• Journal of Marine Life Science
• /
• v.7 no.1
• /
• pp.29-36
• /
• 2022

Sea cucumber, Aposticopus japonicus, is a major invertebrate species in the coastal regions of Korea. To evaluate the short-term stress levels according to the releasing methods, this study investigated the gene expression profiles of heat shock protein 90 (HSP90) by real-time quantitative polymerase chain reaction. When the juvenile sea cucumbers were packed in the vinyl bag with oxygen followed by transportation for 30 min or air-exposed for 1 h, the HSP90 gene expression levels in the experimental groups were significantly increased compared to those of the control groups (transported group, p=0.001; air-exposed group, p=0.032). The experimental group at 6 h post-release by seed-spreading method and at 2~6 h post-release by underwater hose-releasing method on board a fishing boat showed that the levels of HSP90 gene expression were not statistically significant but decreased slightly compared to the control group (seed-spreading group, p=0.069; hose-releasing group, p=0.093). On the other hand, the HSP90 gene expression showed an increasing pattern as the time passed (~6 h) after underwater release of juvenile sea cucumbers by divers (p=0.061). These results suggest that HSP90 gene expression can be used to investigate short-term stress response and effective releasing methods of juvenile sea cucumbers.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.358-366
• /
• 2023

This study aimed to provide a solution for improving ship collision alert of the 'accident vulnerable ship monitoring service' among the 'intelligent marine traffic information system' services of the Ministry of Oceans and Fisheries. The current ship collision alert uses a supervised learning (SL) model with survey labels based on large ship-oriented data and its operators. Consequently, the small ship data and the operator's opinion are not reflected in the current collision-supervised learning model, and the effect is insufficient because the alarm is provided from a longer distance than the small ship operator feels. In addition, the supervised learning (SL) method requires a large number of labeled data, and the labeling process requires a lot of resources and time. To overcome these limitations, in this paper, the classification model of collision alerts for small ships using unlabeled data with the semi-supervised learning (SSL) algorithms (Label Propagation and TabNet) was studied. Results of real-time experiments on small ship operators using the classification model of collision alerts showed that the satisfaction of operators increased.