---
_id: '13475'
abstract:
- lang: eng
text: In the context of data-driven bioprocess modeling, selecting appropriate regression
models remains a critical challenge. This is especially the case when dealing
with time-dependent process dynamics and complex measurement data. The practical
relevance of this study lies in its critical assessment of the application constraints
associated with multivariate linear regression models in bioprocess monitoring
of cell culture processes. The applicability of Partial Least Squares and Ridge
regression was evaluated for different cultivation phases. The results emphasize
that no single linear modeling approach is universally suitable for capturing
the complex behavior of mammalian cell cultures. This is why we present an enhanced
segmented modeling approach by learning the optimal transition point from data
and introducing a gradual model switch, allowing for smoother and more robust
adaptation to process dynamics. This segmented model led to improved predictive
performance compared to single-model regression across the entire process duration.
Nevertheless, the heterogeneity of the 11 mammalian cell culture datasets used
in this study posed significant challenges, with the best-performing models achieving
prediction error of around 0.31 of the average offline viable cell density. These
results underline the potential of phase-adaptive modeling, while also emphasizing
the need for further optimization to robustly handle diverse bioprocess conditions.
author:
- first_name: Selina
full_name: Uhlendorff, Selina
id: '68713'
last_name: Uhlendorff
orcid: https://orcid.org/0000-0002-0502-8032
- first_name: Tatsiana
full_name: Burankova, Tatsiana
last_name: Burankova
- first_name: Katharina
full_name: Dahlmann, Katharina
last_name: Dahlmann
- first_name: Björn
full_name: Frahm, Björn
id: '45666'
last_name: Frahm
- first_name: Miriam
full_name: Pein-Hackelbusch, Miriam
id: '64952'
last_name: Pein-Hackelbusch
orcid: 0000-0002-7920-0595
citation:
ama: Uhlendorff S, Burankova T, Dahlmann K, Frahm B, Pein-Hackelbusch M. Application
Constraints of Linear Multivariate Regression Models for Dielectric Spectroscopy
in Inline Bioreactor Viable Cell Analysis. IEEE; 2026:34-39. doi:10.1109/iwis69004.2025.11339388
apa: Uhlendorff, S., Burankova, T., Dahlmann, K., Frahm, B., & Pein-Hackelbusch,
M. (2026). Application Constraints of Linear Multivariate Regression Models for
Dielectric Spectroscopy in Inline Bioreactor Viable Cell Analysis. In 2025
International Workshop on Impedance Spectroscopy (IWIS) (pp. 34–39). IEEE.
https://doi.org/10.1109/iwis69004.2025.11339388
bjps: 'Uhlendorff S et al. (2026) Application Constraints of Linear
Multivariate Regression Models for Dielectric Spectroscopy in Inline Bioreactor
Viable Cell Analysis. New York: IEEE.'
chicago: 'Uhlendorff, Selina, Tatsiana Burankova, Katharina Dahlmann, Björn Frahm,
and Miriam Pein-Hackelbusch. Application Constraints of Linear Multivariate
Regression Models for Dielectric Spectroscopy in Inline Bioreactor Viable Cell
Analysis. 2025 International Workshop on Impedance Spectroscopy (IWIS).
New York: IEEE, 2026. https://doi.org/10.1109/iwis69004.2025.11339388.'
chicago-de: 'Uhlendorff, Selina, Tatsiana Burankova, Katharina Dahlmann, Björn Frahm
und Miriam Pein-Hackelbusch. 2026. Application Constraints of Linear Multivariate
Regression Models for Dielectric Spectroscopy in Inline Bioreactor Viable Cell
Analysis. 2025 International Workshop on Impedance Spectroscopy (IWIS).
New York: IEEE. doi:10.1109/iwis69004.2025.11339388,
.'
din1505-2-1: 'Uhlendorff, Selina ;
Burankova, Tatsiana ; Dahlmann,
Katharina ; Frahm, Björn
; Pein-Hackelbusch, Miriam: Application
Constraints of Linear Multivariate Regression Models for Dielectric Spectroscopy
in Inline Bioreactor Viable Cell Analysis. New York : IEEE, 2026'
havard: S. Uhlendorff, T. Burankova, K. Dahlmann, B. Frahm, M. Pein-Hackelbusch,
Application Constraints of Linear Multivariate Regression Models for Dielectric
Spectroscopy in Inline Bioreactor Viable Cell Analysis, IEEE, New York, 2026.
ieee: 'S. Uhlendorff, T. Burankova, K. Dahlmann, B. Frahm, and M. Pein-Hackelbusch,
Application Constraints of Linear Multivariate Regression Models for Dielectric
Spectroscopy in Inline Bioreactor Viable Cell Analysis. New York: IEEE, 2026,
pp. 34–39. doi: 10.1109/iwis69004.2025.11339388.'
mla: Uhlendorff, Selina, et al. “Application Constraints of Linear Multivariate
Regression Models for Dielectric Spectroscopy in Inline Bioreactor Viable Cell
Analysis.” 2025 International Workshop on Impedance Spectroscopy (IWIS),
IEEE, 2026, pp. 34–39, https://doi.org/10.1109/iwis69004.2025.11339388.
short: S. Uhlendorff, T. Burankova, K. Dahlmann, B. Frahm, M. Pein-Hackelbusch,
Application Constraints of Linear Multivariate Regression Models for Dielectric
Spectroscopy in Inline Bioreactor Viable Cell Analysis, IEEE, New York, 2026.
ufg: 'Uhlendorff, Selina u. a.: Application Constraints of Linear Multivariate
Regression Models for Dielectric Spectroscopy in Inline Bioreactor Viable Cell
Analysis, New York 2026.'
van: 'Uhlendorff S, Burankova T, Dahlmann K, Frahm B, Pein-Hackelbusch M. Application
Constraints of Linear Multivariate Regression Models for Dielectric Spectroscopy
in Inline Bioreactor Viable Cell Analysis. 2025 International Workshop on Impedance
Spectroscopy (IWIS). New York: IEEE; 2026.'
conference:
end_date: 2025-09-26
location: Chemnitz
name: 2025 International Workshop on Impedance Spectroscopy (IWIS)
start_date: 2025-09-23
date_created: 2026-03-06T08:52:51Z
date_updated: 2026-04-08T11:28:18Z
department:
- _id: DEP4028
doi: 10.1109/iwis69004.2025.11339388
keyword:
- cell culture
- impedance spectroscopy
- partial least squares
- ridge regression
language:
- iso: eng
page: 34-39
place: New York
publication: 2025 International Workshop on Impedance Spectroscopy (IWIS)
publication_identifier:
eisbn:
- 979-8-3315-9322-3
isbn:
- 979-8-3315-9323-0
publication_status: published
publisher: IEEE
status: public
title: Application Constraints of Linear Multivariate Regression Models for Dielectric
Spectroscopy in Inline Bioreactor Viable Cell Analysis
type: conference_editor_article
user_id: '83778'
year: '2026'
...