Abstract
Traditional approaches to aid disaster management practitioners during response and recovery require extensive effort to timely collect, process, and analyze semi-structured data for extracting relevant information from various sources. Similarly, training instructors rely heavily on manual tasks to collect and analyze trainee performance data during the mitigation and preparedness phases. Efforts to collect and analyze data can be partly attributed to the minimal integration of advanced information technologies in current disaster management practices. The growing adoption of sources like social media (SM) and Internet of Things (IoT) networks provides a unique opportunity to collect additional data to aid all disaster management phases. Artificial intelligence (AI) technologies present an unprecedented era to design information systems that can process data from SM and IoT sources at scale in real time to enhance disaster response processes and training performance analyses. They require a systematic design to employ AI-assisted data processing that has the modularity to create processing pipelines for different modalities, including text, videos, images, and numeric sensor data, extensibility to newer analytical capabilities, interactivity for greater human control, and adaptability to dynamic human needs. It is achievable with the help of a human-centered approach. This chapter introduces and illustrates different applications of human-centered AI system design in managing SM and IoT data to support use cases in different disaster management phases using an example of one such system called Citizen-Helper. The lessons from implementing Citizen-Helper use cases will facilitate an understanding of challenges and practitioner expectations for future research and development of human-centered AI applications within different phases of disaster management.KeywordsHuman-centered AIDisaster managementHuman-AI collaborationInformation processingCitizen-Helper
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
