Scribd Logo
Upload

Welcome to Scribd!

  • 6 views

    POSTER Updated

    Uploaded by

    Shweta Pradhan
    The document summarizes a student project on developing a machine learning model using convolutional neural networks (CNN) to classify plant leaves as healthy or diseased based on visual images. The project aimed to address challenges in early and accurate plant disease identification. The methodology involved collecting and preprocessing a dataset to train and validate a CNN model to classify tomato plant leaves. Experimental details described the CNN architecture and training process, achieving 56.39% accuracy. The conclusions discussed potential applications in optimizing hydroponic systems, opportunities to improve the model, and how the innovation could revolutionize agricultural practices.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    POSTER Updated

    Uploaded by

    Shweta Pradhan
    6 views1 page
    The document summarizes a student project on developing a machine learning model using convolutional neural networks (CNN) to classify plant leaves as healthy or diseased based on visual images. The project aimed to address challenges in early and accurate plant disease identification. The methodology involved collecting and preprocessing a dataset to train and validate a CNN model to classify tomato plant leaves. Experimental details described the CNN architecture and training process, achieving 56.39% accuracy. The conclusions discussed potential applications in optimizing hydroponic systems, opportunities to improve the model, and how the innovation could revolutionize agricultural practices.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document summarizes a student project on developing a machine learning model using convolutional neural networks (CNN) to classify plant leaves as healthy or diseased based on visual images. The project aimed to address challenges in early and accurate plant disease identification. The methodology involved collecting and preprocessing a dataset to train and validate a CNN model to classify tomato plant leaves. Experimental details described the CNN architecture and training process, achieving 56.39% accuracy. The conclusions discussed potential applications in optimizing hydroponic systems, opportunities to improve the model, and how the innovation could revolutionize agricultural practices.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    6 views1 page

    POSTER Updated

    Uploaded by

    Shweta Pradhan
    The document summarizes a student project on developing a machine learning model using convolutional neural networks (CNN) to classify plant leaves as healthy or diseased based on visual images. The project aimed to address challenges in early and accurate plant disease identification. The methodology involved collecting and preprocessing a dataset to train and validate a CNN model to classify tomato plant leaves. Experimental details described the CNN architecture and training process, achieving 56.39% accuracy. The conclusions discussed potential applications in optimizing hydroponic systems, opportunities to improve the model, and how the innovation could revolutionize agricultural practices.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 1

    PRADARSHANA 2023

    Open Day - Project Exhibition

    SMART HYDROPONICS SYSTEM

    Department of Electronics and telecommunications Guide Arvind Kumar

    PROJECT POSTER PRESENTATION

    OBJECTIVE METHODOLOGY APPLICATIONS OF THE


    Address the challenge of PROJECT
    accurately identifying and Collecting and preprocessing a dataset • Detect plant diseases early:
    diagnosing, plant diseases of plant leaf images, splitting the to minimize further spread
    based on visual symptoms on dataset into training, and validation and minimize crop losses.
    the leaves and develop a sets. A Convolutional Neural Network • Improve crop yields:
    machine learning model using (CNN) was designed and trained on the identifying the plant disease in
    CNN that can accurately training set and then validated on the
    classify plants into healthy the early stage.
    validation set. The final trained CNN
    and unhealthy categories • Reduce pesticide usage:
    model is used to classify new plant leaf
    based on leaf images. images as healthy or diseased, if With accurate predictions
    diseased then the model further tries to pesticides and fungicides
    predict the disease. would not be overused.
    • Save time and labor costs:
    for manual plant inspection
    BACKGROUND and disease diagnosis.
    Plant leaf disease detection •
    using Convolutional Neural EXPERIMENTAL DETAILS
    Networks (CNNs) is a promising A CNN model was developed using the
    Plant Village tomato plant dataset to CONCLUSION
    approach for automated and
    classify images of healthy and The prediction system using CNN has been
    accurate diagnosis of plant
    unhealthy leaves which has multiple developed for controlling the parameters of
    diseases. CNNs are well-suited
    convolutional layers. The model was hydroponic systems in real-time. The
    for detecting subtle differences
    trained with augmented data and Adam system can be extended by training on a
    between healthy and diseased
    optimizer for 20 epochs, achieving a larger dataset, leading to higher accuracy
    plant leaves, and recent studies
    certain accuracy and a function was and adaptability to different plant species.
    have reported high accuracy
    written to predict the state of a leaf This innovation has the potential to
    rates in identifying various types
    based on the trained model. revolutionize the way we grow plants and
    of plant diseases.
    applies machine learning techniques in
    agriculture.

    RESULTS

    • The following graphs were observed on


    running the model over the training and
    validation datasets.
    • The accuracy of the prediction model was
    found to be 56.39%

    You might also like