegermann M, Beecks C. Towards Gaussian Processes for Automatic
and Interpretable Anomaly Detection in Industry 4.0. Panetto H, Madani K, Smirnov
A, editors. Proceedings of the International Conference on Innovative Intelligent
Industrial Production and Logistics IN4PL - Volume 1. SCITEPRESS - Science and
Technology Publications; 2020.
conference:
end_date: 2020-11-04
location: Budapest, HUNGARY
name: International Conference on Innovative Intelligent Industrial Production and
Logistics (IN4PL)
start_date: 2020-11-02
date_created: 2025-04-17T06:20:07Z
date_updated: 2025-06-26T13:31:38Z
department:
- _id: DEP5000
doi: 10.5220/0010130300870092
editor:
- first_name: H.
full_name: Panetto, H.
last_name: Panetto
- first_name: K.
full_name: Madani, K.
last_name: Madani
- first_name: A.
full_name: Smirnov, A.
last_name: Smirnov
keyword:
- Anomaly Detection
- Gaussian Processes
- Explainable Machine Learning
- Industry 4.0
language:
- iso: eng
page: 87-92
publication: ' Proceedings of the International Conference on Innovative Intelligent
Industrial Production and Logistics IN4PL - Volume 1'
publication_identifier:
isbn:
- 978-989-758-476-3
publication_status: published
publisher: SCITEPRESS - Science and Technology Publications
status: public
title: Towards Gaussian Processes for Automatic and Interpretable Anomaly Detection
in Industry 4.0
type: conference_editor_article
user_id: '83781'
year: '2020'
...
---
_id: '2008'
abstract:
- lang: eng
text: "We concentrate our research activities on the multivariate feature selection,
which is one important part of many machine learning tasks. In partucular, Linear
Discriminant Analysis [1] belongs to the state-of-the-art methods for the multivariate
analysis. From the theoretical point of view, it is the well-known fact that LDA
is best suitable in the case the features are Gaussian distributed.\r\nIn the
theoretical part of the presented paper, we analyse the properties of the multivariate
discriminant analysis with respect to the feature selection. In this context,
we consider a binary supervised learning task and assume that the features are
Gaussian distributed. The discriminant analysis solves the mentioned supervised
learning task by maximising of the discriminant value, calculated for the linear
combination of the features.\r\nThe initial LDA solution a 2 Rd is considered
for all given features from the feature space X \x1A Rd. The corresponding discriminant
is calculated by the formula:\r\nd(a; x1, . . . , xd) := (μ+ − μ−)2\r\n\e2+\r\n+
\e2−\r\n,\r\nwhere μ+/− are projected class means and \e2 +/− are projected class
variances (with respect to a). We proof several propositions with the aim to find
subsets of the features having higher discriminant value as original d(a; x1,
. . . , xd). For the suitability in the real world settings, here we are interested
in fast searching for such subsets.\r\nThe performance of the mentioned propositions
is examined experimentally on datasets from UCI repository [2]. Several application
scenarien will be discussed and tested on the datasets. In addition, tests show
that the performance can be achieved also in the case the features are not Gaussian
distributed."
author:
- first_name: Helene
full_name: Dörksen, Helene
id: '46416'
last_name: Dörksen
- first_name: Volker
full_name: Lohweg, Volker
id: '1804'
last_name: Lohweg
orcid: 0000-0002-3325-7887
citation:
ama: 'Dörksen H, Lohweg V. Multivariate Gaussian Feature Selection. . In: European
Conference on Data Analysis (ECDA2018). Paderborn, Germany; 2018.'
apa: Dörksen, H., & Lohweg, V. (2018). Multivariate Gaussian Feature Selection.
. In European Conference on Data Analysis (ECDA2018). Paderborn, Germany.
bjps: Dörksen H and Lohweg V (2018) Multivariate Gaussian Feature Selection.
. European Conference on Data Analysis (ECDA2018). Paderborn, Germany.
chicago: Dörksen, Helene, and Volker Lohweg. “Multivariate Gaussian Feature Selection.
.” In European Conference on Data Analysis (ECDA2018). Paderborn, Germany,
2018.
chicago-de: 'Dörksen, Helene und Volker Lohweg. 2018. Multivariate Gaussian Feature
Selection. . In: European Conference on Data Analysis (ECDA2018). Paderborn,
Germany.'
din1505-2-1: 'Dörksen, Helene ; Lohweg, Volker: Multivariate Gaussian
Feature Selection. . In: European Conference on Data Analysis (ECDA2018).
Paderborn, Germany, 2018'
havard: 'H. Dörksen, V. Lohweg, Multivariate Gaussian Feature Selection. , in: European
Conference on Data Analysis (ECDA2018), Paderborn, Germany, 2018.'
ieee: H. Dörksen and V. Lohweg, “Multivariate Gaussian Feature Selection. ,” in
European Conference on Data Analysis (ECDA2018), Paderborn, 2018.
mla: Dörksen, Helene, and Volker Lohweg. “Multivariate Gaussian Feature Selection.
.” European Conference on Data Analysis (ECDA2018), 2018.
short: 'H. Dörksen, V. Lohweg, in: European Conference on Data Analysis (ECDA2018),
Paderborn, Germany, 2018.'
ufg: 'Dörksen, Helene/Lohweg, Volker (2018): Multivariate Gaussian Feature
Selection. , in: European Conference on Data Analysis (ECDA2018), Paderborn,
Germany.'
van: 'Dörksen H, Lohweg V. Multivariate Gaussian Feature Selection. . In: European
Conference on Data Analysis (ECDA2018). Paderborn, Germany; 2018.'
conference:
end_date: 2018-07-06
location: Paderborn
name: European Conference on Data Analysis
start_date: 2018-07-04
date_created: 2019-11-25T08:35:48Z
date_updated: 2023-03-15T13:49:38Z
department:
- _id: DEP5023
keyword:
- multivariate feature selection
- Gaussian distribution
- linear discriminant analysis
language:
- iso: eng
place: Paderborn, Germany
publication: European Conference on Data Analysis (ECDA2018)
status: public
title: 'Multivariate Gaussian Feature Selection. '
type: conference
user_id: '15514'
year: 2018
...