DEVELOPMENT OF NON-DESTRUCTIVE ROBOT FOR EGGPLANTS (SOLANUM MELONGENA) PEST DETECTION AND CLASSIFICATION

Effective pest monitoring is essential for farmers to detect potential crop damage, minimize the use of pesticides and insecticides, and optimize harvest yields. Deep learning techniques, such as convolutional neural networks, enable accurate pest identification and decision-making based on insect i...

Full description

Saved in:
Bibliographic Details
Main Authors: Mark Jayson Y. Sutayco, Eidref Simon Dela Cruz, Harold Aranza, Gian Fernan Collado, Kyle Benedict Lui
Format: Article
Language:English
Published: University of Kragujevac 2025-06-01
Series:Proceedings on Engineering Sciences
Subjects:
Online Access:https://pesjournal.net/journal/v7-n2/64.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422192248356864
author Mark Jayson Y. Sutayco
Eidref Simon Dela Cruz
Harold Aranza
Gian Fernan Collado
Kyle Benedict Lui
author_facet Mark Jayson Y. Sutayco
Eidref Simon Dela Cruz
Harold Aranza
Gian Fernan Collado
Kyle Benedict Lui
author_sort Mark Jayson Y. Sutayco
collection DOAJ
description Effective pest monitoring is essential for farmers to detect potential crop damage, minimize the use of pesticides and insecticides, and optimize harvest yields. Deep learning techniques, such as convolutional neural networks, enable accurate pest identification and decision-making based on insect images. Automation through artificial intelligence (AI) provides opportunities to automate labor-intensive insect control techniques, improving efficiency and reducing risks associated with manual labor. This research proposes a real-time, scalable pest monitoring system that leverages computer vision and machine learning for field crop insect identification. To achieve this goal, a camera-based monitoring system was developed that captures images of plants at regular intervals, analyzes them using software, and categorizes the pests on the images. The camera is mounted on a self-moving robot with a self-powering mechanism using a solar panel attached to a portable battery. The results of pest classification are sent to a mobile application via Firebase. The pest classification model developed yielded notable recall rates, notably 76% for caterpillars, 93% for flea beetles, and 89% for other pests. Additionally, with an average prediction test accuracy of 86%, the researchers have deemed the model's performance relatively satisfactory. However, despite these promising findings, the researchers have outlined various recommendations for enhancing future studies in this field.
format Article
id doaj-art-16e62b2a541b410fa2cd8aee56e46f74
institution Kabale University
issn 2620-2832
2683-4111
language English
publishDate 2025-06-01
publisher University of Kragujevac
record_format Article
series Proceedings on Engineering Sciences
spelling doaj-art-16e62b2a541b410fa2cd8aee56e46f742025-08-20T03:31:11ZengUniversity of KragujevacProceedings on Engineering Sciences2620-28322683-41112025-06-017213251334133410.24874/PES07.02C.013DEVELOPMENT OF NON-DESTRUCTIVE ROBOT FOR EGGPLANTS (SOLANUM MELONGENA) PEST DETECTION AND CLASSIFICATIONMark Jayson Y. Sutayco 0https://orcid.org/0000-0002-9114-6069Eidref Simon Dela Cruz 1https://orcid.org/0009-0000-6440-3480Harold Aranza2https://orcid.org/0009-0006-1434-8560Gian Fernan Collado 3https://orcid.org/0009-0003-4475-7670Kyle Benedict Lui 4https://orcid.org/0009-0003-5247-3264Jose Rizal University, Philippines Jose Rizal University, Philippines Jose Rizal University, Philippines Jose Rizal University, Philippines Jose Rizal University, Philippines Effective pest monitoring is essential for farmers to detect potential crop damage, minimize the use of pesticides and insecticides, and optimize harvest yields. Deep learning techniques, such as convolutional neural networks, enable accurate pest identification and decision-making based on insect images. Automation through artificial intelligence (AI) provides opportunities to automate labor-intensive insect control techniques, improving efficiency and reducing risks associated with manual labor. This research proposes a real-time, scalable pest monitoring system that leverages computer vision and machine learning for field crop insect identification. To achieve this goal, a camera-based monitoring system was developed that captures images of plants at regular intervals, analyzes them using software, and categorizes the pests on the images. The camera is mounted on a self-moving robot with a self-powering mechanism using a solar panel attached to a portable battery. The results of pest classification are sent to a mobile application via Firebase. The pest classification model developed yielded notable recall rates, notably 76% for caterpillars, 93% for flea beetles, and 89% for other pests. Additionally, with an average prediction test accuracy of 86%, the researchers have deemed the model's performance relatively satisfactory. However, despite these promising findings, the researchers have outlined various recommendations for enhancing future studies in this field.https://pesjournal.net/journal/v7-n2/64.pdfneural networkconvolutional neural networkimage processingeggplantsrobotics
spellingShingle Mark Jayson Y. Sutayco
Eidref Simon Dela Cruz
Harold Aranza
Gian Fernan Collado
Kyle Benedict Lui
DEVELOPMENT OF NON-DESTRUCTIVE ROBOT FOR EGGPLANTS (SOLANUM MELONGENA) PEST DETECTION AND CLASSIFICATION
Proceedings on Engineering Sciences
neural network
convolutional neural network
image processing
eggplants
robotics
title DEVELOPMENT OF NON-DESTRUCTIVE ROBOT FOR EGGPLANTS (SOLANUM MELONGENA) PEST DETECTION AND CLASSIFICATION
title_full DEVELOPMENT OF NON-DESTRUCTIVE ROBOT FOR EGGPLANTS (SOLANUM MELONGENA) PEST DETECTION AND CLASSIFICATION
title_fullStr DEVELOPMENT OF NON-DESTRUCTIVE ROBOT FOR EGGPLANTS (SOLANUM MELONGENA) PEST DETECTION AND CLASSIFICATION
title_full_unstemmed DEVELOPMENT OF NON-DESTRUCTIVE ROBOT FOR EGGPLANTS (SOLANUM MELONGENA) PEST DETECTION AND CLASSIFICATION
title_short DEVELOPMENT OF NON-DESTRUCTIVE ROBOT FOR EGGPLANTS (SOLANUM MELONGENA) PEST DETECTION AND CLASSIFICATION
title_sort development of non destructive robot for eggplants solanum melongena pest detection and classification
topic neural network
convolutional neural network
image processing
eggplants
robotics
url https://pesjournal.net/journal/v7-n2/64.pdf
work_keys_str_mv AT markjaysonysutayco developmentofnondestructiverobotforeggplantssolanummelongenapestdetectionandclassification
AT eidrefsimondelacruz developmentofnondestructiverobotforeggplantssolanummelongenapestdetectionandclassification
AT haroldaranza developmentofnondestructiverobotforeggplantssolanummelongenapestdetectionandclassification
AT gianfernancollado developmentofnondestructiverobotforeggplantssolanummelongenapestdetectionandclassification
AT kylebenedictlui developmentofnondestructiverobotforeggplantssolanummelongenapestdetectionandclassification