• Journal of Fisheries and Marine Sciences Education
• /
• v.13 no.2
• /
• pp.146-167
• /
• 2001

Korea and China are two opposite countries located aside Yellow Sea and co-utilize the East China Sea. The two countries are close together from geological point of view, however, the competitive development of resources was more emphasized than the cooperative development of resources between the two countries because the special policy relationship. Additionally, after the communist government of China was founded in 1949, the political conception between the two countries was quite different. Therefore the establishment of appropriate international fisheries co-operation was impossible, and the international management problems of fisheries resources in Yellow Sea and East China Sea were let alone. UN convention on the Law of the Sea came to force in 1994, Korea and China adopted the exclusive economic zone system in 1996. On the other hand, Fisheries Law in Korea was enacted in 1953 in order to management of fisheries resources, and also China was enacted fisheries law in 1986. The two countries control the fisheries effort through fisheries license system, meanwhile through prohibition fishing area, prohibition fishing period, limitation of net size, and limitation of body length to conserve and manage the fisheries resource. The serious management methods of resource management in the two countries are similar such as the creation of promptly decreased species and those species that have commercial value, discharge of fish seedling stock, settlement of artificial reef and clean of fishing ground. Therefore, the two countries should consider not only the improvement of formal law system, but also how to recover the fisheries resources in circumference water zone and how to improve the efficiency of fisheries resource management. Specially the settlement and management of artificial reef should be chosen in the area that have the highest benefit to two countries, and should establish the common management system of discharge of fish seedling stock. And the two countries should adopt the same criteria through technical management and limitation of net size, limitation of body length, and prohibition area of special fisheries to ensure the highest fisheries benefit of fisherman in the two countries and the highest efficiency of fisheries resource management.

• International journal of advanced smart convergence
• /
• v.9 no.1
• /
• pp.215-221
• /
• 2020

The paradigm of agriculture is also changing to address the problem of food shortages due to the increase of the world population, climate conditions that are increasingly subtropical, and labor shortages in rural areas due to aging population. With the development of Information Communication Technology (ICT), our daily lives are changing rapidly and heralds a major change in agricultural management. In a hyper-connected society, the introduction of high-tech into traditional Agriculture of the past is absolutely necessary. In the development process of Agriculture, the first generation produced by hand, the second generation applied mechanization, and the third generation introduced automation. The fourth generation is the current ICT operation and the fifth generation is artificial intelligence. This paper investigated Smart Farm that increases productivity through convergence of Agriculture and ICT, such as smart greenhouse, smart orchard and smart Livestock. With the development of sustainable food production methods in full swing to meet growing food demand, Smart Farming is emerging as the solution. In overseas cases, the Netherlands Smart Farm, the world's second-largest exporter of agricultural products, was surveyed. Agricultural automation using Smart Farms allows producers to harvest agricultural products in an accurate and predictable manner. It is time for the development of technology in Agriculture, which benchmarked cases of excellence abroad. Because ICT requires an understanding of Internet of Things (IoT), big data and artificial intelligence as predicting the future, we want to address the status of theory and actual Agriculture and propose future development measures. We hope that the study of the paper will solve the growing food problem of the world population and help the high productivity of Agriculture and smart strategies of sustainable Agriculture.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.37 no.5
• /
• pp.375-379
• /
• 2011

Introduction: This study examined the effect of autogenous tooth bone used as a graft material for bone regeneration in an artificial bony defect of minipigs. Materials and Methods: Four healthy minipigs, weighing approximately 35-40 kg, were used. Four standardized artificial two-walled bony defects, 5 mm in length and depth, were made on the bilateral partial edentulous alveolar ridge on the mandible of minipigs, and autogenous tooth bone was augmented in the right side as the experimental group. On the other hand, only alloplastic bone graft material HA was grafted with the same size and manner in the left side as the control group. All minipigs were sacrificed at 4 weeks after a bone graft and evaluated histologically by Haematoxylin-eosin staining. The specimens were also evaluated semi-quantitatively via a histomorphometric study. The percentage of new bone over the total area was evaluated using digital software for an area calculation. Results: All specimens were available but one in the left side (control group) and two in the right side (experimental group) were missing during specimen preparation. The amount of bone formation and remodeling were higher in all experimental groups than the control. The mean percentage area for new bone in the experimental and control groups was $43.74{\pm}11.96%$ and $30.79{\pm}2.93%$, respectively. Conclusion: Autogenous tooth bone is a good alternative to autogenous bone with the possible clinical feasibility of an autogenous tooth bone graft in the reconstruction of bony defects.

• Journal of Korean Society on Water Environment
• /
• v.33 no.3
• /
• pp.326-333
• /
• 2017

The lakes and reservoirs have been reported as important sources of carbon emissions to the atmosphere in many countries. Although field experiments and theoretical investigations based on the fundamental gas exchange theory have proposed the quantitative amounts of Net Atmospheric Flux (NAF) in various climate regions, there are still large uncertainties at the global scale estimation. Mechanistic models can be used for understanding and estimating the temporal and spatial variations of the NAFs considering complicated hydrodynamic and biogeochemical processes in a reservoir, but these models require extensive and expensive datasets and model parameters. On the other hand, data driven machine learning (ML) algorithms are likely to be alternative tools to estimate the NAFs in responding to independent environmental variables. The objective of this study was to develop random forest (RF) and multi-layer artificial neural network (ANN) models for the estimation of the daily $CO_2$ NAFs in Daecheong Reservoir located in Geum River of Korea, and compare the models performance against the multiple linear regression (MLR) model that proposed in the previous study (Chung et al., 2016). As a result, the RF and ANN models showed much enhanced performance in the estimation of the high NAF values, while MLR model significantly under estimated them. Across validation with 10-fold random samplings was applied to evaluate the performance of three models, and indicated that the ANN model is best, and followed by RF and MLR models.

• Journal of Korean Society of Rural Planning
• /
• v.16 no.4
• /
• pp.1-11
• /
• 2010

This study has intended to evaluate rural subjective landscape through participation of residents and visitors according to space types, and to perform comparative analysis of evaluation results between residents and visitors. This study has employed a survey method for which 58 residents of 8 villages within Seondong region at Gochang-gun and 70 visitors to Green Barley Field Festival in the target region have participated. 42 landscape view points were selected according to landscape scopes and space types, and then the preference was evaluated using landscape adjectives after showing pictures already taken for each landscape view point. This study has found the following results. First, whereas residents gave high points to natural landscape and artificial one at the historical culture areas in comparison with other landscape scopes, visitors gave them low points on the other hand. Second, visitors evaluated the cultivated area among space types of mixed landscapes with high value. Third, based on t-test for comparative analysis, the statistically significant differences of evaluation results appeared at 6 places among 8 natural landscapes, 3 places among 12 artificial landscapes, and 3 places among mixed landscapes.

• International Journal of Knowledge Content Development & Technology
• /
• v.7 no.1
• /
• pp.57-78
• /
• 2017

There are several statistical classification algorithms available for land use/land cover classification. However, each has a certain bias or compromise. Some methods like the parallel piped approach in supervised classification, cannot classify continuous regions within a feature. On the other hand, while unsupervised classification method takes maximum advantage of spectral variability in an image, the maximally separable clusters in spectral space may not do much for our perception of important classes in a given study area. In this research, the output of an ANN algorithm was compared with the Possibilistic c-Means an improvement of the fuzzy c-Means on both moderate resolutions Landsat8 and a high resolution Formosat 2 images. The Formosat 2 image comes with an 8m spectral resolution on the multispectral data. This multispectral image data was resampled to 10m in order to maintain a uniform ratio of 1:3 against Landsat 8 image. Six classes were chosen for analysis including: Dense forest, eucalyptus, water, grassland, wheat and riverine sand. Using a standard false color composite (FCC), the six features reflected differently in the infrared region with wheat producing the brightest pixel values. Signature collection per class was therefore easily obtained for all classifications. The output of both ANN and FCM, were analyzed separately for accuracy and an error matrix generated to assess the quality and accuracy of the classification algorithms. When you compare the results of the two methods on a per-class-basis, ANN had a crisper output compared to PCM which yielded clusters with pixels especially on the moderate resolution Landsat 8 imagery.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.2
• /
• pp.287-295
• /
• 2017

Since Google's AlphaGo defeated a world champion of Go players in 2016, there have been many interests in the deep learning. In the financial sector, a Robo-Advisor using deep learning gains a significant attention, which builds and manages portfolios of financial instruments for investors.In this paper, we have proposed the a deep learning algorithm geared toward identification and forecast of the KOSPI index direction,and we also have compared the accuracy of the prediction.In an application of forecasting the financial market index direction, we have shown that the Robo-Advisor using deep learning has a significant effect on finance industry. The Robo-Advisor collects a massive data such as earnings statements, news reports and regulatory filings, analyzes those and recommends investors how to view market trends and identify the best time to purchase financial assets. On the other hand, the Robo-Advisor allows businesses to learn more about their customers, develop better marketing strategies, increase sales and decrease costs.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.23 no.1
• /
• pp.97-106
• /
• 2020

Urban parks provide a variety of ecosystem services and are an important means of providing positive functions to urban ecosystems. Recently, various studies on wildlifes in urban parks have been conducted. However, there is a lack of research on habitat use in urban parks at important times such as before and after fledging in bird ecology. This study analyzed habitat use and home-range before and after fledging on Cheongsa park, a neighborhood park located in Cheonan city. An artificial nest was set up to check and capture great tit in fledging time. One female was captured and attached to the NTQB-2 (0.4g) radio transmitter, the location was tracked using SIKA Radio Tracking Receiver, hand-held three element Yagi antenna and GPS. Location information was recorded for 10 minutes for 3 hours each morning and afternoon for 12 days from May 17 to May 31, 2019. As a result, the home-range of the target species was 1.776 ha (MCP) and the core area was 499 ㎡ (KD 50%). The average daily home-range was 0.513 ha for the entire period, 0.688 ha before fledging, 0.339 ha after fledging based on MCP. The bird moved about 29.9 m on average and moved up to 131.7 m. For the most of the time, the great tit stayed inside the park, but the bird also used small green spaces such as street trees, tree flower beds, and green areas of unused lands. The results of this study could be applied to the study of habitat use and the greenery management policy of the urban park considering wild birds.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.5
• /
• pp.2610-2616
• /
• 2014

An ejector is a kind of pump which is using pressure energy of high pressure fluid. This study aims to investigate performance influencing according to change the ejector mixing section shape using CFD simulation by Finite Volume Method. Optimum conditions were suggested 3 kind of variable such as nozzle diameter, nozzle length, distance from nozzle tip to the diffuser inlet. The results, It was confirmed that the diameter of the nozzle was the greatest effect in performance of the ejector. The diameter of the nozzle get smaller, mixing ratio was increased. On the other hand, nozzle length, distance from nozzle tip to the diffuser inlet had little effect on performance. It was proposed specific Mixing section, Nozzel diameter 23.8mm using the Artificial Neural Network.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.3
• /
• pp.123-128
• /
• 2019

This paper proposes the stock price prediction based on the artificial intelligence, where the model with recurrent convolution neural network (RCNN) layers is adopted. In the motivation of this prediction, long short-term memory model (LSTM)-based neural network can make the output of the time series prediction. On the other hand, the convolution neural network provides the data filtering, averaging, and augmentation. By combining the advantages mentioned above, the proposed technique predicts the estimated stock price of next day. In addition, in order to emphasize the recent time series, a custom weighted loss function is adopted. Moreover, stock data related to the stock price index are adopted to consider the market trends. In the experiments, the proposed stock price prediction reduces the test error by 3.19%, which is over other techniques by about 19%.