Perbandingan tingkat akurasi algoritma random forest dan k-nearest neighbor (KNN) dalam mengklasifikasi penyakit kanker paru-paru

Lim, Derrick Devin (2023) Perbandingan tingkat akurasi algoritma random forest dan k-nearest neighbor (KNN) dalam mengklasifikasi penyakit kanker paru-paru. Bachelor thesis, Universitas Pelita Harapan.

[img]
Preview
Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (65kB) | Preview
[img]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (382kB) | Preview
[img]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (597kB) | Preview
[img]
Preview
Text (Chapter1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (563kB) | Preview
[img] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)
[img] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[img] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (6MB)
[img] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (198kB)
[img]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (780kB) | Preview
[img] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (6MB)

Abstract

Kanker paru-paru adalah suatu keadaan dimana terdapat sel kanker yang berkembang secara tidak terkendali di dalam organ paru-paru. Kanker paru-paru merupakan jenis kanker dengan tingkat kematian tertinggi dari total kematian akibat penyakit kanker dan menjadi penyebab utama dari kematian akibat kanker pada pria. Gejala pada kanker paru-paru sulit untuk terdeteksi pada stadium awal, dan hanya dapat terdeteksi ketika memasuki stadium lanjut. Oleh karena itu, penting agar dapat melakukan deteksi dini terhadap penyakit kanker paru-paru agar peluang untuk sembuh lebih besar. Solusi untuk mengatasi hal tersebut adalah memanfaatkan machine learning untuk mengklasifikasi tingkat risiko seseorang dalam terkena penyakit kanker paru-paru. Metode yang digunakan dalam penelitian ini adalah K-Nearest Neighbor dan Random Forest. Algoritma K-Nearest Neighbor dan Random Forest merupakan algoritma yang sering digunakan untuk melakukan klasifikasi. Penelitian ini bertujuan untuk melakukan perbandingan antara kedua algoritma tersebut dalam melakukan klasifikasi terhadap tingkat risiko seseorang dalam terkena penyakit kanker paru-paru. Dari hasil penelitian ini, dapat disimpulkan bahwa nilai akurasi yang dimiliki oleh K-Nearest Neighbor adalah 0.890 dan nilai akurasi Random Forest sebesar 0.933. Selain itu, nilai AUC yang dihasilkan oleh K-Nearest Neighbor adalah 0.973 dan untuk algoritma Random Forest adalah 0.991. Yang dapat disimpulkan bahwa Random Forest lebih unggul dari K-Nearest Neighbor. / Lung cancer is a condition where there are cancer cells that develop uncontrollably in the lung organ. Lung cancer has the highest mortality rate of all cancer deaths and is the leading cause of cancer deaths in men. Symptoms of lung cancer are difficult to detect in the early stages, and can only be detected when it enters the advanced stages. Therefore, it is important to be able to do early detection of lung cancer so that the chances of recovery are greater. The solution to overcome this is to utilize machine learning to classify a person's risk level for lung cancer. The methods used in this research are K-Nearest Neighbor and Random Forest. K-Nearest Neighbor and Random Forest algorithms are algorithms that are often used for classification. This research aims to make a comparison between the two algorithms in classifying a person's risk level for lung cancer. From the results of this study, it can be concluded that the accuracy value owned by K-Nearest Neighbor is 0.890 and the accuracy value of Random Forest is 0.933. In addition, the AUC value generated by K-Nearest Neighbor is 0.973 and for the Random Forest algorithm is 0.991. Which can be concluded that Random Forest is superior to K-Nearest Neighbor.

Item Type: Thesis (Bachelor)
Creators:
CreatorsNIMEmail
Lim, Derrick DevinNIM03081200023derricklim.ddl@gmail.com
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorPangaribuan, Jefri JuniferNIDN0130108901jefri.pangaribuan@uph.edu
Uncontrolled Keywords: Kanker paru-paru; K-Nearest Neighbor; Random Forest
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Information Systems
Current > Faculty/School - UPH Medan > School of Information Science and Technology > Information Systems
Depositing User: Derrick Devin Lim Lim
Date Deposited: 06 Feb 2024 03:29
Last Modified: 06 Feb 2024 03:29
URI: http://repository.uph.edu/id/eprint/61530

Actions (login required)

View Item View Item