Classification of maize genotypes by artificial neural network-based method: self organizing feature map
Indian Agricultural Research Journals
View Archive InfoField | 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 |
|