• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.28 no.6
• /
• pp.319-331
• /
• 2016

This study explores the signal characteristics for different averaging intervals and defines representative verticies for each observatory by criterion of percent rate and variance. The shorter averaging interval shows the higher frequency variation, though the lower percent rate. In the tidal currents, we could hardly find the differences between 60-minute and 20-minute averaging. The newly defined criterion improves reliability of HF-radar data compared with the present reference which deselects the half by percent rate.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.2
• /
• pp.188-195
• /
• 2018

Time series analysis was conducted to identify the factors affecting short-term variation of water temperature in Wando. Spectrum analysis showed that air temperature peaks at diurnal period, while water temperature and tide level peak at both semi-diurnal and diurnal periods. Coherence between water temperature and the tide level presented 0.92 at semi-diurnal period. Numerical experiment were carried out to understand the spatio-temporal distribution of water temperature in the study area. Average water temperature difference between maximum ebb and flood was $0.3^{\circ}C$ in spring tide, but $0.13^{\circ}C$ in neap tide. The reason for the large difference in spring tide is that relatively cold water entered with strong tidal currents at flood tide and flowed out at ebb tide. Water temperature on coasts was higher than out at sea. This is because the depth in the coast is shallower than at sea, and water temperature increases rapidly due to solar radiation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.4
• /
• pp.725-732
• /
• 2020

This paper uses variables following as : to follow me well(0-9), it takes a lot of time to make a decision (0-9), lethargy(0-9) during physical activity in the exercise learning program of the children in the marginalized class. This paper classifies 'gender', 'physical education classroom', and 'upper, middle and lower' of age, and observe changes in ego-resiliency and self-control through sports rehabilitation therapy to find out changes in mental health. To achieve this, the data acquired was merged and the characteristics of large and small numbers were removed using the Label encoder and One-hot encoding. Then, to evaluate the performance by applying each algorithm of MLP, SVM, Dicesion tree, RNN, and LSTM, the train and test data were divided by 75% and 25%, and then the algorithm was learned with train data and the accuracy of the algorithm was measured with the Test data. As a result of the measurement, LSTM was the most effective in sex, MLP and LSTM in physical education classroom, and SVM was the most effective in age.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.6
• /
• pp.123-132
• /
• 2019

This study is to estimate the spatial soil moisture using Terra MODIS (Moderate Resolution Imaging Spectroradiometer) satellite data and machine learning technique. Using the 3 years (2015~2017) data of MODIS 16 days composite NDVI (Normalized Difference Vegetation Index) and daily Land Surface Temperature (LST), ground measured precipitation and sunshine hour of KMA (Korea Meteorological Administration), the RDA (Rural Development Administration) 10 cm~30 cm average TDR (Time Domain Reflectometry) measured soil moisture at 78 locations was tested. For daily analysis, the missing values of MODIS LST by clouds were interpolated by conditional merging method using KMA surface temperature observation data, and the 16 days NDVI was linearly interpolated to 1 day interval. By applying the RNN-LSTM (Recurrent Neural Network-Long Short Term Memory) artificial neural network model, 70% of the total period was trained and the rest 30% period was verified. The results showed that the coefficient of determination ($R^2$), Root Mean Square Error (RMSE), and Nash-Sutcliffe Efficiency were 0.78, 2.76%, and 0.75 respectively. In average, the clay soil moisture was estimated well comparing with the other soil types of silt, loam, and sand. This is because the clay has the intrinsic physical property for having narrow range of soil moisture variation between field capacity and wilting point.

• Current Photovoltaic Research
• /
• v.7 no.3
• /
• pp.55-60
• /
• 2019

Polymer:nonfullerene solar cells with an inverted-type device structure were fabricated by employing the bulk heterojunction (BHJ) active layers, which are composed of poly[(2,6-(4,8-bis(5-(2-ethylhexyl)thiophene-2-yl)-benzo[1,2-b:4,5-b']dithiophene))-alt-(5,5-(1',3'-di-2-thienyl-5',7-bis(2-ethylhexyl)benzo[1',2'-c:4',5'-c']dithiophene-4,8-dione))] (PBDB-T) and 3,9-bis(6-methyl-2-methylene-(3-(1,1-dicyanomethylene)-indanone))-5,5,11,11-tetrakis(4-hexylphenyl)-dithieno[2,3-d:2',3-d']-s-indaceno[1,2-b:5,6-b']dithiophene (IT-M). The BHJ layers were formed on a pre-patterned indium-tin oxide (ITO)-coated glass substrate by spin-coating using the blend solutions of PBDB-T and IT-M. The solar cell performances were investigated with respect to the cell position on the ITO-glass substrates. In addition, the short-term shelf lifetime of solar cells was tested by storing the PBDB-T:IT-M solar cells in a glovebox filled with inert gas. The results showed that the performance of solar cells was relatively higher for the cells close to the center of substrates, which was maintained even after storage for 24 h. In particular, the PCE of PBDB-T:IT-M solar cells was marginally decreased after storage for 24 h owing to the slightly reduced fill factor, even though the open circuit voltage was unchanged after 24 h.

• Journal of Korean Biological Nursing Science
• /
• v.23 no.3
• /
• pp.180-187
• /
• 2021

Purpose: This study aimed to compare breast milk minerals between mothers with gestational diabetes mellitus (GDM) and healthy mothers. Methods: This study was a short-term prospective study to determine the difference in milk minerals of 30 GDM mothers and 30 healthy mothers. Mineral concentrations in breast milk were measured for Na, K, Ca, Mg, and P. The first breast milk was collected on the 5th day after childbirth, while the second one was collected on the 14th day. For the variation of mineral content of breast milk over time between groups, generalized estimation equations were used. Results: The mean age of the GDM group and healthy mother group was 32.56 and 31.17 years old, respectively. Na was significantly higher in GDM mother group (Wild 𝛘²=4.35, p=.037) over time (Wild 𝛘²=21.59, p<.001), and Ca was significantly higher in healthy mother group (Wild 𝛘²=1.77, p=.018) over time (Wild 𝛘²=19.09, p<.001). Mg, P, and K showed a significant difference in time (Wild 𝛘²=18.12, p<.001; Wild 𝛘²=7.73, p=.005; Wild 𝛘²=7.10, p=.008). P was significantly higher in GDM mother group on 5th day of delivery (t=2.08, p=.042). Conclusion: There was a difference in the mineral composition of breast milk between GDM mothers and healthy mothers. Therefore, it is necessary to develop and apply intervention programs such as effective prenatal blood sugar management and postpartum breast massage considering the characteristics of GDM mothers.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.3
• /
• pp.183-191
• /
• 2021

A time-series variation of temperature, salinity, and underwater sound speed was analyzed using an Array for Real-time Geostrophic Oceanography (ARGO) float which autonomously collects temperature and salinity for about 10month with 2 days cycle among 12 floats in the center of the Yellow Sea. As a result, the underwater sound channel appeared below the thermocline as the surface sound channel, which is dominant in the winter season, reduced in April. Besides, for a certain time in the spring season, the sound ray reflected the sea surface frequently due to the short-term temperature inversion effect. Based on the case of successful observation of ARGO float in the shallow water, using prolonged monitoring unmanned platform may contribute to predicting sound transmission loss if the temperature inversion and sound channel including background environment focusing are investigated in the center of the Yellow Sea.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.601-612
• /
• 2022

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

• The Journal of Information Systems
• /
• v.31 no.3
• /
• pp.197-220
• /
• 2022

Purpose The purpose of this study is to identifies the demand pattern categorization of repair parts of Automotive After-sales Service(A/S) and proposes a demand prediction model for Auto repair parts using Long Short-Term Memory (LSTM) of artificial neural networks (ANN). The optimal parts inventory quantity prediction model is implemented by applying daily, weekly, and monthly the parts demand data to the LSTM model for the Lumpy demand which is irregularly in a specific period among repair parts of the Automotive A/S service. Design/methodology/approach This study classified the four demand pattern categorization with 2 years demand time-series data of repair parts according to the Average demand interval(ADI) and coefficient of variation (CV²) of demand size. Of the 16,295 parts in the A/S service shop studied, 96.5% had a Lumpy demand pattern that large quantities occurred at a specific period. lumpy demand pattern's repair parts in the last three years is predicted by applying them to the LSTM for daily, weekly, and monthly time-series data. as the model prediction performance evaluation index, MAPE, RMSE, and RMSLE that can measure the error between the predicted value and the actual value were used. Findings As a result of this study, Daily time-series data were excellently predicted as indicators with the lowest MAPE, RMSE, and RMSLE values, followed by Weekly and Monthly time-series data. This is due to the decrease in training data for Weekly and Monthly. even if the demand period is extended to get the training data, the prediction performance is still low due to the discontinuation of current vehicle models and the use of alternative parts that they are contributed to no more demand. Therefore, sufficient training data is important, but the selection of the prediction demand period is also a critical factor.

• Korean Journal of Environmental Agriculture
• /
• v.25 no.2
• /
• pp.164-169
• /
• 2006

This study was conducted for 10 days from 17 July to 26 July in 2005 to measure the amount of xylem sap flow under short-term variation of soil moisture regimes at -20 kPa, -50 kPa and -80 kPa in eight-year-old 'Fuji'/M.9 apple trees with different fruit loads. Fruit load was adjusted as three different treatments with standard (100%), 1/2 times (50%) and 2 times (200%) on the basis of optimum fruiting number per tree as the standard fruit load of Fuji cultivar. Trees with standard fruit load during the experimental period showed higher xylem sap flow at -50 kPa of soil moisture regimes than those of trees with 1/2 times and 2 times fruit load. Trees with 1/2 times and 2 times fruit load had similar patterns of the diurnal changes of xylem sap flow, vapor pressure deficit (VPD), and maximum evapotranspiration (ETm). However, trees with 2 times fruit load at -50 kPa and -80 kPa of soil moisture regimes produced lower amount of xylem sap flow than ETm. Trees with standard fruit load produced $1.06{\sim}3.93$ L/tree more amount of xylem sap flow than ETm at all soil moisture regimes. But xylem sap flow of tees with 2 times fruit load had 21% lower at -50 kPa and $31{\sim}36%$ lower at -20 kPa and -80 kPa of soil moisture regimes, respectively than that of trees with standard fruit load. Shoot growth and leaf area were significantly the highest in trees with standard fruit load while those of trees with 2 times fruit load recorded significantly lowest. Leaf water potential of trees with standard fruit load was lower than that of trees with 1/2 times and 2 times fruit load. It indicated that tees with standard fruit load had higher water use for transpiration than other treatments and tees with 2 times fruit load received more stress for the transpiration process under low soil moisture regimes. Consequently, 'Fuji'/M.9 apple trees, the fruit load and soil moisture should be maintained optimum to increase xylem sap flow and transpiration during higher growth period.