---
_id: '63498'
author:
- first_name: Wilhelm
full_name: Kirchgässner, Wilhelm
last_name: Kirchgässner
- first_name: Nikolas
full_name: Förster, Nikolas
last_name: Förster
- first_name: Till
full_name: Piepenbrock, Till
last_name: Piepenbrock
- first_name: Oliver
full_name: Schweins, Oliver
last_name: Schweins
- first_name: Oliver
full_name: Wallscheid, Oliver
last_name: Wallscheid
citation:
ama: 'Kirchgässner W, Förster N, Piepenbrock T, Schweins O, Wallscheid O. HARDCORE:
H-Field and Power Loss Estimation for Arbitrary Waveforms With Residual, Dilated
Convolutional Neural Networks in Ferrite Cores. IEEE Transactions on Power
Electronics. 2025;40(2):3326-3335. doi:10.1109/TPEL.2024.3488174'
apa: 'Kirchgässner, W., Förster, N., Piepenbrock, T., Schweins, O., & Wallscheid,
O. (2025). HARDCORE: H-Field and Power Loss Estimation for Arbitrary Waveforms
With Residual, Dilated Convolutional Neural Networks in Ferrite Cores. IEEE
Transactions on Power Electronics, 40(2), 3326–3335. https://doi.org/10.1109/TPEL.2024.3488174'
bibtex: '@article{Kirchgässner_Förster_Piepenbrock_Schweins_Wallscheid_2025, title={HARDCORE:
H-Field and Power Loss Estimation for Arbitrary Waveforms With Residual, Dilated
Convolutional Neural Networks in Ferrite Cores}, volume={40}, DOI={10.1109/TPEL.2024.3488174},
number={2}, journal={IEEE Transactions on Power Electronics}, author={Kirchgässner,
Wilhelm and Förster, Nikolas and Piepenbrock, Till and Schweins, Oliver and Wallscheid,
Oliver}, year={2025}, pages={3326–3335} }'
chicago: 'Kirchgässner, Wilhelm, Nikolas Förster, Till Piepenbrock, Oliver Schweins,
and Oliver Wallscheid. “HARDCORE: H-Field and Power Loss Estimation for Arbitrary
Waveforms With Residual, Dilated Convolutional Neural Networks in Ferrite Cores.”
IEEE Transactions on Power Electronics 40, no. 2 (2025): 3326–35. https://doi.org/10.1109/TPEL.2024.3488174.'
ieee: 'W. Kirchgässner, N. Förster, T. Piepenbrock, O. Schweins, and O. Wallscheid,
“HARDCORE: H-Field and Power Loss Estimation for Arbitrary Waveforms With Residual,
Dilated Convolutional Neural Networks in Ferrite Cores,” IEEE Transactions
on Power Electronics, vol. 40, no. 2, pp. 3326–3335, 2025, doi: 10.1109/TPEL.2024.3488174.'
mla: 'Kirchgässner, Wilhelm, et al. “HARDCORE: H-Field and Power Loss Estimation
for Arbitrary Waveforms With Residual, Dilated Convolutional Neural Networks in
Ferrite Cores.” IEEE Transactions on Power Electronics, vol. 40, no. 2,
2025, pp. 3326–35, doi:10.1109/TPEL.2024.3488174.'
short: W. Kirchgässner, N. Förster, T. Piepenbrock, O. Schweins, O. Wallscheid,
IEEE Transactions on Power Electronics 40 (2025) 3326–3335.
date_created: 2026-01-06T08:07:13Z
date_updated: 2026-01-06T08:08:01Z
department:
- _id: '52'
doi: 10.1109/TPEL.2024.3488174
intvolume: ' 40'
issue: '2'
keyword:
- Mathematical models
- Estimation
- Data models
- Convolutional neural networks
- Accuracy
- Magnetic hysteresis
- Magnetic cores
- Temperature measurement
- Magnetic domains
- Temperature distribution
- Convolutional neural network (CNN)
- machine learning (ML)
- magnetics
page: 3326-3335
publication: IEEE Transactions on Power Electronics
status: public
title: 'HARDCORE: H-Field and Power Loss Estimation for Arbitrary Waveforms With Residual,
Dilated Convolutional Neural Networks in Ferrite Cores'
type: journal_article
user_id: '83383'
volume: 40
year: '2025'
...
---
_id: '35620'
abstract:
- lang: eng
text: Deep learning models fuel many modern decision support systems, because they
typically provide high predictive performance. Among other domains, deep learning
is used in real-estate appraisal, where it allows to extend the analysis from
hard facts only (e.g., size, age) to also consider more implicit information about
the location or appearance of houses in the form of image data. However, one downside
of deep learning models is their intransparent mechanic of decision making, which
leads to a trade-off between accuracy and interpretability. This limits their
applicability for tasks where a justification of the decision is necessary. Therefore,
in this paper, we first combine different perspectives on interpretability into
a multi-dimensional framework for a socio-technical perspective on explainable
artificial intelligence. Second, we measure the performance gains of using multi-view
deep learning which leverages additional image data (satellite images) for real
estate appraisal. Third, we propose and test a novel post-hoc explainability method
called Grad-Ram. This modified version of Grad-Cam mitigates the intransparency
of convolutional neural networks (CNNs) for predicting continuous outcome variables.
With this, we try to reduce the accuracy-interpretability trade-off of multi-view
deep learning models. Our proposed network architecture outperforms traditional
hedonic regression models by 34% in terms of MAE. Furthermore, we find that the
used satellite images are the second most important predictor after square feet
in our model and that the network learns interpretable patterns about the neighborhood
structure and density.
article_type: original
author:
- first_name: Jan-Peter
full_name: Kucklick, Jan-Peter
id: '77066'
last_name: Kucklick
- first_name: Oliver
full_name: Müller, Oliver
id: '72849'
last_name: Müller
citation:
ama: 'Kucklick J-P, Müller O. Tackling the Accuracy–Interpretability Trade-off:
Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal.
ACM Transactions on Management Information Systems. Published online 2022.
doi:10.1145/3567430'
apa: 'Kucklick, J.-P., & Müller, O. (2022). Tackling the Accuracy–Interpretability
Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate
Appraisal. ACM Transactions on Management Information Systems. https://doi.org/10.1145/3567430'
bibtex: '@article{Kucklick_Müller_2022, title={Tackling the Accuracy–Interpretability
Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate
Appraisal}, DOI={10.1145/3567430},
journal={ACM Transactions on Management Information Systems}, publisher={Association
for Computing Machinery (ACM)}, author={Kucklick, Jan-Peter and Müller, Oliver},
year={2022} }'
chicago: 'Kucklick, Jan-Peter, and Oliver Müller. “Tackling the Accuracy–Interpretability
Trade-off: Interpretable Deep Learning Models for Satellite Image-Based Real Estate
Appraisal.” ACM Transactions on Management Information Systems, 2022. https://doi.org/10.1145/3567430.'
ieee: 'J.-P. Kucklick and O. Müller, “Tackling the Accuracy–Interpretability Trade-off:
Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal,”
ACM Transactions on Management Information Systems, 2022, doi: 10.1145/3567430.'
mla: 'Kucklick, Jan-Peter, and Oliver Müller. “Tackling the Accuracy–Interpretability
Trade-off: Interpretable Deep Learning Models for Satellite Image-Based Real Estate
Appraisal.” ACM Transactions on Management Information Systems, Association
for Computing Machinery (ACM), 2022, doi:10.1145/3567430.'
short: J.-P. Kucklick, O. Müller, ACM Transactions on Management Information Systems
(2022).
date_created: 2023-01-10T05:16:02Z
date_updated: 2023-01-10T05:20:18Z
department:
- _id: '195'
- _id: '196'
doi: 10.1145/3567430
keyword:
- Interpretability
- Convolutional Neural Network
- Accuracy-Interpretability Trade-Of
- Real Estate Appraisal
- Hedonic Pricing
- Grad-Ram
language:
- iso: eng
main_file_link:
- url: https://dl.acm.org/doi/pdf/10.1145/3567430
publication: ACM Transactions on Management Information Systems
publication_identifier:
issn:
- 2158-656X
- 2158-6578
publication_status: published
publisher: Association for Computing Machinery (ACM)
status: public
title: 'Tackling the Accuracy–Interpretability Trade-off: Interpretable Deep Learning
Models for Satellite Image-based Real Estate Appraisal'
type: journal_article
user_id: '77066'
year: '2022'
...