Imperial College London
Portrait Picture

Professor Norbert Hoffmann

Faculty of Engineering, Department of Mechanical Engineering

Visiting Professor
 
 
 
//

Contact

 

n.hoffmann

 
 
//

Location

 

557City and Guilds BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Stender:2021:10.3397/in-2021-2342,
author = {Stender, M and Wedler, M and Hoffmann, N and Adams, C},
doi = {10.3397/in-2021-2342},
journal = {INTER-NOISE and NOISE-CON Congress and Conference Proceedings},
pages = {3223--3234},
title = {Explainable machine learning: A case study on impedance tube measurements},
url = {http://dx.doi.org/10.3397/in-2021-2342},
volume = {263},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - <jats:p>Machine learning (ML) techniques allow for finding hidden patterns and signatures in data. Currently, these methods are gaining increased interest in engineering in general and in vibroacoustics in particular. Although ML methods are successfully applied, it is hardly understood how these black box-type methods make their decisions. Explainable machine learning aims at overcoming this issue by deepening the understanding of the decision-making process through perturbation-based model diagnosis. This paper introduces machine learning methods and reviews recent techniques for explainability and interpretability. These methods are exemplified on sound absorption coefficient spectra of one sound absorbing foam material measured in an impedance tube. Variances of the absorption coefficient measurements as a function of the specimen thickness and the operator are modeled by univariate and multivariate machine learning models. In order to identify the driving patterns, i.e. how and in which frequency regime the measurements are affected by the setup specifications, Shapley additive explanations are derived for the ML models. It is demonstrated how explaining machine learning models can be used to discover and express complicated relations in experimental data, thereby paving the way to novel knowledge discovery strategies in evidence-based modeling.</jats:p>
AU  - Stender,M
AU  - Wedler,M
AU  - Hoffmann,N
AU  - Adams,C
DO  - 10.3397/in-2021-2342
EP  - 3234
PY  - 2021///
SN  - 0736-2935
SP  - 3223
TI  - Explainable machine learning: A case study on impedance tube measurements
T2  - INTER-NOISE and NOISE-CON Congress and Conference Proceedings
UR  - http://dx.doi.org/10.3397/in-2021-2342
VL  - 263
ER  -
Download