인공지능 기술 기반 넙치 질병 증상 감지 및 분류 기법
(AI-powered Paralichthys olivaceus Disease Symptom Detection and Classification Method)
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구에서는 넙치의 질병을 빠르게 진단하기 위해 딥러닝 기반 질병 증상 감지 및 머신러닝 기반 질병 분류 기법을 제안한다. 질병 증상 감지 기법은 YOLOv9 모델을 사용하였고, mAP 85.4%, F1-score 75.2% 정도의 우수한 정확도를 보여주었다. 질병 분류에서는 SGD 분류기와 랜덤 포레스트 분류기를 사용한 앙상블 모델을 사용였고, Top-1은 약 72%, Top-2는 약 83%, Top-3는 약 94%로 전체적으로 좋은 정답률을 보였다. 두 기법을 결합하여 테스트한 결과는 질병 분류 결과에 임계값을 설정하지 않을 경우 96%라는 좋은 성능을 보였다. 본 연구에서 제안하는 넙치 질병 증상 감지 및 분류 기법은 두 가지 알고리즘이 상호 보완적으로 작용하여 질병 증상을 정확하게 감지하고 질병 정보를 분류함으로써 신속하고 효과적인 질병 치료 및 예방 조치를 취할 수 있다.
Abstract
In this study, we propose a deep learning-based disease symptom detection and machine learning-based disease classification technique to quickly diagnose Paralichthys olivaceus diseases. The disease symptom detection technique, using YOLOv9 model, showed excellent accuracy of about 85.4% of mAP and 75.2% of F1-score. The disease classification, an ensemble model using SGD classifier and random forest classifier was used, and the overall good correct answer rate was about 72% for Top-1, 83% for Top-2, and 94% for Top-3. As a result of testing by combining the two algorithms, when the threshold was not set in the disease classification result, it showed good performance of 96%. The Paralichthys olivaceus disease symptom detection and classification technique proposed in this study can take quick and effective disease treatment and prevention measures by the two algorithms working together to accurately detect disease symptoms and classify disease information.
참고문헌 (27)
- 사회통계국 농어업동향과, "2022년 어류양식동향조사 결과" (2022), 통계청
- 어류 폐사 원인 진단 기초, "수산동물방역센터", 국립수산과학원 어류질병방역센터, ~
- Litjens, Geert, "A Survey on Deep Learning in Medical Image Analysis", Medical Image Analysis, 42, pp.60~88 (2017)
- Vo Thi Tuong Vi, "Automatic Extraction of Liver Region from Medical Images by Using an MFUnet", Smart Media Journal, 9(3), pp.59~70 (2020)
- YuJin Ko, "Deep Learning-based system for plant disease detection and classification", Smart Media Journal, 12(7), pp.9~17 (2023)
- Redmon, J., "You only look once : Unified, real-time object detection", Proceedings of the IEEE conference on computer vision and pattern recognition (2016)
- Loh, Wei‐Yin., "Classification and regression trees", Wiley interdisciplinary reviews: data mining and knowledge discovery, 1(1), pp.14~23 (2011)
- Cortes, Corinna, "Support-Vector Networks", Machine Learning, 20, pp.273~297 (1995)
- Parmar, Aakash, "A review on random forest : An ensemble classifier", International conference on intelligent data communication technologies and internet of things(ICICI)2018 (2019), Springer International Publishing
- Kabir, Fasihul, "Bangla text document categorization using stochastic gradient descent(sgd)classifier", 2015 international conference on cognitive computing and information processing(CCIP) (2015)
- Effect of water temperature on occurrence of Edwardsiella tarda in olive flounder Paralichthys olivaceus farms in Jeju island, South Kore, "Yoo, Juri", ~ (2019)
- Shim, Jae-Dong, "Monitoring of the mortalities in oliver flounder(Paralichthys olivaceus)farms of Korea", Journal of fish pathology, 32(1), pp.29~35 (2019)
- 정종호, "YOLOv8-Segmentation을 이용한 넙치 질병 증상 감지", 한국스마트미디어학회 2023 종합학술대회, pp.20~21 (2023)
- Girshick, Ross, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.580~587 (2014)
- Liu, Wei, "SSD: Single shot multibox detector", Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands (2016), Springer International Publishing
- Redmon, Joseph, "YOLO9000 : better, faster, stronger", Proceedings of the IEEE conference on computer vision and pattern recognition (2017)
- Farhadi, Ali, "Yolov3: An incremental improvement", Computer vision and pattern recognition, 1804 (2018), Springer
- "YOLO models" (2018)[URL]
- Bishop, Christopher M., "Pattern recognition and machine learning" (2006), springer
- Cover, Thomas, "Nearest neighbor pattern classification", IEEE transactions on information theory, 13(1), pp.21~27 (1967)
- Rish, Irina, "An empirical study of the naive Bayes classifier", IJCAI 2001 workshop on empirical methods in artificial intelligence, 3(22) (2001)
- Hosmer Jr, David W., "Applied logistic regression" (2013), John Wiley & Sons
- "scikit documents, GridSearchCV" (2007)[URL]
- 조경원, "넙치 질병 증상 분류를 위한 객체 탐지 딥러닝 모델 성능 평가", 스마트미디어저널, 12(10), pp.71~84 (2023)