• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.199-207
• /
• 2024

Local reservoirs are crucial sources for agricultural water supply, necessitating stable water level management to prepare for extreme climate conditions such as droughts. Water level prediction is significantly influenced by local climate characteristics, such as localized rainfall, as well as seasonal factors including cropping times, making it essential to understand the correlation between input and output data as much as selecting an appropriate prediction model. In this study, extensive multivariate data from over 400 reservoirs in Jeollabuk-do from 1991 to 2022 was utilized to train and validate a water level prediction model that comprehensively reflects the complex hydrological and climatological environmental factors of each reservoir, and to analyze the impact of each input feature on the prediction performance of water levels. Instead of focusing on improvements in water level performance through neural network structures, the study adopts a basic Feedforward Neural Network composed of fully connected layers, batch normalization, dropout, and activation functions, focusing on the correlation between multivariate input data and prediction performance. Additionally, most existing studies only present short-term prediction performance on a daily basis, which is not suitable for practical environments that require medium to long-term predictions, such as 10 days or a month. Therefore, this study measured the water level prediction performance up to one month ahead through a recursive method that uses daily prediction values as the next input. The experiment identified performance changes according to the prediction period and analyzed the impact of each input feature on the overall performance based on an Ablation study.

• Earthquakes and Structures
• /
• v.23 no.3
• /
• pp.259-269
• /
• 2022

In this study, we introduce a canonical correlation analysis method to accurately assess the tunnel damage potential of ground motion. The proposed method can retain information relating to the initial variables. A total of 100 ground motion records are used as seismic inputs to analyze the dynamic response of three different profiles of tunnels under deep and shallow burial conditions. Nine commonly used ground motion parameters were selected to form the canonical variables of ground motion parameters (GMP_CCA). Five structural dynamic response parameters were selected to form canonical variables of structural dynamic response parameters (DRP_CCA). Canonical correlation analysis is used to maximize the correlation coefficients between GMP_CCA and DRP_CCA to obtain multivariate ground motion parameters that can be used to comprehensively assess the tunnel damage potential. The results indicate that the multivariate ground motion parameters used in this study exhibit good stability, making them suitable for evaluating the tunnel damage potential induced by ground motion. Among the nine selected ground motion parameters, peck ground acceleration (PGA), peck ground velocity (PGV), root-mean-square acceleration (RMSA), and spectral acceleration (Sa) have the highest contribution rates to GMP_CCA and DRP_CCA and the highest importance in assessing the tunnel damage potential. In contrast to univariate ground motion parameters, multivariate ground motion parameters exhibit a higher correlation with tunnel dynamic response parameters and enable accurate assessment of tunnel damage potential.

• Structural Engineering and Mechanics
• /
• v.60 no.3
• /
• pp.471-488
• /
• 2016

This study predicts the strength of rotary brace damper by analyzing a new set of probabilistic models using the usual method of multiple linear regressions (MLR) and advanced machine-learning methods of multivariate adaptive regression splines (MARS), Rotary brace damper can be easily assembled with high energy-dissipation capability. To investigate the behavior of this damper in structures, a steel frame is modeled with this device subjected to monotonic and cyclic loading. Several response parameters are considered, and the performance of damper in reducing each response is evaluated. MLR and MARS methods were used to predict the strength of this damper. Displacement was determined to be the most effective parameter of damper strength, whereas the thickness did not exhibit any effect. Adding thickness parameter as inputs to MARS and MLR models did not increase the accuracies of the models in predicting the strength of this damper. The MARS model with a root mean square error (RMSE) of 0.127 and mean absolute error (MAE) of 0.090 performed better than the MLR model with an RMSE of 0.221 and MAE of 0.181.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.46 no.4
• /
• pp.437-444
• /
• 2013

Eight fecal sterols were analyzed in surface sediments collected from shellfish farming areas in Yeoja Bay and Gangjin Bay, Korea, to evaluate sewage-derived fecal pollution. The concentrations of coprostanol, a good marker of sewage-derived organic contamination, in sediments were in the range of 10-530 ng/g-dry in Yeoja Bay, and 10-190 ng/g-dry in Gangjin Bay. Coprostanol levels were markedly higher in the inner bay than in the outer bay. These levels were lower than those reported in urbanized bays in Korea, however, they were comparable to levels in other shellfish farming areas including Gamak Bay. A multivariate analysis of the ratios of other sterols suggested that the sterols originated from sewage and plankton/benthos. Sewage was the dominant source at stations located close to the river mouth and wastewater treatment plant (WWTP) outfalls, and plankton/benthos was the primary source in the outer bay. These results suggest that management of point sources, e.g., WWTP as well as non-point sources, e.g., riverine inputs is important for improving the water quality in Yeoja Bay and Gangjin Bay.

• Korean Journal of Ecology and Environment
• /
• v.44 no.1
• /
• pp.42-57
• /
• 2011

We described the above-ground plant species composition and measured a range of soil physico-chemical properties and the composition and size of the soil seed bank in the remnant natural vegetations on the flood plains of the Han River within Seoul, South Korea. We used analysis of variance and multivariate analyses to analyse the data and S${\o}$rensen's similarity index to compare the composition of the vegetation and seed banks. The soils were circum-neutral and composed of mainly sand and silt fractions with a very limited clay component; a gradient based on sand/clay proportions was identified. The soil seed banks varied markedly between- and within-sites and had much greater species diversity than the above-ground vegetation. Two of the major dominants in the vegetation (Miscanthus saccariflorus and Phragmites australis) were found at very low densities in the seed bank. The site differences appeared to be correlated with the sand-clay gradient, suggesting that the soil properties differentially affected seed inputs into the soil, or that the processes than controlled sediment deposition during floods was also important in differentially affecting seed deposition. Lastly, there was relatively little similarity between the vegetation, dominated mainly by perennials, and the seed bank which contained a relatively large proportion of annuals and biennials. This result suggests that after disturbance caused by flooding there is the potential for many other species to colonize. This may impinge on the regeneration potential of the sites and cause concern for the future conservation of these important remnants of natural vegetation.

• Annals of Hepato-Biliary-Pancreatic Surgery
• /
• v.26 no.1
• /
• pp.17-30
• /
• 2022

Oncological scoring systems in surgery are used as evidence-based decision aids to best support management through assessing prognosis, effectiveness and recurrence. Currently, the use of scoring systems in the hepato-pancreato-biliary (HPB) field is limited as concerns over precision and applicability prevent their widespread clinical implementation. The aim of this review was to discuss clinically useful oncological scoring systems for surgical management of HPB patients. A narrative review was conducted to appraise oncological HPB scoring systems. Original research articles of established and novel scoring systems were searched using Google Scholar, PubMed, Cochrane, and Ovid Medline. Selected models were determined by authors. This review discusses nine scoring systems in cancers of the liver (CLIP, BCLC, ALBI Grade, RETREAT, Fong's score), pancreas (Genç's score, mGPS), and biliary tract (TMHSS, MEGNA). Eight models used exclusively objective measurements to compute their scores while one used a mixture of both subjective and objective inputs. Seven models evaluated their scoring performance in external populations, with reported discriminatory c-statistic ranging from 0.58 to 0.82. Selection of model variables was most frequently determined using a combination of univariate and multivariate analysis. Calibration, another determinant of model accuracy, was poorly reported amongst nine scoring systems. A diverse range of HPB surgical scoring systems may facilitate evidence-based decisions on patient management and treatment. Future scoring systems need to be developed using heterogenous patient cohorts with improved stratification, with future trends integrating machine learning and genetics to improve outcome prediction.