Clustering Gempabumi di Wilayah Regional VII Menggunakan Pendekatan DBSCAN
نویسندگان
چکیده
Wilayah Regional VII meliputi Jawa Tengah, Yogyakarta, dan Timur merupakan wilayah tektonik yang aktif karena terletak di zona subduksi lempeng Indo-Australia Eurasia serta terdapat beberapa patahan daratan. Oleh itu, perlu dilakukan klasifikasi gempabumi untuk memetakan rawan berdasarkan sumbernya kesamaan atribut salah satunya adalah karakteristik dari sumber sama. Pada penelitian ini digunakan pendekatan algoritma Unsupervised Learning Clustering berbasis kepadatan yaitu, Density Based Spatial of Application with Noise atau DBSCAN, membutuhkan parameter input epsilon (ε) MinPts. Data pada data tahun 2017 hingga 2021 diperoleh BMKG. Selanjutnya, proses clustering dengan membagi periode yaitu tahunan lima tujuan mengetahui pola cluster waktu. Hasil terbentuk selanjutnya dievaluasi menggunakan Silhouette Coefficient dibandingkan peta Seismisitas telah ada katalog PuSGeN 2017. DBSCAN jumlah sebanyak 2 6 nilai terendah sebesar 0.270 T5_2017-2021 tertinggi 0.499 T1_2020. AbstractRegional area covering Central Java, Yogyakarta and East Java is an active tectonic region because it located in the subduction zone Indo-Australian Eurasian plates there are several faults on land. Therefore, necessary to classify earthquakes map earthquake-prone zones based their sources similarity attibutes, characteristics from same source. In this study, a density-based algorithm approach was used namely, or requires parameters The study earthquake for obtained Then, process carried out by dividing period, namely annual period five-year aim knowing pattern time period. results then evaluated using Sillhouette compared existing Seismicity catalog. number clusters lowest value highest T1_2020 Â
منابع مشابه
Fuzzy Core DBScan Clustering Algorithm
In this work we propose an extension of the DBSCAN algorithm to generate clusters with fuzzy density characteristics. The original version of DBSCAN requires two parameters (minPts and ) to determine if a point lies in a dense area or not. Merging different dense areas results into clusters that fit the underlined dataset densities. In this approach, a single density threshold is employed for a...
متن کاملDensity - based clustering algorithms – DBSCAN and SNN
This document describes the implementation of two density-based clustering algorithms: DBSCAN [Ester1996] and SNN [Ertoz2003]. These algorithms were implemented within the context of the LOCAL project [Local2005] as part of a task that aims to create models of the geographic space (Space Models) to be used in context-aware mobile systems. Here, the role of the clustering algorithms is to identi...
متن کاملPrivacy Preserving DBSCAN Algorithm for Clustering
In this paper we address the issue of privacy preserving clustering. Specially, we consider a scenario in which two parties owning confidential databases wish to run a clustering algorithm on the union of their databases, without revealing any unnecessary information. This problem is a specific example of secure multi-party computation and as such, can be solved using known generic protocols. H...
متن کاملExperiments in Parallel Clustering with DBSCAN
We present a new result concerning the parallelisation of DBSCAN, a Data Mining algorithm for density-based spatial clustering. The overall structure of DBSCAN has been mapped to a skeletonstructured program that performs parallel exploration of each cluster. The approach is useful to improve performance on high-dimensional data, and is general w.r.t. the spatial index structure used. We report...
متن کاملKrill Herd Clustering Algorithm using DBSCAN Technique
The hybrid approach is proposed to show that the clusters also show the swarm behavior. Krill herd algorithm is used to show the simulation of the herding behavior of the krill individuals. Density based approach is used for discovering the clusters and to show the region with sufficiently high density into clusters of krill individuals that of the arbitrary shape in environment. The minimum di...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Jurnal Teknologi Informasi dan Ilmu Komputer
سال: 2023
ISSN: ['2528-6579', '2355-7699']
DOI: https://doi.org/10.25126/jtiik.20241046918