Comparison of Supervised Learning Methods for COVID-19 classification on X-Ray Lung Images
Keywords:COVID-19, Chest X-Ray, K-NN, SVM, Random Forest
The COVID-19 virus pandemic is still ongoing in almost all countries in the world. The spread of this virus is very fast because the transmission process is through air contaminated with viruses from droplets of COVID-19 patients. RT-PCR usually checks patients suspected of being infected with the COVID-19 virus. In addition to this method, through several previous research, the use of Chest X-Ray images can detect the presence of this virus. Detection of COVID-19 using Chest X-Ray images can use deep learning techniques, but the training process takes long. Therefore, this research uses machine learning techniques hoping that the accuracy results are not too different from deep learning, but the training time is fast. We evaluated three supervised learning methods, namely SVM, K-NN, and Random Forest, to detect this COVID-19 disease. The experimental results show that the accuracy of the SVM method using a polynomial kernel can reach 90% accuracy, and the training speed is only 462 ms. Through these results, machine learning techniques can compensate for the results of the deep learning technique in terms of accuracy, and the training process is faster than the deep learning technique.
Copyright (c) 2022 Faisal Dharma Adhinata, Nur Ghaniaviyanto Ramadhan, Arif Amrulloh, Arief Rais Bahtiar
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
a. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License - Share Alike that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
All articles published Open Access will be immediately and permanently free for everyone to read and download. We are continuously working with our author communities to select the best choice of license options, currently being defined for this journal as follows: Creative Commons Attribution-Share Alike (CC BY-SA)