Abstract
Fish health monitoring systems in land-based aquaculture must be noninvasive, with no sensors on the surface or inside the fish, in order to minimize stress. This study developed a method for monitoring optical ventilation signals from the operculum movement of olive flounders (Paralichthys olivaceus) and combined it with decision trees, a type of machine learning, to achieve continuous and long-term monitoring. The optical ventilation signal monitoring system was realized using a tank with an interpolated multichannel optical detection probe. The proposed system acquires channel signals using a four-channel optical detection probe situated around the gills of the flounder and processes the channel signals every 10 s in mini-batches to classify and select the optical ventilation signal that best reflects the operculum movement, thereby improving robustness. The opercular beats, which represent ventilation frequency, were calculated from the optical ventilation signal to enable continuous monitoring. To further demonstrate the usefulness of this system, the stress response to high water temperature exposure was monitored and compared to the opercular beats and the variability in plasma glucose concentration, which is used as a stress indicator in fish. The results suggest that the opercular beats respond sensitively to stress application, and the system is useful for fish health monitoring.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Remote Sensing Applications: Society and Environment
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.