• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.246-246
• /
• 2023

Multi-purpose dams are operated accounting for both physical and socioeconomic factors. This study aims to evaluate the utility of a deep learning algorithm-based model for three multi-purpose dam operation (Seomjin River dam, Juam dam, and Juam Control dam) in Seomjin River. In this study, the Gated Recurrent Unit (GRU) algorithm is applied to predict hourly water level of the dam reservoirs over 2002-2021. The hyper-parameters are optimized by the Bayesian optimization algorithm to enhance the prediction skill of the GRU model. The GRU models are set by the following cases: single dam input - single dam output (S-S), multi-dam input - single dam output (M-S), and multi-dam input - multi-dam output (M-M). Results show that the S-S cases with the local dam information have the highest accuracy above 0.8 of NSE. Results from the M-S and M-M model cases confirm that upstream dam information can bring important information for downstream dam operation prediction. The S-S models are simulated with altered outflows (-40% to +40%) to generate the simulated water level of the dam reservoir as alternative dam operational scenarios. The alternative S-S model simulations show physically inconsistent results, indicating that our deep learning algorithm-based model is not explainable for multi-purpose dam operation patterns. To better understand this limitation, we further analyze the relationship between observed water level and outflow of each dam. Results show that complexity in outflow-water level relationship causes the limited predictability of the GRU algorithm-based model. This study highlights the importance of socioeconomic factors from hidden multi-purpose dam operation processes on not only physical processes-based modeling but also aritificial intelligence modeling.

• 시스템엔지니어링학술지
• /
• 제12권2호
• /
• pp.47-57
• /
• 2016

As the inventory costs of repairable items in military logistics continue to increase, many studies for optimal inventory level of these items are being carried out in advanced countries, including the US, to reduce these costs. Research on inventory level optimization for repairable items aimed to achieve the availability goal of a system with a MIME(Multi Indenture Multi Echelon) repair policy structure first began with Sherbrooke's METRIC and developed into various types. This research is to analyze and compare recent V-METRIC related studies to search for another variation in this field. This paper mainly looks at how to determine optimum inventory level for each repairable item to achieve a specific availability target within a limited budget, and also how to minimize inventory cost while achieving its availability target by determining optimal inventory level of each repairable item.

• Structural Engineering and Mechanics
• /
• 제37권1호
• /
• pp.17-37
• /
• 2011

This paper presents a new Internet-based computational framework for the realistic simulation of multi-scale response of structural systems. Two levels of parallel processing are involved in this frame work: multiple local distributed computing environments connected by the Internet to form a cluster-to-cluster distributed computing environment. To utilize such a computing environment for a realistic simulation, the simulation task of a structural system has been separated into a simulation of a simplified global model in association with several detailed component models using various scales. These related multi-scale simulation tasks are distributed amongst clusters and connected to form a multi-level hierarchy. The Internet is used to coordinate geographically distributed simulation tasks. This paper also presents the development of a software framework that can support the multi-level hierarchical simulation approach, in a cluster-to-cluster distributed computing environment. The architectural design of the program also allows the integration of several multi-scale models to be clients and servers under a single platform. Such integration can combine geographically distributed computing resources to produce realistic simulations of structural systems.

• 경영과학
• /
• 제28권1호
• /
• pp.117-127
• /
• 2011

In the Multi-Echelon maintenance environment, METRIC(Multi-Echelon Technique for Repairable Item Control) has been used in several different inventory level selection models, such as MOD-METRIC, Vari-METRIC, and Dyna- ETRIC. While this model's logic is easy to be implemented, a critical assumption of infinite maintenance capacity would deteriorate actual values, especially Expected Back Order(EBO)s for each item. To improve the accuracy of EBO, we develop two models using simulation and queueing theory that calculates EBO considering finite capacity. The result of our numerical example shows that the expected backorder from our model is much closer to the true value than the one from Vari-METRIC. The queueing model is preferable to the simulation model regarding the computational time.

• Journal of applied mathematics & informatics
• /
• 제42권2호
• /
• pp.257-281
• /
• 2024

In real life, a decision-maker can assign multiple values for pairwise comparison with a certain confidence level. Studies incorporating multi-choice parameters in multi-criteria decision-making methods are lacking in the literature. So, In this work, an extension of the Best-Worst Method (BWM) with multi-choice pairwise comparisons and multi-choice confidence parameters has been proposed. This work incorporates an extension to the original BWM with multi-choice uncertainty and confidence level. The BWM presumes the Decision-Maker to be fully confident about preference criteria vectors best to others & others to worst. In the proposed work, we consider uncertainty by giving decision-makers freedom to have multiple choices for preference comparison and having a corresponding confidence degree for each choice. This adds one more parameter corresponding to the degree of confidence of each choice to the already existing MCDM, i.e. multi-choice BWM and yields acceptable results similar to other studies. Also, the consistency ratio remained low within the acceptable range. Two real-life case studies are presented to validate our study on proposed models.

• Journal of Forest and Environmental Science
• /
• 제40권1호
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• ETRI Journal
• /
• 제46권1호
• /
• pp.82-95
• /
• 2024

As automated essay scoring (AES) has progressed from handcrafted techniques to deep learning, holistic scoring capabilities have merged. However, specific trait assessment remains a challenge because of the limited depth of earlier methods in modeling dual assessments for holistic and multi-trait tasks. To overcome this challenge, we explore providing comprehensive feedback while modeling the interconnections between holistic and trait representations. We introduce the DualBERT-Trans-CNN model, which combines transformer-based representations with a novel dual-scale bidirectional encoder representations from transformers (BERT) encoding approach at the document-level. By explicitly leveraging multi-trait representations in a multi-task learning (MTL) framework, our DualBERT-Trans-CNN emphasizes the interrelation between holistic and trait-based score predictions, aiming for improved accuracy. For validation, we conducted extensive tests on the ASAP++ and TOEFL11 datasets. Against models of the same MTL setting, ours showed a 2.0% increase in its holistic score. Additionally, compared with single-task learning (STL) models, ours demonstrated a 3.6% enhancement in average multi-trait performance on the ASAP++ dataset.

• 대한교통학회지
• /
• 제20권7호
• /
• pp.79-85
• /
• 2002

각 개인이 발생하는 통행 행태와 이들 가구 구성원간의 연관관계 및 영향에 대한 이해는 활동기반모형의 궁극적 목표라 할 수 있는 미래의 활동패턴 예측의 가장 기본이 되는 연구사항이라 할 수 있다. 일반적인 회귀 모형의 경우 개인의 활동/통행 패턴을 알아내기 위하여 모집단으로부터 수집되는 개인자료는 가구라는 부분모집단으로 세분화되어 계층적 구조(Hierarchical structure)의 성향을 고려하지 못하고 있어, 그 결과는 편이된 추정치를 낳는다. 따라서, 본 연구에서는 계층적 구조를 갖고 있는 자료를 이용하여 다수준 모형(Multi-Level Model)을 사용하여 개인의 활동/통행 패턴 영향을 규명해내고 활동/통행 패턴의 변화를 가구수준의 변동과 개인수준의 변동으로 나누어 분석하였다. 사용된 자료는 미국 Puget Sound 지역의 Transportation Panel 자료(PSTP)를 이용하였다. 분석 결과 개인의 통행사슬 발생모형에서 가구수준의 변동이 전체변동의 1/4를 차지하고 생계활동 지속시간 모형에서는 전체 변동의 1/8을 차지하는 등의 매우 큰 값을 나타내어 개인의 활동/통행 패턴 분석시 다수준 모형을 통한 분석의 필요성이 대두되었다.

• 스마트미디어저널
• /
• 제12권9호
• /
• pp.45-59
• /
• 2023

Weakly supervised object localization (WSOL) is a task of localizing an object in an image using only image-level labels. Previous studies have followed the conventional class activation mapping (CAM) pipeline. However, we reveal the current CAM approach suffers from problems which cause original CAM could not capture the complete defects features. This work utilizes a convolutional neural network (CNN) pretrained on image-level labels to generate class activation maps in a multi-scale manner to highlight discriminative regions. Additionally, a vision transformer (ViT) pretrained was treated to produce multi-head attention maps as an auxiliary detector. By integrating the CNN-based CAMs and attention maps, our approach localizes defective regions without requiring bounding box or pixel-level supervision during training. We evaluate our approach on a dataset of apple images with only image-level labels of defect categories. Experiments demonstrate our proposed method aligns with several Object Detection models performance, hold a promise for improving localization.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 1992년도 수공학연구발표회논문집
• /
• pp.411-418
• /
• 1992

The purpose of this study is to develop dynamic-stochastic models that can forecast the inflow into reservoir during low/drought periods and flood periods. For the formulation of the models, the discrete transfer function is utilized to construct the deterministic characteristics, and the ARIMA model is utilized to construct the stochastic characteristics of residuals. The stochastic variations and structures of time series on hydrological data are examined by employing the auto/cross covariance function and auto/cross correlation function. Also, general modeling processes and forecasting method are used the model building methods of Box and Jenkins. For the verifications and applications of the developed models, the Chungju multi-purpose reservoir which is located in the South Han river systems is selected. Input data required are the current and past reservoir inflow and Yungchun water levels. In order to transform the water level at Yungchon into streamflows, the water level-streamflows rating curves at low/drought periods and flood periods are estimated. The models are calibrated with the flood periods of 1988 and 1989 and hourly data for 1990 flood are analyzed. Also, for the low/drought periods, daily data of 1988 and 1989 are calibrated, and daily data for 1989 are analyzed.