Artificial neural networks for insect identification.

D 2006

Artificial neural networks for insect identification.

VAŇHARA, Jaromír, Natália MURÁRIKOVÁ, Peter FEDOR, Igor MALENOVSKÝ, Josef HAVEL et. al.

Základní údaje

Originální název

Artificial neural networks for insect identification.

Název česky

ANN v identifikaci hmyzu

Autoři

VAŇHARA, Jaromír (203 Česká republika, garant), Natália MURÁRIKOVÁ (703 Slovensko), Peter FEDOR (703 Slovensko), Igor MALENOVSKÝ (203 Česká republika) a Josef HAVEL (203 Česká republika)

Vydání

Fukuoka, Japan, Proceedings of the 6th International Congress of Dipterology, od s. 289-290, 2 s. 2006

Nakladatel

Comittee of the 6th International Congress of Dipterology

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10600 1.6 Biological sciences

Stát vydavatele

Japonsko

Utajení

není předmětem státního či obchodního tajemství

Kód RIV

RIV/00216224:14310/06:00018398

Organizační jednotka

Přírodovědecká fakulta

Klíčová slova anglicky

ANN Insects Identification

Štítky

ANN Insects Identification

Příznaky

Mezinárodní význam

Změněno: 24. 1. 2007 13:59, prof. RNDr. Jaromír Vaňhara, CSc.

Anotace

ORIG CZ

V originále

ANN have already been very rarely applied for identifying of insects. We developed, tested and applied the ANN methodology at three different insect orders: I. Diptera-Tachinidae: There were 17 characters studied, particularly in males and females (Tachina), or in right or left wings (Ectophasia). Additionally, the sex of the studied specimens was included. It was shown that classification using ANN was possible assuming sufficiently high number of specimens of each species in the training set. II. Thysanoptera-Thripidae: The three species were characterized by 20 quantitative and three binary characters, and by sex. Thus, reliable characters were found and the model provided a fast identification tool. III. Hemiptera-Psylloidea-Phacopteronidae: Adults of up to ten species, 17 characters on forewings, antenna, head and hind legs, and sex were used. The ANN model performed well on the data set and unambiguously classified unknown samples.

Česky

ANN jsou vzácně aplikovány pro taxonomii. Je vyvíjena metodologie, která je testována a jiz i aplikována na různé hmyzí řády: I. Diptera-Tachinidae: II. Thysanoptera-Thripidae: III. Hemiptera-Psylloidea-Phacopteronidae:

Návaznosti

MSM0021622416, záměr

Název: Diverzita biotických společenstev a populací: kauzální analýza variability v prostoru a čase

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Diverzita biotických společenstev: kauzální analýza variability v prostoru a čase

Citovat

VAŇHARA, Jaromír, Natália MURÁRIKOVÁ, Peter FEDOR, Igor MALENOVSKÝ a Josef HAVEL. Artificial neural networks for insect identification. In Proceedings of the 6th International Congress of Dipterology. Fukuoka, Japan: Comittee of the 6th International Congress of Dipterology, 2006, s. 289-290.

@inproceedings{709475,
   author = {Vaňhara, Jaromír and Muráriková, Natália and Fedor, Peter and Malenovský, Igor and Havel, Josef},
   address = {Fukuoka, Japan},
   booktitle = {Proceedings of the 6th International Congress of Dipterology},
   keywords = {ANN Insects Identification},
   language = {eng},
   location = {Fukuoka, Japan},
   pages = {289-290},
   publisher = {Comittee of the 6th International Congress of Dipterology},
   title = {Artificial neural networks for insect identification.},
   year = {2006}
}

TY  - JOUR
ID  - 709475
AU  - Vaňhara, Jaromír - Muráriková, Natália - Fedor, Peter - Malenovský, Igor - Havel, Josef
PY  - 2006
TI  - Artificial neural networks for insect identification.
PB  - Comittee of the 6th International Congress of Dipterology
CY  - Fukuoka, Japan
KW  - ANN Insects Identification
N2  - ANN have already been very rarely applied for identifying of insects. We developed, tested and applied the ANN methodology at three different insect orders: I. Diptera-Tachinidae: There were 17 characters studied, particularly in males and females (Tachina), or in right or left wings (Ectophasia). Additionally, the sex of the studied specimens was included. It was shown that classification using ANN was possible assuming sufficiently high number of specimens of each species in the training set. II. Thysanoptera-Thripidae: The three species were characterized by 20 quantitative and three binary characters, and by sex. Thus, reliable characters were found and the model provided a fast identification tool. III. Hemiptera-Psylloidea-Phacopteronidae: Adults of up to ten species, 17 characters on forewings, antenna, head and hind legs, and sex were used. The ANN model performed well on the data set and unambiguously classified unknown samples.
ER  -

VAŇHARA, Jaromír, Natália MURÁRIKOVÁ, Peter FEDOR, Igor MALENOVSKÝ a Josef HAVEL. Artificial neural networks for insect identification. In \textit{Proceedings of the 6th International Congress of Dipterology}. Fukuoka, Japan: Comittee of the 6th International Congress of Dipterology, 2006, s.~289-290.

Podrobný výpis o publikaci