@article{MAKHILLJEAS202217429024,
    title = {Mobile App for Dental Caries Detection by Deploying Deep Learning Model},
    journal = {Journal of Engineering and Applied Sciences},
    volume = {17},
    number = {4},
    pages = {69-75},
    year = {2022},
    issn = {1816-949x},
    doi = {jeas.2022.69.75},
    url = {https://makhillpublications.co/view-article.php?issn=1816-949x&doi=jeas.2022.69.75},
    author = {S.,M. and},
    keywords = {Image processing, deep learning, data collection, accuracy, loss},
    abstract = {<p>A dataset of images of human teeth, both with and without cavities, is gathered via Kaggle. An equal number of images representing each category are selected for testing, training and validation from each of the three compartments of this dataset. The selected images undergo three preprocessing techniques: Image scaling, image scaling and image upscaling. At the same time, we use convolution neural network techniques to develop deep learning models. Then the model is trained on the preprocessed dataset. Accuracy and loss are used to evaluate the effectiveness of training. The values are also tabulated to understand the behavior of the model. The verification process follows the same phases. Analyze and display training and validation data in bar charts. Training and validation results show that the model can analyze images and predict the presence of caries with a short evaluation. Both training and validation yield high accuracy scores and very low loss scores. The model<br />
is trained and validated and finally he is tested once. The final accuracy of the model is determined to be 96% with a loss value of 11%. We found this deep learning model to have good accuracy and loss values, so we used it to build his mobile application. Additionally, the functionality of the application is checked and found to be perfect.</p>
}
    }