Implementation of the Self Organizing Maps (SOM) Method for Grouping Provinces in Indonesia Based on the Earthquake Disaster Impact

Ihsan Dermawan, None Admi Salma, None Yenni Kurniawati, None Tessy Octavia Mukhti
{"title":"Implementation of the Self Organizing Maps (SOM) Method for Grouping Provinces in Indonesia Based on the Earthquake Disaster Impact","authors":"Ihsan Dermawan, None Admi Salma, None Yenni Kurniawati, None Tessy Octavia Mukhti","doi":"10.24036/ujsds/vol1-iss4/83","DOIUrl":null,"url":null,"abstract":"Indonesia is a country prone to earthquakes. This is because the territory of Indonesia is located between the confluence of three tectonic plates (the Eurasian plate, the Indo-Australian plate, and the Pacific Ocean plate) and is also in the Ring of Fire. The number of earthquakes in Indonesia varies in each province due to the different characteristics of the location of the plates of each province in Indonesia. Earthquake disasters have a very detrimental impact on society, such as causing casualties, damaged houses or damage to public facilities. Therefore it is important to grouping the impact of earthquakes in Indonesia as a disaster mitigation effort in order to find out the characteristics of each province in each cluster. The grouping method used is Kohonen Self Organizing Maps (SOM). SOM is a high-dimensional data visualization technique in the form of a low-dimensional map. The results 3 clusters with the characteristics of each cluster. Cluster 1 consisting of 24 provinces has the characteristics of the highest number of earthquake incidents, the number of missing victims, the number of victims suffering and the number of damaged houses. Cluster 2 consisting of 7 provinces does not show any prominent characteristics of the cluster. Cluster 3 consists of 3 provinces with very prominent characteristics, namely the number of victims killed, the number of injured victims, the number of displaced victims, the number of damaged educational facilities, the number of damaged health facilities and the number of damaged worship facilities the most of the other clusters.","PeriodicalId":220933,"journal":{"name":"UNP Journal of Statistics and Data Science","volume":"57 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"UNP Journal of Statistics and Data Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.24036/ujsds/vol1-iss4/83","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Indonesia is a country prone to earthquakes. This is because the territory of Indonesia is located between the confluence of three tectonic plates (the Eurasian plate, the Indo-Australian plate, and the Pacific Ocean plate) and is also in the Ring of Fire. The number of earthquakes in Indonesia varies in each province due to the different characteristics of the location of the plates of each province in Indonesia. Earthquake disasters have a very detrimental impact on society, such as causing casualties, damaged houses or damage to public facilities. Therefore it is important to grouping the impact of earthquakes in Indonesia as a disaster mitigation effort in order to find out the characteristics of each province in each cluster. The grouping method used is Kohonen Self Organizing Maps (SOM). SOM is a high-dimensional data visualization technique in the form of a low-dimensional map. The results 3 clusters with the characteristics of each cluster. Cluster 1 consisting of 24 provinces has the characteristics of the highest number of earthquake incidents, the number of missing victims, the number of victims suffering and the number of damaged houses. Cluster 2 consisting of 7 provinces does not show any prominent characteristics of the cluster. Cluster 3 consists of 3 provinces with very prominent characteristics, namely the number of victims killed, the number of injured victims, the number of displaced victims, the number of damaged educational facilities, the number of damaged health facilities and the number of damaged worship facilities the most of the other clusters.
基于地震灾害影响的印尼省份分组自组织地图(SOM)方法的实现
印度尼西亚是一个地震多发的国家。这是因为印度尼西亚的领土位于三个构造板块(欧亚板块、印度-澳大利亚板块和太平洋板块)汇合处之间,也位于火山带。印度尼西亚的地震次数在每个省都有所不同,这是由于印度尼西亚每个省的板块位置特征不同。地震灾害对社会有非常不利的影响,例如造成人员伤亡,房屋损坏或公共设施损坏。因此,重要的是将印度尼西亚地震的影响归类为减灾工作,以便找出每个集群中每个省的特征。使用的分组方法是Kohonen自组织映射(SOM)。SOM是一种以低维地图形式呈现的高维数据可视化技术。结果具有3个聚类的特点。由24个省份组成的集群1具有地震事件数量最多、失踪人数最多、受灾人数最多、房屋受损数量最多的特点。由7个省份组成的集群2没有表现出明显的集群特征。第3组由3个省组成,其特点非常突出,即受害者死亡人数、受害者受伤人数、流离失所人数、教育设施受损人数、卫生设施受损人数和礼拜设施受损人数是其他组中最多的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信