Thrips (Thysanoptera) identification using artificial neural networks

FEDOR, Peter, Igor MALENOVSKÝ, Jaromír VAŇHARA, W. SIERKA and Josef HAVEL. Thrips (Thysanoptera) identification using artificial neural networks. Bulletin of Entomological Research. Cambridge, England: CAMBRIDGE UNIV PRESS, 2008, vol. 98, No 4, p. 437-447. ISSN 0007-4853.

Basic information

Original name

Thrips (Thysanoptera) identification using artificial neural networks

Name in Czech

Determinace třásněnek za pomoci ANN.

Authors

FEDOR, Peter (703 Slovakia), Igor MALENOVSKÝ (203 Czech Republic), Jaromír VAŇHARA (203 Czech Republic, guarantor, belonging to the institution), W. SIERKA (616 Poland) and Josef HAVEL (203 Czech Republic, belonging to the institution)

Edition

Bulletin of Entomological Research, Cambridge, England, CAMBRIDGE UNIV PRESS, 2008, 0007-4853

---

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10600 1.6 Biological sciences

Country of publisher

United Kingdom of Great Britain and Northern Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

Impact factor

Impact factor: 1.415

RIV identification code

RIV/00216224:14310/08:00027185

Organization unit

Faculty of Science

UT WoS

000260173700002

Keywords in English

ANN; Thrips;identification

Tags

ANN, identification, thrips

Tags

International impact, Reviewed

---

Abstract

V originále

We studied the use of a supervised artificial neural network (ANN) model for semi-automated identification of 18 common European species of Thysanoptera from four genera: Aeolothrips Haliday (Aeolothripidae), Chirothrips Haliday, Dendrothrips Uzel, and Limothrips Haliday (all Thripidae). As input data, we entered 17 continuous morphometric and two qualitative two-state characters measured or determined on different parts of the thrips body (head, pronotum, forewing and ovipositor) and the sex. Our experimental data set included 498 thrips specimens. A relatively simple ANN architecture (multilayer perceptrons with a single hidden layer) enabled a 97% correct simultaneous identification of both males and females of all the 18 species in an independent test. This high reliability of classification is promising for a wider application of ANN in the practice of Thysanoptera identification.

In Czech

Modelové využití supervised artificial neural network (ANN) pro identifikaci 18 evropských druhů trásněnek 4 rodů.

---

Links

MSM0021622416, plan (intention)

Name: Diverzita biotických společenstev a populací: kauzální analýza variability v prostoru a čase Investor: Ministry of Education, Youth and Sports of the CR, Diversity of Biotic Communities and Populations: Causal Analysis of variation in space and time