• Login
    View Item 
    •   NM-AIST Home
    • Computational and Communication Science Engineering
    • Research Articles [CoCSE]
    • View Item
    •   NM-AIST Home
    • Computational and Communication Science Engineering
    • Research Articles [CoCSE]
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Poultry diseases diagnostics models using deep learning

    Thumbnail
    View/Open
    Full text (741.0Kb)
    Date
    2022-08-01
    Author
    Machuve, Dina
    Nwankwo, Ezinne
    Mduma, Neema
    Jimmy, Mbelwa
    Metadata
    Show full item record
    Abstract
    Coccidiosis, Salmonella, and Newcastle are the common poultry diseases that curtail poultry production if they are not detected early. In Tanzania, these diseases are not detected early due to limited access to agricultural support services by poultry farmers. Deep learning techniques have the potential for early diagnosis of these poultry diseases. In this study, a deep Convolutional Neural Network (CNN) model was developed to diagnose poultry diseases by classifying healthy and unhealthy fecal images. Unhealthy fecal images may be symptomatic of Coccidiosis, Salmonella, and Newcastle diseases. We collected 1,255 laboratory-labeled fecal images and fecal samples used in Polymerase Chain Reaction diagnostics to annotate the laboratory-labeled fecal images. We took 6,812 poultry fecal photos using an Open Data Kit. Agricultural support experts annotated the farm-labeled fecal images. Then we used a baseline CNN model, VGG16, InceptionV3, MobileNetV2, and Xception models. We trained models using farm and laboratory-labeled fecal images and then fine-tuned them. The test set used farm-labeled images. The test accuracies results without fine-tuning were 83.06% for the baseline CNN, 85.85% for VGG16, 94.79% for InceptionV3, 87.46% for MobileNetV2, and 88.27% for Xception. Finetuning while freezing the batch normalization layer improved model accuracies, resulting in 95.01% for VGG16, 95.45% for InceptionV3, 98.02% for MobileNetV2, and 98.24% for Xception, with F1 scores for all classifiers above 75% in all four classes. Given the lighter weight of the trained MobileNetV2 and its better ability to generalize, we recommend deploying this model for the early detection of poultry diseases at the farm level.
    URI
    https://doi.org/10.3389/frai.2022.733345
    https://dspace.nm-aist.ac.tz/handle/20.500.12479/1454
    Collections
    • Research Articles [CoCSE]

    Nelson Mandela-AIST copyright © 2021  DuraSpace
    Theme by 
    Atmire NV
     

     

    Browse

    All PublicationsCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Nelson Mandela-AIST copyright © 2021  DuraSpace
    Theme by 
    Atmire NV