Fundamental clustering algorithms suite

Thrun, Michael C.; Stier, Quirin

doi:10.1016/j.softx.2020.100642

Cited by 37 publications

(29 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Benchmarking will be performed on two high-dimensional datasets (D > 7000 and D > 18,000) and four artificially defined data structures with 41 clustering algorithms that are available in a previously published clustering suite 82 . The high-dimensional datasets possess one true partition of the data, which was verified by various methods and a domain expert.…”

Section: Methodsmentioning

confidence: 99%

Distance-based clustering challenges for unbiased benchmarking studies

Thrun

2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Distance-based clustering challenges for unbiased benchmarking studies

Thrun

2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Often, the user cannot manually change the distance metric (c.f. 54 common algorithms listed in [45]), resulting in the implicit application of the Euclidean metric if not otherwise specified. In contrast, projection-based clustering has the advantage that a specific distance metric can be selected by the user, which is then used in the dimensionality reduction and clustering part of the algorithm.…”

Section: Step I: Identification Of Structures In the Datamentioning

confidence: 99%

“…The definition of a cluster remains a matter of ongoing discussion [60,61]. Therefore, the justification for an appropriate choice for any one of the over fifty currently available open-source clustering algorithms [45] is proposed using data-driven criteria of Gaussian mixture models of distances, topographic maps, heatmaps, and Occam's razor (in the following Section 2.1.1, Section 2.1.3, Section 2.2.1, and Section 2.2.2). Additionally, a benchmarking of 34 clustering algorithms revealed for a large variety of distance and density-based cluster structures that projection-based clustering (PBC) is an appropriate choice [42].…”

Section: Step Ii: Cluster Analysis With Projection-based Clustering (mentioning

confidence: 99%

“…Table A1. Contingency table of projection-based clustering of the 2013/2014 versus k-means published in [39] and integrated in FCPS [45]. [90].…”

Section: Appendix B Comparison To the K-means Clustering Approachmentioning

confidence: 99%

“…Contingency table of projection-based clustering of the 2015 versus k-means published in[39] and integrated in FCPS[45]. Contingency table of projection-based clustering of the 2015 versus k-means published in[39] and integrated in FCPS[45]. The clusters should contain samples of different natures and are based on different processes.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Explainable AI Framework for Multivariate Hydrochemical Time Series

Thrun

Ultsch

2021

MAKE

Self Cite

View full text Add to dashboard Cite

The understanding of water quality and its underlying processes is important for the protection of aquatic environments. With the rare opportunity of access to a domain expert, an explainable AI (XAI) framework is proposed that is applicable to multivariate time series. The XAI provides explanations that are interpretable by domain experts. In three steps, it combines a data-driven choice of a distance measure with supervised decision trees guided by projection-based clustering. The multivariate time series consists of water quality measurements, including nitrate, electrical conductivity, and twelve other environmental parameters. The relationships between water quality and the environmental parameters are investigated by identifying similar days within a cluster and dissimilar days between clusters. The framework, called DDS-XAI, does not depend on prior knowledge about data structure, and its explanations are tendentially contrastive. The relationships in the data can be visualized by a topographic map representing high-dimensional structures. Two state of the art XAIs called eUD3.5 and iterative mistake minimization (IMM) were unable to provide meaningful and relevant explanations from the three multivariate time series data. The DDS-XAI framework can be swiftly applied to new data. Open-source code in R for all steps of the XAI framework is provided and the steps are structured application-oriented.

show abstract

A white paper on good research practices in benchmarking: The case of cluster analysis

Mechelen

Boulesteix²,

Dangl

et al. 2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

To achieve scientific progress in terms of building a cumulative body of knowledge, careful attention to benchmarking is of the utmost importance, requiring that proposals of new methods are extensively and carefully compared with their best predecessors, and existing methods subjected to neutral comparison studies. Answers to benchmarking questions should be evidence‐based, with the relevant evidence being collected through well‐thought‐out procedures, in reproducible and replicable ways. In the present paper, we review good research practices in benchmarking from the perspective of the area of cluster analysis. Discussion is given to the theoretical, conceptual underpinnings of benchmarking based on simulated and empirical data in this context. Subsequently, the practicalities of how to address benchmarking questions in clustering are dealt with, and foundational recommendations are made based on existing literature.This article is categorized under: Fundamental Concepts of Data and Knowledge > Data Concepts Fundamental Concepts of Data and Knowledge > Key Design Issues in Data Mining Technologies > Structure Discovery and Clustering

show abstract

Fundamental clustering algorithms suite

Cited by 37 publications

References 42 publications

Distance-based clustering challenges for unbiased benchmarking studies

Distance-based clustering challenges for unbiased benchmarking studies

Explainable AI Framework for Multivariate Hydrochemical Time Series

A white paper on good research practices in benchmarking: The case of cluster analysis

Contact Info

Product

Resources

About