-
Je něco špatně v tomto záznamu ?
Direct Versus Iterated Multi-Step Forecasting of Glycaemia in Type 1 Diabetics Using Autoregressive Models
M. Macaš, K. Saiti, L. Lhotská, K. Štechová, P. Piťhová,
Jazyk angličtina Země Nizozemsko
Typ dokumentu časopisecké články
PubMed
33087605
DOI
10.3233/shti200630
Knihovny.cz E-zdroje
- MeSH
- diabetes mellitus 1. typu * diagnóza MeSH
- lidé MeSH
- předpověď MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
The paper compares two approaches to multi-step ahead glycaemia forecasting. While the direct approach uses a different model for each number of steps ahead, the iterative approach applies one one-step ahead model iteratively. Although it is well known that the iterative approach suffers from the error accumulation problem, there are no clear outcomes supporting a proper choice between those two methods. This paper provides such comparison for different ARX models and shows that the iterative approach outperformed the direct method for one-hour ahead (12-steps ahead) forecasting. Moreover, the classical linear ARX model outperformed more complex non-linear versions for training data covering one-month period.
Citace poskytuje Crossref.org
- 000
- 00000naa a2200000 a 4500
- 001
- bmc20027847
- 003
- CZ-PrNML
- 005
- 20210114152501.0
- 007
- ta
- 008
- 210105s2020 ne f 000 0|eng||
- 009
- AR
- 024 7_
- $a 10.3233/SHTI200630 $2 doi
- 035 __
- $a (PubMed)33087605
- 040 __
- $a ABA008 $b cze $d ABA008 $e AACR2
- 041 0_
- $a eng
- 044 __
- $a ne
- 100 1_
- $a Macaš, Martin $u Czech Insitute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Czech Republic.
- 245 10
- $a Direct Versus Iterated Multi-Step Forecasting of Glycaemia in Type 1 Diabetics Using Autoregressive Models / $c M. Macaš, K. Saiti, L. Lhotská, K. Štechová, P. Piťhová,
- 520 9_
- $a The paper compares two approaches to multi-step ahead glycaemia forecasting. While the direct approach uses a different model for each number of steps ahead, the iterative approach applies one one-step ahead model iteratively. Although it is well known that the iterative approach suffers from the error accumulation problem, there are no clear outcomes supporting a proper choice between those two methods. This paper provides such comparison for different ARX models and shows that the iterative approach outperformed the direct method for one-hour ahead (12-steps ahead) forecasting. Moreover, the classical linear ARX model outperformed more complex non-linear versions for training data covering one-month period.
- 650 12
- $a diabetes mellitus 1. typu $x diagnóza $7 D003922
- 650 _2
- $a předpověď $7 D005544
- 650 _2
- $a lidé $7 D006801
- 655 _2
- $a časopisecké články $7 D016428
- 700 1_
- $a Saiti, Kyriaki $u Czech Insitute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Czech Republic.
- 700 1_
- $a Lhotská, Lenka $u Czech Insitute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Czech Republic.
- 700 1_
- $a Štechová, Kateřina $u Motol University Hospital, Prague, Czech Republic.
- 700 1_
- $a Piťhová, Pavlína $u Motol University Hospital, Prague, Czech Republic.
- 773 0_
- $w MED00180836 $t Studies in health technology and informatics $x 1879-8365 $g Roč. 273, č. - (2020), s. 149-154
- 856 41
- $u https://pubmed.ncbi.nlm.nih.gov/33087605 $y Pubmed
- 910 __
- $a ABA008 $b sig $c sign $y a $z 0
- 990 __
- $a 20210105 $b ABA008
- 991 __
- $a 20210114152459 $b ABA008
- 999 __
- $a ok $b bmc $g 1608182 $s 1119027
- BAS __
- $a 3
- BAS __
- $a PreBMC
- BMC __
- $a 2020 $b 273 $c - $d 149-154 $e 2020Sep04 $i 1879-8365 $m Studies in health technology and informatics $n Stud Health Technol Inform $x MED00180836
- LZP __
- $a Pubmed-20210105
