Pneumonia is an inflammatory lung disease which mainly affects the small air sacs known as alveoli. Symptoms of Pneumonia usually involves a mixture of painful or dry cough, chest discomfort, fatigue and difficulties in breathing. So, symptoms of pneumonia can be detected using chest x-rays. Since chest x-rays plays an important role in the detection of pneumonia a deep learning approach can be used for the detection in order to automate it. In this paper the implementation of deep learning approach for the chest x-rays is proposed. This approach has three convolution layers each with 32 neurons with three different channels (3*3). In order to obtain a more robust accuracy, images are transformed based on various parameters. Experimental analysis validates the accuracy of proposed model as 88.68%. The training accuracy and validation accuracy of the model in each epoch is analysed and observed as comparatively high than conventional process.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Deep Learning Approach to detect Pneumonia


    Contributors:


    Publication date :

    2020-11-05


    Size :

    287863 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Using Deep-Learning Approach to Detect Anomalous Vibrations of Press Working Machine

    Inagaki, Kazuya / Hayamizu, Satoru / Tamura, Satoshi | TIBKAT | 2021


    Deep Learning Based Automated Pneumonia Detection from X-ray Images

    S, Sunil Kumar Aithal / Rajashree | IEEE | 2023


    Using Deep-Learning Approach to Detect Anomalous Vibrations of Press Working Machine

    Inagaki, Kazuya / Hayamizu, Satoru / Tamura, Satoshi | Springer Verlag | 2020


    A Deep Learning Approach to Detect Real-Time Vehicle Maneuvers Based on Smartphone Sensors

    Li, Pei / Abdel-Aty, Mohamed / Cai, Qing et al. | IEEE | 2022


    DEEP NEURAL NETWORK APPROACH TO DETECT GNSS SPOOFING ATTACKS

    Borhani-Darian, Parisa / Li, Haoqing / Wu, Peng et al. | British Library Conference Proceedings | 2020