Using a mixture of experts’ approach to solve the forecasting task
The forecasting problem appears frequently in the aviation industry (demand forecasting, air transport movement forecasting, etc.). In this article, a new approach based on multiple neural networks of different topologies is introduced. An algorithm was tested on real data and showed better results...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Vilnius Gediminas Technical University
2014-10-01
|
| Series: | Aviation |
| Subjects: | |
| Online Access: | http://journals.vgtu.lt/index.php/Aviation/article/view/2939 |
| id |
doaj-13f877e6d9fe4b3cb2c20e644430e197 |
|---|---|
| record_format |
Article |
| spelling |
doaj-13f877e6d9fe4b3cb2c20e644430e1972021-07-02T03:10:11ZengVilnius Gediminas Technical UniversityAviation1648-77881822-41802014-10-0118310.3846/16487788.2014.9698832939Using a mixture of experts’ approach to solve the forecasting taskVictor Sineglazov0Elena Chumachenko1Vladyslav Gorbatyuk2Technical University of Ukraine “KPI”, 03056 Peremogy Ave 37, Kiev, UkraineTechnical University of Ukraine “KPI”, 03056 Peremogy Ave 37, Kiev, UkraineTechnical University of Ukraine “KPI”, 03056 Peremogy Ave 37, Kiev, Ukraine The forecasting problem appears frequently in the aviation industry (demand forecasting, air transport movement forecasting, etc.). In this article, a new approach based on multiple neural networks of different topologies is introduced. An algorithm was tested on real data and showed better results compared to several other methods. This shows its suitability for further usage in aviation forecasting tasks. http://journals.vgtu.lt/index.php/Aviation/article/view/2939artificial neural networkforecasting methodmixture of expertsmean square prediction errorgroup method of data handlingtraining set |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Victor Sineglazov Elena Chumachenko Vladyslav Gorbatyuk |
| spellingShingle |
Victor Sineglazov Elena Chumachenko Vladyslav Gorbatyuk Using a mixture of experts’ approach to solve the forecasting task Aviation artificial neural network forecasting method mixture of experts mean square prediction error group method of data handling training set |
| author_facet |
Victor Sineglazov Elena Chumachenko Vladyslav Gorbatyuk |
| author_sort |
Victor Sineglazov |
| title |
Using a mixture of experts’ approach to solve the forecasting task |
| title_short |
Using a mixture of experts’ approach to solve the forecasting task |
| title_full |
Using a mixture of experts’ approach to solve the forecasting task |
| title_fullStr |
Using a mixture of experts’ approach to solve the forecasting task |
| title_full_unstemmed |
Using a mixture of experts’ approach to solve the forecasting task |
| title_sort |
using a mixture of experts’ approach to solve the forecasting task |
| publisher |
Vilnius Gediminas Technical University |
| series |
Aviation |
| issn |
1648-7788 1822-4180 |
| publishDate |
2014-10-01 |
| description |
The forecasting problem appears frequently in the aviation industry (demand forecasting, air transport movement forecasting, etc.). In this article, a new approach based on multiple neural networks of different topologies is introduced. An algorithm was tested on real data and showed better results compared to several other methods. This shows its suitability for further usage in aviation forecasting tasks.
|
| topic |
artificial neural network forecasting method mixture of experts mean square prediction error group method of data handling training set |
| url |
http://journals.vgtu.lt/index.php/Aviation/article/view/2939 |
| work_keys_str_mv |
AT victorsineglazov usingamixtureofexpertsapproachtosolvetheforecastingtask AT elenachumachenko usingamixtureofexpertsapproachtosolvetheforecastingtask AT vladyslavgorbatyuk usingamixtureofexpertsapproachtosolvetheforecastingtask |
| _version_ |
1721342036783661056 |