TY - GEN
T1 - Optimization of emergency response using higher order learning and clustering of 911 text messages
AU - Nelson, Christie
AU - Pottenger, William M.
PY - 2013
Y1 - 2013
N2 - In real-time emergency response an accurate picture of the situation is needed quickly. Often during large-scale disasters, cell towers become overloaded, and the only way of communication is through text messages. It becomes important to gather information from text messages sent to emergency numbers in order to respond quickly and efficiently with life-saving efforts. In addition, responders are unable to manually handle the large volume of incoming texts. To add to this difficult problem, these data sources tend to be microtext. This research developed a methodology to summarize text messages sent during an emergency, including analysis of locations. The real-time disaster needs were then input into a mixed integer programming resource allocation model for distribution of resources for disaster aid. Prior research included resource allocation and text modeling, but the combination of the two is a novel application not only in this arena, but more broadly across domains.
AB - In real-time emergency response an accurate picture of the situation is needed quickly. Often during large-scale disasters, cell towers become overloaded, and the only way of communication is through text messages. It becomes important to gather information from text messages sent to emergency numbers in order to respond quickly and efficiently with life-saving efforts. In addition, responders are unable to manually handle the large volume of incoming texts. To add to this difficult problem, these data sources tend to be microtext. This research developed a methodology to summarize text messages sent during an emergency, including analysis of locations. The real-time disaster needs were then input into a mixed integer programming resource allocation model for distribution of resources for disaster aid. Prior research included resource allocation and text modeling, but the combination of the two is a novel application not only in this arena, but more broadly across domains.
KW - HO-LDA
KW - HONB
KW - Higher Order Latent Dirichlet Allocation
KW - Higher Order Naïve Bayes
KW - Higher Order topic modeling
KW - LDA
KW - Latent Dirichlet Allocation
KW - disaster response
KW - higher order learning
KW - machine learning
KW - mixed integer programming
KW - operations research
KW - optimization
KW - topic modeling
UR - https://www.scopus.com/pages/publications/84893337598
UR - https://www.scopus.com/pages/publications/84893337598#tab=citedBy
U2 - 10.1109/THS.2013.6699052
DO - 10.1109/THS.2013.6699052
M3 - Conference contribution
SN - 9781479915354
T3 - 2013 IEEE International Conference on Technologies for Homeland Security, HST 2013
SP - 486
EP - 491
BT - 2013 IEEE International Conference on Technologies for Homeland Security, HST 2013
T2 - 2013 13th IEEE International Conference on Technologies for Homeland Security, HST 2013
Y2 - 12 November 2013 through 14 November 2013
ER -