심층신경망을 이용한 스마트 양식장용 사료 공급 시점 감지 시스템 구현
An Implementation of Feeding Time Detection System for Smart Fish Farm Using Deep Neural Network
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In traditional fish farming way, the workers have to observe all of the pools every time and every day to feed at the right timing. This method causes tremendous stress on workers and wastes time. To solve this problem, we implemented an automatic detection system for feeding time using deep neural network. The detection system consists of two steps: classification of the presence or absence of feed and checking DO (Dissolved Oxygen) of the pool. For the classification, the pretrained ResNet18 model and transfer learning with custom dataset are used. DO is obtained from the DO sensor in the pool through HTTP in real time. For better accuracy, the next step, checking DO proceeds when the result of the classification is absence of feed several times in a row. DO is checked if it is higher than a DO reference value that is set by the workers. These actions are performed automatically in the UI programs developed with LabVIEW.
Abstract
In traditional fish farming way, the workers have to observe all of the pools every time and every day to feed at the right timing. This method causes tremendous stress on workers and wastes time. To solve this problem, we implemented an automatic detection system for feeding time using deep neural network. The detection system consists of two steps: classification of the presence or absence of feed and checking DO (Dissolved Oxygen) of the pool. For the classification, the pretrained ResNet18 model and transfer learning with custom dataset are used. DO is obtained from the DO sensor in the pool through HTTP in real time. For better accuracy, the next step, checking DO proceeds when the result of the classification is absence of feed several times in a row. DO is checked if it is higher than a DO reference value that is set by the workers. These actions are performed automatically in the UI programs developed with LabVIEW.
참고문헌 (13)
- 황성일, "u-양식장을 적용한 I CT 기반스마트 양식장 시스템 사례 연구", 한국통신학회논문지C, 39(2), pp.173~181 (2014), 한국통신학회
- J. H. Jeon, "An Implementation of Smart Fish Farm Monitoring System using MQTT", Proceedings of IEMEK, (fall), pp.18~20 (2020)
- 전주현, "스마트 양식장 수조 내 용존 산소 및 온도 제어를 위한 시스템 구현", 대한임베디드공학회논문지, 16(6), pp.299~305 (2021), 대한임베디드공학회[DOI]
- 전주현, "An Implementation of DAQ and Monitoring System for a Smart Fish Farm Using Circulation Filtration System", JIPS(Journal of Information Processing Systems), 17(6), pp.1179~1190 (2021), 한국정보처리학회[DOI]
- 최한석, "퍼지추론을 이용한 어류 활동상태 기반의 지능형 자동급이 모델", 한국콘텐츠학회 논문지, 20(10), pp.167~176 (2020), 한국콘텐츠학회[DOI]
- S. J. Dokko, "Design of the Smart Feeding System based on the LPWA network for Inland Fish Farms", Journal of Internet of Things and Convergence, 2(3), pp.31~35 (2016)
- D. L. Kramer, "Dissolved Oxygen and Fish Behavior", Environmental Biology of Fishes, 18(2), pp.81~92 (1987)
- The Effects of Dissolved Oxygen on Fish Growth in Aquaculture, "Y. J. Mallya", The United Nations University Fisheries Training Programme, ~ (2007)
- J. A. Buentello, "Effects of Water Temperature and Dissolved Oxygen on Daily Feed Consumption, Feed Utilization and Growth of Channel Catfish (Ictalurus Punctatus)", Aquaculture, 182(3-4), pp.339~352 (2000)
- K. HE, "Deep Residual Learning for Image Recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770~778 (2016)
- M. Gao, "A Novel Deep Convolutional Neural Network based on ResNet-18 and Transfer Learning for Detection of Wood Knot Defects", Journal of Sensors, 2021, pp.4428964~ (2021)
- H. Schulzrinne, "Real Time Streaming Protocol (RTSP)", ~ (1998)