Anticipation in Dynamic Optimization: The Scheduling Case
PPSN VI Proceedings of the 6th International Conference on Parallel Problem Solving from Nature
Proceedings of the 34th conference on Winter simulation: exploring new frontiers
Enhancing the Performance of Maximum---Likelihood Gaussian EDAs Using Anticipated Mean Shift
Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
Adaptive resource allocation for efficient patient scheduling
Artificial Intelligence in Medicine
| Hi-index | 0.00 |
We consider the online problem of scheduling patients with urgencies and preferences on hospital resources with limited capacity. To solve this complex scheduling problem effectively we have to address the following sub problems: determining the allocation of capacity to patient groups, setting dynamic rules for exceptions to the allocation, ordering timeslots based on scheduling efficiency, and incorporating patient preferences over appointment times in the scheduling process. We present a scheduling approach with optimized parameter values that solves these issues simultaneously. In our experiments, we show how our approach outperforms standard scheduling benchmarks for a wide range of scenarios, and how we can efficiently trade-off scheduling performance and fulfilling patient preferences.