期刊
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
卷 30, 期 2, 页码 -出版社
ASCE-AMER SOC CIVIL ENGINEERS
DOI: 10.1061/(ASCE)CP.1943-5487.0000483
关键词
Disaster rescue; Emergency response; Indoor localization; Activity recognition; Naive Bayes classifier; Smartphone
资金
- National Science Foundation [1030454]
- Direct For Computer & Info Scie & Enginr
- Office of Advanced Cyberinfrastructure (OAC) [1030454] Funding Source: National Science Foundation
In minor to moderate natural and man-made disasters, such as earthquakes and fires, people may be trapped inside buildings and hurt by the disaster. Considering that trapped victims may be unconscious, there is a high demand by emergency responders to get information on the locations and physical statuses of trapped victims inside a building during a disaster. In this paper, a smartphone-based, in-building emergency response assistance system, named iRescue, is presented. The system is comprised of two subsystems: a Victim Positioning System (VPS) and a Victim Assessment System (VAS). The VPS uses the received signal strength indicator of Wi-Fi signals from multiple wireless access points with referencing a pre-established Wi-Fi fingerprinting map of a building. The VAS uses patterns obtained from measured 3D acceleration changes by status of a victim. A Naive Bayes classifier is employed for both VPS and VAS: for localization in between the fingerprinting map and for recognition of activities to be used for status assessment. The performance of the VPS has been validated by a localization test on a complex building. The VAS has been validated by activity simulation test with five people and real-time monitoring of a person equipped with an activity recording device. (C) 2015 American Society of Civil Engineers.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据