Group approach to solving the tasks of recognition

Yedilkhan Amirgaliyev, Vladimir Berikov, Lyailya S. Cherikbayeva, Konstantin Latuta, Kalybekuuly Bekturgan

Результат исследования: Научные публикации в периодических изданияхстатья

1 Цитирования (Scopus)

Аннотация

In this work, we develop CASVM and CANN algorithms for semi-supervised classification problem. The algorithms are based on a combination of ensemble clustering and kernel methods. A probabilistic model of classification with the use of cluster ensemble is proposed. Within the model, error probability of CANN is studied. Assumptions that make probability of error converge to zero are formulated. The proposed algorithms are experimentally tested on a hyperspectral image. It is shown that CASVM and CANN are more noise resistant than standard SVM and kNN.

Язык оригиналаанглийский
Страницы (с-по)177-192
Число страниц16
ЖурналYugoslav Journal of Operations Research
Том29
Номер выпуска2
DOI
СостояниеОпубликовано - 1 янв 2019

    Fingerprint

Цитировать

Amirgaliyev, Y., Berikov, V., Cherikbayeva, L. S., Latuta, K., & Bekturgan, K. (2019). Group approach to solving the tasks of recognition. Yugoslav Journal of Operations Research, 29(2), 177-192. https://doi.org/10.2298/YJOR180822032Y