Authors :
Hasi Saha, G C Saha, Masum Billah, Najmul Hossain, Suraiya Yasmin
Volume/Issue :
Volume 5 - 2020, Issue 2 - February
Google Scholar :
https://goo.gl/DF9R4u
Scribd :
https://bit.ly/2Sf8sh6
Abstract :
Since Bangladesh is an agrarian nation, its
economy for the most part relies upon farming yield
growth and social agro industry items. Agriculture is to
a great extent affected by some profoundly flighty
parameters such as temperature and rainwater in
Bangladesh. Growth of agriculture also depends on
weather parameters like temperature, rainfall, humidity
as well as various soil parameters, soil moisture, surface
temperature and crop rotation. Since, now-a day’s
Bangladesh is quickly progressing into specialized
advancement therefore technology will end up being
beneficial to agriculture that will expand crop efficiency
which brings about better productions to the farmers.
One of those is also an essentially significant task in
agricultures’ yield prediction. Before the cultivation
process the research suggests different area based
beneficial crops. It recommends some crops for a
specific territory of land that are financially savvy for
farming. Here, the study considered six main crops
which names are rice, wheat, maize, potato, pulses, and
oil seeds in order to achieve these results. Using
Supervised Machine Learning, we find out the
prediction through analyzing a static arrangement of
information. The static dataset contains previous year’s
data of those crops according to the area which are
taken from the Yearbook of Agricultural Statics in
Bangladesh. To obtain this prediction a comparative
analysis between Multiple Linear Regression (MLR)
and K-Nearest Neighbor Regression (KNNR) has been
done in this research. To guarantee learning and
preparing of the algorithm and expanding the exactness
pace of expectation, we utilized past ten years (2006-
2015) dataset and for the case of testing we used one
year (2016) dataset for computing accuracy.
Keywords :
Data Mining; Multiple Linear Regression; K- Nearest Neighbor Regression; Crop Yield; Precision.
Since Bangladesh is an agrarian nation, its
economy for the most part relies upon farming yield
growth and social agro industry items. Agriculture is to
a great extent affected by some profoundly flighty
parameters such as temperature and rainwater in
Bangladesh. Growth of agriculture also depends on
weather parameters like temperature, rainfall, humidity
as well as various soil parameters, soil moisture, surface
temperature and crop rotation. Since, now-a day’s
Bangladesh is quickly progressing into specialized
advancement therefore technology will end up being
beneficial to agriculture that will expand crop efficiency
which brings about better productions to the farmers.
One of those is also an essentially significant task in
agricultures’ yield prediction. Before the cultivation
process the research suggests different area based
beneficial crops. It recommends some crops for a
specific territory of land that are financially savvy for
farming. Here, the study considered six main crops
which names are rice, wheat, maize, potato, pulses, and
oil seeds in order to achieve these results. Using
Supervised Machine Learning, we find out the
prediction through analyzing a static arrangement of
information. The static dataset contains previous year’s
data of those crops according to the area which are
taken from the Yearbook of Agricultural Statics in
Bangladesh. To obtain this prediction a comparative
analysis between Multiple Linear Regression (MLR)
and K-Nearest Neighbor Regression (KNNR) has been
done in this research. To guarantee learning and
preparing of the algorithm and expanding the exactness
pace of expectation, we utilized past ten years (2006-
2015) dataset and for the case of testing we used one
year (2016) dataset for computing accuracy.
Keywords :
Data Mining; Multiple Linear Regression; K- Nearest Neighbor Regression; Crop Yield; Precision.
