Zhuorui Yang

Mobile DIORAMA-II: Infrastructure less information collection system for mass casualty incidents

In this paper we introduce DIORAMA-II system that provides real time information collection in mass casualty incidents. Using a mobile platform that includes active RFID tags and readers as well as Smartphones, the system can determine the location of victims and responders. The system provides user friendly multi dimensional user interfaces as well as collaboration tools between the responders and the incident commander. We conducted two simulated mass casualty incidents with 50 victims each and professional responders. DIORAMA-II significantly reduces the evacuation time by up to 43% when compared to paper based triage systems. All responders that participated in all trials were very satisfied. They felt in control of the incident and mentioned that the system significantly reduced their stress level during the incident. They all mentioned that they would use the system in an actual incident.

Infrastructure-less and calibration-free RFID-based localization algorithm for victim tracking in mass casualty incidents

We introduce an active RFID-based algorithm for real-time tracking of victims during a Mass Casually Incident (MCI). By using responders locations obtained from GPS on their Smartphones as mobile anchors and active RFID readings from the victims, the proposed localization algorithm obtains average localization accuracy commensurate with GPS [1] (under 20 ft.). The proposed algorithm is a mobile, scalable, affordable, calibration-free and infrastructure-less solution, which makes it suitable for use in an MCI.

Egocentric Landmark-Based Indoor Guidance System for the Visually Impaired

In this paper, we introduce an egocentric landmark-based guidance system that enables visually impaired users to interact with indoor environments. The user who wears Google Glasses will capture his surroundings within his field of view. Using this information, we provide the user an accurate landmark-based description of the environment including his relative distance and orientation to each landmark. To achieve this functionality, we developed a near real time accurate vision based localization algorithm. Since the users are visually impaired our algorithm accounts for captured images using Google Glasses that have severe blurriness, motion blurriness, low illumination intensity and crowd obstruction. We tested the algorithm performance in a 12,000 ft2 open indoor environment. When we have mint query images our algorithm obtains mean location accuracy within 5ft., mean orientation accuracy less than 2 degrees and reliability above 88%. After applying deformation effects to the query images such blurriness, motion blurriness and illumination changes, we observe that the reliability is above 75%.

Vision-based responders localization techniques in urban search and rescue scenarios

In this paper, we introduce a vision-based localization algorithm that can accurately track responders during rescue operations in urban areas that are Global Navigation Satellite System (GNSS)-denied. The proposed algorithm works successfully with the rich visual features of an urban environment and obtains an average localization accuracy of 2.5 ft. In addition, we also provide a 3D representation of the disaster field which reflects the current conditions of the site.

DIORAMA enhances efficiency of a mass casualty incident: System and experimentation

In this paper we show DIORAMA efficiency in a simulated Mass Casualty Incident drill. As shown by our results DIORAMA system has achieved orderly transport of patients from site of injury to collection point, all red before the yellow were transported (no order was obeyed in the paper drills). We also show that DIORAMA system was used by responders with very short training time and by responders that are not familiar with each other. The qualitative results show that DIORAMA system was found to be user friendly and useful in tracking patients and responders in real time.

Evaluation of a Scalable Information Analytics System for Enhanced Situational Awareness in Mass Casualty Events

We investigate the utility of DIORAMA-II system which provides enhanced situational awareness within a disaster scene by using real-time visual analytics tools and a collaboration platform between the incident commander and the emergency responders. Our trials were conducted in different geographical areas (feature-rich and featureless regions) and in different lighting conditions (daytime and nighttime). DIORAMA-II obtained considerable time gain in efficiency compared to conventional paper based systems. DIORAMA-II time gain was reflected in reduction of both average triage time per patient (up to 34.3% average triage time reduction per patient) and average transport time per patient (up to 76.3% average transport time reduction per red patient and up to 66.3% average transport time reduction per yellow patient). In addition, DIORAMA-II ensured that no patients were left behind or transported in the incorrect order compared to the conventional method which resulted in patients being left behind and transported in the incorrect order.

Spatiotemporal digital forensic toolkit for mass casualty incidents: Interactive incident playback and anomaly detection

Analyzing and visualizing spatiotemporal events at a disaster site is a challenging task due to the vast number of events captured during the rescue process. At the same time, the availability of spatial temporal information during a disaster event is invaluable to understand the rescue process and enhance the MCI training accordingly. For this purpose, we have developed a spatiotemporal toolkit that will enable us to analyze and visualize these events, playback the events and detect anomalies. This toolkit will be very useful for forensics analysis of the rescue process during a real disaster or during training sessions. Our novel techniques will be used by analysts to examine current practices and significantly enhance our understanding of the rescue process enabling us to improve training.