A hierarchical Self-Organizing Map for egg breakage classification

被引：0

作者：

Moshou, D ^{[1
]}

De Ketelaere, B ^{[1
]}

Coucke, P ^{[1
]}

De Baerdemaeker, J ^{[1
]}

Ramon, H ^{[1
]}

机构：

[1] Katholieke Univ Leuven, Mech Engn Lab, Dept Agroengn & Econ, B-3001 Heverlee, Belgium

来源：

MATHEMATICAL AND CONTROL APPLICATIONS IN AGRICULTURE AND HORTICULTURE | 1997年

关键词：

neural networks; self-organizing systems; classification; hierarchical structures; agriculture;

D O I：

暂无

中图分类号：

S8 [畜牧、动物医学、狩猎、蚕、蜂];

学科分类号：

0905 ;

摘要：

A hierarchical Self-Organizing Map has been developed for solving classification problems, where several measurements have been taken from one object. The algorithm will be used to classify eggs according to their shell state. Broken eggs will be separated from intact eggs. The classification architecture actually consists of two different SOMs. The first SOM clusters the data in an unsupervised way. Afterwards, the ordered activations of each object are collected and fed to the second SOM which associates them with a class. This class-vector is assigned to every node in the second map and it is learned with Kohonen's learning rule.

引用

页码：125 / 129

页数：5