Natural Disaster Clustering Using K-Means, DBSCAN, SOM, GMM, and Mean Shift: An Analysis of Fema Disaster Statistics

Ting Tin Tin; Yap Jia Hao; Yong Chang Yeou; Lim Siew Mooi; Goh Ting Yew; Temitope Olumide Olugbade; Ali Aitizaz

doi:10.14569/IJACSA.2024.0150968

Natural Disaster Clustering Using K-Means, DBSCAN, SOM, GMM, and Mean Shift: An Analysis of Fema Disaster Statistics

Ting Tin Tin (Lead / Corresponding author)
, Yap Jia Hao
, Yong Chang Yeou
, Lim Siew Mooi
, Goh Ting Yew
, Temitope Olumide Olugbade
, Ali Aitizaz

Research output: Contribution to journal › Article › peer-review

7 Citations (Scopus)

155 Downloads (Pure)

Abstract

Natural disasters tend to ruin people’s lives and infrastructure, which requires comprehensive analysis and understanding to inform effective disaster management and response planning. This research addresses the lack of in-depth analysis of federally declared disasters in the United States using a dataset sourced from FEMA. Through the application of unsupervised learning techniques, including K-means clustering, DBSCAN, self-organizing maps (SOM), and the Gaussian mixture model (GMM), similar types of disasters are clustered based on their frequency. The relationship between disaster type and disaster frequency is analyzed to gain insight into patterns and correlations, facilitating targeted mitigation and adaptation strategies. By using the techniques of clustering, we can accurately group similar disaster types, duration time, occurring time and location of disaster. By implementing these approaches, our study aims to improve the understanding of disaster occurrences and inform decision-making processes in disaster mitigation strategies and adaptation strategies.

Original language	English
Pages (from-to)	667-681
Number of pages	15
Journal	International Journal of Advanced Computer Science and Applications
Volume	15
Issue number	9
DOIs	https://doi.org/10.14569/IJACSA.2024.0150968
Publication status	Published - 2024

Keywords

adaptation strategies
clustering
disaster frequency
disaster management
disaster types
mitigation strategies
Natural disasters
unsupervised learning

ASJC Scopus subject areas

General Computer Science

Access to Document

10.14569/IJACSA.2024.0150968Licence: CC BY

Final published version
Copyright Statement: This is an open access article licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.
Final published version, 2.04 MBLicence: CC BY

Cite this

@article{b0548e94f04f4d30895d97d906b0605e,

title = "Natural Disaster Clustering Using K-Means, DBSCAN, SOM, GMM, and Mean Shift: An Analysis of Fema Disaster Statistics",

abstract = "Natural disasters tend to ruin people{\textquoteright}s lives and infrastructure, which requires comprehensive analysis and understanding to inform effective disaster management and response planning. This research addresses the lack of in-depth analysis of federally declared disasters in the United States using a dataset sourced from FEMA. Through the application of unsupervised learning techniques, including K-means clustering, DBSCAN, self-organizing maps (SOM), and the Gaussian mixture model (GMM), similar types of disasters are clustered based on their frequency. The relationship between disaster type and disaster frequency is analyzed to gain insight into patterns and correlations, facilitating targeted mitigation and adaptation strategies. By using the techniques of clustering, we can accurately group similar disaster types, duration time, occurring time and location of disaster. By implementing these approaches, our study aims to improve the understanding of disaster occurrences and inform decision-making processes in disaster mitigation strategies and adaptation strategies.",

keywords = "adaptation strategies, clustering, disaster frequency, disaster management, disaster types, mitigation strategies, Natural disasters, unsupervised learning",

author = "Tin, \{Ting Tin\} and Hao, \{Yap Jia\} and Yeou, \{Yong Chang\} and Mooi, \{Lim Siew\} and Yew, \{Goh Ting\} and Olugbade, \{Temitope Olumide\} and Ali Aitizaz",

year = "2024",

doi = "10.14569/IJACSA.2024.0150968",

language = "English",

volume = "15",

pages = "667--681",

number = "9",

}

Natural Disaster Clustering Using K-Means, DBSCAN, SOM, GMM, and Mean Shift: An Analysis of Fema Disaster Statistics. / Tin, Ting Tin (Lead / Corresponding author); Hao, Yap Jia; Yeou, Yong Chang et al.
In: International Journal of Advanced Computer Science and Applications, Vol. 15, No. 9, 2024, p. 667-681.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Natural Disaster Clustering Using K-Means, DBSCAN, SOM, GMM, and Mean Shift

T2 - An Analysis of Fema Disaster Statistics

AU - Tin, Ting Tin

AU - Hao, Yap Jia

AU - Yeou, Yong Chang

AU - Mooi, Lim Siew

AU - Yew, Goh Ting

AU - Olugbade, Temitope Olumide

AU - Aitizaz, Ali

PY - 2024

Y1 - 2024

N2 - Natural disasters tend to ruin people’s lives and infrastructure, which requires comprehensive analysis and understanding to inform effective disaster management and response planning. This research addresses the lack of in-depth analysis of federally declared disasters in the United States using a dataset sourced from FEMA. Through the application of unsupervised learning techniques, including K-means clustering, DBSCAN, self-organizing maps (SOM), and the Gaussian mixture model (GMM), similar types of disasters are clustered based on their frequency. The relationship between disaster type and disaster frequency is analyzed to gain insight into patterns and correlations, facilitating targeted mitigation and adaptation strategies. By using the techniques of clustering, we can accurately group similar disaster types, duration time, occurring time and location of disaster. By implementing these approaches, our study aims to improve the understanding of disaster occurrences and inform decision-making processes in disaster mitigation strategies and adaptation strategies.

AB - Natural disasters tend to ruin people’s lives and infrastructure, which requires comprehensive analysis and understanding to inform effective disaster management and response planning. This research addresses the lack of in-depth analysis of federally declared disasters in the United States using a dataset sourced from FEMA. Through the application of unsupervised learning techniques, including K-means clustering, DBSCAN, self-organizing maps (SOM), and the Gaussian mixture model (GMM), similar types of disasters are clustered based on their frequency. The relationship between disaster type and disaster frequency is analyzed to gain insight into patterns and correlations, facilitating targeted mitigation and adaptation strategies. By using the techniques of clustering, we can accurately group similar disaster types, duration time, occurring time and location of disaster. By implementing these approaches, our study aims to improve the understanding of disaster occurrences and inform decision-making processes in disaster mitigation strategies and adaptation strategies.

KW - adaptation strategies

KW - clustering

KW - disaster frequency

KW - disaster management

KW - disaster types

KW - mitigation strategies

KW - Natural disasters

KW - unsupervised learning

UR - https://www.scopus.com/pages/publications/85219498375

U2 - 10.14569/IJACSA.2024.0150968

DO - 10.14569/IJACSA.2024.0150968

M3 - Article

AN - SCOPUS:85219498375

SN - 2158-107X

VL - 15

SP - 667

EP - 681

JO - International Journal of Advanced Computer Science and Applications

JF - International Journal of Advanced Computer Science and Applications

IS - 9

ER -

Natural Disaster Clustering Using K-Means, DBSCAN, SOM, GMM, and Mean Shift: An Analysis of Fema Disaster Statistics

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this