imageConsiderable attention has been paid to the problem of how to best deploy ambulances within municipalities to minimize their response times to emergency calls while keeping costs low. Sophisticated operations research models have been developed to address issues such as the optimal number of ambulances, where to place bases, and how to moveunnamed (4) ambulances in real time via system-status management.

However, methods for estimating the inputs to these models, such as travel times on road networks and call arrival rates, are ad hoc. Use of inaccurate parameter estimates in these models can result in poor deployment decisions, leading to low performance1507 and diminished user confidence in the software.

Our work in this area focuses on methods for predicting ambulance demand accurately in fine resolutions in space and time, and addresses challenges including data sparsity at high resolutions and the need to respect complex urban spatial domains.

Related Publications


Preprint: Zhou, Z., and Matteson, D.S. (2015), “Predicting Melbourne Ambulance Demand Using Kernel Warping.”


Westgate, B.S., Woodard, D.B., Matteson, D.S. and Henderson, S.G. (2015), “Large-Network Travel Time Estimation for Ambulance Fleet Management,” To Appear, European Journal of Operational Research.

Zhou, Z., Matteson, D.S., Woodard, D.B., Micheas, A.C. and Henderson, S.G. (2015), “A Spatio-Temporal Point Process Model for Ambulance Demand,” Journal of the American Statistical Association, Vol. 110, No. 509, 6-15.

Zhou, Z., and Matteson, D.S. (2015), “Predicting Ambulance Demand: A Spatio-Temporal Kernel Approach,” Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2297-2303.

Zhou, Z. and Matteson, D.S. (2015), “Temporal and Spatio-Temporal Models for Ambulance Demand,” In Press, Healthcare Data Analysis, Wiley.

Westgate, B.S., Woodard, D.B., Matteson, D.S. and Henderson, S.G. (2013), “Travel Time Estimation for Ambulances using Bayesian Data Augmentation,” Annals of Applied Statistics, Vol. 7, No. 2, 1139-1161.

Matteson, D.S., McLean, M.W., Woodard, D.B. and Henderson, S.G. (2011), “Forecasting Emergency Medical Service Call Arrival Rates,” Annals of Applied Statistics, Vol. 5, No. 2B, 1379-1406.

Research Projects