|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Social media is a source of low cost source of news and information. It is also work as information gathering and distribution toolduring the disaster situation.In this paper, we proposed an experimental model for simulating the use of social media data in disaster management. The focus of the model is to design a system which can early detect the natural disaster, identify the help request, getting feedback of response and obtain the situational awareness of the disaster conditions. In order to accomplish such model we implemented a modified Fuzzy C Means (FCM) clustering algorithms. Additionally by enhancing the centroids calculation for different situations the learning of the model is enhanced with the increasing amount of sample data.The experimental model has been implemented and the experiments are conducted on a publically available dataset. Based on the experimental results the proposed model found effective accuracy and acceptable training time. Therefore this model will help to manage the disaster situation from initiation to the disaster response.
Keyword
Disaster Management, Machine Learning Algorithm, Unsupervised Learning, Experimental Study, Performance Comparison.
PDF Download (click here)
|
|
|
|
|