Pregled bibliografske jedinice broj: 1255422
Development of an automatic monitoring system for pear leaf blister moth and its damage using artificial neural networks
Development of an automatic monitoring system for pear leaf blister moth and its damage using artificial neural networks // Book of Abstract 58th Croatian and 18th International Symposium on Agriculture / Carović-Stanko, Klaudija ; Širić, Ivan (ur.).
Dubrovnik: Agronomski fakultet Sveučilišta u Zagrebu, 2023. str. 232-232 (predavanje, međunarodna recenzija, sažetak, znanstveni)
CROSBI ID: 1255422 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Development of an automatic monitoring system
for pear leaf blister moth and its damage using
artificial neural networks
Autori
Čirjak, Dana ; Aleksi, Ivan ; Miklečić, Ivana ; Lemic, Darija ; Kos, Tomislav ; Antolković, Ana Marija, Vrtodušić, Rea ; Viduka, Antonio ; Pajač Živković, Ivana
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni
Izvornik
Book of Abstract 58th Croatian and 18th International Symposium on Agriculture
/ Carović-Stanko, Klaudija ; Širić, Ivan - Dubrovnik : Agronomski fakultet Sveučilišta u Zagrebu, 2023, 232-232
Skup
58th Croatian & 18th International Symposium on Agriculture
Mjesto i datum
Dubrovnik, Hrvatska, 11.02.2023. - 17.02.2023
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Leucoptera malifoliella (O. Costa, 1836), precise agriculture, pest monitoring device, vegetation monitoring device, pest control
Sažetak
The effectiveness of pest control depends on monitoring methods, most of which are outdated and irrelevant. For example, the pear leaf blister moth (Leucoptera malifoliella (O. Costa, 1836)) is an important apple pest whose larvae damage leaves. Its monitoring is done with pheromone traps, which are time-consuming to inspect and may result in delayed pest control. The most effective time for its control is an early stage of damage occurrence (mines), which is difficult to detect with classical monitoring techniques. Artificial neural networks (ANN) have recently been used for pest monitoring. Therefore, the aim of this study was to develop automatic systems for monitoring pear leaf blister moth and its damage using ANNs. The two ANNs were trained to detect the pear leaf blister moth and its damage using photographs collected in three apple orchards in Zagreb County. The model was developed for use in two prototype smart monitoring devices (pest monitoring device and vegetation monitoring device). The model was tested and the results were processed using a confusion matrix. The developed models showed high accuracy and precision in detecting pear leaf blister moth and its damage, while the monitoring devices showed good functionality in apple orchards. The developed system is effective for automatic monitoring of pear leaf blister moth and its damage, and therefore can significantly improve pest control and apple production in general.
Izvorni jezik
Engleski
Znanstvena područja
Poljoprivreda (agronomija)
POVEZANOST RADA
Profili:
Darija Lemić
(autor)
Ivana Miklečić
(autor)
Ana Marija Antolković
(autor)
Antonio Viduka
(autor)
Dana Čirjak
(autor)
Ivana Pajač Živković
(autor)
Ivan Aleksi
(autor)
Tomislav Kos
(autor)