• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.7
• /
• pp.811-818
• /
• 2014

This study was aimed to detect Submarine Groundwater Discharge (SGD) distribution image of Sea Surface Temperature (SST) using infrared band of Landsat-7 ETM+ around Jeju island. It is used to analyze SST distribution that DN value of satellite images converted into temperature. The estimation of SGD location is that extracting range of $15{\sim}17^{\circ}C$ from SST. The summer season images(July 28. 2006, Aug. 29. 2006 and Sep. 19. 2008) were used to analyze big difference between SST and temperature of SGD. The results, estimated SGD locations were occurred part of coastal area in northeastern of Jeju island.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.40 no.3
• /
• pp.167-177
• /
• 2007

We measured the salinity, pH, and concentrations of $^{222}Rn$ and nutrients in groundwater in the southeastern coastal aquifer off Busan from March to September 2005 to evaluate its submarine discharge and geochemical characteristics. Salinity in coastal groundwater increased sharply at 20 m depth and exceeded 25 ppt below 40 m during the study period, indicating that a strong transition zone between fresh groundwater and seawater developed between 20 and 40 m depths. Fresh groundwater in the upper layer of this transition zone was characterized by high pH, $^{222}Rn$, dissolved inorganic nitrogen (DIN), and dissolved inorganic phosphorus (DIP) and low dissolved inorganic silicate (DSi) relative to seawater in the lower layer. In addition, the vertical profiles of the $^{222}Rn$, DIN, and DIP concentrations imply that a strong advective groundwater flow occurs along the interface of fresh groundwater and seawater near 20 m depth. The geochemical constituents in coastal groundwater also showed strong seasonal variation, with the highest concentrations in summer (June 2005) due to the changes of groundwater recharge and sea level. This implies that the input of terrestrial chemical species into the coastal ocean through submarine groundwater discharge (SGD) could change seasonally. To ascertain the seasonal variation of SGD and SGD-driven chemical species fluxes, and associated ecological responses in the coastal ocean, more extensive studies are necessary using various SGD tracers or seepage meters in the future.

• International journal of advanced smart convergence
• /
• v.8 no.4
• /
• pp.68-74
• /
• 2019

Along with the deeper architecture in the deep learning approaches, the need for the data becomes very big. In the real problem, to get huge data in some disciplines is very costly. Therefore, learning on limited data in the recent years turns to be a very appealing area. Meta-learning offers a new perspective to learn a model with this limitation. A state-of-the-art model that is made using a meta-learning framework, Meta-SGD, is proposed with a key idea of learning a hyperparameter or a learning rate of the fast adaptation stage in the outer update. However, this learning rate usually is set to be very small. In consequence, the objective function of SGD will give a little improvement to our weight parameters. In other words, the prior is being a key value of getting a good adaptation. As a goal of meta-learning approaches, learning using a single gradient step in the inner update may lead to a bad performance. Especially if the prior that we use is far from the expected one, or it works in the opposite way that it is very effective to adapt the model. By this reason, we propose to add a weight term to decrease, or increase in some conditions, the effect of this prior. The experiment on few-shot learning shows that emphasizing or weakening the prior can give better performance than using its original value.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.03a
• /
• pp.711-716
• /
• 2010

This study selected the promising area of submarine groundwater discharge(SGD) that flows into the sea following unconfined physical aquifer through the electrical resistivity survey of the land and sea. The submarine groundwater discharge(SGD) mostly flows into the sea following fracture zones, and the detection of the fault zone becomes the important guideline of groundwater discharge. Electrical sounding of the land assessed the groundwater flow and integration possibility according to the location of a fault that is a water path between underground reservoir and surface water as well as a rock fracture. In addition, the study conducted sea electrical resistivity to expand the area with high potential and selected the expected water potential groundwater area. The areas of the study were Busan and coastal areas, and for the terrain analysis, the candidates of the ground exploration were selected after analyzing lineaments that is expanded to coast direction.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2006.04a
• /
• pp.293-297
• /
• 2006

Submarine groundwater discharge (SGD) and the interface between seawater and freshwater in an unconfined coastal aquifer was evaluated by numerical modeling. A two-dimensional vertical cross section of the aquifer was constructed. Coupled flow and salinity transport modeling were peformed by using a numerical code FEFLOW In this study, we investigated the changes in groundwater flow and salinity transport in coastal aquifer with hydraulic condition such as the magnitude of recharge flux, hydraulic conductivity. Especially, transient simulation considering tidal effect and seasonal change of recharge rate was simulated to compare the difference between quasi-steady state and transient state. Results show that SGD flux is in proportion to the recharge rate and hydraulic conductivity, and the interface between the seawater and the freshwater shows somewhat retreat toward the seaside as recharge flux increases. Considered tidal effect, SGD flux and flow directions are affected by continuous change of the sea level and the interface shows more dispersed pattern affected by velocity variation. The cases which represent variable daily recharge rate instead of annual average value also shows remarkably different result from the quasi-steady case, implying the importance of transient state simulation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.392-395
• /
• 2017

본 연구에서는 일 증발접시 증발량 산정을 위한 딥러닝 (deep learning) 모형의 적용성을 평가하였다. 본 연구에서 적용된 딥러닝 모형은 deep belief network (DBN) 기반 deep neural network (DNN) (DBN-DNN) 모형이다. 모형 적용성 평가를 위하여 부산 관측소에서 측정된 기상자료를 활용하였으며, 증발량과의 상관성이 높은 기상변수들 (일사량, 일조시간, 평균지상온도, 최대기온)의 조합을 고려하여 입력변수집합 (Set 1, Set 2, Set 3)별 모형을 구축하였다. DBN-DNN 모형의 성능은 통계학적 모형성능 평가지표 (coefficient of efficiency, CE; coefficient of determination, $r^2$; root mean square error, RMSE; mean absolute error, MAE)를 이용하여 평가되었으며, 기존의 두가지 형태의 ANN (artificial neural network), 즉 모형학습 시 SGD (stochastic gradient descent) 및 GD (gradient descent)를 각각 적용한 ANN-SGD 및 ANN-GD 모형과 비교하였다. 효과적인 모형학습을 위하여 각 모형의 초매개변수들은 GA (genetic algorithm)를 이용하여 최적화하였다. 그 결과, Set 1에 대하여 ANN-GD1 모형, Set 2에 대하여 DBN-DNN2 모형, Set 3에 대하여 DBN-DNN3 모형이 가장 우수한 모형 성능을 나타내는 것으로 분석되었다. 비록 비교 모형들 사이의 모형성능이 큰 차이를 보이지는 않았으나, 모든 입력집합에 대하여 DBN-DNN3, DBN-DNN2, ANN-SGD3 순으로 모형 효율성이 우수한 것으로 나타났다.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.7
• /
• pp.121-127
• /
• 2021

This study investigates the impact of the COVID-19 pandemic on exchange rates of the top ten currencies according to their trading value with Thailand by employing a regression analysis. Data includes daily number of COVID-19 cases - confirmed, new, deaths - and exchange rates against Thai Baht - CNY, JPY, USD, MYR, SGD, VND, IDR, AUD, HKD, TWD - which cover the period from January 2, 2020 to December 15, 2020. Results show that the confirmed cases of COVID-19 in Thailand relate to changes in all exchange rates; CNY, MYR, SGD, VND, AUD, and TWD have depreciated in relation to the THB, whereas JPY, USD, IDR, and HKD have appreciated. Furthermore, the new cases and deaths of COVID-19 have similar associations with almost all exchange rates. Deprecation of the JPY, USD, VND, HKD, and TWD in relation to the THB is due to new cases, on the contrary the MYR, IDR, and AUD have appreciated. Likewise, the JPY, USD, VND, and HKD have depreciated, but the CNY, MYR, SGD, and AUD have appreciated in relation to the THB owing to deaths cases. The study findings provide useful knowledge to manage an exchange rate risk for business and could help policymakers to improve the efficiency of exchange rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.13-19
• /
• 2019

The accuracy of machine learning is greatly affected by amount of learning data and quality of data. Collecting existing Web-based learning data has danger that data unrelated to actual learning can be collected, and it is impossible to secure data transparency. In this paper, we propose a method for collecting data directly in parallel by blocks in a block - chain structure, and comparing the data collected by each block with data in other blocks to select only good data. In the proposed system, each block shares data with each other through a chain of blocks, utilizes the All-reduce structure of Parallel-SGD to select only good quality data through comparison with other block data to construct a learning data set. Also, in order to verify the performance of the proposed architecture, we verify that the original image is only good data among the modulated images using the existing benchmark data set.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3519-3533
• /
• 2020

Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.317-322
• /
• 2020

Due to the development of artificial intelligence, it is used as a disaster response support system in the field of disaster. Disasters can occur anywhere, anytime. In the event of a disaster, there are four types of reports: fire, rescue, emergency, and other call. Disaster response according to the 119 call also responds differently depending on the type and situation. In this paper, 1280 data set of 119 calls were tested with 3 classes of SVM, NB, k-NN, DT, SGD, and RF situation classification algorithms using a training data set. Classification performance showed the highest performance of 92% and minimum of 77%. In the future, it is necessary to secure an effective data set by disaster in various fields to study disaster response.