Hasan, Julianto Muchtadirul (2022) KLASIFIKASI COVID-19 BERDASARKAN CITRA X-RAY PARU-PARU MENGGUNAKAN CONVULUTIONAL NEURAL NETWORK (CNN). Undergraduate (S1) thesis, Universitas Muhammadiyah Malang.

Preview	Text PENDAHULUAN.pdf.pdf Download (1MB) | Preview
Preview	Text BAB I.pdf.pdf Download (76kB) | Preview
Preview	Text BAB II.pdf.pdf Download (238kB) | Preview
Preview	Text BAB III.pdf.pdf Download (366kB) | Preview
	Text BAB IV.pdf.pdf Restricted to Registered users only Download (331kB) | Request a copy
	Text BAB V.pdf.pdf Restricted to Registered users only Download (88kB) | Request a copy
	Text LAMPIRAN.pdf.pdf Restricted to Registered users only Download (558kB) | Request a copy
Preview	Text POSTER.pdf.pdf Download (415kB) | Preview

Abstract

Coronavirus Disease 2019 or COVID-19 is a disease with a fast spread throughout the world. The impact of the COVID-19 pandemic has caused a decline in almost all sectors, especially in the health sector. So far, the detection of COVID-19 based on PCR (polymerase chain reaction) and swabs on respiratory fluids has been done manually, namely reading the results of the PCR (polymerase chain reaction) or swabs by medical staff. This is considered less effective because the number of positive COVID-19 patients is increasing day by day while medical personnel are still limited. Checking with this method takes more time and an accurate diagnosis. In this study, the authors developed a deep learning Convolutional Neural Networks (CNN) method for a COVID-19 detection system. By utilizing the learning algorithm Convolutional Neural Networks (CNN) the system can detect normal lungs and COVID-19 based on X-Ray images of the lungs. Convolutional Neural Networks (CNN) algorithm is a type of neural network that utilizes image data. Where Convolutional Neural Networks can detect and recognize an object in the image. Therefore, in this study of normal lungs and lungs exposed to COVID-19, we used detection classifications on X-Ray image objects of the lungs. The classification results obtained using CNN have a percentage of detection success of 100% for data sourced from the General Hospital of the University of Muhammadiyah Malang and an accuracy percentage of detection success of 95% for data sourced from the Kaggel.com website.

Item Type:	Thesis (Undergraduate (S1))
Student ID:	201710130311116
Thesis Advisors:	Mohammad Chasrun Hasani (0007086808), Novendra Setyawan (0719119201)
Keywords:	COVID-19, COVID-19 lung detection, CNN, image processing, deep learning
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Engineering > Department of Electrical Engineering (20201)
Depositing User:	201710130311116 julianmuchtadirul98
Date Deposited:	21 Jan 2022 06:13
Last Modified:	21 Jan 2022 06:13
URI :	http://eprints.umm.ac.id/id/eprint/83515

Actions (login required)

View Item