MortCam: An Artificial Intelligence-aided fish mortality detection and alert system for recirculating aquaculture

Alzubaidi, 2021, Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, J. Big Data, 8, 1, 10.1186/s40537-021-00444-8 Amogi, B.R., Ranjan, R., Khot, L.R. 2022, November 03–05. Reliable image processing algorithm for sunburn management in green apples. In 2022 IEEE Workshop on Metrology for Agriculture and Forestry (MetroAgriFor) (pp. 186–190). IEEE. https://doi.org/10.1109/MetroAgriFor55389.2022.9964902. Bilbao, I., & Bilbao, J. 2017, December. Overfitting problem and the over-training in the era of data: Particularly for Artificial Neural Networks. In 2017 Eighth International Conference on Intelligent Computing and Information Systems (ICICIS), Cairo, Egypt, 173–177. https://doi.org/%2010.1109/INTELCIS.2017.8260032. Bochkovskiy, 2020, Yolov4: optimal speed and accuracy of object detection, arXiv Prepr. arXiv, 2004, 10934 Chen, 2022, Underwater abnormal classification system based on deep learning: a case study on aquaculture fish farm in Taiwan, Aquac. Eng., 99, 10.1016/j.aquaeng.2022.102290 Ebeling, 2012, Recirculating aquaculture systems. Aquaculture production systems, 1, 245 Ellis, 2012, Mortality and fish welfare, Fish. Physiol. Biochem., 38, 189, 10.1007/s10695-011-9547-3 Engle, 2020, Cost drivers and profitability of US pond, raceway, and RAS aquaculture, J. World Aquac. Soc., 51, 847, 10.1111/jwas.12706 Føre, 2018, Precision fish farming: a new framework to improve production in aquaculture, Biosyst. Eng., 173, 176, 10.1016/j.biosystemseng.2017.10.014 Glenn, J., 2020. YOLOv5 Documentation. Available at: https://docs.ultralytics.com/ (Accessed on: March 10, 2022). Hu, 2023, Detection of residual feed in aquaculture using YOLO and Mask RCNN, Aquac. Eng., 100, 10.1016/j.aquaeng.2022.102304 Jawad, 2017, Energy-efficient wireless sensor networks for precision agriculture: a review, Sensors, 17, 1781, 10.3390/s17081781 Kennedy, 2016, Potential drivers of virulence evolution in aquaculture, Evolut. Appl., 9, 344, 10.1111/eva.12342 Li, 2022, Robust detection of farmed fish by fusing YOLOv5 with DCM and ATM, Aquac. Eng., 99, 10.1016/j.aquaeng.2022.102301 Martins, 2012, Behavioural indicators of welfare in farmed fish, Fish. Physiol. Biochem., 38, 17, 10.1007/s10695-011-9518-8 Martins, 2010, New developments in recirculating aquaculture systems in Europe: a perspective on environmental sustainability, Aquac. Eng., 43, 83, 10.1016/j.aquaeng.2010.09.002 Muñoz-Benavent, 2022, Impact evaluation of deep learning on image segmentation for automatic bluefin tuna sizing, Aquac. Eng., 99, 10.1016/j.aquaeng.2022.102299 Noble, 1996, Diseases encountered in rainbow trout cultured in recirculating systems, Annu. Rev. Fish. Dis., 6, 65, 10.1016/S0959-8030(96)90006-X O'Donncha, 2019, Precision aquaculture, IEEE Internet Things Mag., 2, 26, 10.1109/IOTM.0001.1900033 Pulkkinen, 2010, Intensive fish farming and the evolution of pathogen virulence: the case of columnaris disease in Finland, Proc. R. Soc. B: Biol. Sci., 277, 593, 10.1098/rspb.2009.1659 Ranjan, 2020, In-field crop physiology sensing aided real-time apple fruit surface temperature monitoring for sunburn prediction, Comput. Electron. Agric., 175, 10.1016/j.compag.2020.105558 Ranjan, 2023, Effects of image data quality on a convolutional neural network trained in-tank fish detection model for recirculating aquaculture systems, Comput. Electron. Agric., 205, 10.1016/j.compag.2023.107644 Rawlinson, P., & Forster, A. 2000, July 10–14. The Economics of Recirculation Aquaculture. In: Microbehavior and Macroresults: Proceedings of the Tenth Biennial Conference of the International Institute of Fisheries Economics and Trade (IIFET), Corvallis, Oregon, USA. https://ir.library.oregonstate.edu/concern/conference_proceedings_or_journals/1z40kt70z. Redmon, J., & Farhadi, A. 2017, July 21–26. YOLO9000: better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 7263–7271. https://doi.org/10.1109/CVPR.2017.690. Redmon, 2018, Yolov3: an incremental improvement, arXiv Prepr. arXiv, 1804, 02767 Redmon, J., Divvala, S., Girshick, R., Farhadi, A., 2016, June 27–30. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 779–788. https://doi.org/10.1109/CVPR.2016.91. Sankaran, 2015, Low-altitude, high-resolution aerial imaging systems for row and field crop phenotyping: a review, Eur. J. Agron., 70, 112, 10.1016/j.eja.2015.07.004 Segner, 2012, Health of farmed fish: its relation to fish welfare and its utility as welfare indicator, Fish. Physiol. Biochem., 38, 85, 10.1007/s10695-011-9517-9 Soares, 2013, Factors affecting variation in mortality of marine Atlantic salmon Salmo salar in Scotland, Dis. Aquat. Org., 103, 101, 10.3354/dao02562 Su, J., Chen, J., Wen, J., Xie, W., & Lin, M. 2020, May. Analysis decision-making system for aquaculture water quality based on deep learning. In Journal of Physics: Conference Series (Vol. 1544, No. 1, p. 012028). IOP Publishing. https:///doi.org/10.1088/1742–6596/1544/1/012028. Summerfelt, 2004, Developments in recirculating systems for Arctic char culture in North America, Aquac. Eng., 30, 31, 10.1016/j.aquaeng.2003.09.001 Summerfelt, 2015, Emerging trends in salmonid RAS—Part II. System enhancements, Glob. Aquac. Adv., 18, 64 Therrien, R., & Doyle, S. 2018, March. Role of training data variability on classifier performance and generalizability. In Proceedings of SPIE Medical Imaging 2018, Houston, Texas, USA, vol. 10581, pp. 58–70. https://doi.org/10.1117/12.2293919. Timmons, M.B., Vinci, B.J. 2022. Recirculating Aquaculture, 5th ed. Ithaca Publishing Company. Wang, C.Y., Bochkovskiy, A., & Liao, H.Y.M. 2022c. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. https://doi.org/10.48550/arXiv.2207.02696. Wang, 2021, Automatic recognition of fish behavior with a fusion of RGB and optical flow data based on deep learning, Animals, 11, 2774, 10.3390/ani11102774 Wang, 2022, Real-time detection and tracking of fish abnormal behavior based on improved YOLOV5 and SiamRPN++, Comput. Electron. Agric., 192, 10.1016/j.compag.2021.106512 Wang, Q., Du, Z., Jiang, G., Cui, M., Li, D., Liu, C., & Li, W. 2022b. A Real-Time Individual Identification Method for Swimming Fish Based on Improved Yolov5. http://dx.doi.org/10.2139/ssrn.4044575. Zhang, 2022, A MobileNetV2-SENet-based method for identifying fish school feeding behavior, Aquac. Eng., 99, 10.1016/j.aquaeng.2022.102288 Zhang, 2020, Automatic fish population counting by machine vision and a hybrid deep neural network model, Animals, 10, 364, 10.3390/ani10020364