SmartAgriDoc: Offline Plant Disease Detection with AI-Powered Mobile App

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

SmartAgriDoc: Offline Plant Disease Detection with AI-Powered Mobile App

C. Aiman Sulthana¹, Niha Dodamani², Isra Tinmekar³, Prof. Vaibhav Chavan´

¹B.E. Student, Dept. of Artificial Intelligence and Data Science, Angadi Institute of Technology and Management, Belagavi, Karnataka, India

²B.E. Student, Dept. of Artificial Intelligence and Data Science, Angadi Institute of Technology and Management, Belagavi, Karnataka, India

³B.E. Student, Dept. of Artificial Intelligence and Data Science, Angadi Institute of Technology and Management, Belagavi, Karnataka, India

⁴Professor & Project Guide, Dept. of Artificial Intelligence and Data Science, Angadi Institute of Technology and Management, Belagavi, Karnataka, India

Abstract - Plant diseases cause significant losses in agriculture,threateningfoodsecurityandfarmerlivelihoods. Traditional disease identification methods require expert knowledge, which is often inaccessible to rural farmers. To address this challenge, we propose SmartAgriDoc, an AIpowered mobile application that enables offline plant disease detection using deep learning. The app leverages Convolutional Neural Networks (CNNs) trained on a diverse dataset of healthy and diseased plant leaf images. Integrated with TensorFlow Lite and developed using Flutter, the app offers real-time disease diagnosis and remedysuggestions without the need for internet connectivity. This offline capabilityensuresaccessibilityinremotefarmingregions.Key features include image preprocessing (resizing, normalization),high-accuracypredictions,andauser-friendly interface. Oursolutionaimstoempowerfarmerswith instant and reliable plant health diagnostics, improving early intervention and crop productivity. Experimental results and literaturecomparisonsindicatehighaccuracyandpracticality of the system for real-world deployment.

Key Words: Plant Disease Detection, Deep Learning, Convolutional Neural Networks (CNN), Mobile Application, Offline Diagnosis, Smart Agriculture, TensorFlowLite,Flutter.

1.INTRODUCTION

AgricultureplaysavitalroleintheIndianeconomy,witha large portion of the population depending on it for livelihood. However, the productivity and quality of crops are often threatened by plant diseases, which can lead to severeeconomiclossesandreducedfoodsecurity.Earlyand accuratedetectionofplantdiseasesisessentialforeffective crop management, but traditional diagnostic methods requireagriculturalexpertiseandlaboratorysupport,which areofteninaccessibletosmall-scalefarmersinremoteareas.

Recentadvancementsinartificialintelligence(AI)anddeep learning have opened new possibilities in precision

agriculture. In particular, Convolutional Neural Networks (CNNs) have demonstrated significant success in image classificationtasks,includingplantdiseasedetection.Several studies have shown that AI models can surpass human expertsinidentifyingvisualsymptomsofcropdiseasesfrom leafimages.However,mostexistingsolutionsrelyoncloudbasedprocessing,requiringconstantinternetconnectivity, whichlimitstheirapplicabilityinruralenvironments.

Toovercomethischallenge,wepropose SmartAgriDoc,a mobileapplicationthatperformsplantdiseasedetectionin an offlineenvironment usinganAImodelembeddedwithin theappvia TensorFlowLite.Theapplicationisdeveloped using Flutter for cross-platform compatibility and is designed to provide a seamless and intuitive user experience. Farmers can simply capture an image of the diseased leaf using their smartphone, and the app will analyzetheimageandprovidethepredicteddiseasealong with suggested remedies without needing an internet connection.This paper presents the development, architecture,andperformanceevaluationofSmartAgriDoc. We also compare our work with existing literature and highlightthereal-worldbenefitsofourofflineAI-powered solutionforsustainableagriculture.

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

1.1 LITERATURE SURVEY

Thissectionreviewsrecentresearcheffortsinthedomain of plant disease detection using artificial intelligence and mobile technologies. Multiple studies have explored deep learning approaches, particularly Convolutional Neural Networks(CNNs),toclassifyandidentifyplantdiseasesfrom leafimages.Forinstance,thepaper“PlantDiseaseDetection andClassificationbyDeepLearning:AReview”emphasizes theeffectivenessofCNNsinagriculturalimagerecognition tasks.Otherworkshavehighlightedthelimitationsofonline detectionsystemsthatrelyheavilyoncloudinfrastructure, whichisofteninaccessibleinruralareas.

Additionally, mobile-based solutions are gaining popularity,withsomeincorporatingAImodelsforreal-time analysis. However, most of these require active internet connectivity,limitingtheirutilityinofflinefieldconditions. Ourproposedworkbuildsuponthesestudiesbyintroducing amobileapplicationthatleverageson-deviceinferencewith TensorFlowLite,makingdiseasedetectionpossibleevenin low-connectivityenvironments.

Table1-Literaturesurvey

Bhanu Prakas hetal.

BasedPlant Disease Detection

Role of AI in Sustainable Agriculture: Recent Trends and Challenges SSRN Workin gPaper Series (2023)

1.3 OBJECTIVES

memory and processing needs Lite for efficient mobile inference

Overview of AI in Agricultur e Lacks implementati ondetailsfor offline deployment Practical deployment using lightweight on-device AImodelfor real-world application

Themaingoalofthisprojectistodesignandimplementa practical, AI-driven solution that assists farmers in identifying plant diseases quickly and accurately, even in ruralorlow-connectivityregions.Thespecificobjectivesof theprojectareasfollows:

 Todevelopacross-platformmobileapplication usingFlutterthatallowsusers(primarilyfarmers) tocaptureimagesofplantleavesandreceiveinstant feedbackonpotentialdiseasesandremedies.

CNN,Deep Learning Focuses mainly on online/cloud -based detection

Title Author (s) Technolo gy Used Limitations Our Improvem ent Plant Disease Detection and Classificatio n by Deep Learning:A Review

Efficient Plant Disease Detection using AI and Mobile Application

CropLeaf: AnEfficient Mobile Application for Plant Disease Diagnosis Using CNN Models

R. Pravee n Kumar etal. Kum aretal. CNN, Android App, Cloud Processi ng

Requires internet connection; lacks offline capability

Provides offline,realtime detection using TensorFlow Lite

Performs detection without internet via on-device AI

 To design and train a deep learning model, specificallyaConvolutionalNeuralNetwork(CNN), capable of classifying various plant diseases from leafimageswithhighaccuracy.Themodelistrained using a publicly available and labeled dataset of plantdiseaseimages.

 To optimize the trained AI model for mobile deployment by converting it to TensorFlow Lite format.Thisenablesthemodeltorunlocallyonthe user'sdevice,eliminatingdependencyoninternet connectivity.

 Toimplementanofflinediagnosissystem that ensurestheapplicationisaccessibleandfunctional inremoteagriculturalareaswhereinternetaccess islimitedorunreliable.

 To provide disease-specific information and remedies, including preventive measures and recommended treatments, to empower farmers withactionableknowledgetoprotecttheircrops.

 To ensure an intuitive and accessible user interface, making the app usable even for individualswithminimaltechnicalbackground.

 To contribute to sustainable agriculture by reducing crop losses, minimizing the need for expertintervention,andpromotingtimelydisease management practices through affordable and scalabledigitaltechnology.

D. Suresh etal.

ResNet, TensorFlo w Complex architecture increases

Optimized model with TensorFlow

Ali Khanet al. CNN, Mobile App, Web backend Heavily dependent on backend servers for predictions Offline detection using embedded model in mobile device Deep Learning for Image-

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

Figure2-SimpleVisualizationofourapp

1.4 SCOPE AND CONTRIBUTION

Thescopeofthisprojectencompassesthedevelopmentand deployment of an AI-powered mobile application that can detectand classifyplantdiseasesusingimagesofaffected leaves. The system is designed specifically for use in agricultural settings, targeting farmers, agronomists, and agriculturalextensionworkers.Theapplicationwilloperate entirely offline, making it highly suitable for rural and remote regions where internet connectivity is limited or unreliable.

The system includes the following components within its scope:

 Apre-trainedConvolutionalNeuralNetwork(CNN) modeloptimizedusingTensorFlowLite.

 AmobileapplicationbuiltusingFlutter,compatible withbothAndroidandiOSplatforms.

 Real-time disease classification from plant leaf imagescapturedthroughamobilecamera.

 Offline functionality with embedded AI model to ensureinstantfeedback.

 Remedy suggestions and disease descriptions tailoredtoeachdetectedcondition.

A clean, user-friendly interface designed for users with minimaldigitalliteracy.

Areasoutsidethescopeofthis projectinclude integration with external sensors, drone-based crop monitoring, and web-basedplatformsforcentralizedfarmmanagement.

ContributionoftheProject

Thisprojectmakesseveralkeycontributionstothefieldof smartagricultureandAI-basedplanthealthmonitoring:

 Offline AI Integration: Introduces an offlinecapablemobileapplicationthatembedsanAImodel using TensorFlow Lite, addressing the major limitationofclouddependencyinexistingsolutions.

 AccessibleAgriculturalTechnology: Provides a low-cost, scalable, and user-friendly tool for farmers,reducingtheirdependenceonagricultural expertsorlabdiagnostics.

 HighAccuracyDiseaseDetection:UtilizesawelltrainedCNNmodeltoofferreliableclassificationof multipleplantdiseasesbasedonvisualsymptoms, improvingearlydetectionandmanagement.

 Improved Crop Management: Enables timely interventionanddecision-makingthroughaccurate diseasepredictionandtreatmentrecommendations, ultimatelycontributingtoincreasedcropyieldand reducedlosses.

 OpenandExtendableArchitecture:Thesystem architectureallowsforfutureenhancementssuchas multilingualsupport,integrationofadditionalcrop datasets,orconnectivitytoagriculturaladvisories andexpertnetworks.

2. METHODOLOGY

The methodology adopted in the development of SmartAgriDoc:OfflinePlantDiseaseDetectionwithAIPowered Mobile App is structured in multiple phases, combiningdatapreprocessing,deeplearningmodeltraining, mobile integration, and offline optimization. The entire workflow is designed to enable real-time, accurate, and offlinedetectionofplantdiseasesthroughasmartphone.

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

2.1 Data Collection and Preprocessing

 Apubliclyavailabledatasetofplantleafimages,such asthePlantVillagedataset,wasusedfortrainingthe model. The dataset includes healthy and diseased leaf samples from various crops such as tomato, corn,andpotato.

Figure4-Datacollectionandpreprocessing

 Preprocessingtechniquesincludedresizingimages to 224x224 pixels, normalization, and data augmentation (rotation, flipping, zooming) to improvegeneralizationandavoidoverfitting.

Figure5-BlockDiagramofDatacollectionand preprocessing

2.2 Model Selection and Training

 A Convolutional Neural Network (CNN) architecturewaschosenforimageclassificationdue toitseffectivenessinextractingvisualfeatures.

 ThemodelwasimplementedusingTensorFlowand trained on labeled data for multiple disease categories.

 Thedatasetwassplitintotraining,validation,and testing subsets to evaluate performance and tune hyperparameters.

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

2.3 Model Optimization and Conversion

 After achieving satisfactory accuracy, the trained modelwasconvertedto TensorFlowLite formatto enabledeploymentonmobiledevices.

 Quantization techniques were applied to reduce model size and improve inference speed while maintainingaccuracy.

2.4 Mobile Application Development

 The mobile app was developed using Flutter, a cross-platform UI toolkit, to ensure compatibility withAndroidandiOS.

 Theappenablesuserstocaptureorselecta plant leafimage, which is then passed tothe embedded TensorFlowLitemodelforprediction.

 Thepredicteddiseaselabelandremedysuggestions aredisplayedtotheuserinrealtime.

2.5 Offline Functionality

Allprocessing,includingdiseasedetection,isperformed locallyonthedevicewithoutrequiringinternetaccess.

Remedy information is hardcoded or stored locally within the app to provide instant suggestions even in remoteareas.

2.6 Backend and Frontend Design

ThedesignoftheSmartAgriDocmobileapplication consistsoftwoprimarycomponents:thefrontend(user interface) and the backend (AI inference and data management).Bothcomponentsarecarefullydeveloped to provide a seamless user experience, quick

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

performance, and reliable disease detection even withoutinternetconnectivity.

Frontend Design

 ThefrontendoftheapplicationisbuiltusingFlutter, across-platformframeworkthatallowsdeployment on both Android and iOS devices using a single codebase.

 The user interface is designed to be minimal, intuitive,anduser-friendly,cateringtofarmersand userswithlimitedtechnicalexpertise.

 KeyUIcomponentsinclude:

o Ahomescreenwithnavigationoptionsto access features such as image capture, imageupload,predictionhistory,andhelp section.

o Acamerainterfaceorimageuploadoption toselecttheplantleafimage.

o A prediction screen that displays the disease name, confidence level, and correspondingremedy.

o Local language support (optional enhancement)toimproveaccessibility.

 The design follows material design principles for responsivelayout,clarity,andconsistency.

Backend Design

 The backend involves the integration of a TensorFlow Lite model within the mobile application.Thereisnoneedforaremoteserveror cloudbackendsincethemodelrunsdirectlyonthe device.

 Themodelisresponsiblefor:

o Acceptinginputimagesandpreprocessing them(resizing,normalization).

o FeedingtheprocessedimageintotheCNN forprediction.

o Mapping prediction results to disease namesandsuggestedtreatments.

 AlocaldatabaseorJSONfileisembeddedwithinthe app to store disease information and remedy suggestions,allowingforofflineaccess.

Offline Integration

 Allfunctionalities,includingimageanalysis,disease prediction, and result display, are performed withoutinternetaccess.

 This offline capability is made possible by embeddingthetrainedandquantizedTensorFlow Litemodeldirectlyintotheapplicationpackage.

This combination of a lightweight backend and accessiblefrontendensuresthatSmartAgriDocprovides a fast, efficient, and reliable solution for plant disease detectioninreal-worldagriculturalenvironments.

our conference for the name of your paper. In this newly created file, highlight all of the contents and import your preparedtextfile.Youarenowreadytostyleyourpaper.

3. CONCLUSIONS

The SmartAgriDoc project demonstrates the successful integrationofartificialintelligenceandmobiletechnologyto address a critical challenge in agriculture early and accessible detection of plant diseases. By leveraging a trained Convolutional Neural Network (CNN) model converted into TensorFlow Lite, the mobile application is capableofdeliveringaccuratediseaseclassificationwithout relyingoninternetconnectivity.

Theappisdesignedwithruralfarmersinmind,offeringa simple and intuitive interface that can be used even by individuals with minimal technical experience. Its offline capabilityisakeyinnovation,enablingreal-timediagnosisin remoteagriculturalareaswherenetworkaccessislimitedor unavailable.

Experimental results show that the model achieves high accuracy in detecting multiple plant diseases from leaf images, and the lightweight design ensures smooth operation on standard smartphones. Remedy suggestions providedwithintheappfurthersupportfarmersintaking timely corrective measures, thereby minimizing crop loss andimprovingyield.

Overall, SmartAgriDoc contributes to the advancement of precision agriculture by making intelligent plant disease diagnosisaffordable,scalable,andaccessible.Thissolution notonlyempowersfarmersbutalsopavesthewayforfuture innovationsinAI-drivenagriculturaltools.

3.1 Applications

The SmartAgriDoc mobile application has broad and practicalapplicationsintheagriculturaldomain.Itsoffline, AI-powered plant disease detection capabilities make it valuableforawiderangeofusersanduse-cases,particularly inresource-limitedsettings.Thekeyapplicationsinclude:

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

 Rural Farming Communities

Enables farmers in remote areas to identify plant diseaseswithouttheneedforexpertconsultationor internet connectivity, facilitating faster and more informeddecision-making.

 Agricultural Extension Services

Can be used by agricultural officers and field workerstosupportfarmersbyofferingon-the-spot diseasediagnosisandguidanceduringfieldvisits.

 Educational Institutions

Actsasapracticaltoolforstudentsandresearchers inagriculturalandAIdomainstounderstandplant pathology,imageclassification,andthereal-world deploymentofmachinelearningmodels.

 Government and NGO Programs

Usefulingovernment-ledorNGO-driveninitiatives aimed at improving crop productivity, digital farmingpractices,andfarmerwelfare.

 Smart Farming Systems

Canbeintegratedasamoduleinbroaderprecision agriculture solutions to enhance real-time plant healthmonitoringandcropmanagement.

 Nurseries and Greenhouses

Helpsnurserymanagersandgreenhouseoperators monitor plant health and control the spread of diseasesinatimelyandcost-effectivemanner.

By offering offline accessibility, real-time feedback, and reliable disease identification, SmartAgriDoc provides a powerful and scalable solution to support sustainable agricultureandfoodsecurityinitiatives.

3.2 Model Accuracy and Performance

The performance of the plant disease classification model was evaluated using standard metrics such as accuracy, precision,recall,andF1-score.Themodelwastrainedona labeled dataset of healthy and diseased plant leaf images, with preprocessing techniques such as resizing, normalization, and augmentation applied to improve generalization.

 TrainingAccuracy: ~98%

 ValidationAccuracy: ~95%

 TestAccuracy: ~94%

 Model Size (TensorFlow Lite): ~5–10 MB (optimizedformobile)

Figure8-TrainingvsValidationaccuracyoverepochs

The high accuracy achieved demonstrates the model's effectivenessincorrectlyidentifyingplantdiseasesbasedon visualsymptoms.Theslightdropintestaccuracyreflectsthe model'sgeneralizationabilityandiswithinacceptablelimits forreal-worldapplications.

The lightweight TensorFlow Lite model maintains nearinstant inference speeds on typical smartphones without requiring high computational power. This makes it highly suitable for offline deployment in rural areas where advancedhardwareandinternetconnectivityarelimited.

3.3 Maintenance and Updates

Thelong-termsuccessandreliabilityoftheSmartAgriDoc application depend not only on its initial deployment but also on consistent maintenance and timely updates. As agricultural diseases evolve and user needs change, maintaining the relevance and accuracy of the system is essential.

ModelUpdates

 Periodic retraining of the Convolutional Neural Network(CNN)modelwillbenecessarytoinclude newplantdiseasesandincorporateadditionalcrop types.

 Newtrainingdatacollectedfromusersubmissions oragriculturalinstitutionscanbeusedtoimprove modelgeneralizationandreducebias.

Remedy and Knowledge Base Updates

 Thelocaldatabasecontainingdiseasedescriptions andremedysuggestionswillbeupdatedregularly based on feedback from agricultural experts and newscientificfindings.

 Offline remedy content can be refreshed through periodic app updates delivered via app stores or directAPKdistribution.

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

AppMaintenance

 Bugs and performance issues will be addressed throughversionedupdatestotheFluttercodebase.

 Compatibility with the latest Android and iOS versionswillbeensuredtoprovideaseamlessuser experience.

UserFeedbackandFeatureEnhancement

 A feedback system can be implemented to allow userstoreportincorrectpredictionsorrequestnew features.

 Featureslikemultilingualsupport,voiceinput,and region-specificadvicecanbeaddedbasedonuser demand.

By maintaining both the AI model and mobile platform, SmartAgriDoc can continue to deliver reliable, real-time plantdiseasedetectionandadapttotheevolvingneedsof theagriculturalcommunity.

ACKNOWLEDGEMENT

We express our sincere gratitude to the Department of ArtificialIntelligenceandDataScience,AngadiInstituteof TechnologyandManagement,Belagavi,forprovidingusthe opportunitytoundertakethisprojecttitled “SmartAgriDoc: Offline Plant Disease Detection with AI-Powered Mobile App.”

Wearedeeplythankfultoourprojectguide, Prof.Vaibhav Chavan,forhisconsistentguidance,technicalexpertise,and valuable suggestions throughout the development of this project.Hisdedication,timelyfeedback,andsupportwere instrumentalinhelpingusshapeourideasintoafunctional and impactful solution. We truly appreciate the time and effortheinvestedinreviewingourworkandmentoringusat everystage.

WealsoextendourthankstoourHeadofDepartmentandall teaching and non-teaching staff for their continuous encouragementandresourcesprovidedduringthecourseof thiswork.

Finally,wewouldliketothankourfamiliesandfriendsfor their motivation, moral support, and encouragement throughoutthejourneyofthisproject.

REFERENCES

[1]BhanuPrakash,M.Divya,etal.,“PlantDiseaseDetection and Classification by Deep Learning A Review,” IEEE Access,vol.10,pp.2493–2510,2022.

[2] R. Praveen Kumar and Dr. S. S. Sridhar, “Plant Disease DetectionusingMachineLearningModels,”SSRN,2023.

[3] A. Khan, K. Ali, et al., “CropLeaf: An Efficient Mobile ApplicationforPlantDiseaseDiagnosisUsingCNNModels,” Int.J.ofComputerApplications,vol.187,no.9,pp.30–36, 2024.

[4]D.Suresh,S.Rekha,“PlantDiseaseDetectionUsingDeep ConvolutionalNeuralNetwork,”AppliedSciences,vol.12,no. 6982,pp.1–15,2022.

[5] R. Patel et al., “Role of AI in Sustainable Agriculture: RecentTrendsandChallenges,”SSRN,2023.

[6]S.Sladojevic,M.Arsenovic,etal.,“DeepNeuralNetworks Based Recognition of Plant Diseases by Leaf Image Classification,”ComputationalIntelligenceandNeuroscience, vol.2016,ArticleID3289801.

[7]D.Picon,A.Roche,“TransferLearningforPlantDisease ClassificationUsingLeafImages,”ComputersandElectronics inAgriculture,vol.189,2021.

[8] TensorFlow Lite Documentation, “TensorFlow Lite for Mobile and Edge Devices,” Available: https://www.tensorflow.org/lite

[9] Flutter Documentation, “Build Apps for Any Screen,” Available:https://flutter.dev/docs

[10]PlantVillageDatasetbyPennStateUniversity,Available: https://plantvillage.psu.edu

[11] J. Deng, W. Dong, et al., “ImageNet: A large-scale hierarchicalimagedatabase,”inProc.IEEECVPR,2009.

[12] S. Mohanty, D. P. Hughes, M. Salathé, “Using Deep Learning for Image-Based Plant Disease Detection,” FrontiersinPlantScience,vol.7,2016.

[13] N. A. Dey and A. S. Das, “Real-Time Smart Farming Solutions Using TensorFlow Lite,” Int. J. of Engineering ResearchandTechnology(IJERT),vol.10,no.5,2021.

[14] J. Brownlee, “Data Augmentation for Deep Learning,” MachineLearningMastery,2020.

[15]P.Krizhevsky,I.Sutskever,andG.E.Hinton,“ImageNet Classification with Deep Convolutional Neural Networks,” AdvancesinNeuralInformationProcessingSystems,vol.25, 2012.

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

Volume:12Issue:05|May2025 www.irjet.net p-ISSN:2395-0072

BIOGRAPHIES

C.AimanSulthana

isaB.E.studentintheDepartmentofArtificialIntelligence and Data Science at Angadi Institute of Technology and Management,Belagavi.Herareasofinterestincludeoverall methodology, deep learning, mobile application development, and smart agriculture solutions. She has actively contributed to model integration and interface designintheproject.

NihaDodamani

is pursuing her B.E. in Artificial Intelligence and Data ScienceatAngadiInstituteofTechnologyandManagement, Belagavi. Her interests lie in machine learning, data analytics,andAIforruraldevelopment.Inthisproject,she played a key role in dataset management, testing, and accuracyanalysis.

IsraTinmekar

isaB.E.studentintheDepartmentofArtificialIntelligence and Data Science at Angadi Institute of Technology and Management,Belagavi.SheispassionateaboutapplyingAI in healthcare and agriculture. Her contributions to the project focused on system architecture, remedy data design,anddocumentation.

Prof.VaibhavChavan

is currently working as Assistant Professor in the Department of Artificial Intelligence and Data Science at AngadiInstituteofTechnologyandManagement,Belagavi. He has extensive experience in teaching, research, and guiding undergraduate projects in the areas of machine learning, data science, and AI applications. His valuable mentorship and technical expertise have significantly contributed to the successful execution of the SmartAgriDocproject.