Learning to Trust the Crowd: Validating ‘crowd’ Sources for Improved Situational Awareness in Disaster Response
Procedia engineering(2016)
Abstract
Making the best decision under time constraint is dependent on presentation of a single view with acceptable confidence levels, even when that view and confidence has been derived from a wealth of available yet uncertain data. For example, in a disaster response scenario, many data sources exist in great volume (satellite imagery, field reports, open-source reports and professional monitoring services) with varying levels of uncertainty depending on the source and post-processing performed. In a cross-sector collaboration between humanitarian response, academia, and defense, Rescue Global is working with Oxford University and BMT Defence Services to combine recent developments in machine learning and data provenance to exploit the swell of data generated following a disaster by using a crowd of volunteers with varying levels of ability to enhance decision-making in the field.
MoreTranslated text
Key words
crowd sourcing,provenance,machine learning,disaster response,inter-agency collaboration
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined