Komparasi Hasil Klasifikasi Citra Infeksi Telinga Dengan Algoritma Support Vector Machine Dan K-Nearest Neighbor

Ariadi, Kuncoro (2024) Komparasi Hasil Klasifikasi Citra Infeksi Telinga Dengan Algoritma Support Vector Machine Dan K-Nearest Neighbor. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010096.-cover.pdf Download (525kB)
	Text (bab 1) 20081010096.-bab1.pdf Download (51kB)
	Text (bab 2) 20081010096.-bab2.pdf Restricted to Repository staff only until 20 September 2026. Download (434kB)
	Text (bab 3) 20081010096.-bab3.pdf Restricted to Repository staff only until 20 September 2026. Download (478kB)
	Text (bab 4) 20081010096.-bab4.pdf Restricted to Repository staff only until 20 September 2026. Download (554kB)
	Text (bab 5) 20081010096.-bab5.pdf Download (33kB)
	Text (daftar pustaka) 20081010096.-daftarpustaka.pdf Download (103kB)

Abstract

Ear infections are one of the health conditions that affect the ear organ. This study aims to compare two different image classification algorithms, namely Support Vector Machine (SVM) and K-Nearest Neighbor (KNN), in classifying ear infection image. The ear infection image data used in this study consists of 880 images with four classes: Chronic Otitis Media (COM), Earwax Plug, Myringosclerosis, and Normal. The initial stage of the classification process begins with image data preprocessing, followed by designing models using the SVM and KNN algorithms. The next process is to split the training data into validation and training sets, then hyperparameter tuning is performed to determine the best model for each classification algorithm. After the training step is completed, testing and model evaluation are conducted. Based on this process, a comparison will be made to asses the performance of both the SVM and KNN models. The SVM algorithm achieved the best accuracy score using a Linear kernel, with an accuracy of 88%, precision of 88%, recall of 87%, dan F1-Score of 87%. The KNN algorithm achieved its best accuracy score with k = 1, with an accuracy of 73%, precision of 76%, recall of 73%, dan F1-Score of 72%. Keywords: Image Classification, SVM, KNN, Ear Infection, Feature Extraction

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Anggraeny, Fetty Tri	NIDN0711028201	fettyanggraeny.if@upnjatim.ac.id
Thesis advisor	Sihananto, Andreas Nugroho	NIDN0012049005	andreas.nugroho.jarkom@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Kuncoro Ariadi

Date Deposited:

20 Sep 2024 03:59

Last Modified:

20 Sep 2024 03:59

URI:

https://repository.upnjatim.ac.id/id/eprint/29614