• The Journal of Engineering Geology
• /
• v.23 no.2
• /
• pp.137-147
• /
• 2013

For the effective management of groundwater resources, it is necessary to predict groundwater level fluctuations in response to rainfall events. In the present study, time series models using artificial neural networks (ANNs) and support vector machines (SVMs) have been developed and applied to groundwater level data from the Gasan, Shingwang, and Cheongseong stations of the National Groundwater Monitoring Network. We designed four types of model according to input structure and compared their performances. The results show that the rainfall input model is not effective, especially for the prediction of groundwater recession behavior; however, the rainfall-groundwater input model is effective for the entire prediction stage, yielding a high model accuracy. Recursive prediction models were also effective, yielding correlation coefficients of 0.75-0.95 with observed values. The prediction errors were highest for Shingwang station, where the cross-correlation coefficient is lowest among the stations. Overall, the model performance of SVM models was slightly higher than that of ANN models for all cases. Assessment of the model parameter uncertainty of the recursive prediction models, using the ratio of errors in the validation stage to that in the calibration stage, showed that the range of the ratio is much narrower for the SVM models than for the ANN models, which implies that the SVM models are more stable and effective for the present case studies.

• Journal of Korea Water Resources Association
• /
• v.41 no.3
• /
• pp.293-303
• /
• 2008

Reservoir turbidity flows degrade the efficiency and sustainability of water supply system in many countries located in monsoon climate region. A decision support system called RTMMS aimed to assist reservoir operations was developed for the real time monitoring, modeling, and management of turbidity flows induced by flood runoffs in Daecheong reservoir. RTMMS consists of a real time data acquisition module that collects and stores field monitoring data, a data assimilation module that assists pre-processing of model input data, a two dimensional numerical model for the simulation of reservoir hydrodynamics and turbidity, and a post-processor that aids the analysis of simulation results and alternative management scenarios. RTMMS was calibrated using field data obtained during the flood season of 2004, and applied to real-time simulations of flood events occurred on July of 2006 for assessing its predictive capability. The system showed fairly satisfactory performance in reproducing the density flow regimes and fate of turbidity plumes in the reservoir with efficient computation time that is a vital requirement for a real time application. The configurations of RTMMS suggested in this study can be adopted in many reservoirs that have similar turbidity issues for better management of water supply utilities and downstream aquatic ecosystem.

• Journal of Korea Water Resources Association
• /
• v.38 no.8 s.157
• /
• pp.655-664
• /
• 2005

A real-time monitoring and modeling system (RTMMS) for rainfall-induced turbidity flow, which is one of the major obstacles for sustainable use of reservoir water resources, is under development. As a prediction model for the RTMMS, a laterally integrated two-dimensional hydrodynamic and water quality model, CE-QUAL-W2 was tested by simulating the temperature stratification, density flow regimes, and temporal and spatial distributions of turbidity in a reservoir. The inflow water temperature and turbidity measured every hour during the flood season of 2004 were used as the boundary conditions. The monitoring data showed that inflow water temperature drop by 5 to $10^{\circ}C$ during rainfall events in summer, and consequently resulted in the development of density flow regimes such as plunge flow and interflow in the reservoir. The model showed relatively satisfactory performance in replicating the water temperature profiles and turbidity distributions, although considerable discrepancies were partially detected between observed and simulated results. The model was either very efficient in computation as the CPU run time to simulate the whole flood season took only 4 minutes with a Pentium 4(CPU 2.0GHz) desktop computer, which is essentially requited for real-time modeling of turbidity plume.

• Journal of Korea Water Resources Association
• /
• v.53 no.3
• /
• pp.155-166
• /
• 2020

In this study, we applied the Radar-AWS Rainrates (RAR), weather radar-based quantitative precipitation estimations (QPEs), to the Yongdam study watershed in order to perform the flood runoff simulation and calculate the inflow of the dam during flood events using hydrologic model. Since the Yongdam study watershed is a representative area of the mountainous terrain in South Korea and has a relatively large number of monitoring stations (water level/flow) and data compared to other dam watershed, an accurate analysis of the time and space variability of radar rainfall in the mountainous dam watershed can be examined in the flood modeling. HEC-HMS, which is a relatively simple model for adopting spatially distributed rainfall, was applied to the hydrological simulations using HEC-GeoHMS and ModClark method with a total of eight independent flood events that occurred during the last five years (2014 to 2018). In addition, two NCL and Python script programs are developed to process the radar-based precipitation data for the use of hydrological modeling. The results demonstrate that the RAR QPEs shows rather underestimate trends in larger values for validation against gauged observations (R² 0.86), but is an adequate input to apply flood runoff simulation efficiently for a dam watershed, showing relatively good model performance (E_NS 0.86, R² 0.87, and PBIAS 7.49%) with less requirements for the calibration of transform and routing parameters than the spatially averaged model simulations in HEC-HMS.

• Parasites, Hosts and Diseases
• /
• v.50 no.2
• /
• pp.119-126
• /
• 2012

Carboxylic acids play an important role in both aerobic and anaerobic metabolic pathways of both the snail and the parasite. Monitoring the effects of infection by schistosome on Biomphalaria alexandrina carboxylic acids metabolic profiles represents a promising additional source of information about the state of metabolic system. We separated and quantified pyruvic, fumaric, malic, oxalic, and acetic acids using ion-suppression reversed-phase high performance liquid chromatography (HPLC) to detect correlations between these acids in both hemolymph and digestive gland gonad complex (DGG's) samples in a total of 300 B. alexandrina snails (150 infected and 150 controls) at different stages of infection. The results showed that the majority of metabolite pairs did not show significant correlations. However, some high correlations were found between the studied acids within the control group but not in other groups. More striking was the existence of reversed correlations between the same acids at different stages of infection. Some possible explanations of the underlying mechanisms were discussed. Ultimately, however, further data are required for resolving the responsible regulatory events. These findings highlight the potential of metabolomics as a novel approach for fundamental investigations of host-pathogen interactions as well as disease surveillance and control.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.10
• /
• pp.1-7
• /
• 2009

Nowadays there are many studies and there's huge development about RFID and WSN which have great developmental potential to many kinds of applications. In particular, the healthcare field is expected to could be securing international competitive power in u-Healthcare and combined medical treatment industry and service. More and more real time application apply RFID and WSN technology to identify, data collect and locate objects. Wide deployment of RFID and WSN will generate an unprecedented volume of primitive data in a short time. Duplication and redundancy of primitive data will affect real time performance of application. Thus, emerging applications must filter primitive data and correlate them for complex pattern detection and transform them to events that provide meaningful, actionable information to end application. In this paper, we design a complex event processing system. This system will process RFID and WSN primitive data and event and perform data transformation. Integrate RFID and WSN system had applied each now in medical treatment through this study and efficient data transmission and management forecast that is possible.

• Quality Improvement in Health Care
• /
• v.24 no.2
• /
• pp.41-61
• /
• 2018

Purpose: Falls are one of the most frequent health events in medical institutions, however, they can be predicted and prevented. The Quality Improvement Nurse Society clinical practice guideline Steering Committee developed the Clinical Practice Guideline for the assessment and prevention of falls in adult people. The purpose of this study was to assess the risk factors for falls in adults aged 19 years and older, to present an evidence for preventing falls, formulate a recommendations, and indicators for applying the recommendations. Methods: This clinical practice guideline was developed using a 23-step adaptation method according to the Handbook for clinical practice guideline developer (version 1.0) by National Evidence-based Healthcare Collaborating Agency. Evidence levels and recommendation ratings were established in accordance to SIGN 2011 (The Scottish Intercollegiate Guidelines Network). Results: The final 15 recommendations from four domains were derived from experts' advice; 1) assessment of risk factor for falls in adult 2) preventing falls and reducing the risks of falls or falls-related injury 3) management and reassessment after a person falls 4) leadership and culture. Conclusion: This clinical practice guideline can be used as a basis for evaluation and prevention of fall risk factors for adults, to formulate recommendations for fall risk assessment and fall prevention, and to present monitoring indicators for applying the recommendations.

• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.140-140
• /
• 2021

Urban flood management is a crucial and challenging task, particularly in developed cities. Therefore, accurate prediction of urban flooding under heavy precipitation is critically important to address such a challenge. In recent years, machine learning techniques have received considerable attention for their strong learning ability and suitability for modeling complex and nonlinear hydrological processes. Moreover, a survey of the published literature finds that hybrid computational intelligent methods using nature-inspired algorithms have been increasingly employed to predict or simulate the streamflow with high reliability. The present study is aimed to propose a novel approach, an ensemble tree, Bayesian Additive Regression Trees (BART) model incorporating a nature-inspired algorithm to predict hourly multi-step ahead streamflow. For this reason, a hybrid intelligent model was developed, namely GA-BART, containing BART model integrating with Genetic algorithm (GA). The Jungrang urban basin located in Seoul, South Korea, was selected as a case study for the purpose. A database was established based on 39 heavy rainfall events during 2003 and 2020 that collected from the rain gauges and monitoring stations system in the basin. For the goal of this study, the different step ahead models will be developed based in the methods, including 1-hour, 2-hour, 3-hour, 4-hour, 5-hour, and 6-hour step ahead streamflow predictions. In addition, the comparison of the hybrid BART model with a baseline model such as super vector regression models is examined in this study. It is expected that the hybrid BART model has a robust performance and can be an optional choice in streamflow forecasting for urban basins.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.22 no.6
• /
• pp.115-124
• /
• 2019

In a climate change environment where heat damage and drought occur during a rainy season such as in 2018, a vegetation-based LID system that enables disaster prevention as well as environment improvement is suggested in lieu of an installation-type LID system that is limited to the prevention of floods. However, the quantification of its performance as against construction cost is limited. This study aims to present an experiment environment and evaluation method on quantitative performance, which is required in order to disseminate the vegetation-based LID system. To this end, a 3^rd quartile huff time distribution mass curve was generated for 20-year frequency, 60-minute probable rainfall of 68mm/hr in Cheonan, and effluent was analyzed by recreating artificial rainfall. In order to assess the reliability of the rainfall event simulator, 10 repeat tests were conducted at one-minute intervals for 20 minutes with minimum rainfall intensity of 22.29mm/hr and the maximum rainfall intensity of 140.69mm/hr from the calculated probable rainfall. Effective rainfall as against influent flow was 21.83mm/hr (sd=0.17~1.36, n=20) on average at the minimum rainfall intensity and 142.27mm/hr (sd=1.02~3.25, n=20) on average at the maximum rainfall intensity. In artificial rainfall recreation experiments repeated for three times, the most frequent quartile was found to be the third quartile, which is around 40 minutes after beginning the experiment. The peak flow was observed 70 minutes after beginning the experiment in the experiment zone and after 50 minutes in the control zone. While the control zone recorded the maximum runoff intensity of 2.26mm/min(sd=0.25) 50 minutes after beginning the experiment, the experiment zone recorded the maximum runoff intensity of 0.77mm/min (sd=0.15) 70 minutes after beginning the experiment, which is 20 minutes later than the control zone. Also, the maximum runoff intensity of the experiment zone was 79.6% lower than that of the control zone, which confirmed that vegetation unit-type LID system had rainfall runoff reduction and delay effects. Based on the above findings, the reliability of a lab-level rainfall simulator for monitoring the vegetation-based LID system was reviewed, and maximum runoff intensity reduction and runoff time delay were confirmed. As a result, the study presented a performance evaluation method that can be applied to the pre-design of the vegetation-based LID system for rainfall events on a location before construction.