Neural network-based performance analysis of coastal vulnerability classification using social physical parameters in the special region of Yogyakarta

Name: Haryani, Dwi

Organization : Universitas Gadjah Mada Yogyakarta. Electrical and Information Engineering Departement

Email : dwiharyani@mail.ugm.ac.id

Name: Nugroho, Lukito Edi

Organization : Universitas Gadjah Mada Yogyakarta. Electrical and Information Engineering Departement

Email : lukito@ugm.ac.id

Name: Hartanto, Rudy

Organization : Universitas Gadjah Mada Yogyakarta. Electrical and Information Engineering Departement

Email : rudy@ugm.ac.id

keyword: Coastal Vulnerability

LCSH: Neural networks (Computer science)

; ANN

; SVM

; CVI

Abstract: Natural disasters present a serious threat to the coastal environment. Coastal disasters like erosion, floods, rising sea levels, droughts, and landslides frequently cause significant loss of life and property damage. Determining the disaster risk in these areas is crucial for providing early warnings to communities. This study employs neural network techniques to assess disaster vulnerability in coastal areas. Specifically, it demonstrates how the neural network algorithm, with varying configurations of dense layers, can effectively classify the level of vulnerability in coastal areas compared to the machine learning method. The classification of disaster vulnerability in coastal regions is segmented into five hazard categories: Very Low, Low, Medium, High, and Very High. The results of the neural network method show that multiple hidden dense layers produced an accuracy of 0,983, which is higher than that of a single hidden dense, which produced 0.977. However, the results from both applications of the neural network method are greater than those from the SVM machine learning method, which provides results of 0.97. These findings indicate that using a multiple hidden dense layer would be more appropriate for classifying vulnerability on the coast of the Special Region of Yogyakarta province using 4724 data points

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Created: 2024

Modified: 2025-04-09

Issued: 2025-04-09

บทความ/Article

application/pdf

BibliograpyCitation : In IEEE Thailand Section. Antennas and Propagation/Electron Devices/Microwave Theory and Techniques Joint Chapter, Electrical Engineering/Electronics, Computer, Telecommunications, and Information Technology Association, and King Mongkut's University of Technology North Bangkok. The 5th Research, Invention and Innovation Congress (RI2C 2024) (pp.100-107). Bangkok : IEEE Thailand Section

eng

©copyrights King Mongkut's University of Technology North Bangkok

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	RI2C 2024pp.100-107.pdf	1.06 MB

ใช้เวลา

0.037366 วินาที