Analysis of Chromatographic Data using the Probabilistic PARAFAC2

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

PARAFAC2 is a widely applicable method often used for analyzing multi-way chromatographic data. We recently proposed a probabilistic framework for PARAFAC2[1]. The probabilistic formulations allow for a principled way of determining the number of latent components as well as modeling heteroscedastic noise. In this work we present a summary of the probabilistic PARAFAC2 models and their properties by revisiting the previous results of the analyzed data sets in a concise fashion.
Original languageEnglish
Title of host publicationProceedings of Second Workshop on Machine Learning and the Physical Sciences
Number of pages5
Publication date2019
Publication statusPublished - 2019
Event33rd Conference on Neural Information Processing Systems - Vancouver Convention Centre, Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019
Conference number: 33
https://nips.cc/Conferences/2019/

Conference

Conference33rd Conference on Neural Information Processing Systems
Number33
LocationVancouver Convention Centre
CountryCanada
CityVancouver
Period08/12/201914/12/2019
Internet address

Cite this

Jørgensen, P. J. H., Nielsen, S. F. V., Hinrich, J. L., Schmidt, M. N., Madsen, K. H., & Mørup, M. (2019). Analysis of Chromatographic Data using the Probabilistic PARAFAC2. In Proceedings of Second Workshop on Machine Learning and the Physical Sciences