Comparison of GMM, AHC, and K-Medoids Methods in Clustering Suroboyo Bus Stops Based on Passenger Volume

Putri, Thalita Syahlani (2025) Comparison of GMM, AHC, and K-Medoids Methods in Clustering Suroboyo Bus Stops Based on Passenger Volume. Undergraduate thesis, Univesitas Pembangunan Nasional "Veteran" Jawa Timur.

	Text (Cover) Cover.pdf Download (896kB)
	Text (Chapter I) Chapter I.pdf Download (265kB)
	Text (Chapter II) Chapter II.pdf Restricted to Repository staff only until 27 November 2028. Download (413kB)
	Text (Chapter III) Chapter III.pdf Restricted to Repository staff only until 27 November 2028. Download (1MB)
	Text (Chapter IV) Chapter IV.pdf Restricted to Repository staff only until 27 November 2028. Download (1MB)
	Text (Chapter V) Chapter V.pdf Download (227kB)
	Text (References) References.pdf Download (241kB)
	Text (Appendix) Appendix.pdf Restricted to Repository staff only until 27 November 2028. Download (288kB)

Abstract

This study aims to compare the performance of three clustering algorithms—Agglomerative Hierarchical Clustering (AHC), Gaussian Mixture Model (GMM), and K-Medoids—in analyzing passenger density in the Suroboyo Bus system. The dataset contains information on passenger counts and operational time, which underwent preprocessing involving attribute selection, time transformation, outlier detection using the IQR method, and Z-score normalization. Clustering was performed to classify passenger density patterns based on data characteristics, and the resulting clusters were labeled as low, medium, high, and very high density. The quality of the clustering results was evaluated using the Silhouette Score metric, which measures the clarity of cluster separation. The results show that the K-Medoids method achieved the highest performance with a Silhouette Score of 0.4222, followed by AHC with a score of 0.3657, and GMM with 0.3024. Therefore, K-Medoids is considered the most effective method for identifying distinct passenger density patterns. This study is expected to serve as a reference for policymakers in optimizing bus schedules and operational capacity based on passenger clustering insights.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Mas Diyasa, I Gede Susrama	NIDN0019067008	igsusrama.if@upnjatim.ac.id
Thesis advisor	Junaidi, Achmad	NIDN0710117803	achmadjunaidi.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)
T Technology > T Technology (General) > T55.4-60.8 Industrial engineering. Management engineering
T Technology > T Technology (General) > T58.6-58.62 Management Information Systems

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Thalita Syahlani Putri

Date Deposited:

28 Nov 2025 07:52

Last Modified:

28 Nov 2025 09:10

URI:

https://repository.upnjatim.ac.id/id/eprint/47114