IMPLEMENTASI SPECTRAL CLUSTERING DENGAN OPTIMASI PSO UNTUK PENGELOMPOKAN WILAYAH BERDASARKAN TINGKAT KEMISKINAN DI JAWA TIMUR

Herdianti, Rahmalia Anindya (2025) IMPLEMENTASI SPECTRAL CLUSTERING DENGAN OPTIMASI PSO UNTUK PENGELOMPOKAN WILAYAH BERDASARKAN TINGKAT KEMISKINAN DI JAWA TIMUR. Undergraduate thesis, UNIVERSITAS PEMBANGUNAN NASIONAL VETERAN JAWA TIMUR.

	Text (Cover) 21083010084_Cover.pdf Download (1MB)
	Text (Bab 1) 21083010084_Bab I.pdf Download (123kB)
	Text (Bab 2) 21083010084_Bab II.pdf Restricted to Registered users only until 20 June 2028. Download (370kB)
	Text (Bab 3) 21083010084_Bab III.pdf Restricted to Registered users only until 20 June 2028. Download (225kB)
	Text (Bab 4) 21083010084_Bab IV.pdf Restricted to Registered users only until 20 June 2028. Download (2MB)
	Text (Bab 5) 21083010084_Bab V.pdf Download (10kB)
	Text (Daftar Pustaka) 21083010084_Daftar Pustaka.pdf Download (82kB)
	Text (Lampiran) 21083010084_Lampiran.pdf Restricted to Registered users only until 20 June 2028. Download (144kB)

Abstract

The high poverty rate in East Java is a problem that requires special attention. The purpose of this research is to map the poverty level in each district/city in East Java using the Spectral Clustering algorithm with Particle Swarm Optimization (PSO) optimization. Spectral Clustering is used to group districts/municipalities, while PSO is used to increase the parameter values so that the accuracy of the clustering increases. The number of poor people, poverty line, average years of schooling, and percentage of poor people are some of the main factors that affect the poverty rate in this study. From the results of the research, two clusters can be identified, namely, areas with high poverty rates (31 districts/municipalities) and low poverty rates (7 districts/municipalities). Evaluation of the clustering quality shows that the Davies-Bouldin Index (DBI) value decreased from 0.4401 to 0.0943, while the Silhouette Score value increased from 0.6655 to 0.9315 after optimization. This indicates a significant improvement in the quality of separation and cohesion of the clusters formed. This research is expected to provide a deeper insight into the pattern of poverty in East Java and become the basis for more appropriate and effective government policies to deal with the problem of poverty. Keywords: East Java, Poverty, Clustering, Particle Swarm Optimization (PSO), Spectral Clustering.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Saputra, Wahyu Syaifullah Jauharis	NIDN0725088601	wahyu.s.j.saputra.if@upnjatim.ac.id
Thesis advisor	Prasetya, Dwi Arman	NIDN0005128001	arman.prasetya.sada@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics
Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Mrs Rahmalia Anindya Herdianti

Date Deposited:

20 Jun 2025 01:57

Last Modified:

20 Jun 2025 01:57

URI:

https://repository.upnjatim.ac.id/id/eprint/38775