Record Details

Classification of maize genotypes by artificial neural network-based method: self organizing feature map

Indian Agricultural Research Journals

View Archive Info
 
 
Field Value
 
Title Classification of maize genotypes by artificial neural network-based method: self organizing feature map
 
Creator DASH, SUKANTA
WAHI, S D
RAO, A R
 
Subject ANN
City-block distance
Cluster analysis
Euclidean distance
Maize
 
Description Seventy seven maize (Zea mays L.) genotypes collected from Annual progress report 2005-06 of All India Coordinated Maize Improvement Project, Directorate of Maize Research are classified by 6 different clustering methods including ANN and compared based on probability of misclassification. The percentage probability of misclassification for small, moderate and large sample sizes based on ANN method was 5.666, 5.417 and 4.534 respectively. The second best method for small sample size was Ward’s method with 9.333 as percentage probability of misclassification. Whereas for moderate and large sample sizes K-means method was the second best method with 6.984 and 6.899 as percentage probability of misclassification. Hence, it can be concluded that the performance of ANN method is the best among the six methods of clustering irrespective of the sample size and dissimilarity measures used.
 
Publisher Indian Council of Agricultural Research
 
Date 2012-02-07
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
 
Format application/pdf
 
Identifier https://epubs.icar.org.in/index.php/IJAgS/article/view/15293
10.56093/ijas.v82i2.15293
 
Source The Indian Journal of Agricultural Sciences; Vol. 82 No. 2 (2012); 161–3
2394-3319
0019-5022
 
Language eng
 
Relation https://epubs.icar.org.in/index.php/IJAgS/article/view/15293/7668
 
Rights Copyright (c) 2014 The Indian Journal of Agricultural Sciences
https://creativecommons.org/licenses/by-nc-sa/4.0