Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : International Journal of Engineering and Emerging Technology

Detection of Covid Chest X-Ray using Wavelet and Support Vector Machines Ni Wayan Sumartini Saraswati; Ni Wayan Wardani; I Gusti Ayu Agung Diatri Indradewi
International Journal of Engineering and Emerging Technology Vol 5 No 2 (2020): July - December
Publisher : Doctorate Program of Engineering Science, Faculty of Engineering, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/IJEET.2020.v05.i02.p019

Abstract

The study of digital image processing is still a hot topic in the realm of research, especially in medical research. The presence of various digital image processing methods and machine learning also contributes to the progress of research in this field. Detecting Covid Chest X-Ray is a prediction problem solving with a supervised classification method. In this study, the SVM method was chosen because it is proven to function as a good classifier as has been done in previous studies. Where previously the chest x-ray image feature extraction was carried out using wavelet transform. Feature extraction using wavelets has given the distinctive features of normal lung X-rays and distinguishes them from the distinctive features of Covid lung X-rays. The measurement results of the average classification model for the approximate, vertical, horizontal and diagonal dataset are 93.91% accuracy, 6.09% error rate, 98.75% recall, 89.06% specificity, and 91.26% precision. The vertical dataset is the best dataset to get a classification model because it has the best value in the accuracy and recall variables, but still provides good performance in measuring precision.