• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.57 no.4
• /
• pp.479-488
• /
• 2024

In recent years, changes in the fishing ground environment have led to reduced catches by fishermen at traditional fishing spots and increased operational costs related to vessel exploration, fuel, and labor. In this study, we developed a deep learning model to classify the fishing activities of drift gillnet fishing boats using AIS (automatic identification system) trajectory data. The proposed model integrates long short-term memory and 1-dimensional convolutional neural network layers to effectively distinguish between fishing (throwing and hauling) and non-fishing operations. Training on a dataset derived from AIS and validation against a subset of CCTV footage, the model achieved high accuracy, with a classification accuracy of 90% for fishing events. These results show that the model can be used effectively to monitor and manage fishing activities in coastal waters in real time.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.73-82
• /
• 2022

Marine fisheries resources face major anthropogenic threat from unregulated fishing activities; thus require precise detection for protection through marine surveillance. Korea developed an efficient land-based small fishing vessel monitoring system using real-time V-Pass data. However, those data directly do not provide information on fishing activities, thus further efforts are necessary to differentiate their activity status. In Korea, especially in Busan, longlining is practiced by many small fishing vessels to catch several types of fishes that need to be identified for proper monitoring. Therefore, in this study we have improved the existing fishing status classification method by applying Hidden Markov Model (HMM) on V-Pass data in order to further classify their fishing status into three groups, viz. non-fishing, longlining and other types of fishing. Data from 206 fishing vessels at Busan on 05 February, 2021 were used for this purpose. Two tiered HMM was applied that first differentiates non-fishing status from the fishing status, and finally classifies that fishing status into longlining and other types of fishing. Data from 193 and 13 ships were used as training and test datasets, respectively. Using this model 90.45% accuracy in classifying into fishing and non-fishing status and 88.23% overall accuracy in classifying all into three types of fishing statuses were achieved. Thus, this method is recommended for monitoring the activities of small fishing vessels equipped with V-Pass, especially for detecting longlining.

• Journal of Climate Change Research
• /
• v.5 no.4
• /
• pp.301-311
• /
• 2014

In this study, we estimated the amount of fuel used fishing boats of individual based on the results of survey of the activity data such as operations and activities specification of fishing boats in Korea. Based on the classification system of the domestic fishing boat, and to estimate average fuel consumption and the greenhouse gas emissions, showed emission factors per fishing boat. This was suggested to be able to apply the registration data area in the future, and estimates the emissions of greenhouse gases. Based on these results, it tries to provide the basic data that can be used when you want to create a local government measures to reduce scenario in the future.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.23 no.3
• /
• pp.69-79
• /
• 1995

The purpose of this study is to clarify the classification and the spatial form of the named coastal landforms which are collected from the specialized magazine for fishing as a collective representative. The costal landform, viewing from the fishing activity, is divided into 9 types which are Yo(sunken rock), Kaeppai(rock-ribbed coast), Jolbyeok(cliff), Koppuri(spite), Chagalmadang(shringle beach), Kanchulam(intermitent rock), Mulgol(valley sea), Kaeppul(tidal flat), Sajang(sandy coast). And the characterstics of the 9types of landform were analyzed. The results of this study will contribute to establish teory on conservation and rehabilitation of costal landscape.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.17 no.4
• /
• pp.297-305
• /
• 2014

In this study, we installed the Automatic Identification System (AIS) receiver on the Ieodo Ocean Research Station (IORS) from November 21 to 30, 2013 in order to monitor marine traffic and fishery activity in the jurisdictional sea area. The collected AIS raw data consist of static data report (MMSI, IMO NO., Call Sign, Ship Name, etc.) and position information report (position, speed, course, etc.), and the developed program was applied to classify ships according to ship flag and type information. The nationalities are released from the first three-digit numbers (MID) of MMSI, but in general most of small ships do not send an exact ship flag through Class B type AIS, a simplified and low-power equipment. From AIS data with flag information, ships under the flag of China had the highest frequency and the second was Korean flag, while in ship type cargo and fishing vessels were dominant in sequence. As for the ships without flag information, we compared the tracks with others in order to estimate ship flags. It can be said that fleets of ships with Chinese frequently appear sail together for fisheries over the waters, because the unknown ships followed a similar moving pattern with Chinese fishing vessels.