Klasifikasi Varian Covid-19 Menggunakan Convolutional Neural Network Dan Hybrid Model

Prasyanto, Ramadhani (2023) Klasifikasi Varian Covid-19 Menggunakan Convolutional Neural Network Dan Hybrid Model. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06111540000079-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2025. Download (3MB) | Request a copy

Abstract

Jumlah penyebaran COVID-19 di Indonesia bahkan di dunia menunjukan jumlah penyebaran yang meningkat. COVID-19 merupakan penyakit yang disebabkan oleh virus dari golongan virus corona yaitu SARS-CoV-2. Virus merupakan makhluk hidup yang hanya memiliki satu asam nukleat yaitu Deoxyribonucleic acid (DNA) saja atau ribonukleat acid (RNA) saja. Virus dapat berkembang sehingga menimbulkan varian baru yang terkadang memiliki sifat dan karakteristik yang berbeda dari virus awal. Virus SARS-CoV-2 yang tergolong dalam variant of concern (VOC) yaitu alpha, beta, delta, gamma, dan omicron. Dengan banyaknya data sekuens DNA untuk setiap varian virus diperlukan komputasi untuk mengklasifikasikan varian virus tersebut. Penelitian ini menggunakan Convolutional Neural Network dan hybrid model untuk mengklasifikasikan varian virus Covid-19 berdasarkan sekuens DNA virus. Dalam penelitian ini algoritma yang digunakan untuk mengklasifikasikan sekuens DNA VOC COVID-19 adalah Convolutional Neural Network (CNN), Convolutional Neural Network Long Short-term Memory (CNN-LSTM) dan Convolutional Neural Network bidirectional Long Short-term Memory (CNN-biLSTM). Hasil pengujian menunjukan bahwa algoritma CNN adalah algoritma terbaik, dengan akurasi 79.52% untuk mengklasifikasikan sekuens DNA.
=======================================================================================================================================
The number of COVID-19 spread in Indonesia and even in the world shows an increasing number of spread. COVID-19 is a disease caused by a virus from the corona virus group, namely SARS-CoV-2. Viruses are living things that only have one nucleic acid, namely Deoxyribonucleic acid (DNA) only or ribonukleat acid (RNA) only. Viruses can evolve to create new variants that sometimes have different properties and characteristics from the initial virus. The SARS-CoV-2 virus is classified as a variant of concern (VOC), namely alpha, beta, delta, gamma, and omicron. With the large amount of DNA sequence data for each virus variant, computation is needed to classify the virus variants. This research uses Convolutional Neural Network and hybrid model to classify Covid-19 virus variants based on viral DNA sequences. In this study, the algorithms used to classify VOC COVID-19 DNA sequences are Convolutional Neural Network (CNN), Convolutional Neural Network Long Short-term Memory (CNN-LSTM) and Convolutional Neural Network bidirectional Long Short-term Memory (CNN-biLSTM). The test results show that CNN algorithm is the best algorithm, with 79.52% accuracy to classify DNA sequences.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	covid-19, sekuens DNA, klasifikasi, CNN, CNN hybrid model,COVID-19, DNA sequence, classification, CNN, CNN hybrid model
Subjects:	Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Ramadhani prasyanto
Date Deposited:	16 Feb 2023 09:08
Last Modified:	16 Feb 2023 09:08
URI:	http://repository.its.ac.id/id/eprint/97584

Actions (login required)

View Item