An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images

Kanishkha Jaisankar; Pranav M. Pawar; Diana Susan Joseph

doi:10.1109/icaia57370.2023.10169832

An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images

Kanishkha Jaisankar, Pranav M. Pawar, Diana Susan Joseph

Birla Institute of Technology and Science Pilani

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Covid-19 was a global phenomenon which spread rapidly and cost so many lives across the globe. It can be detected at early stages from radiology scans using Deep Learning. This Research analyses the comparison between a Hybrid Learning Model and pre-trained models VGG19, Xception and MobileNet. The aim of the research was to classify the Chest X-Ray scans as COVID-19 positive or negative using deep learning techniques. The results showed that the Hybrid Learning model built from scratch produced better accuracy than other transfer learning approaches. These results show us that implementing these Computer-aided diagnoses (CAD) systems in hospitals and clinics can be an efficient way of detecting COVID-19 presence from chest X-rays. This method can provide much more accurate results and timely diagnosis and cure for patients.

Original language	English
Title of host publication	2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665456272
DOIs	https://doi.org/10.1109/icaia57370.2023.10169832
State	Published - 2023
Externally published	Yes
Event	2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Hybrid, Bangalore, India Duration: 21 Apr 2023 → 22 Apr 2023

Publication series

Name	2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding

Conference

Conference	2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023
Country/Territory	India
City	Hybrid, Bangalore
Period	21/04/23 → 22/04/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

ANN
CAD
CNN
HOG
KNN
MobileNet
NB
Random Forest
ResNet
SMOTE
SVM
VGG-19
VGG16
XGB-L
XGboost
Xception

Access to Document

10.1109/icaia57370.2023.10169832

Cite this

Jaisankar, K., Pawar, P. M., & Joseph, D. S. (2023). An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images. In 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding (2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/icaia57370.2023.10169832

Jaisankar, Kanishkha ; Pawar, Pranav M. ; Joseph, Diana Susan. / An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images. 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding).

@inproceedings{16a662827c97479abff1fe400f4856f0,

title = "An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images",

abstract = "Covid-19 was a global phenomenon which spread rapidly and cost so many lives across the globe. It can be detected at early stages from radiology scans using Deep Learning. This Research analyses the comparison between a Hybrid Learning Model and pre-trained models VGG19, Xception and MobileNet. The aim of the research was to classify the Chest X-Ray scans as COVID-19 positive or negative using deep learning techniques. The results showed that the Hybrid Learning model built from scratch produced better accuracy than other transfer learning approaches. These results show us that implementing these Computer-aided diagnoses (CAD) systems in hospitals and clinics can be an efficient way of detecting COVID-19 presence from chest X-rays. This method can provide much more accurate results and timely diagnosis and cure for patients.",

keywords = "ANN, CAD, CNN, HOG, KNN, MobileNet, NB, Random Forest, ResNet, SMOTE, SVM, VGG-19, VGG16, XGB-L, XGboost, Xception",

author = "Kanishkha Jaisankar and Pawar, {Pranav M.} and Joseph, {Diana Susan}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 ; Conference date: 21-04-2023 Through 22-04-2023",

year = "2023",

doi = "10.1109/icaia57370.2023.10169832",

language = "אנגלית",

series = "2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding",

address = "ארצות הברית",

}

Jaisankar, K, Pawar, PM & Joseph, DS 2023, An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images. in 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding. 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding, Institute of Electrical and Electronics Engineers Inc., 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023, Hybrid, Bangalore, India, 21/04/23. https://doi.org/10.1109/icaia57370.2023.10169832

An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images. / Jaisankar, Kanishkha; Pawar, Pranav M.; Joseph, Diana Susan.
2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images

AU - Jaisankar, Kanishkha

AU - Pawar, Pranav M.

AU - Joseph, Diana Susan

PY - 2023

Y1 - 2023

N2 - Covid-19 was a global phenomenon which spread rapidly and cost so many lives across the globe. It can be detected at early stages from radiology scans using Deep Learning. This Research analyses the comparison between a Hybrid Learning Model and pre-trained models VGG19, Xception and MobileNet. The aim of the research was to classify the Chest X-Ray scans as COVID-19 positive or negative using deep learning techniques. The results showed that the Hybrid Learning model built from scratch produced better accuracy than other transfer learning approaches. These results show us that implementing these Computer-aided diagnoses (CAD) systems in hospitals and clinics can be an efficient way of detecting COVID-19 presence from chest X-rays. This method can provide much more accurate results and timely diagnosis and cure for patients.

AB - Covid-19 was a global phenomenon which spread rapidly and cost so many lives across the globe. It can be detected at early stages from radiology scans using Deep Learning. This Research analyses the comparison between a Hybrid Learning Model and pre-trained models VGG19, Xception and MobileNet. The aim of the research was to classify the Chest X-Ray scans as COVID-19 positive or negative using deep learning techniques. The results showed that the Hybrid Learning model built from scratch produced better accuracy than other transfer learning approaches. These results show us that implementing these Computer-aided diagnoses (CAD) systems in hospitals and clinics can be an efficient way of detecting COVID-19 presence from chest X-rays. This method can provide much more accurate results and timely diagnosis and cure for patients.

KW - ANN

KW - CAD

KW - CNN

KW - HOG

KW - KNN

KW - MobileNet

KW - NB

KW - Random Forest

KW - ResNet

KW - SMOTE

KW - SVM

KW - VGG-19

KW - VGG16

KW - XGB-L

KW - XGboost

KW - Xception

UR - http://www.scopus.com/inward/record.url?scp=85166365735&partnerID=8YFLogxK

U2 - 10.1109/icaia57370.2023.10169832

DO - 10.1109/icaia57370.2023.10169832

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85166365735

T3 - 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding

BT - 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023

Y2 - 21 April 2023 through 22 April 2023

ER -

Jaisankar K, Pawar PM, Joseph DS. An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images. In 2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 International Conference on Artificial Intelligence and Applications, ICAIA 2023 and Alliance Technology Conference, ATCON-1 2023 - Proceeding). doi: 10.1109/icaia57370.2023.10169832

An End to End Hybrid Learning Model for Covid-19 Detection from Chest X-ray Images

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this