Final PPT Phase 2 Viva

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 32

CROP MONITORING AND YIELD

PREDICTION USING MACHINE


LEARNING

Project Phase II
31/03/2021

Guided By Presented By
Dr.N.Suba Rani ,AP(SG) D.Suriya
CSE Department 19MCS002
MCET II ME CSE
Overview
• Introduction
• Objective
• Existing System & Drawbacks
• Research Questions
• Proposed System
• Data Collection
• Modules and Implementation Setup
• Results and Inferences
• Conclusion and Future Work
• Publications
• References
CROP MONITORING AND YIELD
31/03/2021 PREDICTION USING MACHINE 2
LEARNING
Introduction
• Domain:
The Agriculture using Machine learning
Techniques.
• The crop monitoring and yield prediction are the
critical issues faced by the farmers handling small to
large scale farms.
• Machine learning is a type of Artificial intelligence
that provides computers with the ability to learn
without being explicitly programmed.
CROP MONITORING AND YIELD
31/03/2021 PREDICTION USING MACHINE 3
LEARNING
Objective
• Classification methods used to find accuracy of the
results from supervised learning and unsupervised
learning.
• In this system compare the analysis and performance
of classification algorithm.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 4
LEARNING
Existing System
• The Core idea using the data mining techniques with
the machine learning to increase suitability for the
agriculture.
• Decision tree algorithm
• The model was simple with single feature
consideration and the result was not having accuracy
Literature Review
(link to literature ppt)

Ref: Shavian S.Kale and Preeti S.Patil 2019, ‘Data Mining Technology with Fuzzy
Logic,, Neural Networks, Machine Learning for Agriculture”, Published by Springer,
Data Management, Analytics and Innovation, Advances in Intelligent Systems and
Computing https://doi.org/10.1007/978-981-13-1274-86 5
Block Diagram of Existing System

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 6
LEARNING
Research Questions
• Single selection of feature main drawback of the
existing system with respect to the agriculture.
• Multi criteria should be taken into consideration
in order to get possible result accuracy.
• The proposed work will be comparison of
different algorithms in terms to produce best
solutions and results.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 7
LEARNING
Proposed System
• To find accuracy of classification algorithm and
predicate crop yield based on available data.
• Supervised learning method used for Decision Tree,
Naïve Bayes, Random Forest algorithm.
• Unsupervised learning used to SVM,KNN algorithm.
• The classification technique applied to soil data set
analyzing to soil properties.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 8
LEARNING
Block Diagram of Proposed System

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 9
LEARNING
Data Collection
• The data collection is preliminarily carried out for
soil optimum health Macronutrients and
micronutrients.
• A lack of any one micronutrients in the soil will limit
growth, when nutrients are present in sufficient
amounts.
• The dataset can be taken from kaggle.com

Ref :www.http/10.1080/17538947.soildata/kaggle.com
CROP MONITORING AND YIELD
31/03/2021 PREDICTION USING MACHINE 10
LEARNING
Modules
1. Input dataset
2. Classification algorithm
Implementation Setup
3. Decision tree Language : R Programming
4. Naive Bayes Tools Used: R Studio
RAM : 4 GB
5. Random Forest
6. Support Vector Machine
7. KNN

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 11
LEARNING
Module1: Input dataset
• The prediction of crop is dependent on numerous
factors past crop production.
• Depending on the current user location, system mines
soil properties in the respective area from soil
repository.
• A crop can be cultivable are include extensive
parameters to soil. The constraints are compared to
the crops data are trained.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 12
LEARNING
Snap Shot of Module 1

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 13
LEARNING
Module 2:Classification Algorithm
• Classification algorithm applied for data mining
function that assign in a collection to target categories
or classes.
• The goal of classification is to accurately predict the
target class for each case in the soil data.
➢ Supervised Learning
➢ Un Supervised Learning

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 14
LEARNING
Snap Shot of Module 2

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 15
LEARNING
Module 3:Decision Tree
• A decision tree that uses a model to make decisions
and consequences also includes chance event
outcomes, resource costs, and utility.
• It is a process to display an algorithm that contains
conditional control statements.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 16
LEARNING
Snap Shot of Module 3

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 17
LEARNING
Module 4: Naïve Bayes
• Classification technique based on Bayes theorem with
an assumption to independent of the predictors.
• The principle of soil testing is field physical
properties and chemical properties such as EC, pH,
along with micronutrients N, P, K and macro nutrients
Zn, Cu, Fe.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 18
LEARNING
Snap Shot of Module

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 19
LEARNING
Module 5:Random forest
• Classification method of regression technique
and other tasks are used to operate for
constructing a decision tree at specific training
time using random Forest.
• The mode of the classification or mean
prediction (regression) of the individual trees
is also calculated.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 20
LEARNING
Snap Shot of Module

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 21
LEARNING
Evaluation Metrics
• The different algorithms are available to based on
accuracy and prediction algorithm.
• It measures the proportion of true positives that are
correctly identified.
• Accuracy measured for actual true value.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 22
LEARNING
Results and Inferences
• The machine learning algorithms are used to
accuracy and prediction.
• Correct prediction can be improved.
Algorithm High Low Medium Accuracy

Naïve Bayes 15 23 27 90%

Decision 15 30 29 89%
Tree
Random 15 28 25 98%
Forest
KNN 13 29 26 96%
SVM 12 28 25 97%

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 23
LEARNING
Conclusion
• The Random Forest Algorithm best accuracy on the
test set is the higher accuracy score of the Machine
learning method from calculating precision, recall.
• The proposed system considers the data related to
soil data best profitable crop yield prediction.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 24
LEARNING
Publication
International Conference
1. Dr.N. Suba Rani,2021, “Crop Monitoring and yield prediction
using machine learning”, International Conference on Latest
Trends in Science, Engineering and Technology
(ICLTSET’21),Karpagam institute of Technology,Coimbatore.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 25
LEARNING
References
[1] N Hemageetha and G.M. Nasira ,(2017),“Analysis of the Soil Data
Using Classification Techniques for Agricultural Purpose” International
Journal of Computer Sciences and Engineering, 4(6), PP:27-236.

[2] S.Hari Ganesh and Mrs. Jayasudha,(2015)” Data Mining Technique to


Predict the Accuracy of the Soil Fertility”, International Journal of Computer
Science and Mobile Computing,Vol(7),Issue 3,PP:330-334.

[3] P. Kanjana Devi and S.Shenbagavadivu”,(2018) Enhanced Crop Yield


Prediction and Soil Data Analysis Using Data Mining”, International Journal
of Modern Computer Science vol 4(6),pp:30-285.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 26
LEARNING
[4] R. M. Kumar,(2017), “Crop Selection Method to Maximize Crop Yield
Rate Using Machine Learning Technique”, International Conference on Smart
Technologies and Management for Computing, Communication, Controls,
Energy and Materials, vol 1,Issue 4,pp: 13-241.

[5] E. Manjula and S. Djodiltachoumy, (2017),”A Model for Prediction of


Crop Yield”, International Journal of Computational Intelligence and
Informatics, vol 6,Issue(4),PP:446-455.

[6] V. Rajeswari and K. Arunesh ,(2018),“Analysing Soil Data using Data


Mining Classification Techniques”, Indian Journal of Science and Technology,
Vol 9,Issue(19),pp:220-288.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 27
LEARNING
[7] D Ramesh and B Vishnu Vardhan,(2016)”Analysis Of Crop Yield
Prediction Using Data Mining Techniques”, International Journal of Research
in Engineering and Technology, Vol(8),Issue 4(1),PP:112-145

[8] Ghodsi, R.; Yani, R.M.; Jalali, R.; Ruzbahman, (2016), “Predicting wheat
production in Iran using an artificial neural networks approach”, Int. J. Acad.
Res. Bus. Soc. Sci.,Vol( 2), pp: 34– 47

[9] Niketa Gandhi, Owaiz Petkar and Leisa J. Armstrong , (2018), “Rice
Crop Yield Prediction Using Artificial Neural Networks”, IEEE International
Conference on Technological Innovations in ICT For Agriculture and Rural
Development, vol(6), pp:105-110

[10] Arun Kumar, Naveen Kumar, Vishal Vat,(2019), “Efficient Crop Yield
Prediction Using Machine Learning Algorithms”, International Research
Journal of Engineering and Technology, vol(6),pp:234-346.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 28
LEARNING
Thank You
Literature Review
Title of Paper/ Authors/ year​/
S. No​ Idea of the paper Remarks
Publisher

“A comprehensive review on
automation in agriculture using
Regression The accuracy of
1​ artificial intelligence” M.Shashi,
algorithms, Artificial system only 50%
Y. a. Prathumchai, Science
Neural Network
direct published 2019.
“Implementation of artificial
intelligence in agriculture for Integration of The classification
optimization of irrigation and different embedded and prediction
2​
application of pesticides and systems and ML cannot be done
herbicides” , Miss.Snehal, S. devices. correctly
D.,2019.
CROP MONITORING AND YIELD
31/03/2021 PREDICTION USING MACHINE 30
LEARNING
Literature Review
Title of Paper/
S. No​ Idea of the paper Remarks
Authors/ year​/ Publisher

“Prediction On Crop
Cultivation”, Oboe, W.
SVM, Soil fertilizers to
International Journal of
3 Naïve Bayes farmers thus leading
Advanced Research in
to poor crop yields
Computer Science and
Electronics Engineering , 2017.
Soil and excessive or
“Applications of Machine less application of
k-nearest neighbour,
learning Techniques in fertilizers. Match
Support Vector
4 Agricultural Crop Production” Crops with Soil,
Regression (SVG).
,Kumar, R. M., IEEE, October Fertilizer
2018 Recommendation.

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 31
LEARNING
Literature Review
Title of Paper/
S. No​ Idea of the paper Remarks
Authors/ year​/ Publisher

V. Rajeswari and K. Arunesh Micro-nutrient


“Analysing Soil Data using Crop type and seed deficiencies in soil
5 Data Mining Classification variety as input to excessive or less
Techniques”, Indian Journal of the prediction model. application Nutrients
Science and Technology,(2018). present in the soil
Omkar Buchade,, “Crop
Multiple Linear
prediction System using A smart wireless
Regression(MLR)
Machine Learning", Journal of device for sensing
6 technique for crop
Advance Engineering and soil moisture and
analysis, Decision
Research Development, Dec meteorological data.
tree
2017

CROP MONITORING AND YIELD


31/03/2021 PREDICTION USING MACHINE 32
LEARNING

You might also like