• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.11-11
• /
• 2023

2020년 기준 우리나라 전체 지하수 시설은 총 1,659천개소, 이용량은 2,916백만m³/년, 년간 지하수 개발가능량은 130억m³대비 22.3%이다(환경부 등, 2021). 단위면적당 지하수 시설수와 이용량은 16.8개소/km², 29,168m³/년/km²(81.1m3/일/km²)이다. 이러한 자료는 가뭄 대응시 신규 관정 개발도 필요하지만, 기존에 개발된 관정들을 최대한 효율적으로 활용하는 방안을 우선적으로 고려해야 한다는 것을 시사한다. 관정들을 상호 연계하게 되면 여러 개의 관정에서 나오는 물을 합하여 총량을 늘릴 수 있기 때문에, 가뭄 등 비상시에 일시적으로 다량의 물을 공급할 수 있다. 또한, 평상시에도 적절한 양수량 조절을 통해 지하수 자원의 손실을 막고 수위 저하에 의한 문제를 최소화할 수 있다. 관정연계시스템(well network system, WNS)은 기존 관정들을 가상의(virtually) 또는 물리적(physical) 연계를 하여, 최적의 지하수를 공급할 수 있는 시스템으로 정의할 수 있다. 가뭄 대응 및 효율적 지하수 자원 활용을 위한 관정연계시스템 개발과 실증을 위해 홍성군 서부면 양곡리 일대에 양수제어, 관로시설, 물탱크 등 물리적인 시설을 시험 설치하여 운영하고 있다. 또한, 관정연계시스템은 ICT 기술과 지하수관리 기법을 연동하여 지하수 관정들을 연계하고 최적으로 운영할 수 있는 하나의 의사결정시스템으로서 관정연계 플랫폼을 개발하였다. 관정연계 플랫폼은 웹기반으로 개발되었으며, 대수층의 수리지질 특성, 수요에 기반한 물공급량 평가, 관정 연계 시나리오 및 최적 운영 알고리즘, 지하수 모델링 등이 가능하도록 각각의 모듈들이 구성 및 통합·운영 되도록 설계되었다. 본 시스템 개발을 통해 가뭄 발생시 현장에서 신속히 지하수로 물을 공급할 수 있으며, 신규 관정 개발에 드는 비용을 절약할 수 있고, 기존 시설을 활용하기 때문에 새로운 수자원 건설 인프라 구축 비용도 절감할 수 있을 것이다. 또한, 개별관정에 대한 이용률 제고와 지하수관리도 보다 체계적, 과학적으로 할 수 있을 것으로 기대한다. 하지만, 이러한 시스템이 제대로 운영 및 보급되기 위해서는 관정연계와 관련한 법제도적 보완과 함께, 지역사회의 공적자원으로서의 지하수에 대한 인식개선과 지하수의 개발 및 보전, 적합한 합리적 배분·이용 등 적극적인 협조가 이루어져야 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.487-489
• /
• 2020

인공지능 기술을 도입한 의료분야에서 진단 및 예측과 연계한 임상의사결정지원 시스템(CDSS)에 관련된 연구가 활발하게 진행되고 있다. 특히, 인공지능 기술 적용에 가장 많은 이슈를 일으키고 있는 의료영상기반의 질환진단연구가 다양한 제품으로 출시되고 있는 실정이다. 그러나 의료영상 데이터는 일관되지 않은 데이터들로 이루어져 있으며, 그것을 정제하여 연구에 사용하기 위해서는 상당한 시간이 필요한 것이 현실이다. 본 논문에서는 익명화된 데이터를 정제하여 인공지능 연구에 사용할 수 있는 표준화된 데이터 셋을 만들고, 그 데이터를 기반으로 인공지능 알고리즘 개발 연구를 지원하기 위한 원스톱 인공지능학습 플랫폼에 대하여 기술한다. 이를 위해 전체 인공지능 연구프로세스를 보이고 이에 따라 학습을 위한 데이터셋 생성과 인공지능 학습학습용 플랫폼에서 수행되는 수행 과정을 결과로 보인다 제안한 플랫폼을 통해 다양한 영상기반 인공지능 연구에 활용될 것으로 기대하고 있다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2D
• /
• pp.319-327
• /
• 2009

In order to estimate accurate position by GPS observations, it is prerequisite to define both of the correct function model and the realistic stochastic model. In the case that un-modeled outliers exist in observations, estimates become biased, and their standard deviations are unable to be used as a measure which represents their accuracy. Hence, such outliers should be appropriately removed from the observations before estimating final solutions, so that the accuracy can be maximized with the improvement of the reliability. For this purpose, this research deals with quality control and quality measure computation algorithms for GPS stand-alone positioning. After theoretical studies, all the algorithms have been implemented and tested with real observations. Results of the tests indicate that the reliability of the estimated position is improved by increasing redundancy as well as using good satellite geometry and more realistic stochastic model. Moreover, the adaptation of the quality control procedure enable to improve positioning reliability and accuracy by appropriately excluding outlier in observations.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6A
• /
• pp.1023-1032
• /
• 2006

In this paper, a new method for the bridge maintenance is proposed to overcome the limit of the existing methods and to implement the preventive bridge maintenance system. The proposed method can establish the lifetime optimum maintenance strategy of the deteriorating bridges considering the life-cycle performance as well as the life-cycle cost. The lifetime performance of the deteriorating bridges is evaluated by the safety index based on the structural reliability and the condition index detailing the condition state. The life-cycle cost is estimated by considering not only the direct maintenance cost but also the user and failure cost. The genetic algorithm is applied to generate a set of maintenance scenarios which is the multi-objective combinatorial optimization problem related to the life-cycle cost and performance. The study examined the proposed method by establishing a maintenance strategy for the existing bridge and its advantages. The result shows that the proposed method can be effectively applied to deciding the bridge maintenance strategy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.307-307
• /
• 2022

최근 기후변화와 댐 상류 토지이용 변화 등과 같은 다양한 원인에 의해 댐 유입량의 변동성이 증가하면서 댐 관리 및 운영조작 의사 결정에 어려움이 발생하고 있다. 따라서 이러한 댐 유입량의 변동 특성을 반영하여 댐 유입량을 정확하고 효율적으로 예측할 수 있는 방안이 필요한 실정이다. 머신러닝 기술이 발전하면서 Auto-ML(Automated Machine Learning)이 다양한 분야에서 활용되고 있다. Auto-ML은 데이터 전처리, 최적 알고리즘 선택, 하이퍼파라미터 튜닝, 모델 학습 및 평가 등의 모든 과정을 자동화하는 기술이다. 그러나 아직까지 수문 분야에서 댐 유입량을 예측하기 위한 모델을 개발하는데 있어서 Auto-ML을 활용한 사례는 부족하고, 특히 댐 유입량의 예측 정확성을 확보하기 위해 High-inflow and low-inflow 의 변동 특성을 고려한 하이브리드 결합 방식을 통해 Auto-ML 기반 앙상블 모델을 개발하고 평가한 연구는 없다. 본 연구에서는 Auto-ML의 패키지 중 Auto-sklearn을 통해 홍수기, 비홍수기 유입량 변동 특성을 반영한 하이브리드 앙상블 댐 유입량 예측 모델을 개발하였다. 소양강댐을 대상으로 적용한 결과, 하이브리드 Auto-sklearn 앙상블 모델의 댐 유입량 예측 성능은 R² 0.868, RMSE 66.23 m³/s, MAE 16.45 m³/s로 단일 Auto-sklearn을 통해 구축 된 앙상블 모델보다 전반적으로 우수한 것으로 나타났다. 특히 FDC (Flow Duration Curve)의 저수기, 갈수기 구간에서 두 모델의 유입량 예측 경향은 큰 차이를 보였으며, 하이브리드 Auto-sklearn 모델의 예측 값이 관측 값과 더욱 유사한 것으로 나타났다. 이는 홍수기, 비홍수기 구간에 대한 앙상블 모델이 독립적으로 구축되는 과정에서 각 모델에 대한 하이퍼파라미터가 최적화되었기 때문이라 판단된다. 향후 본 연구의 방법론은 보다 정확한 댐 유입량 예측 자료를 생성하기 위한 방안 수립뿐만 아니라 다양한 분야의 불균형한 데이터셋을 이용한 앙상블 모델을 구축하는데도 유용하게 활용될 수 있을 것으로 사료된다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.131-136
• /
• 2023

Local youth outmigration is increasingly growing. Various studies are being conducted to identify the factors contributing to this problem, but there is a lack of research analyzing each region individually. Therefore, this study aims to analyze the factors influencing youth outmigration in Busan and predict the risk levels of youth population outflow using machine learning techniques. By utilizing district-level data collected from the KOSIS, we divided the population into three groups based on age (the early 20s, late 20s, and early 30s) and employed Decision Tree and Random Forest algorithms to classify and predict the risk levels of youth population outmigration. The results indicate that the predictive model for youth outmigration risk levels achieves the highest accuracies of 0.93, 0.75, and 0.63 for each age group, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.11-20
• /
• 2024

This study presents TabNet, a novel deep learning method, to enhance corporate credit rating accuracy amidst growing financial market uncertainties due to technological advancements. By analyzing data from major Korean stock markets, the research constructs a credit rating prediction model using TabNet. Comparing it with traditional machine learning, TabNet proves superior, achieving a Precision of 0.884 and an F1 score of 0.895. It notably reduces misclassification of high-risk companies as low-risk, emphasizing its potential as a vital tool for financial institutions in credit risk management and decision-making.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.243-264
• /
• 2018

Although the worldwide battery market is recently spurring the development of lithium secondary battery, lead acid batteries (rechargeable batteries) which have good-performance and can be reused are consumed in a wide range of industry fields. However, lead-acid batteries have a serious problem in that deterioration of a battery makes progress quickly in the presence of that degradation of only one cell among several cells which is packed in a battery begins. To overcome this problem, previous researches have attempted to identify the mechanism of deterioration of a battery in many ways. However, most of previous researches have used data obtained in a laboratory to analyze the mechanism of deterioration of a battery but not used data obtained in a real world. The usage of real data can increase the feasibility and the applicability of the findings of a research. Therefore, this study aims to develop a model which predicts the battery deterioration using data obtained in real world. To this end, we collected data which presents change of battery state by attaching sensors enabling to monitor the battery condition in real time to dozens of golf carts operated in the real golf field. As a result, total 16,883 samples were obtained. And then, we developed a model which predicts a precursor phenomenon representing deterioration of a battery by analyzing the data collected from the sensors using machine learning techniques. As initial independent variables, we used 1) inbound time of a cart, 2) outbound time of a cart, 3) duration(from outbound time to charge time), 4) charge amount, 5) used amount, 6) charge efficiency, 7) lowest temperature of battery cell 1 to 6, 8) lowest voltage of battery cell 1 to 6, 9) highest voltage of battery cell 1 to 6, 10) voltage of battery cell 1 to 6 at the beginning of operation, 11) voltage of battery cell 1 to 6 at the end of charge, 12) used amount of battery cell 1 to 6 during operation, 13) used amount of battery during operation(Max-Min), 14) duration of battery use, and 15) highest current during operation. Since the values of the independent variables, lowest temperature of battery cell 1 to 6, lowest voltage of battery cell 1 to 6, highest voltage of battery cell 1 to 6, voltage of battery cell 1 to 6 at the beginning of operation, voltage of battery cell 1 to 6 at the end of charge, and used amount of battery cell 1 to 6 during operation are similar to that of each battery cell, we conducted principal component analysis using verimax orthogonal rotation in order to mitigate the multiple collinearity problem. According to the results, we made new variables by averaging the values of independent variables clustered together, and used them as final independent variables instead of origin variables, thereby reducing the dimension. We used decision tree, logistic regression, Bayesian network as algorithms for building prediction models. And also, we built prediction models using the bagging of each of them, the boosting of each of them, and RandomForest. Experimental results show that the prediction model using the bagging of decision tree yields the best accuracy of 89.3923%. This study has some limitations in that the additional variables which affect the deterioration of battery such as weather (temperature, humidity) and driving habits, did not considered, therefore, we would like to consider the them in the future research. However, the battery deterioration prediction model proposed in the present study is expected to enable effective and efficient management of battery used in the real filed by dramatically and to reduce the cost caused by not detecting battery deterioration accordingly.

• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.23-31
• /
• 2020

The need for personalized recommendation is growing due to convenient access and various types of items due to the development of information communication and smartphones. Weather and weather conditions have a great influence on the decision-making of users' places and activities. This weather information can increase users' satisfaction with recommendations. In this paper, we propose a collaborative filtering-based place recommendation system using living index by utilizing living index of users' location information on mobile platform to find users with similar propensity and to recommend places by predicting preferences for places. The proposed system consists of a weather module for analyzing and classifying users' weather, a recommendation module using collaborative filtering for place recommendations, and a management module for user preferences and post-management. Experiments have shown that the proposed system is valid in terms of the convergence of collaborative filtering algorithms and living indices and reflecting individual propensity.

• Information Systems Review
• /
• v.10 no.2
• /
• pp.137-158
• /
• 2008

Rapid development of various information technologies creates new opportunities in online and offline markets. In this changing market environment, customers have various demands on new products and services. Therefore, their power and influence on the markets grow stronger each year. Companies have paid great attention to customer relationship management. Especially, personalized product recommendation systems, which recommend products and services based on customer's private information or purchasing behaviors in stores, is an important asset to most companies. CRM is one of the important business processes where reliable information is mined from customer database. Data mining techniques such as artificial intelligence are popular tools used to extract useful information and knowledge from these customer databases. In this research, we propose a recommendation system that predicts customer's purchase intention. Then, customer's purchasing intention of specific product is predicted by using data mining techniques using receipt data set. The performance of this suggested method is compared with that of other data mining technologies.