Photometric clustering of regenerated plants of gladiolus by neural networks and its biological validation

V. S.S. Prasad, S. Dutta Gupta

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Photometric clustering of regenerated plants of gladiolus was described using fuzzy adaptive resonance theory (ART) and the resultant grouping pattern was compared with ART 2, and self-organizing map (SOM) neural network modules. Classical clustering techniques such as hierarchical (HC) and k-means clustering (KM) were also applied to analyze the same data set to evaluate the performance of the artificial neural network (ANN)-based clustering. Regenerated plants were clustered into two groups in varying numbers by ART 2, SOM, HC and KM. With ART 2, 19 of 55 plants were sorted into group '0' and the remaining 36 plants were placed in group '1', whereas; SOM distributed the regenerated plants in the ratio of 28:27. The clustering ratios of HC and KM were 34:21 and 26:29, respectively. However, a refined clustering of regenerated plants into seven groups was observed with Fuzzy ART. There was a similarity in the number of generated clusters between the training and validation data sets indicating the network efficiency. Biological validation of photometric clustering of regenerated plants was also assessed by indexing the corm induction potential of the sorted groups. A significant difference in corm induction potential between the groups was noted only with ART 2. Fuzzy ART-assisted grouping patterns are not conducive to segregate the potential corm producing shoots. ART 2-aided clustering of the regenerated plants appeared to be more promising for selecting group of plants capable of corm development than did other clustering approaches.

Original languageEnglish
Pages (from-to)8-17
Number of pages10
JournalComputers and Electronics in Agriculture
Volume60
Issue number1
DOIs
Publication statusPublished - 01-01-2008
Externally publishedYes

Fingerprint

Gladiolus
neural networks
Neural networks
Self organizing maps
artificial neural network
shoot
shoots

All Science Journal Classification (ASJC) codes

  • Forestry
  • Animal Science and Zoology
  • Agronomy and Crop Science
  • Computer Science Applications
  • Horticulture

Cite this

@article{436ee340263a4bc59dd4c5dd9d4ac978,
title = "Photometric clustering of regenerated plants of gladiolus by neural networks and its biological validation",
abstract = "Photometric clustering of regenerated plants of gladiolus was described using fuzzy adaptive resonance theory (ART) and the resultant grouping pattern was compared with ART 2, and self-organizing map (SOM) neural network modules. Classical clustering techniques such as hierarchical (HC) and k-means clustering (KM) were also applied to analyze the same data set to evaluate the performance of the artificial neural network (ANN)-based clustering. Regenerated plants were clustered into two groups in varying numbers by ART 2, SOM, HC and KM. With ART 2, 19 of 55 plants were sorted into group '0' and the remaining 36 plants were placed in group '1', whereas; SOM distributed the regenerated plants in the ratio of 28:27. The clustering ratios of HC and KM were 34:21 and 26:29, respectively. However, a refined clustering of regenerated plants into seven groups was observed with Fuzzy ART. There was a similarity in the number of generated clusters between the training and validation data sets indicating the network efficiency. Biological validation of photometric clustering of regenerated plants was also assessed by indexing the corm induction potential of the sorted groups. A significant difference in corm induction potential between the groups was noted only with ART 2. Fuzzy ART-assisted grouping patterns are not conducive to segregate the potential corm producing shoots. ART 2-aided clustering of the regenerated plants appeared to be more promising for selecting group of plants capable of corm development than did other clustering approaches.",
author = "Prasad, {V. S.S.} and {Dutta Gupta}, S.",
year = "2008",
month = "1",
day = "1",
doi = "10.1016/j.compag.2007.05.006",
language = "English",
volume = "60",
pages = "8--17",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",
number = "1",

}

Photometric clustering of regenerated plants of gladiolus by neural networks and its biological validation. / Prasad, V. S.S.; Dutta Gupta, S.

In: Computers and Electronics in Agriculture, Vol. 60, No. 1, 01.01.2008, p. 8-17.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Photometric clustering of regenerated plants of gladiolus by neural networks and its biological validation

AU - Prasad, V. S.S.

AU - Dutta Gupta, S.

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Photometric clustering of regenerated plants of gladiolus was described using fuzzy adaptive resonance theory (ART) and the resultant grouping pattern was compared with ART 2, and self-organizing map (SOM) neural network modules. Classical clustering techniques such as hierarchical (HC) and k-means clustering (KM) were also applied to analyze the same data set to evaluate the performance of the artificial neural network (ANN)-based clustering. Regenerated plants were clustered into two groups in varying numbers by ART 2, SOM, HC and KM. With ART 2, 19 of 55 plants were sorted into group '0' and the remaining 36 plants were placed in group '1', whereas; SOM distributed the regenerated plants in the ratio of 28:27. The clustering ratios of HC and KM were 34:21 and 26:29, respectively. However, a refined clustering of regenerated plants into seven groups was observed with Fuzzy ART. There was a similarity in the number of generated clusters between the training and validation data sets indicating the network efficiency. Biological validation of photometric clustering of regenerated plants was also assessed by indexing the corm induction potential of the sorted groups. A significant difference in corm induction potential between the groups was noted only with ART 2. Fuzzy ART-assisted grouping patterns are not conducive to segregate the potential corm producing shoots. ART 2-aided clustering of the regenerated plants appeared to be more promising for selecting group of plants capable of corm development than did other clustering approaches.

AB - Photometric clustering of regenerated plants of gladiolus was described using fuzzy adaptive resonance theory (ART) and the resultant grouping pattern was compared with ART 2, and self-organizing map (SOM) neural network modules. Classical clustering techniques such as hierarchical (HC) and k-means clustering (KM) were also applied to analyze the same data set to evaluate the performance of the artificial neural network (ANN)-based clustering. Regenerated plants were clustered into two groups in varying numbers by ART 2, SOM, HC and KM. With ART 2, 19 of 55 plants were sorted into group '0' and the remaining 36 plants were placed in group '1', whereas; SOM distributed the regenerated plants in the ratio of 28:27. The clustering ratios of HC and KM were 34:21 and 26:29, respectively. However, a refined clustering of regenerated plants into seven groups was observed with Fuzzy ART. There was a similarity in the number of generated clusters between the training and validation data sets indicating the network efficiency. Biological validation of photometric clustering of regenerated plants was also assessed by indexing the corm induction potential of the sorted groups. A significant difference in corm induction potential between the groups was noted only with ART 2. Fuzzy ART-assisted grouping patterns are not conducive to segregate the potential corm producing shoots. ART 2-aided clustering of the regenerated plants appeared to be more promising for selecting group of plants capable of corm development than did other clustering approaches.

UR - http://www.scopus.com/inward/record.url?scp=36749028298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36749028298&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2007.05.006

DO - 10.1016/j.compag.2007.05.006

M3 - Article

VL - 60

SP - 8

EP - 17

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

IS - 1

ER -