Some properties of the classification algorithms using ensemble kernels

Результат исследования: Научные публикации в периодических изданияхстатья по материалам конференциирецензирование


In this paper, we study the properties of the KCCE algorithm (Kernel-based Classification with Cluster Ensemble) proposed in our previous publication. Different strategies for choosing the ensemble weights are investigated from the point of view of their influence on the quality and speed of the algorithm. We perform numerical experiments with the algorithm on real datasets from the UCI repository under conditions of artificially added noise at different levels.

Язык оригиналаанглийский
Номер статьи012011
ЖурналJournal of Physics: Conference Series
Номер выпуска1
СостояниеОпубликовано - 4 янв. 2021
СобытиеInternational Conference on Marchuk Scientific Readings 2020, MSR 2020 - Akademgorodok, Novosibirsk, Российская Федерация
Продолжительность: 19 окт. 202023 окт. 2020