A Boosting Algorithm for the Classifiers in the Nurse Rostering Problems

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00208850" target="_blank" >RIV/68407700:21230/13:00208850 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
A Boosting Algorithm for the Classifiers in the Nurse Rostering Problems
Original language description
Nurse rostering problem is a well-known combinatorial problem. It can be solved by many (meta/hyper) heuristics while these methods are based on two usual steps: generate new solutions first and then determine their quality using an objective function. Unfortunately, this process is very expensive in terms of the computational complexity. Thus, we propose a faster evaluation of the objective function based on the solution structure. The idea is to mimic the human mind because the human schedulers are able to quickly recognize an obviously bad roster using only their own experience instead of complex computing. For this purpose, a neural network as a classifier can be used not only to distinguish between good and bad solutions but also to determine howmuch good or bad the solutions are. We apply an adaptive boosting algorithm to achieve more precise classification rates too. The results from the experiments show that the proposed approaches can reduce the runtime of the scheduling algo
Czech name
—
Czech description
—

Project
<a href="/en/project/7H12008" target="_blank" >7H12008: Design, Monitoring and Operation of Adaptive Networked Embedded Systems</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
POSTER 2013 - 17th International Student Conference on Electrical Engineering
ISBN
978-80-01-05242-6
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
1-5
Publisher name
Czech Technical University
Place of publication
Prague
Event location
Prague
Event date
May 16, 2013
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)