loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Katrin Bohnsack ; Alexander Engelsberger ; Marika Kaden and Thomas Villmann

Affiliation: Saxon Institute for Computational Intelligence and Machine Learning, University of Applied Sciences Mittweida, Technikumplatz 17, 09648 Mittweida, Germany

Keyword(s): Machine Learning, Embedding, Dissimilarity Representation, Graph Kernels, Structured Data, Small Molecules.

Abstract: We present an approach to efficiently embed complex data objects from the chem- and bioinformatics domain like graph structures into Euclidean vector spaces such that those data bases can be handled by machine learning models. The method is denoted as sensoric response principle (SRP). It uses a small subset of objects serving as so-called sensors. Only for these sensors, the computationally demanding dissimilarity calculations, e.g. graph kernel computations, have to be executed and the resulting response values are used to generate the object embedding into an Euclidean representation space. Thus, the SRP avoids to calculate all object dissimilarities for embedding, which usually is computationally costly due to the complex proximity measures in use. Particularly, we consider strategies to determine the number of sensors for an appropriate embedding as well as selection strategies for SRP. Finally, the quality of the embedding is evaluated w.r.t. to the preservation of the original object relations in the embedding space. The SRP can be used for unsupervised and supervised machine learning. We demonstrate the ability of the approach for classification learning in context of an interpretable machine learning classifier. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.118.144.98

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Bohnsack, K.; Engelsberger, A.; Kaden, M. and Villmann, T. (2023). Efficient Representation of Biochemical Structures for Supervised and Unsupervised Machine Learning Models Using Multi-Sensoric Embeddings. In Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - BIOINFORMATICS; ISBN 978-989-758-631-6; ISSN 2184-4305, SciTePress, pages 59-69. DOI: 10.5220/0011644000003414

@conference{bioinformatics23,
author={Katrin Bohnsack. and Alexander Engelsberger. and Marika Kaden. and Thomas Villmann.},
title={Efficient Representation of Biochemical Structures for Supervised and Unsupervised Machine Learning Models Using Multi-Sensoric Embeddings},
booktitle={Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - BIOINFORMATICS},
year={2023},
pages={59-69},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011644000003414},
isbn={978-989-758-631-6},
issn={2184-4305},
}

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - BIOINFORMATICS
TI - Efficient Representation of Biochemical Structures for Supervised and Unsupervised Machine Learning Models Using Multi-Sensoric Embeddings
SN - 978-989-758-631-6
IS - 2184-4305
AU - Bohnsack, K.
AU - Engelsberger, A.
AU - Kaden, M.
AU - Villmann, T.
PY - 2023
SP - 59
EP - 69
DO - 10.5220/0011644000003414
PB - SciTePress