ENVIRONMENT
MONITORING SYSTEM
FOR AGRICULTURAL
APPLICATION USING
IOT AND CONNECT THE
FARMERS WITH CROP
BUYING MARKET
Problem Statement
To develop an Environment Monitoring System for
Agricultural Application using Microcontroller and
Predicting Crop Yield using Machine Learning and
connect the farmers with crop buying company/Market.
Introduction
■ Smart farming is one such methodology to do it. In this type of farming the crop is fed up with the enough
quantity of resources required for it to grow and by taking the calculated amount of time. due to the lack
of knowledge farmer is not capable of irrigating his/her field at the exact duration of time which
significantly lead to a wastage of water. Hence to overcome such issue smart farming method is employed.
■ To overcome the issue of traditional farming, a soil moisture detection sensor is implanted at the
observation site to get the soil moisture content and with this the crop is irrigated accordingly. Similarly,
soil moisture sensor, temperature sensor, Humidity sensor and pH sensor are used around the plant to get
the desired value, which helps in reducing the exploitation of extra resources used initially in traditional
farming
■ This system basically suggests an idea to generate the sensor node which can send the data to the central
node i.e., to the AWS cloud. This system consists of methodology used in smart farming and after
visualizing the exact percentage of resources required for crop to appropriately predict the crop yield using
various data mining techniques.
Objectives
■ To predict the crop production in advance so that farmer always got
to know the extent of accuracy of their farming techniques.
■ To connect the farmers with crop buying company/Market.
■ To monitor warehouse from remote location.
■ To predict suitable type of fertilizer and pesticides is used to
eliminate the disease.
■ To decide proper crop rotation strategies can help reduce a farmer's
fertilizer costs, enrich the soil, and increase take-home earnings.
Proposed Architecture
Algorithm Used – Decision Tree and KNN
■ Decision Tree – To predict Crop - The decision tree is method of selecting best root nodes
until we get elements of same class, we keep on splitting the tree based on attributes. With
versatile features helping actualize both categorical and continuous dependent variables, it
is a type of supervised learning algorithm mostly used for classification problems
■ KNN- Rain fall Prediction and weather prediction- KNN may be a variety of instance-
based learning, wherever the performance is barely approximated regionally and everyone
computation is delayed till it's the classification. both for classification and regression, a
helpful technique will be to assign weights to the contributions of the neighbors, in order
that the nearer neighbors contribute additional to the typical than the additional distant
ones.
Mathematical Model
■ S= {I, O, F, Success, Failure}
I = {i1, i2,i3} Number of Inputs
i1 = temperature
i2 = Humidity
i3 = Soil Moisture
O = {o1, o2} Number of Outputs
o1 = Turn on Water Pump
o2 = Display Parameters on LCD
F = {f1, f2} Functions
f1 = Predict crop, weather
f2 = Send notification over cloud
Success = System works as per requirements
Failure = Unable to work as per requirements
RESULTS
Cloud, User Interface
Project Planning
No. Activity Tentative work to be accomplished Proposed Duration
1. Implementation and Divide project into module using divide and 4 Weeks
Coding conquer strategy
Start coding each module and integrate them
2. Testing Perform various Blackbox and Whitebox 1 Weeks
testing methods and find and fix the bugs.
3. Deployment and Create detailed document of the system 1 Weeks
Documentation (Project)
Deploy project to client
4. Revision and Support Provide support to client for any difficulties. 2 Weeks
Paper Publication Details
■ Journal Name : International Journal for Research in Applied
Science and Engineering Technology (IJRASET)
■ Scientific Journal Impact Factor: 7.429
■ UGC Approved
■ Plagiarism – 100% Unique
Conclusion
This system showed the transformation of system which can collect the data from senor node
with the help of IoT in the field of agriculture. This system successfully able to sense the data
and sending the data locally to AWS cloud which is further access by user in his/her custom-
made website. Data mining techniques are used to predict the crop production in advance so that
farmer always got to know the extent of accuracy of their farming techniques. Various methods
of regression and classification to get the output and their plot are plotted successfully. In future
whether showing the data in custom made website can show the data in mobile app. Further, it
detects the disease of the crop by using the concept of image detection. With that suitable type of
fertilizer and pesticides is used to eliminate the disease. Artificial Intelligence and neural network
could also be used as a regression method that promises to give more precise results.
References
[1]http://www.thehindu.com/news/cities/Kochi/banned-pesticide-residues-found-in-vegetable samples/article4824152.ece .
[2] S Selvi and U Vanitha, Organic Farming: Technology for Environment-Friendly Agriculture, International Conference on Advances in
Engineering, Science and Management, 2012, 132 -136.
[3] C Somerville, M Cohen, E Pantanella, A Stankus and A Lovatelli, Small-Scale Aquaponic Food Production, Integrated Fish and Plant
Farming, FAO, Fisheries and Aquaculture Technical Paper, 2014.
[4] Reshmi Menon and Shahana G.V and Sruthi V, Small Scale Aquaponics System, International Journal of Agriculture and Food Science
Technology, 2013, 4 (10), 970-980.
[5] DC Love, JP Fry, L Genello, ES Hill, KSJ Adam Frederick and Ximin Li, An International Survey of
Aquaponics Practitioners, PLoS One, 2014, 9, e102662.
[6]Jun-Hong Cui, Jiejun Kong and Mario Gerla, and Shengli Zhou, The Challenges of Building Scalable Mobile Underwater Wireless
Sensor Networks for Aquatic Applications, IEEE Network, 2006, 12-18.
[7] Xiping Yang, KG Ong, WR Dreschel, K Zeng, CS Mungle and CA Grimes, Design of a Wireless Sensor Network for Long-Term, In-Situ
Monitoring of an Aqueous Environment, Sensors, 2002, 2 (11), 455-472.
[8] Neethu Prasannan and M Akhil and KP Soman, Internet of Things through Motes, International Journal of Advanced Research in
Computer Science and Software Engineering, 2013, 3, 1698-1705.
THANK Y U
