• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 추계학술대회
• /
• pp.307-312
• /
• 2003

The object of this study is to investigate a damage estimation of single edge cracked tensile specimens ($2_a$/W) as a function of acoustic emission (AE) according to the unidirectionally oriented carbon/epoxy composites, CFRP AE signals were analyzed and classified 3 regions by event counts, energy and amplitude for coressponding applied load. On tensile loading and using the results of the AE analysis, it was found that the event counts, cumulative counts or energy, and amplitude distributions useful for the prediction of damage failure.

• 한국강구조학회 논문집
• /
• 제8권4호통권29호
• /
• pp.77-84
• /
• 1996

The structural members under seismic loading actually show inelastic behavior, so the inelastic responses should be calculated for the seismic design of structures or estimating the structural damage level. Although direct time history analysis may calculate the exact dynamic nonlinear responses for given ground motions, this approach involves a high computational cost and long period. Therefore, it should be developed the approach to estimate nonlinear responses for the practical purpose. The artificial earthquake accelerograms were generated to obtain the smoothed responses spectra, and the samples of generated accelerogram for each seismic event was used to examine average nonlinear response spectra. The stabilized response spectra for each earthquake event was used to evaluate the effects of various yield strength ratios, damping values and nonlinear hysteretic models. The approach, which can simply predict the nonlinear seismic responses of structures, was shown in this study.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2018년도 제58차 하계학술대회논문집 26권2호
• /
• pp.364-366
• /
• 2018

본 논문에서는 Digital Twin 기반 건설기계 지능화를 위한 실시간 건설기계 데이터 처리 및 이상 유무 예측 시스템을 제안한다. 이 시스템은 빅 데이터 분산처리 기반으로 실시간 스트리밍 처리가 가능하며, CEP(Complex Event Processing)의 Sliding Window Operator를 활용한 Rule 적용을 통해 건설기계 데이터 처리 및 분석한다. 분석된 결과로 건설기계의 실시간 이상 유무를 판단할 수 있으며, 결과를 기반으로 Deep Learning 기술을 적용하고 학습된 모델을 통해 건설기계의 이상 유무를 예측하여 원활한 부품관리를 할 수 있다.

• 한국환경과학회지
• /
• 제2권1호
• /
• pp.29-36
• /
• 1993

An instantaneous unit sediment graph (IUSG) model is investigated for prediction of sediment yield from an upland watershed In Northwestern Mississippi. Sediment yields are predicted by convolving source runoff with an IUSG. The IUSG is the distribution of sediment from an instantaneous burst of rainfall producing one unit of runoff. The IUSG, defined as a product of the sediment concentration distribution (SCD) and the instantaneous unit hydrograph (IUH), is known to depend on the characteristics of the effective rainfall. The IUH is derived by the Nash model for each event. The SCD is assumed to be an exponential function for each event and its parameters were correlated with the effective rainfall characteristics. A sediment routing function, based on travel time and sediment particle size, is used to predict the SCD.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.2161-2166
• /
• 2009

It is important for 0-6 hour nowcasting to provide for a high-quality initial condition in a meso-scale atmospheric model by a data assimilation of several observation data. The polarimetric radar data is expected to be assimilated into the forecast model, because the radar has a possibility of measurements of the types, the shapes, and the size distributions of hydrometeors. In this paper, an impact on rainfall prediction of the data assimilation of hydrometeor types (i.e. raindrop, graupel, snowflake, etc.) is evaluated. The observed information of hydrometeor types is estimated using the fuzzy logic algorism. As an implementation, the cloud-resolving nonhydrostatic atmospheric model, CReSS, which has detail microphysical processes, is employed as a forecast model. The local ensemble transform Kalman filter, LETKF, is used as a data assimilation method, which uses an ensemble of short-term forecasts to estimate the flowdependent background error covariance required in data assimilation. A heavy rainfall event occurred in Okinawa in 2008 is chosen as an application. As a result, the rainfall prediction accuracy in the assimilation case of both hydrometeor types and the Doppler velocity and the radar echo is improved by a comparison of the no assimilation case. The effects on rainfall prediction of the assimilation of hydrometeor types appear in longer prediction lead time compared with the effects of the assimilation of radar echo only.

• 한국인공지능학회지
• /
• 제6권2호
• /
• pp.11-15
• /
• 2018

Breast cancer is one of the leading causes of cancer related death among women. So prediction of overall survival status is important into decided in adjuvant treatment. Deep belief network is a kind of artificial intelligence (AI). We intended to construct prediction model by deep belief network using associated clinicopathologic factors. 103881 cases were found in the Korean Breast Cancer Registry. After preprocessing of data, a total of 15733 cases were enrolled in this study. The median follow-up period was 82.4 months. In univariate analysis for overall survival (OS), the patients with advanced AJCC stage showed relatively high HR (HR=1.216 95% CI: 0.011-289.331, p=0.001). Based on results of univariate and multivariate analysis, input variables for learning model included 17 variables associated with overall survival rate. output was presented in one of two states: event or cencored. Individual sensitivity of training set and test set for predicting overall survival status were 89.6% and 91.2% respectively. And specificity of that were 49.4% and 48.9% respectively. So the accuracy of our study for predicting overall survival status was 82.78%. Prediction model based on Deep belief network appears to be effective in predicting overall survival status and, in particular, is expected to be applicable to decide on adjuvant treatment after surgical treatment.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1243-1249
• /
• 2019

특정한 이벤트나 콘텐츠를 즐기기 위해 모인 사람들을 관중 또는 관객이라고 하고, 모임의 특성에 따라 다양한 성향을 나타낸다. 그러한 차이점은 있지만, 일반적으로 관중 수는 경영적인 측면과 직결되는 요소로써, 관람료부터 다른 시설의 이용료 등 다양한 수입을 통해 콘텐츠 판매를 위한 안정적인 재정 운영을 가능케 한다. 따라서 관중 수에 대한 예측은 마케팅과 예산 전략 수립에 주요한 요소로 활용될 수 있다. 본 연구에서는 관중 수에 대한 예측을 위한 여러 가지 기존 모델을 검토하고, 그 중에서 효율적인 머신러닝 모델을 제안하고자 한다. 또한 딥러닝과 랜덤포레스트 모델을 혼용하여 일별 관중 수 예측과 비정상적 관중 수 예측에 대한 연구를 진행하였다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제27권4호
• /
• pp.115-128
• /
• 2018

Purpose The purpose of this study is to predict future behaviors of business process. Specifically, this study tried to predict the last activities of process instances. It contributes to overcoming the limitations of existing approaches that they do not accurately reflect the actual behavior of business process and it requires a lot of effort and time every time they are applied to specific processes. Design/methodology/approach This study proposed a novel approach based using deep learning in the form of dynamic recurrent neural networks. To improve the accuracy of our prediction model based on the approach, we tried to adopt the latest techniques including new initialization functions(Xavier and He initializations). The proposed approach has been verified using real-life data of a domestic small and medium-sized business. Findings According to the experiment result, our approach achieves better prediction accuracy than the latest approach based on the static recurrent neural networks. It is also proved that much less effort and time are required to predict the behavior of business processes.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권4호
• /
• pp.135-142
• /
• 2021

Estimating the locations of workers in a shipyard is beneficial for a variety of applications such as selecting potential forwarders for transferring data in IoT services and quickly rescuing workers in the event of industrial disasters or accidents. In this work, we propose a human movement stream processing system for estimating worker locations in shipyards based on Apache Spark and TensorFlow serving. First, we use Apache Spark to process location data streams. Then, we design a worker location prediction model to estimate the locations of workers. TensorFlow serving manages and executes the worker location prediction model. When there are requirements from clients, Apache Spark extracts input data from the processed data for the prediction model and then sends it to TensorFlow serving for estimating workers' locations. The worker movement data is needed to evaluate the proposed system but there are no available worker movement traces in shipyards. Therefore, we also develop a mobility model for generating the workers' movements in shipyards. Based on synthetic data, the proposed system is evaluated. It obtains a high performance and could be used for a variety of tasksin shipyards.

• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.4014-4021
• /
• 2021

If safety injection systems (SISs) do not work in the event of a loss-of-coolant accident (LOCA), the accident can progress to a severe accident in which the reactor core is exposed and the reactor vessel fails. Therefore, it is considered that a technology that provides recoverable maximum time for SIS actuation is necessary to prevent this progression. In this study, the corresponding time was defined as the golden time. To achieve the objective of accurately predicting the golden time, the prediction was performed using the deep fuzzy neural network (DFNN) with rule-dropout. The DFNN with rule-dropout has an architecture in which many of the fuzzy neural networks (FNNs) are connected and is a method in which the fuzzy rule numbers, which are directly related to the number of nodes in the FNN that affect inference performance, are properly adjusted by a genetic algorithm. The golden time prediction performance of the DFNN model with rule-dropout was better than that of the support vector regression model. By using the prediction result through the proposed DFNN with rule-dropout, it is expected to prevent the aggravation of the accidents by providing the maximum remaining time for SIS recovery, which failed in the LOCA situation.