• Journal of Wetlands Research
• /
• v.13 no.3
• /
• pp.707-720
• /
• 2011

For the lake case, the detention phenomenon of water body occurs and stays for a long time. Especially, following the layer of water depth direction, the lake body and water quality problems are different from the water quality of river. So according to time, the stream and water quality can be simulated by the 3-Dimensional Model, which can divide water layer for reservoir or lake. The water quality simulation result will become more reliability. For this study, the 3-Dimension Model - EFDC was used to simulate water quality of Unam reservoir in the Sumjin Dam. The HEC-GeoHMS and HEC-HMS Rainfall - Runoff Model based on GIS were used to estimate long-term runoff, and input data was constructed to the observed water level, meteorological data, water temperature, T-N and T-P. In order to apply the EFDC model, water depth was divided into 3 layers and 5,634 grids were extracted. After constructing the grid net, the water quality change of Unam reservoir in time and space was simulated. Overall, long term runoff simulation reflected the actual observed runoff well, through the water quality simulation, according to the pollution factors, the behavior characteristics can be checked, and the simulated water quality can be properly reflected. The function of EFDC has been confirmed, which water quality can be properly simulated. In the near future, to establish countermeasures for Intake Facilities of Watershed and Management, this support which some basic tools can be applied is in expectation.

• Magazine of the Korea Concrete Institute
• /
• v.10 no.6
• /
• pp.149-159
• /
• 1998

The reasonable prediction of time-dependent deformation of prestressed concrete(PSC) box girder bridges is very important for accurate construction as well as good serviceability. The long-term behavior is mostly influenced by the probabilistic characteristic of creep and shrinkage. This paper presents a method of statistical analysis and sensitivity analysis of creep and shrinkage effects in PSC box been taken into account - model uncertainty, parameter variation and environmental condition. The statistical and sensitivity analyses are performed by using the numerical simulation of Latin Hypercube sampling. For each sample, the time-dependent structural analysis is performed to produce response data, which are then statistically analyzed. The probabilistic prediction of the confidence limits on long-term effects of creep and shrinkage is then expressed. Three measure are examined to quantify the sensitivity of the outputs of each of the input variables. These are rank correlation coefficient(RCC), partical rank correlation coefficient(PRCC) and standardiozed rank regression coefficient(SRRC) computed on the ranks of the observations. Three creep and shrinkage models - i. e., ACI model. CEB-FIP model and the model in Korea Highway Bridge Specification - are studied. The creep model uncertainy factor and the relative humidity appear to be the most dominant factors with regard to the model output uncertainty.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.43-58
• /
• 2014

As the use of trading systems has increased rapidly, many researchers have become interested in developing effective stock market prediction models using artificial intelligence techniques. Stock market prediction involves multifaceted interactions between market-controlling factors and unknown random processes. A successful stock prediction model achieves the most accurate result from minimum input data with the least complex model. In this research, we develop a combination model of ${\pi}$-fuzzy logic and support vector machine (SVM) models, using a genetic algorithm to optimize the parameters of the SVM and ${\pi}$-fuzzy functions, as well as feature subset selection to improve the performance of stock market prediction. To evaluate the performance of our proposed model, we compare the performance of our model to other comparative models, including the logistic regression, multiple discriminant analysis, classification and regression tree, artificial neural network, SVM, and fuzzy SVM models, with the same data. The results show that our model outperforms all other comparative models in prediction accuracy as well as return on investment.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.853-862
• /
• 2002

Face Detection can be defined as follows : Given a digitalized arbitrary or image sequence, the goal of face detection is to determine whether or not there is any human face in the image, and if present, return its location, direction, size, and so on. This technique is based on many applications such face recognition facial expression, head gesture and so on, and is one of important qualify factors. But face in an given image is considerably difficult because facial expression, pose, facial size, light conditions and so on change the overall appearance of faces, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact face detection which overcomes some restrictions by using neural network. The proposed system can be face detection irrelevant to facial expression, background and pose rapidily. For this. face detection is performed by neural network and detection response time is shortened by reducing search region and decreasing calculation time of neural network. Reduced search region is accomplished by using skin color segment and frame difference. And neural network calculation time is decreased by reducing input vector sire of neural network. Principle Component Analysis (PCA) can reduce the dimension of data. Also, pose estimates in extracted facial image and eye region is located. This result enables to us more informations about face. The experiment measured success rate and process time using the Squared Mahalanobis distance. Both of still images and sequence images was experimented and in case of skin color segment, the result shows different success rate whether or not camera setting. Pose estimation experiments was carried out under same conditions and existence or nonexistence glasses shows different result in eye region detection. The experiment results show satisfactory detection rate and process time for real time system.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.2
• /
• pp.67-76
• /
• 2017

In industrial site in various fields it will be generated in combination with large amounts of data have a correlation. It is able to collect a variety of data in types of industry process, but they are unable to integrate each other's association between each process. For the data of the existing industry, the set values of the molding condition table are input by the operator as an arbitrary value When a problem occurs in the work process. In this paper, design the fusion and analysis processing model of data collected for each industrial type, Prediction Case(Automobile Connect), a through for corporate earnings improvement and process manufacturing industries such as master data through standard molding condition table and the production history file comparison collected during the manufacturing process and reduced failure rate with a new molding condition table digitized by arbitrary value for worker, a new pattern analysis and reinterpreted for various malfunction factors and exceptions, increased productivity, process improvement, the cost savings. It can be designed in a variety of data analysis and model validation. In addition, to secure manufacturing process of objectivity, consistency and optimization by standard set values analyzed and verified and may be optimized to support the industry type, fits optimization(standard setting) techniques through various pattern types.

• Tunnel and Underground Space
• /
• v.18 no.1
• /
• pp.44-57
• /
• 2008

In this study, a 2D finite-element analysis, using the SEEP/W program, was carried out to estimate the amount of groundwater flawing into a tunnel, as well as the groundwater tables around wetland areas during and after a tunnel excavation through rock mass. Four sites along the Wonhyo-tunnel in Cheonseong Mountain (Gyeongnam, Korea) were analysed, where the model damain of the tunnel included both wetland and fault zone. The anisotropy of the hydraulic conductivities of the rock mass was calculated using the DFN model, and then used as an input parameter for the cantinuum model. Parametric study on the influencing factors was perofrmed to minimize uncertainties in the hydraulic properties. Moreover, the volumetric water content and hydraulic conductivity functions were applied ta the model to reflect the ability of a medium ta store and transport water under both saturated and unsaturated conditions. The conductivity of fault zone was assumed ta be $10^{-5}m/sec\;or\;10^{-6}m/sec$ and the conductivity of grouting zone was assumed as 1/10, 1/50 or 1/100 of the conductivity of rock mass. Totally $6{\sim}8$ cases of transient flow simulation were peformed at each site. The hydraulic conductivities of fault zone showed a significant influence on groundwater inflow when the fault zone crossed the tunnel. Also, groundwater table around wetland maintained in case that the hydraulic conductivity of grouting zone was reduced ta be less than 1/50 of the hydraulic conductivity of rock mass.

• Korean Journal of Remote Sensing
• /
• v.36 no.3
• /
• pp.487-501
• /
• 2020

As a viable option for retrieval of LST (Land Surface Temperature), this paper presents a DNN (Deep Neural Network) based approach using 148 Landsat 8 images for South Korea. Because the brightness temperature and emissivity for the band 10 (approx. 11-㎛ wavelength) of Landsat 8 are derived by combining physics-based equations and empirical coefficients, they include uncertainties according to regional conditions such as meteorology, climate, topography, and vegetation. To overcome this, we used several land surface variables such as NDVI (Normalized Difference Vegetation Index), land cover types, topographic factors (elevation, slope, aspect, and ruggedness) as well as the T₀ calculated from the brightness temperature and emissivity. We optimized four seasonal DNN models using the input variables and in-situ observations from ASOS (Automated Synoptic Observing System) to retrieve the LST, which is an advanced approach when compared with the existing method of the bias correction using a linear equation. The validation statistics from the 1,728 matchups during 2013-2019 showed a good performance of the CC=0.910~0.917 and RMSE=3.245~3.365℃, especially for spring and fall. Also, our DNN models produced a stable LST for all types of land cover. A future work using big data from Landsat 5/7/8 with additional land surface variables will be necessary for a more reliable retrieval of LST for high-resolution satellite images.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.19 no.4
• /
• pp.297-309
• /
• 2016

This study was carried out to investigate the differences in sedimentary environments and benthic polychaete communities between farming grounds and natural habitats (non-farming ground) in Gamak Bay. Sampling stations of natural habitats were evenly distributed in the entire bay. And mussel farm, oyster farm and ark-shell farm were selected as farming grounds. Dominant sedimentary facies was mud in most sampling stations of farming grounds and natural habitats. However organic contents were higher in the farming grounds than natural habitats of the bay. The species number and mean density of polychaetous community in the natural habitats were greater than those from the farming grounds. Lumbrineris longifolia, known as potential organic enrichment indicator species, was first dominant species both in farming grounds and natural habitats of the bay. However, the next dominant species consisted of different species between two benthic habitats. As a result of community analysis using cluster analysis and nMDS, the natural habitats were divided into several station groups, but most of stations in farming grounds were clustered into one group. Pearson' correlation analysis and PCA showed high relationships between sedimentary environmental factors and benthic polychaetous community in natural habitats, but low or no relationships in farming grounds. That means benthic polychaetous community established in farming ground was under unusual condition such as high input of organic matter. Thus it is necessary to improve the benthic environmental quality of the farming grounds as well as the north-western inner part in Gamak Bay through long-term monitoring efforts.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.6
• /
• pp.1-7
• /
• 2017

The atomization of a liquid into multiple droplets has many important industrial applications, including the atomization of fuels in combustion processes and coating of surfaces and particles. Ultrasonic atomizing nozzle has a transducer that receives electrical input in the form of a high frequency signal from a power generator and converts that into mechanical energy at the same frequency. Liquid is atomized into a fine mist spray using high frequency sound vibrations. In coating applications, the unpressurized, low-velocity spray reduces the amount of overspray significantly because the droplets tend to settle on the substrate, rather than bouncing off it. The spray can be controlled and shaped precisely by entraining the slow-moving spray in an ancillary air stream using specialized types of spray-shaping equipment. The desired patterns of spray can be obtained using an air stream. To simulate the water mist behavior of an ultrasonic atomizing nozzle using an air stream, the Lagrangian dispersed phase model was employed using the commercial code FLUENT. The effects of the nozzle contraction shape, water droplet size and the pneumatic pressure drop on the spray characteristics were investigated to obtain the optimal condition for coating applications.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.7 no.1
• /
• pp.13-21
• /
• 2004

Temporal changes of Chl-α, physical and chemical factors were investigated by diurnal observation at 2-hour interval at three fixed stations in the western Chinhae Bay from 12 Aug. to 13 Aug. 1999. Difference of dissolved oxygen between surface and bottom layer was maximum when the thermocline were strong. Organic distribution such as COD was affected by the growth of phytoplankton. Limitting factor was nitrogen, that is, inorganic nitrogen plays a significant role on regulating the algal growth. Surface distribution of dissolved inorganic nitrogen was very low compared to bottom layer by uptake of organisms. Maximum value of Chl-α at station C2 and C11 were observed from subsurface layer, ranges of which exceeded possibility concentration of red tide outbreak, 10 mg/㎥. On the other hand, that of C15 exist at surface layer. In this area, DIN and DIP concentrations increased by input sources such as rainfall and benthic flux before the bloom of phytoplankton. Accumulation of phytoplankton occurred at subsurface layer by the rapid uptake of DIN, especially nitrate ion, when strong thermocline existed as approach to the afternoon, which led to the increase of organics in water column and oxygen deficiency water mass at bottom layer until late at evening. Since then, DIN increases gradually as water temperature decrease to minimum. The quantitative understanding of nitrogen of fluxed to and from the various sources is necessary for environmental management.