Kisan Seeva

Kisan Seeva

UG Student, Dept. of I.T., Vidyalankar Institute of Technology, Mumbai University, India

UG Student, Dept. of I.T., Vidyalankar Institute of Technology, Mumbai University, India

UG Student, Dept. of I.T., Vidyalankar Institute of Technology, Mumbai University, India Assistant Professor, Dept. of IT Engineering, VIT college, Maharashtra, India ***

Abstract - The world population is rapidly increasing and is expected to reach 8.6 billion by 2030. As a result, food production and consumption will increase,leadingtoagreater threat to food security from crop diseases that can damage agricultural products. Unfortunately, in several parts of India, inadequate infrastructure makes it challenging to identify crop-damaging diseases quickly. Farmers now grow a diverse array of crops and often aim to expand the variety they grow, making it difficult to foresee crop illnesses at an early stage. This "Experimental farming" mentality often results in significant losses, making it more expensive for farmers to learn from past mistakes.

To addressthese challenges, an electronic expert system,inthe form of an android app, is proposed. This app will enable farmers to make wise decisions and enhance their farming operations without incurring significant losses. The system employs an innovative method of object detection to identify plant diseases, significantly improving the speed and accuracy of disease detection on leaves. Convolutional neural network (CNN) models are utilized to detect diseases, which are more accurate than other models available in the market. With this approach, the systemwillidentifywhethercropsareinfectedor not, and if they are, the user will be informed, and appropriate action can be taken to address the sick crop.

The app's approach allows farmers to take crop photographs and analyze the presence or absence of illnesses quickly, providing a workable solution to the lack of adequate infrastructure. It also caters to farmers' needs for a diverse array of crops while minimizing the risk of significant losses. The suggested system offers a solution to the issue of food security by providing farmers with the tools to detect and address crop diseases at an early stage, thus improving food production and consumption.

Key Words: Farmer, Crop, Leaf Disease, Renting Farming Equipment, Mandi Price, Disease Prediction

1. INTRODUCTION

Afterconductingasurveyinsomevillagesandcities,we foundthatover70%offarmersareinterestedintryingnew cropsinsteadoftheirtraditionalones.However,duetoalack ofknowledgeandexperience,manyfarmersstruggletogrow thesenewcrops,andtheyoftensufferfromdiseases,nutrient

deficiencies,andotherfactorsthatharmtheircrops.Many farmers in the area rely on experience rather than proper understanding, and they make decisions based on visual inspections of their plants. However, this method requires ongoingevaluationofexpertise,whichcanbetooexpensive forlargefarms.

Inaddition,somefarmershavetotravellongdistancesto consult with agricultural officers, which can be costly and time-consuming. To address these challenges, automatic diagnosisofplantdiseasesfromthesymptomsthatoccuron theplantleavesisaninterestingstudyareathatcouldprove advantageous in monitoring vast fields of crops. Machine visionmakesthispossible,allowingforimage-basedprocess control,robotnavigation,andautonomousinspection.

Diagnosing plant diseases by visually inspecting the symptoms on plant leaves is a complex process, even for seasoned agronomists and plant pathologists. This complexityisduetothevastnumberofcultivatedplantsand theirPhytopathologicalissues.Therefore,thedevelopment of an automated computational system for identifying and diagnosingplantdiseaseswouldgreatlybenefitagronomists whoarerequestedtomakethesediagnoses.

Forfarmersinregionswithoutthenecessaryinfrastructure foragronomicandPhytopathologicaladvice,asimple-to-use mobileapplicationcouldprovetobeausefultool.However, forthissystemtobeeffective,itmustbeabletodetectand diagnose certain diseases in real-world settings and be compatiblewithasuitablemobileapplication

1.1 Problem Statement

To increase production in their fields, farmers should regularlyinspecttheircropsforpestsanddiseases.However, many farmers struggle to identify infections in a timely manner and evenseekinghelp fromfarmingprofessionals canresultinsignificantdelays.Toaddressthischallenge,we are creating an Android application that uses plant photographstohelpfarmersdetectdiseases.Furthermore, the app will provide information on the prices of various cropsatnearbymarketsthroughanAPI,offerrentaloptions for farming equipment, and support farmers in multiple regionswithitsmultilingualfeatures.

1.2 Objectives

 The objective of the agricultural project is to help farmersidentifycropdiseasesbyimplementingacrop diseasepredictionmodel.

 The project offers a rental service for equipment and providesprofessionalfarmingadvicetofarmersbased ontheircropfields'condition.

 The initiative is designed to enable farmers to make informed decisions regarding theircropsandincrease theiryield,resultingingreaterprofitability.

 Thegoaloftheprojectistosupportfarmersinproducing high-quality,healthycrops.

 Theprojectalsoaimstocontributetothedevelopmentof sustainableagriculturepractices.

 Byleveragingtechnologytoprovidepredictiveinsights, theprojectseekstomodernizeandimprovetraditional farmingmethods.

 Throughthisinitiative,theprojecthopestopromotethe growthanddevelopmentoftheagriculturalsectorwhile supportingthelivelihoodsoffarmers.

1.2 Features

The proposed system is an android application which has followingservicesforfarmers-

 Image processing - Leaf-based plant disease detection system utilizes digital image processing techniques to identify diseases in plant leaves. The system captures imagesofplantleavesandanalyzesthemtoidentifythe presenceofanydiseasesymptoms.Thistechnologycan aidinearlydetectionandtimelyinterventiontoprevent the spread of diseases, thus increasing crop yield and quality.

 MarketMandiPrice-MarketMandiPriceisafeaturethat enablesuserstogatherinformationonmarketratesfor different commodities across multiple markets. The featureprovidesupdatedpricinginformationforvarious cropsandproduce,allowingfarmerstomakeinformed decisionsaboutsellingtheirproducts.Thisfeaturecan help farmers secure better prices for their crops, increasingtheirprofitsandpromotingeconomicgrowth intheagriculturalsector.

 RentFarmingResources-RentFarmingResourcesisa platformthatallowsfarmerstorentfarmingequipment and tools, such as tractors, harvesters, and irrigation systems,onashort-termbasis.Thisserviceeliminates the need for farmers to invest heavily in expensive equipment,makingiteasierandmorecost-effectivefor

them to manage their farms and increase their productivity.

2. Flowchart and its explanation

1. ResearchandAnalysis

 Conductresearchonthecurrentstateofagricultureand theproblemsfacedbysmallfarmers.

 Analyze existing solutions for leaf-based disease detection, renting equipment, and mandi price information.

 Identifythetargetusersandtheirrequirements.

 Definethescopeoftheproject.

2. RequirementsGathering

 Definethefunctionalandnon-functionalrequirementsof theapplication.

 Create user stories and use cases to capture user requirements.

 Definethedatarequirementsfortheapplication.

3. Design

 Createwireframesandmockupsoftheuserinterface.

 Definethearchitectureoftheapplication.

 Identifyandevaluatethetechnologiesandframeworks requiredtoimplementthesolution.

4. Development

 Implement the core functionality of the application, including leaf-based disease detection, renting equipment,andmandipriceinformation.

 Implementuserauthenticationusingphonenumberand OTP.

 DevelopasimpleUIthatisintuitiveandeasytouse.

 Test the application to ensure it meets the defined requirements.

5. Deployment

 ReleasetheapplicationtotheGooglePlayStore

 Monitor the application's performance and user feedback.

 Updatetheapplicationwithbugfixesandnewfeatures asnecessary.

6. MaintenanceandSupport

 Provide ongoing maintenance and support for the application.

 Addressanyissuesorbugsthatarise.

 Continuously improve the application based on user feedbackandchangingrequirements.

3. SYSTEM IMPLEMENTATION

4. Conclusion

We have successfully developed and implemented an intelligent crop recommendation system in this study that Indian farmers can utilize right away. The farmers would benefitfromthissystem'shelpinmakingeducateddecisions aboutthetypesofdiseasesaffectingtheircropsandpossible treatments.MandiPrice,theabilitytorentoutequipment. Utilizingthemethodsoutlinedpreviously,thebuildingofan electronic expert system for the identification of plant diseases affecting the leaves is accomplished with the inclusionoftheotherservicesoutlinedabove.

5. Future Scope

 Imageauthenticitycheck:Inthefuture,theprojectcan be enhanced to include an image authenticity check feature.Thisfeaturewouldallowthemodeltolearnto verifywhetheranimageisgenuineorhasbeentampered with.

 Communitysupport:Anotherfutureupdatecouldbethe inclusionofacommunitysupportfeature.Thisfeature would allow users to connect with other farmers, exchangeideasandgetsupportfromeachother.

 Agriculture-related news: The app can be updated to includeanewssectionthatcoversthelatesttrendsand updatesintheagricultureindustry.Userscangetaccess tonewsarticlesrelatedtofarming,agriculturepolicies, andotherrelevantinformation.

 Bankdocumentsforloans:Theprojectcanalsoincludea feature that provides users with access to bank documentsrequiredforloans.Thisfeaturewouldhelp farmerstoeasilyapplyforloansandgetthenecessary documentswithoutanyhassle.

 Multilingualsupport:Theappcanbeupdatedtosupport multiple languages. This feature would help farmers fromdifferentregionsofthecountrytousetheappin their preferred language, making it moreaccessible to them.

REFERENCES

[1] Reddy,Santosh,etal."Asurveyoncropdiseasedetection and prevention using an android application." InternationalJournalofInnovativeScience,Engineering &Technology2.4(2015):621-6.

[2] Alam, Mohammad Jahangir, Md Abdul Awal, and Md Nurul Mustafa. "Crop disease detection and solution system."InternationalJournalofElectricalandComputer Engineering9.3(2019):2112.

[3] Ashok, Vani, and D. S. Vinod. "A novel fusion of deep learning and android application for real-time mango

fruit disease detection." Intelligent System Design. Springer,Singapore,2021.781-791.

[4] Konstantinos P. Ferentinos, Deep learning models for plant disease detection and diagnosis, Computers and ElectronicsinAgriculture,Volume145,2018,Pages311318, ISSN 0168-1699, https://doi.org/10.1016/j.compag.2018.01.009

[5] N. Patil, S. Kelkar, M. Ranawat and M. Vijayalakshmi, "Krushi Sahyog: Plant disease identification and Crop recommendationusingArtificialIntelligence,"20212nd International Conference for Emerging Technology (INCET), 2021, pp. 1-6, doi: 10.1109/INCET51464.2021.9456114.

[6] Z. Doshi, S. Nadkarni, R. Agrawal and N. Shah, "AgroConsultant: Intelligent Crop Recommendation System Using Machine Learning Algorithms," 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), 2018,pp.1-6,doi:10.1109/ICCUBEA.2018.8697349.

[7] TY -BOOKAU -Kumar,RakeshAU -Singh,Maharana AU -Kumar,PrabhatAU -Singh,JyotiPY -2015/05/06 T1 -CropSelectionMethodtoMaximiseCropYieldRate using Machine Learning Technique DO10.1109/ICSTM.2015.7225403.

[8] A. Morbekar, A. Parihar and R. Jadhav, "Crop Disease DetectionUsingYOLO,"2020InternationalConference for Emerging Technology (INCET), 2020, pp. 1-5, doi: 10.1109/INCET49848.2020.9153986.

AUTHOR={Roy,ArunabhaM.andBhaduri,Jayabrata}, TITLE = {A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision}, JOURNAL = {AI}, VOLUME = {2}, YEAR = {2021}, NUMBER = {3}, PAGES = {413 428}, URL = {https://www.mdpi.com/2673-2688/2/3/26}, ISSN = {2673-2688}.

[9] Wani,J.A.,Sharma,S.,Muzamil,M.etal.MachineLearning andDeepLearningBasedComputationalTechniquesin Automatic Agricultural Diseases Detection: Methodologies, Applications, and Challenges. Arch Computat Methods Eng 29, 641–677 (2022). https://doi.org/10.1007/s11831-021-09588-5

[10]V.Pallagani,V.Khandelwal,B.Chandra,V.Udutalapally, D.DasandS.P.Mohanty,"dCrop:ADeep-LearningBased FrameworkforAccuratePredictionofDiseasesofCrops in Smart Agriculture," 2019 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS), 2019, pp. 29-33, doi: 10.1109/iSES47678.2019.00020.

[11]A.Nigam,S.Garg,A.AgrawalandP.Agrawal,"CropYield Prediction Using Machine Learning Algorithms," 2019

Fifth International Conference on Image Information Processing (ICIIP), 2019, pp. 125-130, doi: 10.1109/ICIIP47207.2019.8985951.

[12]Ahmed, A.A.; Reddy, G.H. A Mobile-Based System for Detecting Plant Leaf Diseases Using Deep Learning. AgriEngineering 2021, 3, 478-493. https://doi.org/10.3390/agriengineering3030032

[13]Medar,Ramesh&Rajpurohit,Vijay&Shweta,Shweta. (2019). Crop Yield Prediction using Machine Learning Techniques.1-5.10.1109/I2CT45611.2019.9033611.

[14]ManikRakhra,RamandeepSingh,Astudyofmachinery andequipmentusedbyfarmerstodevelopanuberized model for renting and sharing, Materials Today: Proceedings, 2021, ISSN 2214-7853, https://doi.org/10.1016/j.matpr.2020.11.784

[15]Suresh, N., Ramesh, N. V. K., Inthiyaz, S., Priya, P. P., Nagasowmika, K., Kumar,K.V. N. H., … Reddy,B.N. K. (2021). Crop Yield Prediction Using Random Forest Algorithm. 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS).doi:10.1109/icaccs51430.2021.9441871.

[16]Medar, R., Rajpurohit, V. S., & Shweta, S. (2019). Crop Yield Prediction using Machine Learning Techniques. 2019IEEE5thInternationalConferenceforConvergence in Technology (I2CT). doi:10.1109/i2ct45611.2019.9033611

[17]Selvaraj, M.G., Vergara, A., Ruiz, H. et al. AI-powered bananadiseasesandpestdetection.PlantMethods15,92 (2019).https://doi.org/10.1186/s13007-019-0475-z

[18]GeetharamaniG.,ArunPandianJ.,Identificationofplant leaf diseases using a nine-layer deep convolutional neural network, Computers & Electrical Engineering, Volume 76, 2019, Pages 323-338, ISSN 0045-7906, https://doi.org/10.1016/j.compeleceng.2019.04.011

[19]S. M. PANDE, P. K. RAMESH, A. ANMOL, B. R. AISHWARYA, K. ROHILLA and K. SHAURYA, "Crop Recommender System Using Machine Learning Approach," 2021 5th International Conference on ComputingMethodologiesandCommunication(ICCMC), 2021, pp. 1066-1071, doi: 10.1109/ICCMC51019.2021.9418351.