UGC Approved Journal no 63975(19)

ISSN: 2349-5162 | ESTD Year : 2014
Call for Paper
Volume 11 | Issue 3 | March 2024

JETIREXPLORE- Search Thousands of research papers



WhatsApp Contact
Click Here

Published in:

Volume 9 Issue 5
May-2022
eISSN: 2349-5162

UGC and ISSN approved 7.95 impact factor UGC Approved Journal no 63975

7.95 impact factor calculated by Google scholar

Unique Identifier

Published Paper ID:
JETIR2205985


Registration ID:
402857

Page Number

i592-i598

Share This Article


Jetir RMS

Title

Hybrid Deep Learning Algorithm for Detecting Pneumonia Diseases

Abstract

Abstract:-Pneumonia is an infection in the lung tissue caused by a variety of different pathogens, including viruses, bacteria, and fungi, and the result is inflammation. The inflammation brings water into the lung tissue, and that extra water can make it harder to breathe. To know if the patient has Pneumonia [1], experts will start by asking about the patient’s medical history and doing a physical exam, including listening to your lungs with a stethoscope to check for abnormal bubbling or crackling sounds that suggest pneumonia. If pneumonia is suspected, the doctor may recommend the following tests Blood tests, Chest X-ray, CT scan, MRI, etc. Early detection and treatment of pneumonia can reduce mortality rates among children significantly in countries having a high prevalence. The progression of Deep Learning contributes to helping in the decision-making process of the experts to diagnose patients with pneumonia or not. The main motivation behind this research was to identify Pneumonia just by using the X-Ray images of the patients to facilitate the diagnosis decision process. Therefore, a convolutional neural network (CNN) and Machin learning algorithm (Random Forest and XGBoost) ware proposed for diagnosis of pneumonia. To solve the cumbersome problem, six different CNN models will develop, to make the work of the radiologist simpler. CNN model( MobileNet, VGG-16, AlexNet, Inception-v3, ResNet-50, and LeNet models) pre-trained on the ImageNet dataset and other machine learning (Random Forest and XGBoost) classifiers were trained with the appropriate transfer learning with a dataset of 5856 images and using a 224x224 resolution with 32 batch sizes are applied to verify the performance of each models being trained. After the classification of the RF and XGBoosting classifiers differently using CNN model trained features, the accuracy obtained respectively were 97.70%, and 97.50%. This proposed CNN-RF hybrid method is comparable with other existing conventional methods having an accuracy of 97.70% and an AUC score of 98%.

Key Words

Pneumonia Detection, Deep Learning, CNN, VGG16, XGBoost, Random Forest, Hybrid Algorithm.

Cite This Article

"Hybrid Deep Learning Algorithm for Detecting Pneumonia Diseases", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.i592-i598, May 2022, Available :http://www.jetir.org/papers/JETIR2205985.pdf

ISSN


2349-5162 | Impact Factor 7.95 Calculate by Google Scholar

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 7.95 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Cite This Article

"Hybrid Deep Learning Algorithm for Detecting Pneumonia Diseases", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppi592-i598, May 2022, Available at : http://www.jetir.org/papers/JETIR2205985.pdf

Publication Details

Published Paper ID: JETIR2205985
Registration ID: 402857
Published In: Volume 9 | Issue 5 | Year May-2022
DOI (Digital Object Identifier):
Page No: i592-i598
Country: Visakhapatnam, Andhra Pradesh, India .
Area: Science & Technology
ISSN Number: 2349-5162
Publisher: IJ Publication


Preview This Article


Downlaod

Click here for Article Preview

Download PDF

Downloads

000207

Print This Page

Current Call For Paper

Jetir RMS