• Journal of the Earthquake Engineering Society of Korea
• /
• v.10 no.6 s.52
• /
• pp.1-8
• /
• 2006

This paper describes the procedures developing the algorithm for analyzing signals acquired from the Bridge Weigh-in-Motion (BWIM) system installed in Seohae Bridge as a part of the bridge monitoring system. Through the analysis procedure, information about heavy traffics such as weight, speed, and number of axles are attempted to be extracted from time domain strain data of the BWIM system. One of numerous pattern recognition techniques, artificial neural network (ANN) is employed since it can effectively include dynamic effects, bridge-vehicle interaction, etc. A number of vehicle running experiments with sufficient load cases are executed to acquire training and/or test set of ANN. Extracted traffic information can be utilized for developing quantitative database of loading effect. Also, it can contribute to estimate fatigue lift or current health condition, and design truck can be revised based on the database reflecting recent trend of traffic.

• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.203-210
• /
• 2014

This study proposes adaptive decision making method having feed-back structure of regression and simulation models to support the quick decision making of production managers by managing and integrating the mutual relationship among historical data. For that, from historical data that have extracted and accumulated from each process, we first selected major constraint resources that are used as independent variables in regression model. The regression model is designed by using the dependent variables (objectives) that defined above by managers and independent variables selected in previous step and simulation model that are composed of constraint resources is designed. In process of simulation run, we obtain the multiple feasible solutions (alternatives) by using meta-heuristic method. Each solution is substituted by regression equation and we found the optimal solution that is minimum of difference between values obtained by regression model and simulation results. The optimal solution is delivered and incorporated to production site and current operation results from production site is used to generate new regression model after that time.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.6
• /
• pp.1655-1665
• /
• 2014

Dynamic displacements of structures shows general behavior of structures. Generally, It is used to estimate structure condition and trustworthy physical quantity directly. Especially, measuring vertical displacement which is affected by moving load is very important part to find or identify a problem of bridge in advance. However directly measuring vertical displacement of the bridge is difficult because of test conditions and restriction of measuring equipment. In this study, Artificial Neural Network (ANN) is used to suggest estimation method of bridge displacement to overcome constrain conditions, restriction and so on. Horizontal strain and vertical displacement which are measured by appling random moving load on the bridge are applied for learning and verification of ANN. Measured horizontal strain is used to learn ANN to estimate vertical displacement of the bridge. Numerical analysis is used to acquire learning data for axis strain and vertical displacement for applying ANN. Moving load scenario which is made by vehicle type and vehicle distance time using Pearson Type III distribution is applied to analysis modeling to reflect real traffic situation. Estimated vertical displacement in respect of horizontal strain according to learning result using ANN is compared with vertical displacement of experiment and it presents vertical displacement of experiment well.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.79-101
• /
• 2023

The current status of local road pavement management in Jeollabuk-do only relies on the accomplishments of the site construction company's pavement repair and is only managed through Microsoft Excel and word documents. Furthermore, the budget is irregular each year. Accordingly, a systematic maintenance plan for local roads is necessary. In this paper, data related to road damage and road environment were collected and processed to derive possible areas which could suffer from road damage. The effectiveness of the methodology was reviewed through the on-site inspection of the area. According to the Ministry of Land, Infrastructure and Transport, in 2018, the number of damages on general national roads were about 47,000. In 2019, it reached around 38,000. Furthermore, the number of lawsuits regarding the road damages were about 93 in 2018 and it increased to 119 in 2019. In the case of national roads, the number of damages decreased compared to 2018 due to pavement repairs. To measure the priorities in maintenance of local roads at Jeollabuk-do, data on maintenance history, local port hole occurrence site, overlapping business section, and emergency maintenance section were transformed into data. Eventually, it led to improvements in maintenance of local roads. Furthermore, spatial data were constructed using various current status data related to roads, and finally the data was processed into a new form that could be utilized in machine learning and predictions. Using the spatial data, areas requiring maintenance on pavement were predicted and the results were used to establish new budgets and policies on road management.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.8 no.4
• /
• pp.63-69
• /
• 2004

In this paper, a nonlinear modeling of lead rubber bearings(LRBs) was presented by a neural network theory. An shaking table test for a scaled frame model, of which base was isolated by the LRBs, was performed to verify numerical accuracies of the neural network model. White noise and three types of seismic records were adoped as base loads of the shaking table in order to train and generalize the neural network in case of seismic loads, numerical results of the neural network model were evaluated according to different magnitudes of PGA. As results, it is concluded that the presented neural network model has given a good agreement with the experimental data in details and can be useful to a nonlinear modeling of LRBs within prescribed domains.

• Journal of Korea Water Resources Association
• /
• v.52 no.12
• /
• pp.963-973
• /
• 2019

This study reviews a urban flooding risk criteria estimation model to predict risk criteria in areas where flood risk criteria are not precalculated by using watershed characteristic data and limit rainfall based on damage history. The risk criteria estimation model was designed using Support Vector Machine, one of the machine learning algorithms. The learning data consisted of regional limit rainfall and watershed characteristic. The learning data were applied to the SVM algorithm after normalization. We calculated the mean absolute error and standard deviation using Leave-One-Out and K-fold cross-validation algorithms and evaluated the performance of the model. In Leave-One-Out, models with small standard deviation were selected as the optimal model, and models with less folds were selected in the K-fold. The average accuracy of the selected models by rainfall duration is over 80%, suggesting that SVM can be used to estimate flooding risk criteria.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2794-2796
• /
• 2002

기업 네트워크에서 안전하고 효과적이며 안정된 망 운영관리 환경 제공은 당면한 중요과제이며 기업 경쟁력의 핵심인 정보기술을 통한 생산성과도 연계성을 갖고 있다. 특히 전력통신망의 경우 전자메일, 회계관리, 전자결재, 도면자료관리 등의 데이터 통신망에서부터 IBM 온라인, 사내 방송망, 전력계통설비 원방 제어용 시스템들 간을 연결하는 EMS, SCADA 등 전력 수급용 전용 통신망에 이르기까지 다양한 종류의 통신망이 구축 운용되고 있다. 이러한 기업환경에 따라 네트워크를 효율적으로 관리하기 위한 네트워크 관리 시스템에 대한 관심이 증대되고 있으며 많은 네트워크 관리 시스템들이 도입되어 운영되었으나 이들 관리 시스템들은 모니터링에 의한 통계값 제공과 같은 단순 평면적인 관리 기능만을 제공한 뿐 네트워크의 특성과 환경에 따른 분석, 진단 기능은 제공하지 못하고 있다. 이와 더불어 네트워크 관리자는 보다 손쉬운 방법으로 네트워크를 관리하고자 하며, 보다 지능적이고 효율적으로 관리하고자 한다. 하지만 관리 시스템이 모든 네트워크에 대해 효율적이고 지능적인 관리 기능을 제공하기는 매우 어려우며 이는 장기간의 관리 네트워크의 특성과 트래픽 형태를 파악한 후에나 가능하다. 결국 지능적이고 효율적인 네트워크 관리는 네트워크의 특성과 함께 이전에 관리자에 의해서 내려졌던 관리 행위 및 의견 그리고 조치에 대한 이력정보를 학습하고 있을 때만 가능하다. 본 논문은 전력통신망을 대상으로 전력통신망이 지닌 네트워크 특성을 반영하며 네트워크 운영 과정에서 축적된 관리자의 의견과 이에 대한 조치를 지식 데이터베이스화하여 지능적인 관리 시스템을 제공하기 위한 기반 시스템으로써 전력통신망 운용 관리 지원시스템을 설계 및 구현하였다. 본 시스템은 향후 지식 정보를 학습하고 이를 바탕으로 논리적인 추론을 통해 관리 네트워크를 지능적이고 자동적으로 관리할 수 있는 시스템으로 확대 개발될 것이다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.796-801
• /
• 2009

In medical practice, the diagnosis or prediction models requiring complicated computations are not widely recognized due to difficulty in interpreting the course of reasoning and the complexity of computations. Medical personnel have used the nomograms which are a graphical representation for numerical relationships that enables to easily compute a complicated function without help of computation machines. It has been widely paid attention in diagnosing diseases or predicting the progress of diseases. A nomogram is constructed from a set of clinical data which contain various attributes such as symptoms, lab experiment results, therapy history, progress of diseases or identification of diseases. It is of importance to select effective ones from available attributes, sometimes along with parameters accompanying the attributes. This paper introduces a nomogram construction method that uses a naive Bayesian technique to construct a nomogram as well as a genetic algorithm to select effective attributes and parameters. The proposed method has been applied to the construction of a nomogram for a real clinical data set.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.2
• /
• pp.11-19
• /
• 2020

When a character's pose changes, its center of mass(COM) also changes. The change of COM has distinctive patterns corresponding to various motion types like walking, running or sitting. Thus the motion type can be predicted by using COM movement. We propose a motion generator that uses character's center of mass information. This generator can generate various motions without annotated action type labels. Thus dataset for training and running can be generated full-automatically. Our neural network model takes the motion history of the character and its center of mass information as inputs and generates a full-body pose for the current frame, and is trained using simple Convolutional Neural Network(CNN) that performs 1D convolution to deal with time-series motion data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.5
• /
• pp.641-656
• /
• 2019

In this study, a machine learning method was proposed to use in predicting optimal replacement period of shield TBM (Tunnel Boring Machine) disc cutter. To do this, a large dataset of ground condition, disc cutter replacement records and TBM excavation-related data, collected from a shield TBM tunnel site in Korea, was built and they were used to construct a disc cutter replacement period prediction model using a machine learning algorithm, SVM (Support Vector Machine) and to assess the performance of the model. The results showed that the performance of RBF (Radial Basis Function) SVM is the best among a total of three SVM classification functions (80% accuracy and 10% error rate on average). When compared between ground types, the more disc cutter replacement data existed, the better prediction results were obtained. From this results, it is expected that machine learning methods become very popularly used in practice in near future as more data is accumulated and the machine learning models continue to be fine-tuned.