Premium
An adaptive bivariate kernel smoothing method for determining instars of Austrosimulium tillyardianum (Diptera: Simuliidae) larvae
Author(s) -
Cen GuanJun,
Gao XuYuan,
Long XiuZhen,
Zeng XianRu,
Liu JiMin,
Wei DeWei,
Yu YongHao
Publication year - 2018
Publication title -
ecological entomology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.865
H-Index - 81
eISSN - 1365-2311
pISSN - 0307-6946
DOI - 10.1111/een.12523
Subject(s) - smoothing , bivariate analysis , instar , univariate , statistics , biology , kernel (algebra) , mathematics , larva , multivariate statistics , combinatorics , ecology
This study demonstrated that an adaptive bivariate kernel smoothing method is capable of accurately clustering all nine instars of Austrosimulium tillyardianum using pairs of separating variables. The analyses show that the paired variables of mandible length and antennal segment 3 length provided the highest accuracy of instar clustering via this method. By strengthening the distributed character through the increase of dimensions and using variable bandwidth matrix, the adaptive bivariate kernel smoothing method is better than previous methods at instar determination.