Sie sind auf Seite 1von 4

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072

PREDICTION OF FUTURE CROPPING USING HADOOP


FRAMEWORK
Arun Kumar.S1, Naveen Kumar.S2, Vijay.S.V3, Vivekanandha.R4 ,Neethu Mariam Joseph5
1234
Students,Information Technology Department,
Er.Perumal Manimekalai College of Engineering,Hosur,Tamil Nadu,India
5
Professor Information Technology Department,
Er.Perumal Manimekalai College of Engineering,Hosur,Tamil Nadu,India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Agriculture in India plays a pre-dominant role in the form of blocks, which next will be separated into different
economy and employment.The common problem existing clusters of blocks. There are many nodes (or) parts of big data
analytics tool
among the Indian farmers are they don’t choose the right
crop as a result of this they face a serious setback in Hadoop = HDFS + Map-Reduce: HDFS is a Java- based
productivity.This problem of farmers has been addressed Hadoop Distributed File System, stores all kinds of data
and provides excessive-throughput to get application data.
through precision agriculture. In this paper, this problem is Map-Reduce plays a key role in Hadoop framework, it’s a
solved by proposing a recommendation system through a software encoding model for parallel processing of huge
Map- Reduce and Classification Algorithms to recommend a data sets. The role of mapper is to process input data by
crop for the site specific parameters with high accuracy and that generate intermediate data, then reducer acts a key
efficiency. As a result, farmer will act as leading producers to role to merge all intermediate data and generates final
output data.[3]
our nation and its economy. This paper emphasizes the usage
of Big Data which enables the farmers empowerment to
improve the really worth in their products through right
decisions.

KeyWords: Map-Reduce,HDFS,K-Nearest
Neighbour,Predictive Analysis.

1.INTRODUCTION

The outcome of the crops depends on the several


factors like rainfall, season, temperature, and also the price
announced by the Government.In this project,we will
categorize the crops based on the season,based on
Minimum price announced by the government, based on
temperature.This data are represented to the user in a Fig 1: Classic Hadoop Cluster
visualize statistical manner.
The data also contains different crops planted in
Area(Hectares) and Production(Tonnes).The project also II.EXISTING SYSTEM
visualizes the different categories of data for the better of
understanding of Agriculture in India.[2] Many of the existing systems are implemented using
A dataset or heap of data will be called as a big data Data Mining techniques where the prediction accuracy of
when the amount of data in the file or system is more than classifying the data is lower when compared to the big
the amount of data any one processor can handle in these data analytics.
situations,we will handle the data using big data The existing systems do not consider the dependency
Techniques.[2] between the various factor affecting the crop production.
There are many types of big data techniques and tools And more over the existing does use the old data which is
available,but we will concentrate more on the standard not up to date. Thus the classification and prediction of
common MapReduce,Yarn,Hdfs & Flume. data can’t be true and accurate. Thus using up to date data
with the “Big Data analytics” helps in accurate
Initially, we will store the data which has been classification and prediction of data.[2]
collected by and want to be analyzed in the Hdfs storage
system. In a Hdfs storage system, the data will be stored in

© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072

Present sites and application give ,so that it can be easy to understand.We select the month
suggestions only for identifying, in which we plan to sow the crop and then we provide the
 Crop yield production rate previous year information analyse the data sets of that
 Soil Conditions particular month and then classify the data based
 Diseases of Crops ondisease and data extracted from the classifier and finally
 Weather Conditions predict the soil and crop. The prediction of the soil is
 Online Fertilizers shopping etc., (Study) represented with a pie-chart with the respective
Some of issues arising in a existing system are, percentages of the prediction of the crop. Based on the
predictions, the crop and soil are divided in to five
 High use of fertilisers categories such as “very good”, “good”, “average”, “bad” and
 Susceptibility to pests “very bad”. [5]
 Environmental pollution
 Loss of biodiversity IV.IMPLEMENTATION
Monoculture policy will be increased if the proper 1.Dataset collection: Here in this process, we collect all
suggestive measures not discussed between the harvesters, the required dataset. Regarding the datasets the initial
hence generating the waste of yielded crops. Only
description and the point to be remembered is about the
Experienced farmers see benefit through planting different
crop variety, that is they sow a high yield variety of crop attributes. The dataset regarding the attributes which
and see income but others efforts gone in vain this is the suits the project must be analysed such that the entire
main problem using the existing Data mining system. results depend on the dataset collected and attributes
containing in it.[2] The data set collected are
There exist numerous methods and proposed
mechanism/models for the prediction of crop yield with  crops vs. seasons
innovative ways of analysing and classifying datasets. But  crops vs. price(various years)
they hardly discuss the issues and methods of handling
large and complex datasets are, Hence classifying large 2.Map reduction: Map reduction technique in the
datasets remains a very difficult and complicated task with Hadoop tool is used to get the data that’s only required.
an additional expectation of enhanced performance makes Map reduction technique reduces the amount of data
it more challenging. Soft computing and advanced technical
needed to be processed by the classification algorithm is
methods have been applied in the field of farming such as
artificial neural networks, the k nearest neighbour, the k- reduced.
means, support vector machines and ID3 algorithms.The
application of Data mining techniques in is a moderately
new approach and provides the prediction of agricultural
crops. India has the ability to achieve extraordinary
increase in the crop yield production with the help of
expansion of irrigation and technological innovation in
agriculture. There are multiple strategies which can be
adopted to improve the number and quality of crops. [5]

III.PROPOSED SYSTEM
Instead of using the data mining techniques we will use
the Map reduction Techniques of Big Data Analysis. The Big
data Analytics provides following advantages compared to
Fig 2: Map-Reduce operation on Crop Demand
data mining techniques.[2]

 Faster and Better decision making by It is a method of calculating demand of common crops
using distribute solutions. from input files on HDFS. The information saved in HDFS
 Extensibility and More Reliable way of should split into varied partitions and mapped to workers.
analyzing data. The process of mapper phase is to take the input files and
map it into intermediate < key, value > pairs of shuffled
We create an analysis site which perform Hadoop
and deposited into local disks, in which each file holds
based functions and predict the demanded crop which is
records with one particular key. When mapping process is
not grown in order to maintain Sustainable Growth to
over, reducer phase recover the mapping files from
Farmers Strain. We collect the Data from Agri based
workers of remote device and begins the reducing process
government sites of recently grown and predict the crops
and eventually stores the top outcome to output files on
which is required in nearest future, so that farmers can be
HDFS. [2]
saved from getting loss. And convert it to statistical format
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072

3.Visualization: The next module in the project will be the V.SCREENSHOTS


visualization of the classified data. The visualization helps in
better understanding of the classified data. The Visualization
is the process where the prediction of the data takes place. [2]

Screenshot 1: Sample Page

Fig 3: Demand by Crop

Fig 4: Production by Crop

Screenshot 2: Registration Page

TABLE-1: SOFTWARE USED

Java(JDK) Java 1.8

BACK-END HDFS,PHP MyAdmin

GUI CSS,HTML,JS Screenshot 3: Log-in Page

OS Ubuntu 18.04

IDE Word Press, C-Panel,


Apache Hadoop 3.1.1,
Eclipse Photon

Screenshot 4: Message Inbox

© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 3
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072

[3] Ch.Chandra Sekhar, J.UdayKumar, B.Kishor Kumar and


Ch.Sekhar, Effective use of Big Data Analytics in Crop
planning to increase Agriculture Production in
India,International Journal of Advanced Science and
Technology Vol.113 (2018), pp.31-40.

[4] A Review on the Practice of Big Data Analysis in


Agriculture (Kamilaris_agri_bigdata_survey.pdf), Article in
Computers and Electronics in Agriculture·October 2017.

[5] AshwaniKumarKushwaha,Crop yield prediction using


Screenshot 5:Message Module Agro Algorithm in Hadoop,IRACST - International Journal
V. CONCLUSION & FUTURE ENHANCEMENT of Computer Science and Information Technology &
Security (IJCSITS), Vol. 5, No2, April 2015.
India is a Primary Nation in which agriculture plays is a
major Occupation for many People.In prosperity of the [6] Asst. Prof. Vinod B. Ingale, Asst. Prof. Dhanaji,K.
farmers, prospers the nation. Thus our work would help Jadhav, Big Data A Great Revolution in Precision
farmers in sowing the right seed based on soil Agriculture using Predictive Weather Analysis andSoil
requirements and demand to increase productivity and Analysis, International Journal of Agriculture
acquire profit out of such a technique. Thus, the farmer’s Innovations and Research Volume 5, Issue 3, ISSN
can plant the right crop increasing his yield and also (Online) 2319-1473,2016.
increasing the overall productivity of the nation. Our future
work is aimed at an improved data set with large number [7] Farmer Buddy-Weather Prediction and Crop
of attributes and also implementing maximum yield Suggestion using Artificial Neural Network on Map-
prediction.The big data is massive tool with the prospective Reduce Framework ,International Journal of Computer
for creating various solutions for Farmers and decision Applications (0975 – 8887) Volume 159 – No 7,
makers, policy makers. A large amount of data set will February 2017
improve the analysis and predictive decision making
related with agriculture sector.There is a lot of scope for [8] ksankaranara,Cropthesis-Crop Monitoring and
doing more work on agriculture data in future. Some of Recommendation System Using Machine Learning
them will be listed below, Techniques, people.cs.umass.edu, April 2017.
 Using text analytics to find out the opinions
[9] R.Karthikeyan1, M.Gowthami2, A.Abhishhek3,
of common people.
P.Karthikeyan4, Implementation of Effective Crop
 Using more new advanced algorithms for
increased accuracy in predictions. Selection by Using the Random Forest Algorithm,
 Increasing the number of International Journal of Engineering & Technology, 7
recommendations in fields like fertilizers (3.34) (2018) 287-290.
and pesticide usage based upon the
[10] Prof.D.S.Zingade1,OmkarBuchade2,NileshMehta3,
previous usage.
 Using the cloud to store and retrieve data ShubhamGhodekar, Chandan Mehta - Crop Prediction
(Azure). System using Machine Learning, Volume 4, Special Issue
REFERENCES 5,Dec.-2017.

[1] S.Pudumalar ,E.Ramanujam, J.Nisha, C.Kavya, Crop


Recommendation System for Precision Agriculture, 2016
IEEE Eighth International Conference on Advanced
Computing (ICoAC).

[2] K.Ravisankar, K.Sidhardha, Prabadevi..B, Analysis of


Agricultural Data Using Big Data Analytics,Journal of
Chemical and Pharmaceutical Sciences,2017.

© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 4

Das könnte Ihnen auch gefallen