Journal of Engineering and Applied Sciences
ISSN: Online 1818-7803ISSN: Print 1816-949x
102
Views
0
Downloads
Abstract
Malaysia’s National Security Council Directive No. 20 (MNSC No. 20) was established to ensure a disaster could be managed in an integrated, systematic and coordinated manner. When disasters occur, quick decisions must be taken to prevent more damage to property and loss of lives. Although, MNSC No. 20 had been established, since the year 1997, the system used by responders to manage the disaster is not effective. Conventionally, the first responder operation system during disaster is conducted through writing the disasters information on paper forms and there is no standardize report forms. There are often difficulties in updating and conveying any new information to other responders as well as possibilities in missing some of the important information regarding the disaster. Additionally, the disadvantage of conventional system is that it consumes a lot of time for the responders to decide, the type and number of rescue transport, man power and logistic needed in a limited time frame when the expertise is not available at the disaster site. A new system that can institute a quick and reliable decision for disaster and complies with the standard issued in MNSC No. 20 that is highly demanded. The disaster management system will fully be developed using Matlab software and the main source of data are from Fire and Rescue Department Malaysia (FRDM), MNSC No.20 policy and other Standard Operating Procedure (SOP). The objective of designing the system is to help and assisting responders especially FRDM in proposing the number of resources needed and determining the level of disaster during response phase effectively and efficiently.
How to cite this article:
W. Ahmad Syafiq Hilmi Wan Abdull Hamid, Mohamad Fahmi Hussin, Khairilmizal Samsudin, Ahmad Ihsan Mohd Yassin and Anas Mohd Rafi . Disaster Management System using Artificial Neural Network.
DOI: https://doi.org/10.36478/jeasci.2017.4637.4642
URL: https://www.makhillpublications.co/view-article/1816-949x/jeasci.2017.4637.4642