Distance-based clustering challenges for unbiased benchmarking studies
Abstract Benchmark datasets with predefined cluster structures and high-dimensional biomedical datasets outline the challenges of cluster analysis: clustering algorithms are limited in their clustering ability in the presence of clusters defining distance-based structures resulting in a biased clust...
Guardado en:
Autor principal: | |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/80c3566d0abb42cbb16bd430d6a3c752 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:80c3566d0abb42cbb16bd430d6a3c752 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:80c3566d0abb42cbb16bd430d6a3c7522021-12-02T18:14:08ZDistance-based clustering challenges for unbiased benchmarking studies10.1038/s41598-021-98126-12045-2322https://doaj.org/article/80c3566d0abb42cbb16bd430d6a3c7522021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98126-1https://doaj.org/toc/2045-2322Abstract Benchmark datasets with predefined cluster structures and high-dimensional biomedical datasets outline the challenges of cluster analysis: clustering algorithms are limited in their clustering ability in the presence of clusters defining distance-based structures resulting in a biased clustering solution. Data sets might not have cluster structures. Clustering yields arbitrary labels and often depends on the trial, leading to varying results. Moreover, recent research indicated that all partition comparison measures can yield the same results for different clustering solutions. Consequently, algorithm selection and parameter optimization by unsupervised quality measures (QM) are always biased and misleading. Only if the predefined structures happen to meet the particular clustering criterion and QM, can the clusters be recovered. Results are presented based on 41 open-source algorithms which are particularly useful in biomedical scenarios. Furthermore, comparative analysis with mirrored density plots provides a significantly more detailed benchmark than that with the typically used box plots or violin plots.Michael C. ThrunNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Michael C. Thrun Distance-based clustering challenges for unbiased benchmarking studies |
description |
Abstract Benchmark datasets with predefined cluster structures and high-dimensional biomedical datasets outline the challenges of cluster analysis: clustering algorithms are limited in their clustering ability in the presence of clusters defining distance-based structures resulting in a biased clustering solution. Data sets might not have cluster structures. Clustering yields arbitrary labels and often depends on the trial, leading to varying results. Moreover, recent research indicated that all partition comparison measures can yield the same results for different clustering solutions. Consequently, algorithm selection and parameter optimization by unsupervised quality measures (QM) are always biased and misleading. Only if the predefined structures happen to meet the particular clustering criterion and QM, can the clusters be recovered. Results are presented based on 41 open-source algorithms which are particularly useful in biomedical scenarios. Furthermore, comparative analysis with mirrored density plots provides a significantly more detailed benchmark than that with the typically used box plots or violin plots. |
format |
article |
author |
Michael C. Thrun |
author_facet |
Michael C. Thrun |
author_sort |
Michael C. Thrun |
title |
Distance-based clustering challenges for unbiased benchmarking studies |
title_short |
Distance-based clustering challenges for unbiased benchmarking studies |
title_full |
Distance-based clustering challenges for unbiased benchmarking studies |
title_fullStr |
Distance-based clustering challenges for unbiased benchmarking studies |
title_full_unstemmed |
Distance-based clustering challenges for unbiased benchmarking studies |
title_sort |
distance-based clustering challenges for unbiased benchmarking studies |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/80c3566d0abb42cbb16bd430d6a3c752 |
work_keys_str_mv |
AT michaelcthrun distancebasedclusteringchallengesforunbiasedbenchmarkingstudies |
_version_ |
1718378462446616576 |