DIMAS WILDAN MUBAROK (2022) SISTEM DETEKSI COVID-19 BERDASARKAN TEKSTUR MENGGUNAKAN ALGORITMA TRANSFORMASI HAAR WAVELETT DAN MACHINE LEARNING. S1 thesis, Universitas Muhammadiyah Yogyakarta.
Halaman Judul.pdf
Download (609kB)
Lembar Pengesahan.pdf
Restricted to Registered users only
Download (698kB)
Abstrak.pdf
Restricted to Registered users only
Download (15kB)
Bab I.pdf
Download (84kB)
Bab II.pdf
Restricted to Registered users only
Download (397kB)
Bab III.pdf
Restricted to Registered users only
Download (309kB)
Bab IV.pdf
Restricted to Registered users only
Download (3MB)
Bab V.pdf
Restricted to Registered users only
Download (11kB)
Daftar Pustaka.pdf
Restricted to Registered users only
Download (137kB)
Naskah Publikasi.pdf
Restricted to Registered users only
Download (662kB)
Full Text.pdf
Restricted to Repository staff only
Download (5MB)
Abstract
Covid-19 is still the main focus worldwide because until now, covid-19 is still proliferating and has a significant impact on all human activities. They prevent transmission by detecting so that who can carry out other actions. Various research efforts are carried out to detect a covid-19 virus. As technology develops, the Covid-19 detection process can be carried out by image processing or using machine learning. The detection process in this study was carried out using X-ray images of 101 Covid-19 positive people and then reproduced through pre-processing to 404, then compared with X-ray images, 202 ordinary people through pre-processing to 390 pieces and also 390 pneumonia-positive x-ray images. With this data, the extraction process is carried out using the Haar Wavelet Transformation method with the results of level 1, level 2, and combined level, then classified by SVM (Support Vector Machine) and KNN (K-Nearest Neighbor). KNN is 86.13%. For level 2 and the combined level, the best accuracy is obtained with the Quadratic SVM model with 79.8% and 83.4%, respectively.
Item Type: | Thesis (S1) |
---|---|
Uncontrolled Keywords: | COVID-19, HAAR WAVELET TRANSFORMATION, SVM, KNN |
Divisions: | Fakultas Teknik > Teknik Elektro S1 |
Depositing User: | M. Erdiansyah |
Date Deposited: | 20 Apr 2022 02:20 |
Last Modified: | 20 Apr 2022 02:20 |
URI: | https://etd.umy.ac.id/id/eprint/29629 |