The Next-Generation Connected and Smart Cyber-Fire Fighter System

According to the fire fighter fatalities report issued by the U.S. Fire Administration, ninety-one firefighters
including 56 volunteer, 30 career and five wildland agencies died while on duty in the year of 2014.
Respecting the fact that the total number of fire incidents across the country is actually decreasing, being a
fire fighter becomes more and more dangerous disregarding other significant advances in various areas of
science and technology. In the proposed research project, we investigate a new connected and smart infrastructure
that allows the development of next-generation first responder coordination protocols. The proposed
system will fundamentally augment existing systems used by first responders, with an initiative that couples
novel hardware and software components to the fire fighters’ existing equipment, keeping minimal weight
and firefighter training. The proposed system will provide a predictive modeling capability that supports
the incident commanders evaluating possible alternative actions and choosing the best approach based on
their experience and available resources. We enhance the information flow by creating a concept of case
awareness through simulating the fire spreading based on the shared perspectives from both the incident
commander and individual fire fighters. Current systems use voice-only radio channels for fireground and
tactical communications. The proposed communication system is based on a Software Defined Network
approach that supports the use of heterogeneous communication assets, and provides instant deployment
and hot reconfiguration, cyber-security, resiliency and recovery abilities, and the possibility of service externalization
with bounded latency and encryption. The proposed smart mesh communications structure
combined with the situational awareness provides location and search capabilities. The communications
backbone, in addition to the voice channel, will be enhanced and extended to enable the increased data flow
from various sensors collected locally but not yet integrated into a larger picture or awareness.

The proposed project seeks to make fundamental technical and algorithmic advances within the context
of connected and smart cyber firefighting. More specifically, 1) we will devise a sensor-rich hardware layout
that collects firsthand information for each individual fire fighter on duty, including RGB/thermal vision,
heart/breathing rate, blood oxygen, wind condition, regional temperature, and smoke level etc. 2) Novel machine
learning based algorithms will be developed and customized for firefighting, which allow an efficient
knowledge extraction for the local situational awareness with the data collected from wearable sensors. 3)
A Software Defined Network approach will be studied and deployed for a more effective communication
among fire fighters as well as the incident commander. This will also be coupled with a fast data compression
algorithm to further improve the transmission capacity of the data channel. 4) We will investigate a
computational intelligence model based on the existing fire incident and training data, from our partner fire
departments and consulting firms. This model directs a computer-analysis-based optimal decision to the fire
fighters or the commander on the top of the collected real-time ground data. We will also develop a novel
subspace numerical simulator to predict the fire behavior based on the collected field data, which could be
critical for the wildland firefighting.

The state of the project is the following. Sensor hardware and software are under development. Two
data collection procedures have been submitted to the Institutional Review Board to obtain experimental
data about tiredness and stress with volunteers, and to record and analyze voice in fire fighters during fire
training. All feature extraction procedures with body sensors and IR imagery have been initiated. The communications
mesh is under development. Two journal papers are under development. Two PhD dissertations
are initiated. Many graduate students have expressed interest in this project.