The objective of the US team for this project is to devise effective techniques for comprehensive data collection. The challenge is that, during a disaster, the availability of information is spatially biased and some areas are not well covered by available information. Towards this end, USC's spatial crowdsourcing platform, dubbed MediaQ, is being utilized to collect pictures and videos on-demand from mobile devices of people in the vicinity of the disaster areas to facilitate effective collection, orchestration and aggregation of information.

Credit: Cyrus Shahabi, USC

Over the last seven years, a Florida International University (FIU) team has been working in collaboration with government and industry partners (such as the Miami-Dade and Palm Beach Offices of Emergency Management, WalMart, Home Depot, Verizon Wireless and many others) to build an FIU-hosted and community-driven service for information sharing and exchange to operate during and after a hurricane recovery period. This image shows a snapshot of the current web-based prototype that displays in an intuitive and user-friendly manner the information collected from various sources. In this project, leveraging their prior research results and a new corroboration with researchers from the University of Tokyo, the team will develop intelligent, context-aware and user-specific solutions to address the critical information exchange needs in disaster affected networks.

Credit: Tao Li, School of Computing and Information Sciences, Florida International University

This figure shows the trajectories of particles (e.g. a contaminant) released very closely together in an evolving turbulent field. It shows that the particle paths differ significantly. So when a sensor detects a signal, it has been "encoded" by the complex dynamics of turbulence and it must "decipher" this complex encoding to identify the source upstream.

Credit: Tamer Zaki and Charles Meneveau, Johns Hopkins University

Tri-TON, an Autonomous Underwater Vehicle (AUV) that U.S. and Japanese researchers will use for the real-time verification of their search olfactory algorithms.

Credit: Tamer Zaki and Charles Meneveau, Johns Hopkins University

A sensor cloud that connects different types of sensor networks spreading in a large geographical area and is accessible by multiple users at the same time, will be used to address the critical information collection, analysis, and processing in disaster management applications. This figure depicts the proposed sensor cloud architecture integrated with a big data management framework. The sensor cloud collects multi-dimensional data from the sensors which are embedded in the environment, available in mobile devices, and generated by social media. The collected data are spatiotemporally indexed in such a fashion that they provide a scalable and robust big data indexing framework for efficient insertion, updating and analysis. The system optimizes network bandwidth and enables faster analysis of past data/events as well as dissemination of timely and correct information to people responsible for decision making.

Credit: Sanjay Madria, Missouri University of Science and Technology