A feasibility Study of Detecting Chironomidae Larva in Water Treatment Filtration Processes using ResNet-based Image Recognition Deep Learning

There is a possibility that Chironomidae Larva may appear in sand and activated carbon filters during drinking water treatment. This study was conducted to determine whether the presence or absence of larva that may appear in filters through image data analysis. Image data were created for cases wit...

Full description

Saved in:
Bibliographic Details
Main Authors: Si Hyeong Park, Myeong Eon Choi, Seung Yong Lee, Jong-Oh Kim, No-Suk Park
Format: Article
Language:English
Published: Korean Society of Environmental Engineers 2025-05-01
Series:대한환경공학회지
Subjects:
Online Access:http://www.jksee.or.kr/upload/pdf/KSEE-2025-47-5-354.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762447786770432
author Si Hyeong Park
Myeong Eon Choi
Seung Yong Lee
Jong-Oh Kim
No-Suk Park
author_facet Si Hyeong Park
Myeong Eon Choi
Seung Yong Lee
Jong-Oh Kim
No-Suk Park
author_sort Si Hyeong Park
collection DOAJ
description There is a possibility that Chironomidae Larva may appear in sand and activated carbon filters during drinking water treatment. This study was conducted to determine whether the presence or absence of larva that may appear in filters through image data analysis. Image data were created for cases with and without larva background with interference materials such as sand and activated carbon granules used in the actual water treatment process. We used ResNet, one of the image classification deep learning models, and verified and evaluated its accuracy. Among the 12 models, the top three models with high TPR were ResNet50 No-pretrained LR=0.1, ResNet18 No-pretrained LR=0.001, and ResNet18 No-pretrained LR=0.01. Models trained by only obtaining the structure of the ResNet model without pre-training showed higher accuracy and superior performance. Among the models with the highest accuracy, ResNet50 No-pretrained LR=0.1 had a large TPR value. However, FPR also showed a large value. Therefore, it could not be suitable for judging the presence or absence of larva in the water treatment process.When comparing ResNet18 No-pretrained LR=0.001 and ResNet18 No-pretrained LR=0.01, which had the second and third highest TPRs, the ResNet18 No-pretrained LR=0.01 model had the highest Accuracy and F1 Score.
format Article
id doaj-art-e6db7e92f13d46a9858a38a18b98a43d
institution DOAJ
issn 1225-5025
2383-7810
language English
publishDate 2025-05-01
publisher Korean Society of Environmental Engineers
record_format Article
series 대한환경공학회지
spelling doaj-art-e6db7e92f13d46a9858a38a18b98a43d2025-08-20T03:05:44ZengKorean Society of Environmental Engineers대한환경공학회지1225-50252383-78102025-05-0147535436510.4491/KSEE.2025.47.5.3544596A feasibility Study of Detecting Chironomidae Larva in Water Treatment Filtration Processes using ResNet-based Image Recognition Deep LearningSi Hyeong Park0Myeong Eon Choi1Seung Yong Lee2Jong-Oh Kim3No-Suk Park4Korea Institute of Hydrological SurveyDepartment of Civil Engineering and Engineering Research Institute, Gyeongsang National UniversityDepartment of Civil Engineering and Engineering Research Institute, Gyeongsang National UniversityDepartment of Urban Engineering, Gyeongsang National UniversityDepartment of Civil Engineering and Engineering Research Institute, Gyeongsang National UniversityThere is a possibility that Chironomidae Larva may appear in sand and activated carbon filters during drinking water treatment. This study was conducted to determine whether the presence or absence of larva that may appear in filters through image data analysis. Image data were created for cases with and without larva background with interference materials such as sand and activated carbon granules used in the actual water treatment process. We used ResNet, one of the image classification deep learning models, and verified and evaluated its accuracy. Among the 12 models, the top three models with high TPR were ResNet50 No-pretrained LR=0.1, ResNet18 No-pretrained LR=0.001, and ResNet18 No-pretrained LR=0.01. Models trained by only obtaining the structure of the ResNet model without pre-training showed higher accuracy and superior performance. Among the models with the highest accuracy, ResNet50 No-pretrained LR=0.1 had a large TPR value. However, FPR also showed a large value. Therefore, it could not be suitable for judging the presence or absence of larva in the water treatment process.When comparing ResNet18 No-pretrained LR=0.001 and ResNet18 No-pretrained LR=0.01, which had the second and third highest TPRs, the ResNet18 No-pretrained LR=0.01 model had the highest Accuracy and F1 Score.http://www.jksee.or.kr/upload/pdf/KSEE-2025-47-5-354.pdfchironomidae larvaresnet modeldeep learningactivated carbon filters
spellingShingle Si Hyeong Park
Myeong Eon Choi
Seung Yong Lee
Jong-Oh Kim
No-Suk Park
A feasibility Study of Detecting Chironomidae Larva in Water Treatment Filtration Processes using ResNet-based Image Recognition Deep Learning
대한환경공학회지
chironomidae larva
resnet model
deep learning
activated carbon filters
title A feasibility Study of Detecting Chironomidae Larva in Water Treatment Filtration Processes using ResNet-based Image Recognition Deep Learning
title_full A feasibility Study of Detecting Chironomidae Larva in Water Treatment Filtration Processes using ResNet-based Image Recognition Deep Learning
title_fullStr A feasibility Study of Detecting Chironomidae Larva in Water Treatment Filtration Processes using ResNet-based Image Recognition Deep Learning
title_full_unstemmed A feasibility Study of Detecting Chironomidae Larva in Water Treatment Filtration Processes using ResNet-based Image Recognition Deep Learning
title_short A feasibility Study of Detecting Chironomidae Larva in Water Treatment Filtration Processes using ResNet-based Image Recognition Deep Learning
title_sort feasibility study of detecting chironomidae larva in water treatment filtration processes using resnet based image recognition deep learning
topic chironomidae larva
resnet model
deep learning
activated carbon filters
url http://www.jksee.or.kr/upload/pdf/KSEE-2025-47-5-354.pdf
work_keys_str_mv AT sihyeongpark afeasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT myeongeonchoi afeasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT seungyonglee afeasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT jongohkim afeasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT nosukpark afeasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT sihyeongpark feasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT myeongeonchoi feasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT seungyonglee feasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT jongohkim feasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning
AT nosukpark feasibilitystudyofdetectingchironomidaelarvainwatertreatmentfiltrationprocessesusingresnetbasedimagerecognitiondeeplearning