• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1081-1088
• /
• 2020

In this paper, the method of detecting sea fog through CCTV image is proposed based on convolutional neural networks. The study data randomly extracted 1,0004 images, sea-fog and not sea-fog, from a total of 11 ports or beaches (Busan Port, Busan New Port, Pyeongtaek Port, Incheon Port, Gunsan Port, Daesan Port, Mokpo Port, Yeosu Gwangyang Port, Ulsan Port, Pohang Port, and Haeundae Beach) based on 1km of visibility. 80% of the total 1,0004 datasets were extracted and used for learning the convolutional neural network model. The model has 16 convolutional layers and 3 fully connected layers, and a convolutional neural network that performs Softmax classification in the last fully connected layer is used. Model accuracy evaluation was performed using the remaining 20%, and the accuracy evaluation result showed a classification accuracy of about 96%.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.1D
• /
• pp.81-88
• /
• 2012

This present research was carried out by dividing two parts; field surveying and data processing, in order to analyze changed patterns of a shoreline. Firstly, the shoreline information measured by the precise GPS positioning during long duration was collected. Secondly, the algorithm for detecting an auto boundary with regards to the changed shoreline with multi-image data was developed. Then, a comparative research was conducted. Haeundae beach which is one of the most famous ones in Korea was selected as a test site. RTK-GPS surveying had been performed overall eight times from September 2005 to September 2009. The filed test by aerial Lidar was conducted twice on December 2006 and March 2009 respectively. As a result estimated from both sensors, there is a slight difference. The average length of shoreline analyzed by RTK-GPS is approximately 1,364.6 m, while one from aerial Lidar is about 1,402.5 m. In this investigation, the specific algorithm for detecting the shoreline detection was developed by Visual C++ MFC (Microsoft Foundation Class). The analysis result estimated by aerial photo and satellite image was 1,391.0 m. The level of reliability was 98.1% for auto boundary detection when it compared with real surveying data.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.30 no.3
• /
• pp.319-328
• /
• 1997

To develop a beneficial microbial feed for the cultivation of rotifer, Brachionus plicatilis, an aerobic photosynthetic bacterium, Erythrobacter sp. $S\;\pi-I$ was isolated from marine structure at Haeundae beach in Pusan, Korea. Feeding effects of Erythrobacter sp. $S\;\pi-I$ on the growth of rotifer were analyzed comparing to other feeds such as PSB (purple nonsulfur bacteria), Chlorella sp. and baker's yeast. Erythrobacter sp. $S\;\pi-I$ contained more linoleic acid $(C_{18:3\omega3})$ and oleic acid $(C_{18:1\omega9})$ and amino acids than PSB (purple nonsulfur bacteria), Chlorella sp. and baker's yeast. The rotifer fed on Erythrobacter sp. $S\;\pi-I$ showed better effects than those fed on other feeds in the individual growth, size and weight. Also, the rotifer especially contained more eicosapentaenoic acid $(C_{20:5\omega3})$ and docosahexaenoic acid $(C_{22:6\omega3})$ in case of Erythrobacter sp. $S\;\pi-I$ feeding than the other feeds. In case of the feed of PSB and baker's yeast docosahexaenoic acid $(C_{22:6\omega3})$ did not show. In amino acid analysis, the rotifer fed on Erthrobacter sp, $S\;\pi-I$ showed more amino acid content comparing to those fed on other diets. Especially, arginine, isoleucine, histidine, lysine, methionine, phenylalanine, threonine, which are essential amino acid for fish growth, showed high contents. These results suggested that the aerobic photosynthetic bacterium, Erythrobacter sp. $S\;\pi-I$ would be a beneficial microbial teed for the cultivation of rotifer.

• The Korean Journal of Quaternary Research
• /
• v.18 no.1 s.22
• /
• pp.21-30
• /
• 2004

The Ilgwang Fault is NNE-striking, elongated 40 Km between Ulsan and Haeundae-ku, Busan in southeastern part of the Korean Peninsula. This paper si mainly concerned about the ages of the fault activities especially in the Quaternary, inferred from classification of geomorphic surfaces and trench excavation for the construction of Singori nuclear power plant. The geomorphic surfaces are classified into Beach and the Alluvial plain, the 10 m a.s.l. Marine terrace(MIS 5a), the 20 m a.s.l. Marine terrace(MIS 5e), the Reworked surface of 45 m a.s.l. Marine terrace(MIS 7 or 9) and the Low relief erosional surface. The Low relief erosional surface is distributed coastal side, the Reworked surface of 45m a.s.l. Marine terrace inland side by the Ilgwang Fault Line as the boundary line. But the former is above 10 m higher in relative height than the latter. The 20 m a.s.l. Marine terrace on the elongation line of the Ilgwang Fault reveals no dislocation. A site was trenched on the straight contact line with $N30^{\circ}E$-striking between the 10 m a.s.l. Marine terrace and the 20 m a.s.l. Marine terrace. Fault line or dislocation was not observable in the trench excavation. Accordingly, the straight contact line is inferred as the ancient shore line of the 10 m a.s.l. Marine terrace. The Ages of the Fault activities are inferred after the formation of the Ichonri formation - before the formation of the 45 m a.s.l. Marine terrace(220 Ka. y. B.P. or 320. Ka. y. B.P.). The Low relief erosional surface was an island above the sea-level during the formation of the 45 m a.s.l. marine terrace in the paleogeography.