Application of deep learning models for pest detection and identification

The quality and productivity of crops are seriously threatened by insect infestations, which is the primary focus of this research. Traditional monitoring methodologies tend to be ineffective and incorrect, resulting in wasted resources and loss of money. By incorporating cutting-edge AI and deep le...

Full description

Saved in:
Bibliographic Details
Main Authors: Ayesha Rafique, Madiha Abbasi, Noreen Akram, Quratulain
Format: Article
Language:English
Published: Mehran University of Engineering and Technology 2025-04-01
Series:Mehran University Research Journal of Engineering and Technology
Subjects:
Online Access:https://murjet.muet.edu.pk/index.php/home/article/view/293
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849701222310739968
author Ayesha Rafique
Madiha Abbasi
Noreen Akram
Quratulain
author_facet Ayesha Rafique
Madiha Abbasi
Noreen Akram
Quratulain
author_sort Ayesha Rafique
collection DOAJ
description The quality and productivity of crops are seriously threatened by insect infestations, which is the primary focus of this research. Traditional monitoring methodologies tend to be ineffective and incorrect, resulting in wasted resources and loss of money. By incorporating cutting-edge AI and deep learning technologies, this study unveils a fresh method for rapid and precisely identifying pests in agricultural settings. This research makes use of high-resolution image technologies and Convolutional Neural Networks (CNNs) to showcase the promise of deep learning models in automated pest detection. The generalizability and model performance may be improved using transfer learning techniques leading to more efficient use of available resources. Key goals of this research include extensive testing across varied pest types and environmental settings, combined with the design and refinement of a CNN model specifically engineered for accurate pest identification. The gap between traditional pest monitoring practices and data-driven procedures is filled by the suggested method which ensures a significant increase in agricultural productivity that will contribute to greater food security and overall economic prosperity. This research strengthens the influential effects on agriculture, including enhancement of pest control, increasing food security, and boosting economic expansion. To promote this cutting-edge use of deep learning in agriculture, continuous cooperation between academics, businesses, and farmers is essential.
format Article
id doaj-art-a7400f26ecdb455a8bb0169899a16cef
institution DOAJ
issn 0254-7821
2413-7219
language English
publishDate 2025-04-01
publisher Mehran University of Engineering and Technology
record_format Article
series Mehran University Research Journal of Engineering and Technology
spelling doaj-art-a7400f26ecdb455a8bb0169899a16cef2025-08-20T03:18:01ZengMehran University of Engineering and TechnologyMehran University Research Journal of Engineering and Technology0254-78212413-72192025-04-0144211712810.22581/muet1982.3080295Application of deep learning models for pest detection and identificationAyesha Rafique0Madiha Abbasi1Noreen Akram2Quratulain3Sir Syed University of Engineering and Technology, Karachi, PakistanSir Syed University of Engineering and Technology, Karachi, PakistanSir Syed University of Engineering and Technology, Karachi, PakistanSir Syed University of Engineering and Technology, Karachi, PakistanThe quality and productivity of crops are seriously threatened by insect infestations, which is the primary focus of this research. Traditional monitoring methodologies tend to be ineffective and incorrect, resulting in wasted resources and loss of money. By incorporating cutting-edge AI and deep learning technologies, this study unveils a fresh method for rapid and precisely identifying pests in agricultural settings. This research makes use of high-resolution image technologies and Convolutional Neural Networks (CNNs) to showcase the promise of deep learning models in automated pest detection. The generalizability and model performance may be improved using transfer learning techniques leading to more efficient use of available resources. Key goals of this research include extensive testing across varied pest types and environmental settings, combined with the design and refinement of a CNN model specifically engineered for accurate pest identification. The gap between traditional pest monitoring practices and data-driven procedures is filled by the suggested method which ensures a significant increase in agricultural productivity that will contribute to greater food security and overall economic prosperity. This research strengthens the influential effects on agriculture, including enhancement of pest control, increasing food security, and boosting economic expansion. To promote this cutting-edge use of deep learning in agriculture, continuous cooperation between academics, businesses, and farmers is essential.https://murjet.muet.edu.pk/index.php/home/article/view/293deep learningpest detectionfusioncnnaucroc
spellingShingle Ayesha Rafique
Madiha Abbasi
Noreen Akram
Quratulain
Application of deep learning models for pest detection and identification
Mehran University Research Journal of Engineering and Technology
deep learning
pest detection
fusion
cnn
auc
roc
title Application of deep learning models for pest detection and identification
title_full Application of deep learning models for pest detection and identification
title_fullStr Application of deep learning models for pest detection and identification
title_full_unstemmed Application of deep learning models for pest detection and identification
title_short Application of deep learning models for pest detection and identification
title_sort application of deep learning models for pest detection and identification
topic deep learning
pest detection
fusion
cnn
auc
roc
url https://murjet.muet.edu.pk/index.php/home/article/view/293
work_keys_str_mv AT ayesharafique applicationofdeeplearningmodelsforpestdetectionandidentification
AT madihaabbasi applicationofdeeplearningmodelsforpestdetectionandidentification
AT noreenakram applicationofdeeplearningmodelsforpestdetectionandidentification
AT quratulain applicationofdeeplearningmodelsforpestdetectionandidentification