Ekstraksi Fitur Menggunakan Metode Multi Linear Predictive Coding (M-LPC) dan Singular Value Decomposition (SVD) untuk Klasifikasi Sinyal Genom Varian COVID-19 dan Influenza

Ardamayanti, Thaliah Fauz (2023) Ekstraksi Fitur Menggunakan Metode Multi Linear Predictive Coding (M-LPC) dan Singular Value Decomposition (SVD) untuk Klasifikasi Sinyal Genom Varian COVID-19 dan Influenza. Masters thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 6002221014-Master_Thesis.pdf] Text
6002221014-Master_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2025.

Download (8MB) | Request a copy

Abstract

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) adalah virus yang menyerang sistem pernapasan hewan dan manusia yang menyebabkan penyakit COVID-19. COVID-19 pertama kali dideteksi di Wuhan, China pada akhir Desember 2019 dan sejak saat itu terus mengalami peningkatan jumlah kasus di seluruh dunia dengan diikuti munculnya varian baru. Dalam Tesis ini dilakukan ekstraksi fitur menggunakan metode Multi Linear Predictive Coding (M-LPC) dalam aplikasi machine learning untuk klasifikasi varian COVID-19 berdasarkan sinyal genom. M-LPC adalah penggabungan metode LPC dan sliding window. Proses ekstraksi dengan M-LPC menghasilkan nilai statistik sederhana untuk mengidentifikasi fitur-fitur seperti frekuensi nukleotida, distribusi GC, nilai maksimum, minimum, rata-rata, dan standar deviasi, yang akurat untuk membedakan varian COVID-19 dengan virus yang memiliki gejala sejenis, seperti influenza. Keunggulan metode M-LPC adalah bisa diterapkan untuk sekuens DNA dengan panjang berapapun dan dapat menghasilkan fitur sederhana untuk selanjutnya diklasifikasikan menggunakan metode machine learning. Hasil penelitian menunjukkan bahwa metode ekstraksi fitur menggunakan M-LPC berhasil mengidentifikasi fitur-fitur penting dalam sinyal genom COVID-19 dengan akurasi hasil klasifikasi sebesar 99,86% untuk klasifikasi menjadi 3 kelas, dan 92,45% untuk klasifikasi ke dalam 12 kelas berbeda. Oleh karena itu, Tesis ini diharapkan dapat menjadi pendukung keputusan untuk diagnosis varian COVID-19 dengan hasil yang akurat.
=====================================================================================================================================
Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a virus that attacks the respiratory system of animals and humans and causes COVID-19 disease. COVID-19 was first detected in Wuhan, China, at the end of December 2019 and since then has become a pandemic in the world, followed by the emergence of new variants. This thesis proposes a feature extraction method using Multi Linear Predictive Coding (M-LPC) in the application of machine learning for the classification of COVID-19 variants based on genomic signals. M-LPC is an extension of the LPC method and sliding window technique. M-LPC uses a mathematical approach to produce simple statistical values to identify features such as nucleotide frequency, GC distribution, maximum, minimum, mean, and standard deviation, which accurately differentiate COVID-19 variants from other viruses with similar symptoms, such as influenza. The advantage of the M-LPC method lies in its ability to be applied to DNA sequences of any length and generate simple features for subsequent classification using machine learning methods. The research results indicate that the feature extraction method using M-LPC successfully identifies important features in COVID-19 genomic signals with a classification accuracy of 99.86% for three classes of classification and 92.25% for 12 classes of classification. Therefore, it is expected that this thesis can serve as a decision-support for diagnosing COVID-19 variants with more accurate results.

Item Type: Thesis (Masters)
Uncontrolled Keywords: COVID-19, Ekstraksi Fitur, M-LPC, Machine Learning, Sliding Windows. COVID-19, Feature Extraction, M-LPC, Machine Learning, Sliding Windows.
Subjects: Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Q Science > QA Mathematics > QA76.9.D33 Data compression (Computer science)
T Technology > T Technology (General) > T57.5 Data Processing
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44101-(S2) Master Thesis
Depositing User: Thaliah Fauz Ardamayanti
Date Deposited: 07 Aug 2023 07:39
Last Modified: 07 Aug 2023 07:39
URI: http://repository.its.ac.id/id/eprint/103427

Actions (login required)

View Item View Item