Self-adaptive clustering method based on feature similarity and application

The invention discloses a feature similarity-based adaptive clustering method, which comprises the following steps of S01, setting initial deep learning parameters, and extracting sample features; S02, setting an initial clustering number k and a step length x so as to determine m clustering numbers...

Full description

Saved in:
Bibliographic Details
Main Authors LI CHEN, TIAN PAN, SUN HONGXIA, FU HAO, YU XUERU
Format Patent
LanguageChinese
English
Published 17.07.2020
Subjects
CALCULATING
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a feature similarity-based adaptive clustering method, which comprises the following steps of S01, setting initial deep learning parameters, and extracting sample features; S02, setting an initial clustering number k and a step length x so as to determine m clustering numbers; S03, clustering the characteristics of the sample; S04, calculating a clustering effect function value f (p) corresponding to each group of clustering results; S05, determining a new clustering number k'according to the clustering effect function value gradient corresponding to the maximum clustering number; S06, repeating the steps S03-S05 until the clustering effect function value gradient corresponding to the maximum clustering number is smaller than the gradient threshold, and recording the current clustering effect function value f (k '); S07, deep learning parameters are adjusted, the steps S02 to S06n times are repeated, the deep learning parameters and the clustering number which enable the current cluste
Bibliography:Application Number: CN202010162913