• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.87-87
• /
• 2017

최근 이상기후로 인해 국내 가뭄피해가 증가하고 있는 추세이며, 미래 가뭄의 심도 및 지속시간은 증가할 것으로 예측되고 있다. 특히 우리나라는 용수공급의 56.5%를 댐에 의존하여 댐 유역의 가뭄은 생 공 농업용수 공급제한 등의 광범위한 피해를 발생시킬 수 있다. 다만 가뭄은 홍수와 달리 진행속도가 비교적 느리기 때문에 사전에 정확한 댐 유입량 예측이 가능하다면, 용수공급량 조정을 통해 피해를 최소화할 수 있다. 국내에서는 댐 유입량 예측에 ESP (Ensemble Streamflow Prediction) 기법을 활용하고 있으며, ESP 기법은 과거 기상자료를 기반으로 미래를 예측하기 때문에 기상자료, 초기수문조건, 매개변수 등에 불확실성을 가지고 있다. 본 연구에서는 베이지안 이론을 이용하여 댐 예측유입량의 정확도 향상기법을 개발하고 예측성을 평가하고자 하며, 강우유출모델은 ABCD를 활용하였다. 대상유역은 국내의 대표 다목적댐인 충주댐 유역을 선정하였으며, 기상자료는 기상청, 국토교통부 및 한국수자원공사의 지점자료를 수집하였다. 예측성 평가기법으로는 도시적 분석방법인 시계열 분석, 통계적 분석방법인 Skill Score (SS)를 활용하였다. 시계열 분석 결과 ESP 댐 예측유입량(ESP)은 매년 월별 전망값의 큰 차이가 없었으며, 다우년 및 과우년의 예측성이 떨어지는 것으로 나타났다. 베이지안 기반의 댐 예측유입량(BAYES-ESP)는 ESP의 과소모의하는 경향을 보정하였으며, 다우년에 예측성이 향상되었다. 월별 평균 댐 관측유입량과 ESP, BAYES-ESP의 SS 비교분석 결과 ESP는 유입량 값이 적은 1, 2, 3월에 SS가 양의 값을 가졌으며, 이외의 월에는 음의 값으로 나타났다. BAYES-ESP는 ESP와 관측값이 비교적 선형관계를 나타내는 1, 2, 3월에 ESP의 예측성을 개선시키는 것으로 나타났다. ESP 기법은 강수량의 월별, 계절별 변동성이 큰 우리나라에 적용하기에는 예측성의 한계가 있었으며, 이를 개선한 BAYES-ESP 기법은 댐 유입량 예측 연구에 가치가 있는 것으로 판단된다.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.12
• /
• pp.445-452
• /
• 2022

Class distribution of unbalanced data is an important part of the digital world and is a significant part of cybersecurity. Abnormal activity of unbalanced data should be found and problems solved. Although a system capable of tracking patterns in all transactions is needed, machine learning with disproportionate data, which typically has abnormal patterns, can ignore and degrade performance for minority layers, and predictive models can be inaccurately biased. In this paper, we predict target variables and improve accuracy by combining estimates using Synthetic Minority Oversampling Technique (SMOTE) and Light GBM algorithms as an approach to address unbalanced datasets. Experimental results were compared with logistic regression, decision tree, KNN, Random Forest, and XGBoost algorithms. The performance was similar in accuracy and reproduction rate, but in precision, two algorithms performed at Random Forest 80.76% and Light GBM 97.16%, and in F1-score, Random Forest 84.67% and Light GBM 91.96%. As a result of this experiment, it was confirmed that Light GBM's performance was similar without deviation or improved by up to 16% compared to five algorithms.

• Journal of Korea Water Resources Association
• /
• v.56 no.spc1
• /
• pp.1059-1069
• /
• 2023

Dam-break flow occurs when an elevated dam suddenly collapses, resulting in the catastrophic release of rapid and uncontrolled impounded water. This study compares laminar and turbulent closure models for simulating three-dimensional dam-break flows using OpenFOAM. The Reynolds-Averaged Navier-Stokes (RANS) model, specifically the k-ε model, is employed to capture turbulent dissipation. Two scenarios are evaluated based on a laboratory experiment and a modified multi-layered block obstacle scenario. Both models effectively represent dam-break flows, with the turbulent closure model reducing oscillations. However, excessive dissipation in turbulent models can underestimate water surface profiles. Improving numerical schemes and grid resolution enhances flow recreation, particularly near structures and during turbulence. Model stability is more significantly influenced by numerical schemes and grid refinement than the use of turbulence closure. The k-ε model's reliance on time-averaging processes poses challenges in representing dam-break profiles with pronounced discontinuities and unsteadiness. While simulating turbulence models requires extensive computational efforts, the performance improvement compared to laminar models is marginal. To achieve better representation, more advanced turbulence models like Large Eddy Simulation (LES) and Direct Numerical Simulation (DNS) are recommended, necessitating small spatial and time scales. This research provides insights into the applicability of different modeling approaches for simulating dam-break flows, emphasizing the importance of accurate representation near structures and during turbulence.

• Journal of Korea Water Resources Association
• /
• v.44 no.7
• /
• pp.511-522
• /
• 2011

Two-dimensional shallow water model based on the cut cell and the adaptive mesh refinement techniques is presented in this paper. These two mesh generation methods are combined to facilitate modeling of complex geometries. By using dynamically adaptive mesh, the model can achieve high resolution efficiently at the interface where flow changes rapidly. The HLLC Reimann solver and the MUSCL method are employed to calculate advection fluxes with numerical stability and precision. The model was applied to simulate the extreme urban flooding experiments performed by the IMPACT (Investigation of Extreme Flood Processes and Uncertainty) project. Simulation results were in good agreement with observed data, and transient flows as well as the impact of building structures on flood waves were calculated with accuracy. The cut cell method eased the model sensitivity to refinement. It can be concluded that the model is applicable to the urban flood simulation in case the effects of sewer and stormwater drainage system on flooding are relatively small like the dam brake.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.4
• /
• pp.337-342
• /
• 2016

In this paper, we studied a modified linear prediction method to estimate target signal correctly. Linear prediction method estimate direction-of-arrival to linear combination for any antenna element and other antenna elements. Modified linear prediction used optimal weight and posterior probability method. Through simulation, we are comparative analysis about the performance of proposed, bartlett and MUSIC method. From simulation, Bartlett and MUSIC method was estimation 3 targets signal, and proposed method estimated 4 targets. We showed the superior performance of the proposed algorithm relative to the classical method in order to estimate of target signals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.796-799
• /
• 2006

This paper presents a new method for automatic detection of skew in a document image using mathematical morphology. To speed up processing, we use reduced image but it still requires long time to estimate the skew angle so the proposed method works with region of interest, not with whole image. Character strings are connected by using morphological closing operation and a component labeling is used to select region of interest. The method considers the lowermost pixels of characters in candidate regions in the binary image of original document image. Experimental results shows that the proposed method is extremely fast and robust as well as independent of script forms.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.213-220
• /
• 2024

This paper proposes an optimization strategy for performing Federated Learning between devices and edge clouds using WebAssembly (WASM). The proposed strategy aims to maximize efficiency by conducting partial training on devices and the remaining training on edge clouds. Specifically, it mathematically describes and evaluates methods to optimize data transfer between GPU memory segments and the overlapping of computational tasks to reduce overall training time and improve GPU utilization. Through various experimental scenarios, we confirmed that asynchronous data transfer and task overlap significantly reduce training time, enhance GPU utilization, and improve model accuracy. In scenarios where all optimization techniques were applied, training time was reduced by 47%, GPU utilization improved to 91.2%, and model accuracy increased to 89.5%. These results demonstrate that asynchronous data transfer and task overlap effectively reduce GPU idle time and alleviate bottlenecks. This study is expected to contribute to the performance optimization of Federated Learning systems in the future.

• The KIPS Transactions:PartB
• /
• v.18B no.3
• /
• pp.147-156
• /
• 2011

This paper proposes a 3-stage (preprocessing, feature extraction, and classification) fault detection and classification algorithm for induction motors. In the first stage, a low-pass filter is used to remove noise components in the fault signal. In the second stage, a discrete cosine transform (DCT) and a statistical method are used to extract features of the fault signal. Finally, a back propagation neural network (BPNN) method is applied to classify the fault signal. To evaluate the performance of the proposed algorithm, we used one second long normal/abnormal vibration signals of an induction motor sampled at 8kHz. Experimental results showed that the proposed algorithm achieves about 100% accuracy in fault classification, and it provides 50% improved accuracy when compared to the existing fault detection algorithm using a cross-covariance method. In a real-world data acquisition environment, unnecessary noise components are usually included to the real signal. Thus, we conducted an additional simulation to evaluate how well the proposed algorithm classifies the fault signals in a circumstance where a white Gaussian noise is inserted into the fault signals. The simulation results showed that the proposed algorithm achieves over 98% accuracy in fault classification. Moreover, we developed a testbed system including a TI's DSP (digital signal processor) to implement and verify the functionality of the proposed algorithm.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.433-437
• /
• 2007

최근 환경부에서는 낙동강 유역의 오염총량관리제도의 시행에 따라 이제까지의 배출구 수질기준으로부터 총량수질기준을 통한 수질관리를 실시하고 있다. 오염총량관리를 실행하기 위해서는 주요지천 및 폐수처리장에서의 수질개선 및 비점오염원 관리가 선행되어야 하는데 이를 효율적으로 제어하기 위해서 낙동강 유역에 적합한 최적 수질해석 모델의 개발이 요구되는 상황이다. 수질모델의 가장 큰 목적은 유역으로부터 발생한 오염물이 하천으로 유입되었을 때 하천 수질 및 생태계의 수학적 표현을 통해 장래의 수질을 예측하고, 예측된 결과에 따라 합리적인 수질관리대책을 수립하는 것이다. 낙동강은 대표적인 수지상 하천망의 형태로서 댐 방류량 및 지류유입량은 본류 수계에 직접적인 영향을 미치며, 수질해석의 기본이 되는 수리계산에 매우 중요한 변수가 된다. 또한 대구, 구미, 왜관, 김천 등에서의 오염부하가 금호강, 남강 등의 주요 지류를 통하여 본류부로 유입되고 있으며, 하류부 칠서, 원동, 매리, 물금 등에서는 대량의 하천수를 취수하여 부산, 울산, 마산, 창원 지역 등의 생활 및 공업용수의 원수로 사용하고 있다. 다시 말해서 댐 방류량, 낙동강 하구언의 수위조절, 지류 유입량, 비점원 유입량 등 계산영역 경계에서의 비정상상태의 수리조건과 수질관리 계획에 의해 일률적으로 오염이 부하되는 정상상태의 수질조건이 공존하고 있는 실정이다. 본 연구에서는 낙동강 유역에 적합한 동적 수질모델을 개발하였다. 본 연구에서 개발된 수치모형은 갈수저수조건 및 불규칙한 하도단면을 반영하고, 동적 상태의 댐 방류량, 낙동강 하구언의 수위조절 영향, 지류 유입량 등 다양한 하천조건에서 발생하는 동적 흐름을 안정적으로 해석하여 낙동강 수질해석의 신뢰도를 향상시킴으로서 낙동강에 유입된 오염물질이 수계에 미치는 영향을 정확히 분석하고자 하였다. 동적수질해석에 의한 모의결과는 유량의 경우 상류부분은 모의치와 실측치가 잘 일치하지만, 중류 이후 지류의 유입이 많아지면서 지류의 변화를 정확히 입력하지 못해 모의치와 실측치의 차이가 발생한다. BOD의 경우는 수질이 양호한 상류지역은 모의치와 실측치가 잘 일치하지만, 오염원의 유입이 많은 중류지역부터는 실측치와 차이를 나타내다가 하류지역에서 다시 비교적 일치함을 알 수 있다. TN의 경우는 전반적으로 실측치보다 높게 모의되었고, TP는 전반적으로 실측치와 비교하여 잘 모의되었다. 본 연구에서 구축한 동적 수리해석모형 및 동적 수질해석모형은 낙동강 유역에 대해 유량 및 수질 등의 실제 하천의 경향에 비교적 잘 반영하므로 오염물총량규제에 따른 합리적인 하천 수질관리대책을 수립하는데 크게 기여할 수 있을 것으로 기대된다.