PENGELOMPOKAN TINDAK KRIMINAL DI INDONESIA MENGGUNAKAN ALGORITMA SELF ORGANIZING MAPS (SOM) DAN K-MEANS

KHOTIJA, KHOTIJA (2022) PENGELOMPOKAN TINDAK KRIMINAL DI INDONESIA MENGGUNAKAN ALGORITMA SELF ORGANIZING MAPS (SOM) DAN K-MEANS. Sarjana / Sarjana Terapan (S1/D4) thesis, Universitas Muhammadiyah Semarang.

[img]
Preview
Text
HALAMAN JUDUL.pdf

Download (614kB) | Preview
[img]
Preview
Text
ABSTRAK.pdf

Download (431kB) | Preview
[img]
Preview
Text
BAB I.pdf

Download (738kB) | Preview
[img]
Preview
Text
BAB II.pdf

Download (657kB) | Preview
[img] Text
BAB III.pdf
Restricted to Repository staff only

Download (845kB) | Request a copy
[img] Text
BAB IV.pdf
Restricted to Repository staff only

Download (1MB) | Request a copy
[img]
Preview
Text
BAB V.pdf

Download (723kB) | Preview
[img]
Preview
Text
Daftar pustakadocx.pdf

Download (579kB) | Preview
[img] Text
LAMPIRAN.pdf
Restricted to Repository staff only

Download (1MB) | Request a copy
[img] Text
SKRIPSI FULL TEXT.pdf
Restricted to Repository staff only

Download (6MB) | Request a copy
Official URL: http://repository.unimus.ac.id

Abstract

ABSTRAK Khotija, 2022, Pengelompokan Tindak Kriminal Di Indonesia Menggunakan Algoritma Self Organizing Maps (SOM) Dan K-Means. Skripsi, Program Studi Statistika, Universitas Muhammadiyah Semarang. Pembimbing: I. Dr Rochdi Wasono, M.Si., II. Tiani Wahyu Utami, M.Si. Tindak kriminal merupakan suatu tindakan antisosial yang melanggar hukum dalam bermasyarakat karena tindak kriminal itu sendiri dapat menimbulkan suatu kerugian terhadap orang lain. Pada penelitian ini digunakan metode Self Organzing Maps (SOM) dan K-Means untuk mengetahui pengelompokkan apa saja yang berpengaruh dan mengelompokkan wilayah sejenis atau yang memiliki kesamaan karakter yang paling tepat. Tujuan penelitian ini untuk mengetahui hasil pengelompokan yang terbaik antara metode SOM dan K-Means. Pada penelitian ini menggunakan data tindak kriminal yang bersumber dari Badan Pusat Statistik Indonesia (BPS) dengan jumlah 22 indikator variable. Pada analisis metode SOM dan K-Means menghasilkan 3 cluster dengan anggota kelompok yang berbeda-beda pada masing-masing metode. Pada metode SOM menghasilkan cluster 1 dengan nilai rata-rata tindak kriminal rendah, cluster 2 dengan nilai rata-rata tindak kriminal cukup tinggi, dan pada cluster 3 dengan nilai rata-rata tindak kriminal tinggi. Sedangkankan pada metode K-Means menghasilkan cluster 1 dengan nilai rata-rata tindak kriminal tinggi, cluster 2 dengan nilai rata-rata tindak kriminal cukup tinggi, cluster 3 dengan nilai rata-rata tindak kriminal rendah. Berdasarkan nilai DBI hasil clustering terbaik adalah menggunakan metode SOM yaitu sebesar 0,08 lebih kecil dibandingkan dengan nilai DBI metode K-Means yaitu sebesar 0,40. Kata kunci: Tindak Kriminal, Self Organizing Maps (SOM), K-Means. ABSTRACT Khotija, 2022, Grouping of Crimes in Indonesia Using Self Organizing Maps (SOM) And K-Means Algorithms. Undergraduate Thesis, Statistics Departmen, University of Muhammadiyah Semarang. Supervisor: I. Dr. Rochdi Wasono, M.Si., II. Tiani Wahyu Utami, M.Si. Crime is an antisocial act that violates the law in society because the crime itself can cause harm to others. In this study, the Self Organzing Maps (SOM) and K-Means methods were used to find out what groupings were influential and grouping similar areas or those with the most appropriate character similarities. The purpose of this study was to determine the best grouping results between the SOM and K-Means methods. This study uses data on criminal acts sourced from the Indonesian Central Statistics Agency (BPS) with a total of 22 variable indicators. The analysis of the SOM and K-Means methods resulted in 3 clusters with different group members in each method. The SOM method produces cluster 1 with a low average crime value, cluster 2 with a fairly high average crime value, and cluster 3 with a high crime average value. While the K-Means method produces cluster 1 with a high average crime value, cluster 2 with a fairly high average crime value, cluster 3 with a low crime average value. Based on the DBI value, the best clustering result is using the SOM method, which is 0.08 which is smaller than the DBI value of the K-Means method, which is 0.40. Keywords: Crime, Self Organizing Maps (SOM), K-Means.

Item Type: Thesis (Sarjana / Sarjana Terapan (S1/D4) )
Call Number: 016/Statistika/IX/2022
Subjects: L Education > Statistics
Divisions: Faculty of Science and Mathematics > S1 Statistics
Depositing User: perpus unimus
URI: http://repository.unimus.ac.id/id/eprint/5998

Actions (login required)

View Item View Item