• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.515-515
• /
• 2023

팔당호는 북한강과 남한강이 합류하여 생성된 호소로 수도인 서울과 수도권인 경기도 동부지역의 물 공급을 담당하는 중요한 상수원이다. 이러한 팔당호에서 유해남조 발생은 상수원수 활용과 직접적으로 연관되어 있어 신속하고 정확한 관리 및 예측이 필요하다. 본 연구에서는 안전한 상수원 활용을 위해, 딥러닝 기법을 이용하여 유해남조 사전 예측 모델을 구축하고자 하였다. 모델 입력 변수는 2012년부터 2021년까지 10년 동안의 주간 팔당호 수질(수온, DO, BOD, COD, Chl-a, TN, TP, pH, 전기전도도, TDN, NH4N, NO3N, TDP, PO4P, 부유물질)과 수문(유입량, 총방류량), 기상 정보(평균기온, 최저기온, 최고기온, 일 강수량, 평균풍속, 평균 상대습도, 합계일조량), 그리고 북한강과 남한강 유입지점의 남조 세포 수를 사용하였다. 모델 출력 변수는 수질, 수문, 기상 요인으로 인한 남조의 성장 발현 시기를 고려하여 1주 후의 댐앞 남조 세포수를 사용하였다. 사용한 딥러닝 기법은 최근 주목받고 있는 Temporal Fusion Transformer (TFT)를 사용하였다. 모델 훈련용 데이터와 테스트용 데이터는 각각 8:2의 비율로 나누었으며, 검증용 데이터는 훈련용 데이터 내에서 훈련 데이터와 검증 데이터를 6:4 비율로 분배하였다. Lookback은 5로 설정하였고, 이는 주단위 데이터로 구성된 데이터세트의 특성을 반영한 것이다. 모델의 성능은 실측값과 예측값을 토대로 R-square와 Root Mean Squared Error (RMSE)를 계산하여 평가하였다. 모델학습은 총 154번 반복 진행되었으며, 이 중 성능이 가장 준수한 시점은 54번째 반복 시점으로 훈련손실 대비 검증손실이 가장 양호한 값을 나타냈다(훈련손실:0.443, 검증손실 0.380). R-square는 훈련단계에서 0.681, 검증단계에서 0.654였고, 테스트 단계에서 0.606으로 산출되었다. RMSE는 훈련단계에서 0.614(㎍/L), 검증단계에서 0.617(㎍/L), 테스트 단계에서 0.773(㎍/L)였다. 모델에 사용한 데이터세트가 주간 데이터라는 특성을 고려하면, 소규모 데이터를 사용하였음에도 본 연구에서 구축한 모델의 성능은 양호하다고 평가할 수 있다. 향후 연구에서 데이터세트를 보강하고 모델을 업데이트한다면, 모델의 성능을 더욱더 개선할 수 있을 것으로 기대된다.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.137-146
• /
• 2008

Fault localization plays a significant role in enormous distributed system because it can identify root cause of observed faults automatically, supporting self-managing which remains an open topic in managing and controlling complex distributed systems to improve system reliability. Although many Artificial Intelligent techniques have been introduced in support of fault localization in recent research especially in increasing complex ubiquitous environment, the provided functions such as diagnosis and prediction are limited. In this paper, we propose fault localization for self-managing in performance evaluation in order to improve system reliability via learning and analyzing real-time streams of system performance events. We use probabilistic reasoning functions based on the basic Bayes' rule to provide effective mechanism for managing and evaluating system performance parameters automatically, and hence the system reliability is improved. Moreover, due to large number of considered factors in diverse and complex fault reasoning domains, we develop an efficient method which extracts relevant parameters having high relationships with observing problems and ranks them orderly. The selected node ordering lists will be used in network modeling, and hence improving learning efficiency. Using the approach enables us to diagnose the most probable causal factor with responsibility for the underlying performance problems and predict system situation to avoid potential abnormities via posting treatments or pretreatments respectively. The experimental application of system performance analysis by using the proposed approach and various estimations on efficiency and accuracy show that the availability of the proposed approach in performance evaluation domain is optimistic.

• Journal of Korea Water Resources Association
• /
• v.45 no.11
• /
• pp.1187-1199
• /
• 2012

A hybrid forecasting scheme based on wavelet decomposition coupled to a support vector machine model is presented for water demand series that exhibit nonlinear behavior. The use of wavelet transform followed by the SVM model of each leading component is explored as a model for water demand data. The proposed forecasting model yields better results than a traditional ARIMA time series forecasting model in terms of self-prediction problem as well as reproducing the properties of the observed water demand data by making use of the advantages of wavelet transform and SVM model. The proposed model can be used to substantially and significantly improve the water demand forecasting and utilized in a real operation.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.199-208
• /
• 2008

Prediction the performance of pavement provides proper information to an agency on decision-making process; especially evaluating the pavement performance and prioritizing the work plan. To date, there are a number of approaches to predict the future deterioration of pavements. However, there are some limitation to proper prediction of the pavement service life. In this paper, pavement performance model and pavement condition prediction model are developed in order to improve pavement condition prediction method. The prediction model of pavement condition through the regression analysis of real pavement condition is based on the probability distribution of pavement condition, which set to 5%, 15%, 25% and 50%, by condition of the pavement and traffic volume. The pavement prediction model presented from the behavior of individual pavement condition which are set to 5%, 15%, 25% and 50% of probability distribution. The performance of the prediction model is evaluated from analyzing the average, standard deviation of HPCI, and the percentage of HPCI which is lower than 3.0 of comparable section. In this paper, we will suggest the more rational method to determine the future pavement conditions, including the probabilistic duration and deterministic modeling methods regarding the impact of traffic volume, age, and the type of the pavement.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.7
• /
• pp.1313-1329
• /
• 2015

In MANET, frequent route breaks lead to repeated route discovery process and this increases control packet overhead and packet drop. AODV-I improves performance of AODV by using the event driven approach which removes periodic Hello message. Unlike the Hello message, Interrupt message which is sent for each event can detect and predict the link failure because it allows node to know the status of the neighbor node. From this characteristics of Interrupt message, performance of AODV-I can be further improved by adding a processing procedures for each type of Interrupt message and it is also possible to improve AODV-I by adding the Backup path scheme because it originally has problems due to a single path of AODV. In this paper, we propose AODV-IB that combines improved Backup path scheme and Interrupt message approach of AODV-I in order to reduce transmission delay and the number of route discoveries. AODV-IB improves AODV-I by adding proper processing procedures for the link failure prediction and detection for each Interrupt message. We also implement improved Backup path strategy in AODV-IB by minimizing delay without additional Control packet. Simulation results, using the simulator QualNet 5.0, indicate that proposed AODV-IB performs better than AODV-I.

• Journal of the Korean earth science society
• /
• v.40 no.3
• /
• pp.259-271
• /
• 2019

A statistical downscaling method was adopted in order to establish the high-resolution wave prediction system in the East Sea coastal area. This system used forecast data from the Global Wave Watch (GWW) model, and the East Sea and Busan Coastal Wave Watch (CWW) model operated by the Korea Meteorological Administration (KMA). We used the CWW forecast data until three days and the GWW forecast data from three to seven days to implement the statistical downscaling method (inverse distance weight interpolation and conditional merge). The two-dimensional and station wave heights as well as sea surface wind speed from the high-resolution coastal prediction system were verified with statistical analysis, using an initial analysis field and oceanic observation with buoys carried out by the KMA and the Korea Hydrographic and Oceanographic Agency (KHOA). Similar to the predictive performance of the GWW and the CWW data, the system has a high predictive performance at the initial stages that decreased gradually with forecast time. As a result, during the entire prediction period, the correlation coefficient and root mean square error of the predicted wave heights improved from 0.46 and 0.34 m to 0.6 and 0.28 m before and after applying the statistical downscaling method.

• Journal of Digital Contents Society
• /
• v.9 no.2
• /
• pp.305-315
• /
• 2008

Pre-proposed AHHS(Adaptive Hierarchical Hexagon Search) is a kind of the fast hierarchical block matching algorithm based on the AHS(Adaptive Hexagon Search). It is characterized as keeping the merits of the AHS capable of fast estimating motion vectors and also adaptively reducing the local minima often occurred in the video sequences with higher spatio-temporal motion activity. The objective of this paper is to propose the method effectively extending the horizontal biased pattern and the vertical biased pattern of the AHHS to improve its predictive image quality. In the paper, based on computer simulation results for multiple video sequences with different motion characteristics, the performance of the proposed method was analysed and assessed in terms of the predictive image quality and the computational time. The simulation results indicated that the proposed method was both suitable for (quasi-) stationary and large motion searches. While the proposed method increased the computational load on the process extending the hexagon search patterns, it could improve the predictive image quality so as to cancel out the increase of the computational load.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1594-1609
• /
• 2010

In the case that multiple services are in race condition for limited I/O resource, the services or processes with lower priority occasionally occupy most of limited I/O resource. And it decreases QoS and performance of important services and makes it difficult to efficiently use limited I/O resource. Although system administrator allocates I/O resource according to priority of process, he/she can't know or expect how much resource will be used by the specific process. Due to these reasons, it causes the problem that he/she can't guarantee the service QoS and performance stability. Therefore, in this paper, we propose service based disk I/O control supporting predictable I/O bandwidth to resolve upper problems. Proposed I/O control guarantees the service QoS and performance stability by supporting the service based predictable I/O bandwidth and it makes limited I/O resource to be efficiently used in respect of service.

• Annual Conference of KIPS
• /
• 2008.05a
• /
• pp.423-426
• /
• 2008

한국증권선물거래소의 유가증권 매매체결시스템은 안정적이고 신속한 데이터 처리에 초점을 둔 시스템이다. 인터넷과 HTS(Home Trading System)의 대중화로 인해 대량의 데이터로부터 적시에 정보를 추출하고 분석하고자 하는 요구가 증가하고 있다. 그러나 현재의 통계정보시스템은 이와 같은 요구를 수용하기 어려우며 개발자의 별도 노력이 요구된다. 또한 목표성능에 대한 요구가 매우 높아짐에 따라 시스템 및 어플리케이션의 증설과 개선작업이 빈번하지만 그 효과를 예측하기 어려우며 정량화 된 근거자료의 부재로 의사결정을 지연시킨다. 따라서 이와 같은 요구사항들을 해결하기 위해 기존의 통계정보시스템을 활용하고 추가적인 데이터들을 다양한 차원에서 분석 가능하도록 웨어하우스 데이터베이스를 구축하며 성능예측을 위한 요소들을 추출하고 데이터마이닝을 수행하여 의사결정에 도움을 줄 수 있는 다차원 모델링 기반의 거래분석 시스템을 제안한다. 거래분석 시스템의 구축으로 사용자는 웹상에서 적시에 다차원 분석보고서를 생성할 수 있다. 또한 관리자는 외부적 환경변화에 따른 향후 시스템 성능 감소를 예측할 수 있으며 내부적 요인을 제어하여 이를 상쇄할 수 있는 방안을 찾을 수 있게 된다.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.