Pitria sari, - (2022) PENGELOMPOKAN PROVINSI DI INDONESIA PERIODE 2020/2021 DENGAN METODE DENSITY BASED SPATIAL CLUSTERING APPLICATION WITH NOISE (DBSCAN) (Studi Kasus: Data Perekonomian Provinsi di Indonesia Periode 2020/2021). S1 thesis, Universitas Pendidikan Indonesia.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_PPB_1800258_Chapter1.pdf Download (1MB) |
|
Text
S_PPB_1800258_Chapter2.pdf Restricted to Staf Perpustakaan Download (3MB) |
|
Text
S_PPB_1800258_Chapter3.pdf Download (1MB) |
|
Text
S_PPB_1800258_Chapter4.pdf Restricted to Staf Perpustakaan Download (6MB) |
|
Text
S_PPB_1800258_Chapter5.pdf Download (323kB) |
|
Text
S_PPB_1800258_Appendix.pdf Restricted to Staf Perpustakaan Download (2MB) |
Abstract
Analisis klaster merupakan suatu metode pengelompokan data dengan mempertimbangkan sebuah pendekatan yang berarti untuk mencari kesamaan dalam data dan membuat data yang sama menjadi suatu kelompok. Sehingga, data dalam suatu klaster memiliki tingkat kemiripan yang besar sedangkan data antar-klaster memiliki Sarmila Nurhasanah, 2022 METODE AVERAGE-BASED WEIGHTED FUZZY INTEGRATED TIME SERIES LEE HIGH ORDER (Studi Kasus pada Peramalan Mata Uang Kripto Bitcoin) Universitas Pendidikan Indonesia | repository.upi.edu | perpustakaan.upi.edu tingkat kemiripan yang kecil. Secara garis besar analisis klaster terdiri atas analisis hierarki (hierarchial clustering) dan analisis partisi (partional clustering). Jain (1988) telah mengembangkan algoritma clustering dengan pendekatan berdasarkan kepekatan (density-based approach). Algoritma density based-approach mampu mengindentifikasi klaster dalam bentuk apapun. Namun, algoritma tersebut memerlukan ruang penyimpanan yang besar dan membutuhkan waktu pemrosesan yang lama, sehingga Ester dkk. (1996) mengusulkan algoritma DBSCAN untuk mengatasi kelemahan tersebut. DBSCAN merupakan suatu metode clustering yang menentukan klaster berdasarkan kepadatan di mana kepadatan di dalam klaster akan lebih besar dibandingkan kepadatan di luar klaster. Tujuan penelitian ini adalah mengelompokkan perekonomian provinsi di Indonesia periode 2020/2021 dengan metode density based spatial clustering application with noise. Dengan menggunakan data perekonomian Indonesia tahun 2020/2021 didapatkan 2 klaster optimal dan 9 noise. Dari hasil noise didapatkan provinsi dengan karakteristik perekonomian yang sangat baik (ekstrem tinggi) dan sangat buruk (ekstrem rendah). Provinsi yang tergolong ekstrem rendah adalah provinsi Papua. Sehingga provinsi Papua menjadi prioritas pemulihan ekonomi paska pandemi. Kata kunci: Analisis Klaster, DBSCAN, Indeks Validitas, Data Perekonomian. Abstract Cluster analysis is a method of grouping data by considering a meaningful approach to look for similarities in the data and make the same data into a group. Thus, data in a cluster has a high degree of similarity while data between clusters has a small degree of similarity. Broadly speaking, cluster analysis consists of hierarchical clustering and partition analysis. Jain (1988) has developed a clustering algorithm with a density-based approach. Density based-approach algorithm is able to identify clusters in any form. However, the algorithm requires large storage space and requires a long processing time, so Ester et al. (1996) proposed the DBSCAN algorithm to overcome these weaknesses. DBSCAN is a clustering method that determines clusters based on density where the density inside the cluster will be greater than the density outside the cluster. The purpose of this study is to classify the provincial economy in Indonesia for the 2020/2021 period using the density based sp atial clustering application with noise method. By using data on the Indonesian economy for 2020/2021, 2 optimal clusters and 9 noise were obtained. From the noise results, we get provinces with very good (extremely high) and very bad (extremely low) economic characteristics. The province that is classified as extreme low is the province of Papua. Thus, the author recommends the government to make a province classified as extreme low, namely Papua province, as a priority for post-pandemic economic recovery. Keywords: Cluster Analysis, DBSCAN, Validity Index, Economic Data.
| Item Type: | Thesis (S1) |
|---|---|
| Uncontrolled Keywords: | Cluster Analysis, DBSCAN, Validity Index, Economic Data. |
| Subjects: | B Philosophy. Psychology. Religion > BF Psychology L Education > L Education (General) |
| Divisions: | Fakultas Pendidikan Matematika dan Ilmu Pengetahuan Alam > Jurusan Pendidikan Matematika > Program Studi Matematika (non kependidikan) |
| Depositing User: | Pitria sari |
| Date Deposited: | 19 May 2022 02:35 |
| Last Modified: | 23 May 2022 03:17 |
| URI: | http://repository.upi.edu/id/eprint/72341 |
Actions (login required)
 |
View Item |