Researchers at the Georgia Institute of Technology are proposing a new way of gathering and sharing information during natural disasters without having to rely on the internet.
By using the computing power that is built into mobile phones, routers and other hardware to create a network, emergency managers and first responders can share and act on the information that is gathered from people impacted by hurricanes, tornados, floods and other disasters.
"Increasingly, data gathered from passive and active sensors that people carry with them, such as their mobile phones, is being used to inform situational awareness in a variety of settings," said Kishore Ramachandran, computer science professor at Georgia Tech, "In this way, humans are providing beneficial social sensing services. However, current social sensing services depend on internet connectivity since the services are deployed on central cloud platforms."
The Georgia Tech research team says it is possible to access these centralized services using a decentralized network that leverages the growing amount of computing power at the edge of the internet. This will give a huge advantage to first responders.
In a flooded area, search and rescue personnel using a geo-distributed network would be able to continuously ping the enabled phones, sensors and other devices in an area to determine the exact locations. The data would then be used to create density maps of people in the search region to prioritize and guide emergency response teams.
The proposal takes advantages of edge computing. Edge computing, also known as fog computing, places more processing capabilities in sensing devices—like surveillance cameras, embedded pavement sensors and consumer devices—in order to improve network latency between sensors, apps and users.
Instead of only being able to communicate if there is an internet connection with central cloud platforms, the Georgia Tech team has demonstrated that by harnessing edge computing resources, sensing devices can be enabled to identify and communicate with other sensors in the area.
"We believe fog computing can become a potent enabler of decentralized, local social sensing services that can operate when internet connectivity is constrained," said Ramachandran, “This capability will provide first responders and others with the level of situational awareness they need to make effective decisions in emergency situations."
The team proposed a generic software architecture for social sensing applications that is capable of exploiting the fog-enabled devices. The design has three components: a central management function that resides in the cloud, a data processing element placed in the fog infrastructure and a sensing component on the user’s device.
The researchers say that it is not enough to run a centralized social sensing service on a number of parallel fog nodes.
Beyond emergency response during natural disasters, the team believes its proposed fog architecture can also benefit communities with limited or no internet access, including applications for public transportation management, job recruitment and housing. Another possible application of this new approach is monitoring sensing devices in remote areas.
To monitor far-flung devices in areas with no internet access, a bus could be fitted with fog-enabled sensing capabilities. As the bus travels in remote areas, it would collect data from a sensing device. When it is in range of internet connectivity, the “data mule” bus would upload the information to the centralized cloud-based platforms.
A paper on this research was presented at the second International Workshop on Social Sensing.