miscluster

English

Etymology

mis- +‎ cluster

Pronunciation

• IPA^(key): /mɪsˈklʌstə(ɹ)/

Verb

miscluster (third-person singular simple present misclusters, present participle misclustering, simple past and past participle misclustered)

1. To cluster incorrectly.
   • 1992, Greg Chungmou Lee, Reconstruction of Line Drawing Graphs from Fused Range and Intensity Imagery:

     However, if a wing is wrongly clustered, it, in effect, has introduced a spurious wing in one cluster and its rightful cluster will be missing a wing. The effect is potentially damaging if several wings are misclustered.

   • 1997, The Nation - Volume 265, page 31:

     Ordinarily, I suppose, we think of death as taking place when something goes wrong with the physical body: when vessel walls collapse or cells miscluster or the immune system crashes.

   • 2012, Gregory O'Grady, An Improved Foundation for the Investigation and Treatment of Gastric Dysrhythmia, page 103:

     Indeed, the result of the fourth test case shows that, for instances when REGROUPS may miscluster a few isolated points, incorporating information from a relatively large number of ATs in the polynomial surface protects against 'run-away' misclustering.

Noun

miscluster (countable and uncountable, plural misclusters)

1. An instance of misclustering.
   • 1971, International Institute for Aerial Survey and Earth Sciences, Publications: Photogrammetry volume 61:

     Test-areas 17 and 18 were again misclusters.

   • 2017, G. Surya Narayana, D. Vasumanthi, K. Prasanna, “A New Stratified Immune Based Approach for Clustering High Dimensional Categorical Data”, in Kapila Rohan Attele, Amit Kumar, V. Sankar, N. V. Rao, T. Hitendra Sarma, editors, Emerging Trends in Electrical, Communications and Information Technologies, page 149:

     The rate of miscluster increases slightly with the increase of number of clusters and RAI objects.

   • 2019, Dr. G. Surya Narayana, Unsupervised Clustering Categorical Data Using Evolutionary Optimization Techniques:

     The thesis is split up into four phases of categorical data where the first phase evaluates the miscluster rate over the clustering on categorical data which results in significant improvement over the performance than the earlier reported algorithms.