Project Review II

PROJECT
REVIEW-II
Project Guide GROUP ID-35
Prof. Mayur Chavan Ambre Vikram
Upadhyay Ashutosh
Malu Anuj
Sarode Vivek
CONTENTS
• PROBLEM STATEMENT
• IDEA and MOTIVATION
• OBJECTIVES
• LITERATURE SURVEY
• S/W and H/W REQUIREMENT

• MATHEMATICAL MODEL
• SYSTEM ARCHITECTURE
• SDLC (Software Development Life Cycle)
• RELATED DIAGRAMS
• PROJECT MODULES
• IMPLEMENTATION
• PAPER PUBLICATION
• CONCLUSION
PROBLEM
STATEMENT
Design a system to estimate crop production for a region
based on Weather (Rainfall, Humidity) and previous
production data which provides following features:
• Provide updates to farmer regarding suggestions for his

cultivation plan
• Notify farmers regarding recent/ existing government
plans/ schemes
• Suggest proper pesticides/fertilizers for production of a
crop
IDEA
AND
MOTIVATION
India ranks second worldwide in farm output.
Agriculture and allied sectors like forestry and
fisheries accounted for 13.7% of the GDP (gross
domestic product) in 2013, about 50% of the
workforce.
Since then, the economic contribution of agriculture

to India's GDP is steadily declining with the country's
broad-based economic growth.
There is a need for innovation in the way farming is carried
out in India.
Our system will help farmers take an informed decision while

choosing the type of crop to plant, considering the
geographical location of the farm.
The system will take into account available weather

information, past crop-based cultivation statistics and
suggest a suitable crop for plantation.
OBJECTIVES
• To study the effect of weather on crop production.
• To study the effect of past crop production on future

crop production.
• To predict suitable crops for given weather and soil

conditions
LITERATURE
SURVEY
• Y. Chen and Y. Li "Entropy-Based Combining Prediction
of Grey Time Series and Its Application" suggested
entropy based combining prediction model for the unit
crop yield prediction.
The grey forecasting model and radial basis function

neural network forecasting models are combined to
increase the accuracy of prediction.
This conjunction forecasting model is less risky in
practice and more intuitive and feasible.
• G. Chen et al "The corn output in a time series prediction
model", proposed ARIMA (Autoregressive Integrated
Moving Average) for the prediction of corn output in a
time series prediction model.
The time series data sets obtained from Dehui city, Jilin
Province from 1990 to 2000 is given to the proposed
model and the output of corn prediction is validated
from the year 2001 to 2003.
The results obtained from the model are satisfactory

because the relative error was controlled within 5%.
• Deepti Gupta, Udayan Ghose Ghose, " A Comparative
Study of Classification Algorithms for Forecasting
Rainfall ", developed rainfall forecasting models based
on Classification and Regression Tree algorithm, Naive
Bayes approach, K nearest Neighbour and 5-10-1
Pattern Recognition Neural Network.
The result accuracy obtained to the corresponding

techniques are 80.3%, 78.9%, 80.7% and 82.1%
respectively.
• V. B. Nikam and B. B. Meshram "Modeling Rainfall
Prediction Using Data Mining Method: A Bayesian
Approach", identified the challenges in weather
prediction.
The data obtained from Indian Meteorological

Department (IMD) is taken into account for the study.
The Bayesian data mining techniques is used for analyzing

and prediction of the rain fall. The results indicate that the
accuracy of Prediction is good with moderate computing
resources by using the Bayesian Approach.
S/W AND H/W
REQUIREMENTS
SOFTWARE REQUIREMENTS
• Operating System: Linux 64-bit/ Windows 64-bit
• Technologies: Machine Learning, MySQL, JSP,

Tomcat Server, Java Spring, REST
• Programming Language: Python, Java

HARDWARE REQUIREMENTS
Sr. No. Parameter Minimum Requirement Justification
1.8 GHz or
1 CPU Speed 1.8 GHz faster multicore.
2 RAM 4 GB Recommended RAM

4 GB or more
3 System One 64 bit x86 multicore 1 x86 computer

system
MATHEMATICAL
MODEL
Let S be the solution for the prediction model,
S = {s, e, X, Y, F, DD, NDD, Su, Fl }
where,
s = start state = Home screen displayed
e = end state =
X= Input Set
X= {DS, X1, X2, X3}
Where,
DS = Dataset = { Cinfo, Winfo }
Where,
Cinfo = {Cname, Cprod, Area, Temp, Humid, Rain}
Where,
Cname = name of the crop = [A-Z] [a-z0-9] *
Cprod = production of crop in tons € Z+
Area € Z+
Temp = Temperature in ℃ € Z
Humid = Humidity in % € Z+
Rain = Rainfall in mm € Z-Z-
X1 = Cname
X2 = Weather Conditions = Cinfo - Cname
X3 = {Cinfo, Cprod}
Y= Output Set
Y= {Y1, Y2, Y3}
Where,
Y1 = Cinfo - Cname
Y2 = Cname
Y3 = C`prod
Where,
C`prod = estimated production of crop in tons € Z+
F = set of functions
F = {FcropInfo, Fsearch, Fpredict}
Where,
FcropInfo = Information Retrieval Function
FcropInfo: X1 →Y1
Fsearch = Search Function to return suitable crop to plant

Fsearch: X2 →Y2
Fpredict = Function to predict production of crop
Fpredict: X3 →Y3
DD = Deterministic data
DD = {DS}
NDD = Non-deterministic data
NDD = {Y}
Su = Success case = {Correct Output Displayed}
Fl = Failure case = {Output displayed is Incorrect}
SYSTEM
ARCHITECTURE
SDLC
(SOFTWARE
DEVELOPMENT
LIFE - CYCLE)

crop production.

conditions
RELATED
DIAGRAMS
• TASK NETWORK
• TIMELINE CHART
• USE-CASE VIEW
• LEVEL 0 DATA FLOW DIAGRAM
• LEVEL 1 DATA FLOW DIAGRAM
• ACTIVITY DIAGRAM
• STATE DIAGRAM
• CLASS DIAGRAM
PROJECT
MODULES

crop production.

conditions
IMPLEMENTATION

crop production.

conditions
PAPER
PUBLICATION

crop production.

conditions
CONCLUSION
• The time series analysis of crop yield prediction is subjected to
analysis by the existing techniques: Support Vector Machine and
Naive Bayes with the proposed techniques viz., AdaSVM and
AdaNaive.
• The results show that the accuracy and classification error of

prediction by SVM and Naive Bayes can be improved using
AdaSVM and AdaNaive.
• It may be concluded from the results that there is a considerable

amount of increase in accuracy of prediction and also a
considerable amount of decrease in the classification error in
both the proposed techniques.

Project Review II

Uploaded by

Copyright:

Available Formats

Project Review II

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Project Review II

Uploaded by

Copyright:

Available Formats

PROJECT

• IDEA and MOTIVATION

• S/W and H/W REQUIREMENT

• SDLC (Software Development Life Cycle)

• Provide updates to farmer regarding suggestions for his

Since then, the economic contribution of agriculture

Our system will help farmers take an informed decision while

The system will take into account available weather

• To study the effect of past crop production on future

• To predict suitable crops for given weather and soil

The grey forecasting model and radial basis function

The results obtained from the model are satisfactory

The result accuracy obtained to the corresponding

The data obtained from Indian Meteorological

The Bayesian data mining techniques is used for analyzing

• Operating System: Linux 64-bit/ Windows 64-bit

• Technologies: Machine Learning, MySQL, JSP,

• Programming Language: Python, Java

2 RAM 4 GB Recommended RAM

3 System One 64 bit x86 multicore 1 x86 computer

Fsearch = Search Function to return suitable crop to plant

• To study the effect of past crop production on future

• To predict suitable crops for given weather and soil

• To study the effect of past crop production on future

• To predict suitable crops for given weather and soil

• To study the effect of past crop production on future

• To predict suitable crops for given weather and soil

• To study the effect of past crop production on future

• To predict suitable crops for given weather and soil

• The results show that the accuracy and classification error of

• It may be concluded from the results that there is a considerable

You might also like