A Frame Work for the Development of a Suitable Method to Find Shoot Length at Maturity of Mustard Plant Using Soft Computing Model
Abstract—
The production of a plant can be measured in terms of
seeds. The generation of seeds plays a critical role in our social and
daily life. The fruit production which generates seeds, depends on the
various parameters of the plant, such as shoot length, leaf number,
root length, root number, etc When the plant is growing, some leaves
may be lost and some new leaves may appear. It is very difficult to
use the number of leaves of the tree to calculate the growth of the
plant.. It is also cumbersome to measure the number of roots and
length of growth of root in several time instances continuously after
certain initial period of time, because roots grow deeper and deeper
under ground in course of time. On the contrary, the shoot length of
the tree grows in course of time which can be measured in different
time instances. So the growth of the plant can be measured using the
data of shoot length which are measured at different time instances
after plantation. The environmental parameters like temperature, rain
fall, humidity and pollution are also play some role in production of
yield. The soil, crop and distance management are taken care to
produce maximum amount of yields of plant. The data of the growth
of shoot length of some mustard plant at the initial stage (7,14,21 &
28 days after plantation) is available from the statistical survey by a
group of scientists under the supervision of Prof. Dilip De. In this
paper, initial shoot length of Ken( one type of mustard plant) has
been used as an initial data. The statistical models, the methods of
fuzzy logic and neural network have been tested on this mustard
plant and based on error analysis (calculation of average error) that
model with minimum error has been selected and can be used for the
assessment of shoot length at maturity. Finally, all these methods
have been tested with other type of mustard plants and the particular
soft computing model with the minimum error of all types has been
selected for calculating the predicted data of growth of shoot length.
The shoot length at the stage of maturity of all types of mustard
plants has been calculated using the statistical method on the
predicted data of shoot length.
Keywords—Fuzzy time series, neural network, forecasting error,
average error.
I. INTRODUCTION
THE production of a plant can be measured in terms of
seeds. The generation of seeds play a critical role in our
social and daily life. The fruit production which generates
seeds, depends on the various parameters of the plant, such as
shoot length, leaf number, root length, root number, etc When
the plant is growing, some leaves may be lost and some new
leaves may appear. It is very difficult to use the number of
leaves of the tree to calculate the growth of the plant.. It is
also cumbersome to measure the number of roots and length
of growth of root in several time instances continuously after
certain initial period of time, because roots grow deeper and
deeper under ground in course of time. On the contrary, the
shoot length of the tree grows in course of time which can be
measured in different time instances. So the growth of the
plant can be measured using the data of shoot length which
are measured at different time instances after plantation. The
data of the growth of shoot length of some mustard plant at
the initial stage (7,14,21 & 28 days after plantation) is
available from the statistical survey by a group of scientists
under the supervision of Prof. Dilip Dey. In this paper, initial
shoot length of Ken( one type of mustard plant) has been used
as an initial data.
The main work of this paper is to select a particular method
which can give the best result in terms of prediction of shoot
length at the stage of maturity by using certain data of initial
shoot lengths after plantation of the plant. The statistical
models, the methods of fuzzy logic and neural network have
been tested on the mustard plant and based on error analysis
(calculation of average error) that model with minimum error
has been selected and can be used for the assessment of shoot
length at maturity. At the beginning the data related to
mustard type Ken has been used and thereafter other mustard
types(B-59, Seeta, B-65, Kranti, B-54, etc.) have been used.
The particular selected soft computing model with the
minimum error of all types of all types of mustard plants has
been selected for calculating the predicted data of growth of
shoot length. The shoot length at the stage of maturity of all
types of mustard plants have been calculated using the
statistical method on the predicted shoot length data computed
earlier.

Download full report
http://citeseerx.ist.psu.edu/viewdoc/dow...1&type=pdf