Abrianna Elke Chairil’s (Graduate School of Bioresource and Bioenvironmental Sciences) paper has been accepted in the Journal of Limnology and Oceanography: Methods.
Congratulations!
Authors
Abrianna Elke Chairil, Yuki Takai, Yosuke Koba, Shinya Kijimoto, Yukinari Tsuruda, Ik-Joon Kang, Yuji Oshima, Yohei Shimasaki
Affiliation
Graduate School of Bioresource and Bioenvironmental Sciences
Manuscript Title
First application of one-class support vector machine algorithms for detecting abnormal behavior of marine medaka Oryzias javanicus exposed to the harmful alga Karenia mikimotoi
Abstract
It is empirically known that fish exposed to harmful algal blooms (HABs) exhibit abnormal behaviour. This might serve as a method for early detection of HABs. There has been no report of the detection of behavioral abnormalities of fish exposed to harmful algae using machine learning. In this study, the behavior of Oryzias javanicus (Java medaka) exposed in a stepwise manner to the HAB species Karenia mikimotoi at densities of 0 cells mL^−1 (control), 1 × 10^3 cells mL^−1 (non-lethal), and 5 × 10^3 cells mL^−1 (sub-lethal) was recorded for 30 minutes at each cell density using two digital cameras connected to a software that tracked behavioral metrics of fish. The level of anomaly in the behavior of Java medaka was then analyzed using One-Class Support Vector Machines (OC-SVM) to determine whether the behavioral changes could be considered abnormal. The results revealed abnormal swimming behavior evidenced by an increase of swimming speed, a decrease of shoaling behavior, and a greater depth of swimming in Java medaka exposed especially to the sub-lethal K. mikimotoi density. The medaka exposed to K. mikimotoi also displayed physical deformities of their gills that were thought to have caused their abnormal behavior. This supposition was confirmed by further analysis using OC-SVM because the behavior of groups exposed to non-lethal and sub-lethal densities of K. mikimotoi were considered abnormal compared to that of the control groups. The results of this study show the possibility of using this system for early and real-time detection of HABs.
Journal name
Limnology and Oceanography: Methods
Relevant SDGs
14. Life Below Water
Comments from Abrianna
Hello, I am Abri (D2) from the Graduate School of Bioresource and Bioenvironment. I’m happy to announce that our research work was published in the international journal “Limnology and Oceanography: Methods” last April. In brief, our research used machine learning algorithms (with the support of members from the Department of Mechanical Engineering) to identify changes in fish behavior when they are exposed to harmful alga. Although we are using harmful alga this time, our method of using fish behavior as parameter for biomonitoring may also be applicable for other water pollutants as well. Also, this paper has been made open access thanks to the research funding provided by K-SPRING. Please feel free to read and download it!
