Perbandingan tingkat akurasi algoritma K-Nearest Neighbor dan Support Vector Machine dalam mendeteksi penyakit obesitas

Billie, Felix (2024) Perbandingan tingkat akurasi algoritma K-Nearest Neighbor dan Support Vector Machine dalam mendeteksi penyakit obesitas. Bachelor thesis, Universitas Pelita Harapan.

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

Download (132kB) | Preview
[thumbnail of Abstract]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (286kB) | Preview
[thumbnail of ToC]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (264kB) | Preview
[thumbnail of Chapter1]
Preview
Text (Chapter1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (238kB) | Preview
[thumbnail of Chapter2] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (699kB)
[thumbnail of Chapter3] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (570kB)
[thumbnail of Chapter4] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter5] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (218kB)
[thumbnail of Bibliography]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Share Alike.

Download (359kB) | Preview
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (14MB)

Abstract

Obesitas adalah suatu penyebab dari penyakit yang tidak menular yang dapat meningkatkan mortalitas dan Indonesia dengan persebaran terbanyak dan pada tahun 2007 hingga tahun 2018 mengalami peningkatan terhadap pasien obesitas dari 10,5% menjadi sekitar 21,8%. Pada penelitian yang dilakukan sebelumnya, peneliti menggunakan algoritma K-Nearest Neighbor (KNN) dengan tingkat akurasi sebesar 90% dan algoritma Support Vector Machine (SVM) memberikan tingkat akurasi sebesar 71.8% yang menggunakan bantuan evaluasi model yatiu confusion matrix. Data pasien obesitas berisikan 1822 data dan memiliki 17 kolom atribut yang dibagi menjadi 70% data dilatih dan 30% data diuji menggunakan bantuan aplikasi Orange Data Mining. Hasil dari penelitian berupa nilai akurasi K-Nearest Neighbor sebesar 98,2% dan nilai akurasi Support Vector Machine sebesar 94,3%. Dalam confusion matrix tingkat kesalahan yang diberikan K-Nearest Neigbor lebih kecil dibandingkan Support Vector Machine. Kesimpulan yang diperoleh adalah algoritma K-Nearest Neighbor lebih unggul dalam mendeteksi penyakit obesitas dibandingkan algoritma Support Vector Machine. / Obesity is a cause of non-communicable diseases which can increase mortality and Indonesia has the largest distribution and from 2007 to 2018 experienced an increase in obese patients from 10.5% to around 21.8%. In previous research, researchers used the K-Nearest Neighbor (KNN) algorithm with an accuracy level of 90% and the Support Vector Machine (SVM) algorithm provided an accuracy level of 71.8% using the help of an evaluation model, namely the confusion matrix. Obese patient data contains 1822 data and has 17 attribute columns which are divided into 70% trained data and 30% tested data using the help of the Orange Data Mining application. The results of the research are a K-Nearest Neighbor accuracy value of 98.2% and a Support Vector Machine accuracy value of 94.3%. In the confusion matrix, the error rate given by K-Nearest Neighbor is smaller than that of Support Vector Machine. The conclusion obtained is that the K-Nearest Neighbor algorithm is superior in detecting obesity compared to the Support Vector Machine algorithm.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Billie, Felix
NIM03081200042
felixxbillie@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Barus, Okky
NIDN0127068803
okky.barus@uph.edu
Uncontrolled Keywords: obesitas; K-Nearest Neighbor; Support Vector Machine; Confusion Matrix, Orange Data Mining.
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: Felix Billie
Date Deposited: 09 Aug 2024 23:41
Last Modified: 09 Aug 2024 23:41
URI: http://repository.uph.edu/id/eprint/64750

Actions (login required)

View Item
View Item