Establishing Collecting and Analysis Models for the Multiple Disaster Information Collecting and Analysis( III )

View Statistics Email Alert RSS Feed

Information

Details

Project title

Code/計畫編號

MOST104-2625-M865-001

Translated Name/計畫中文名

結合開放式災情回報與預警技術建置即時互動式土石流災情資訊平台-子計畫:多元災情資訊蒐整分析模組建置(III)

Funding Organization/主管機關

National Science and Technology Center for Disaster Reduction

Co-Investigator(s)/共同執行人

蘇文瑞(計畫主持人)

Department/Unit

National Science and Technology Center for Disaster Reduction

Website

https://www.grb.gov.tw/search/planDetail?id=11477621

Year

2015

Start date/計畫起

01-08-2015

Expected Completion/計畫迄

31-07-2016

Co-Investigator(s)

Yuan-Fong Su

Bugetid/研究經費

826千元

ResearchField/研究領域

防災工程

台灣因其特殊的地理位置、形變化和質條件，經常受到颱風水災山崩土石流、地震等許多自然災害的侵襲，也因此造成人民生命財產嚴重損失。為了減少天然災害造成的損失，如何整合發生後之情資料並加以分析運用是非常重要最近社群媒體已成為天然災害的資訊傳播利器，其在救災中發揮了重要作用，雖然社交媒體可以帶來積極的協助救災工作，但他也有不容易協調和資訊共享資源及如何整合不同的救援組織提供災害資訊等議題待解決。本計畫已將颱風災情資料表的民眾回報資料，使用空間統計模組進行分析及時序。以期未來防救災動所採的資料，能夠妥善利用民間大眾的力量以及現代科技便性建立更準確、即時災情預測模式。研究成果顯示民間資訊皆具有空自相關特性與群聚現象空間特性以洪災分布較廣，交通阻斷及坡地害為零星；時效來說則是災、交通阻斷反應較為迅速，坡地害類別情回報延遲。本研究成果可提供後續進行民間災情彙整運用之參考。另外每當災害發生時，各類社群媒體均會產巨量之災情資訊，針對這些巨量料如何探勘歸納成有用為另一重要課題因此本研究運用資料清理與探勘以及群聚分析方法分析災情資料，以提供更有效率之情資訊。本研究也將整合空間資訊技術建置災情地圖。最後，本研究將發展一個依照不同分類之災情整合呈現視覺化模組與簡易災情查詢模組。 Due to its special geographic location and geological conditions, Taiwan often affected by typhoons, floods, landslides, debris flows, earthquakes and many other natural disasters, which resulted in heavy losses of life and property of the people. In order to reduce the damage caused by the natural disaster, how to integrate and analysis the condition of a disaster is very important. Especially, social media has recently played a critical role in natural disasters as an information propagator that can be leveraged for disaster relief. Although social media can positively impact disaster relief efforts, it does not provide an inherent coordination capability for easily coordinating and sharing information, resources, and plans among disparate relief organizations. This study will use data cleansing, data mining and cluster analysis method analysis of disaster data, to provide more efficient disaster information. This study will also be integrating localization technology to build disaster mapping. Finally, the study will develop suitable disaster data visualization and simple disaster inquiry modules for disaster relief.

DSpace CRIS

Establishing Collecting and Analysis Models for the Multiple Disaster Information Collecting and Analysis( III )

Details

Description