110. Genetic programming based algorithm for managing of rescue teams in crisis situations
Invited abstract in session MC-38: Automating the Design, Generation and Control of Optimization Algorithms 2, stream Data Science meets Optimization.
Monday, 12:30-14:00Room: Michael Sadler LG19
Authors (first author is the speaker)
| 1. | Adam Górski
|
| Department of Information Technologies, Jagiellonian University in Kraków | |
| 2. | Maciej Ogorzałek
|
| Department of Information Technologies, Jagiellonian University in Kraków |
Abstract
Crisis situations like traffic accidents, tsunamis, fires, etc. demands coordinated cooperation of many rescue teams. Such teams can be: emergences, fire brigades, police, divers, etc. In crisis situations time is critical. Rescue teams need to help people unless it is too late. Therefore an appropriate management of the teams including choosing the number and type of rescue teams and the assignment of given tasks is very important. We present a genetic programming based algorithm which is able to optimize the cost of rescue action by choosing the number and type of rescue teams and assignment of the tasks. the algorithm starts from initial population which is consistent of randomly created genotypes. Each genotype is a tree. In the nodes of the tree are decisions about sending a new rescue team or assigning the tasks to the teams. The next generations of individual are created using standard genetic operators: selection, mutation and crossover. We believe that proposed methodology is able to make the rescue action more effective, faster and cheaper.
Keywords
- Algorithms
- Artificial Intelligence
- Multi-Objective Decision Making
Status: accepted
Back to the list of papers