GRIMP: A machine-learning method for improving groups of
discriminating species in expert systems for vegetation
classification

J 2019

GRIMP: A machine-learning method for improving groups of discriminating species in expert systems for vegetation classification

TICHÝ, Lubomír, Milan CHYTRÝ a Flavia LANDUCCI

Základní údaje

Originální název

GRIMP: A machine-learning method for improving groups of discriminating species in expert systems for vegetation classification

Autoři

TICHÝ, Lubomír (203 Česká republika, garant, domácí), Milan CHYTRÝ (203 Česká republika, domácí) a Flavia LANDUCCI (380 Itálie, domácí)

Vydání

Journal of Vegetation Science, Hoboken, Wiley, 2019, 1100-9233

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10611 Plant sciences, botany

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

Full Text

Impakt faktor

Impact factor: 2.698

Kód RIV

RIV/00216224:14310/19:00107368

Organizační jednotka

Přírodovědecká fakulta

DOI

http://dx.doi.org/10.1111/jvs.12696

UT WoS

000459812100002

Klíčová slova anglicky

diagnostic species group; discriminating species group; expert system; phytosociology; plant community; vegetation classification; vegetation-plot database; vegetation survey

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 17. 3. 2020 15:45, Mgr. Marie Šípková, DiS.

Anotace

V originále

Aims: Expert systems are increasingly popular tools for supervised classification of large datasets of vegetation-plot records, but their classification accuracy depends on the selection of proper species and species groups that can effectively discriminate vegetation types. Here, we present a new semi-automatic machine-learning method called GRIMP (GRoup IMProvement) to optimize groups of species used for discriminating among vegetation types in expert systems. We test its performance using a large set of vegetation-plot records. - Methods: We defined discriminating species groups as the groups that are unique to each vegetation type and provide optimal discrimination of this type against other types. The group of discriminating species of each vegetation type considerably overlaps with the group of diagnostic species of this type, but these two groups are not identical because not all diagnostic species have sufficient discriminating power. We developed the GRIMP iterative algorithm, which optimizes the groups of discriminating species to provide the most accurate vegetation classification, using a training set of a priori classified plot records. We tested this method by comparing classification accuracy before and after the GRIMP optimization of species groups using vegetation-plot records from the Czech Republic a priori classified to 39 phytosociological classes, and three initial sets of candidate discriminating species from different sources. - Results: The GRIMP algorithm improved the classification accuracy at the class level from 65% correctly classified plots in the test dataset before group optimization to 88% thereafter. The other plots were misclassified or unclassified, but misclassifications were reduced by adding further expert-based criteria considering dominant growth forms. - Conclusions: GRIMP-optimized groups of discriminating species are very useful for semi-automatic construction of expert systems for vegetation classification. Such expert systems can be developed from an a priori unsupervised or expert-based classification of at least some vegetation plots.

Návaznosti

GA17-15168S, projekt VaV

Název: Expertní systémy nové generace pro klasifikaci vegetace v kontinentálním měřítku

Investor: Grantová agentura ČR, Next generation expert systems for vegetation classification on a continental scale

Citovat

TICHÝ, Lubomír, Milan CHYTRÝ a Flavia LANDUCCI. GRIMP: A machine-learning method for improving groups of discriminating species in expert systems for vegetation classification. Journal of Vegetation Science. Hoboken: Wiley, 2019, roč. 30, č. 1, s. 5-17. ISSN 1100-9233. Dostupné z: https://dx.doi.org/10.1111/jvs.12696.

@article{1524877,
   author = {Tichý, Lubomír and Chytrý, Milan and Landucci, Flavia},
   article_location = {Hoboken},
   article_number = {1},
   doi = {http://dx.doi.org/10.1111/jvs.12696},
   keywords = {diagnostic species group; discriminating species group; expert system; phytosociology; plant community; vegetation classification; vegetation-plot database; vegetation survey},
   language = {eng},
   issn = {1100-9233},
   journal = {Journal of Vegetation Science},
   title = {GRIMP: A machine-learning method for improving groups of discriminating species in expert systems for vegetation classification},
   url = {https://onlinelibrary.wiley.com/doi/full/10.1111/jvs.12696},
   volume = {30},
   year = {2019}
}

TY  - JOUR
ID  - 1524877
AU  - Tichý, Lubomír - Chytrý, Milan - Landucci, Flavia
PY  - 2019
TI  - GRIMP: A machine-learning method for improving groups of discriminating species in expert systems for vegetation classification
JF  - Journal of Vegetation Science
VL  - 30
IS  - 1
SP  - 5-17
EP  - 5-17
PB  - Wiley
SN  - 11009233
KW  - diagnostic species group
KW  - discriminating species group
KW  - expert system
KW  - phytosociology
KW  - plant community
KW  - vegetation classification
KW  - vegetation-plot database
KW  - vegetation survey
UR  - https://onlinelibrary.wiley.com/doi/full/10.1111/jvs.12696
L2  - https://onlinelibrary.wiley.com/doi/full/10.1111/jvs.12696
N2  - Aims: Expert systems are increasingly popular tools for supervised classification of large datasets of vegetation-plot records, but their classification accuracy depends on the selection of proper species and species groups that can effectively discriminate vegetation types. Here, we present a new semi-automatic machine-learning method called GRIMP (GRoup IMProvement) to optimize groups of species used for discriminating among vegetation types in expert systems. We test its performance using a large set of vegetation-plot records. - Methods: We defined discriminating species groups as the groups that are unique to each vegetation type and provide optimal discrimination of this type against other types. The group of discriminating species of each vegetation type considerably overlaps with the group of diagnostic species of this type, but these two groups are not identical because not all diagnostic species have sufficient discriminating power. We developed the GRIMP iterative algorithm, which optimizes the groups of discriminating species to provide the most accurate vegetation classification, using a training set of a priori classified plot records. We tested this method by comparing classification accuracy before and after the GRIMP optimization of species groups using vegetation-plot records from the Czech Republic a priori classified to 39 phytosociological classes, and three initial sets of candidate discriminating species from different sources. - Results: The GRIMP algorithm improved the classification accuracy at the class level from 65% correctly classified plots in the test dataset before group optimization to 88% thereafter. The other plots were misclassified or unclassified, but misclassifications were reduced by adding further expert-based criteria considering dominant growth forms. - Conclusions: GRIMP-optimized groups of discriminating species are very useful for semi-automatic construction of expert systems for vegetation classification. Such expert systems can be developed from an a priori unsupervised or expert-based classification of at least some vegetation plots.
ER  -

TICHÝ, Lubomír, Milan CHYTRÝ a Flavia LANDUCCI. GRIMP: A machine-learning method for improving groups of discriminating species in expert systems for vegetation classification. \textit{Journal of Vegetation Science}. Hoboken: Wiley, 2019, roč.~30, č.~1, s.~5-17. ISSN~1100-9233. Dostupné z: https://dx.doi.org/10.1111/jvs.12696.

Podrobný výpis o publikaci