• 대한의용생체공학회:의공학회지
• /
• 제22권4호
• /
• pp.369-375
• /
• 2001

The statistical regression model is one of the most frequently used clinical analysis methods. It has basic assumption of linearity, additivity and normal distribution of data. However, most of biological data in medical field are nonlinear and unevenly distributed. To overcome the discrepancy between the basic assumption of statistical model and actual biological data, we propose a new analytical method based on artificial neural network. The newly developed multilayer perceptron(MLP) is trained with 120 data set (60 normal, 60 patient). On applying test data, it shows the discrimination power of 0.76. The diabetic risk factors were also identified from the MLP neural network model and the logistic regression model. The signigicant risk factors identified by MLP model were post prandial glucose level(PP2), sex(male), fasting blood sugar(FBS) level, age, SBP, AC and WHR. Those from the regression model are sex(male), PP2, age and FBS. The combined risk factors can be identified using the MLP model. Those are total cholesterol and body weight, which is consistent with the result of other clinical studies. From this experiment we have learned that MLP can be applied to the combined risk factor analysis of biological data which can not be provided by the conventional statistical method.

• 한국해양공학회지
• /
• 제32권6호
• /
• pp.474-484
• /
• 2018

In this study, a new numerical modeling system was proposed to predict oil spills, which increasingly occur at sea as a result of abnormal weather conditions such as global warming. The hydrodynamic conditions such as the flow velocity needed to calculate oil dispersion were estimated using a three dimensional hydrodynamic model based on the Navier-Stokes equation, which considered all of the physical variations in the vertical direction. This improved the accuracy compared to those estimated by the conventional shallow water equation. The advection-diffusion model for the spilled oil was combined with the hydrodynamic model to predict the movement and fate of the oil. The effects of absorption, weathering, and wind were also considered in the calculation process. The combined model developed in this study was then applied to various test cases to identify the characteristics of oil dispersion over time. It is expected that the developed model will help to establish initial response and disaster prevention plans in the event of a nearshore oil spill.

• Geomechanics and Engineering
• /
• 제18권2호
• /
• pp.133-140
• /
• 2019

Strain-rate and temperature have significant effects on the one-dimensional (1D) compression behavior of soils. This paper focuses on the bonding degradation effect of soil structure on the time and temperature dependent behavior of soft structured clay. The strain-rate and temperature dependency of preconsolidation pressure are investigated in double logarithm plane and a thermal viscoplastic model considering the combined effect of strain-rate and temperature is developed to describe the mechanical behavior of unstructured clay. By incorporating the bonding degradation, the model is extended that can be suitable for structured clay. The extended model is used to simulate CRS (Constant Rate of Strain) tests conducted on structural Berthierville clay with different strain-rates and temperatures. The comparisons between predicted and experimental results show that the extended model can reasonably describe the effect of bonding degradation on the stain-rate and temperature dependent behavior of soft structural clay under 1D condition. Although the model is proposed for 1D analysis, it can be a good base for developing a more general 3D model.

• Wind and Structures
• /
• 제37권5호
• /
• pp.383-397
• /
• 2023

In the Structural Health Monitoring (SHM) system of civil engineering, data missing inevitably occurs during the data acquisition and transmission process, which brings great difficulties to data analysis and poses challenges to structural health monitoring. In this paper, Convolution Neural Network (CNN) is used to recover the nonstationary wind speed data missing randomly at sampling points. Given the technical constraints and financial implications, field monitoring data samples are often insufficient to train a deep learning model for the task at hand. Thus, simulation combined transfer learning strategy is proposed to address issues of overfitting and instability of the deep learning model caused by the paucity of training samples. According to a portion of target data samples, a substantial quantity of simulated data consistent with the characteristics of target data can be obtained by nonstationary wind-field simulation and are subsequently deployed for training an auxiliary CNN model. Afterwards, parameters of the pretrained auxiliary model are transferred to the target model as initial parameters, greatly enhancing training efficiency for the target task. Simulation synergy strategy effectively promotes the accuracy and stability of the target model to a great extent. Finally, the structural dynamic response analysis verifies the efficiency of the simulation synergy strategy.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.87.2-87
• /
• 2001

By the state transformation including independent outputs functions, a nonlinear process model can be decomposed into two subsystems; the one(design model) is described in output variables as new states and used for control system synthesis and the other(disturbance model) is described in the original unavailable states and its couplings with the design model are treated as uncertain time-varying parameters in the design model. Its existence with respect to the design model is ignored. So, the design model is an uncertain time-variant system. Control synthesis based on a reduced design model is a combined ...

• 응용통계연구
• /
• 제28권6호
• /
• pp.1235-1243
• /
• 2015

최근 들어 ICT 분야의 발달에 따라 데이터 사용량의 급격한 증가로 인터넷 트래픽 사용량 예측은 중요성은 강조되고 있다. 이러한 예측치를 적절한 트래픽 관리와 제어를 위한 계획 수립에 도움을 준다. 본 논문은, 5분 단위의 인터넷 트래픽 자료를 이용하여 결합 예측 모형을 제안하고자 한다. 이에 대하여 시계열의 대표적인 3개 모형인 Seasonal ARIMA, Fractional ARIMA(FARIMA), Taylor의 수정된 Holt-Winters 모형을 적용하였다. 모형 간 결합 예측 방법으로 예측치 간의 SA(Simple Average) 결합 예측 방법과 OLS(Ordinary Least Square)를 이용한 결합방법, ERLS(Equality Restricted Least Squares)를 이용한 결합 예측 방법, Armstrong(2001)이 제안한 MSE 기반 결합 예측 방법을 사용한다. 이에 따른 결과로서 3시간에서의 예측은 Seasonal ARIMA가 선택된 반면, 6시간 이후 예측에서는 결합 예측 방법이 좋은 예측 성능을 보여준다.

• International Journal of Railway
• /
• 제5권2호
• /
• pp.77-83
• /
• 2012

Railroad signaling systems are to control intervals and routes of trains. There are ATS, ATP, ATO and ATC system. Trains are operated in the section which is met on the signaling system because various signaling systems are used in Korea. Hence, trains are not operated in the section which is used in the other signaling system. To solve this problem, recently combined on-board system has been developed. The combined on-board system designed by doubling the ATS, ATP and ATC system to ensure the safety of system. The inductance of antenna is change and in return the resonance frequency of antenna is varied by the electromagnetic induction. Therefore, the information signal is not received exactly in the combined on-board system and in return accidents between trains occur. In this paper, electric model of the combined on-board system for considering the ATS and ATP antenna is presented. Moreover, the mutual inductance including the distance between the ATS and ATP antenna is calculated. As a result of the frequency response of the antennas, the mutual inductance met on operation range of resonance frequency is defined.

• Geomechanics and Engineering
• /
• 제21권4호
• /
• pp.379-390
• /
• 2020

The behavior of a piled raft system in multi-layered soil subjected to vertical loading has been studied numerically using 3D finite element analysis. Initially, the 3D finite element model has been validated by analytically simulating the field experiments conducted on vertically loaded instrumented piled raft. Subsequently, a comprehensive parametric study has been conducted to assess the performance of a combined piled raft system in terms of optimum pile spacing and settlement of raft and piles, in multi-layered soil stratum subjected to vertical loading. It has been found that a combined pile raft system can significantly reduce the total settlement as well as the differential settlement of the raft in comparison to the raft alone. Two different arrangements below the piled raft with the same pile numbers show a significant amount of increase of load transfer of piled raft system, which is in line with the load transfer mechanism of a piled raft. A methodology for the factor of safety assessment of a combined pile raft foundation has been presented to improve the performance of piled raft based on its serviceability requirements. The findings of this study could be used as guidelines for achieving economical design for combined piled raft systems.

• Earthquakes and Structures
• /
• 제16권5호
• /
• pp.523-532
• /
• 2019

Different types of gas reservoir such as Liquid Natural Gas (LNG) are among the strategic infrastructures, and have great importance for any government or their private owners. To keep the tank and its contents safe during earthquakes especially if the contents are of hazardous or flammable materials; using seismic protection systems such as base isolator can be considered as an effective solution. However, the major deficiency of this system can be the large deformation in the isolation level which may lead to the failure of bearing system. In this paper, as a solution, the efficacy of an optimally designed combined vibration control system, the combined laminated rubber isolator and rotational friction damper, is investigated to evaluate the enhancement of an existing metal tank response under both far- and near-field earthquakes. Responses like impulsive and convective accelerations, base shear, and sloshing height are studied herein. The probabilistic framework is used to consider the uncertainties in the structural modeling, as well as record-to-record variability. Due to the high calculation cost of probabilistic methods, a simplified structural model is used. By using the Mont-Carlo simulation approach, it is revealed that this combined isolation system is a highly reliable system which provides considerable enhancement in the performance of reservoir, not only leads to the reduction of probability of catastrophic failure of the tank but also decrease the reservoir damage during the earthquake. Moreover, the relative displacement of the isolation level is controlled very well by this combined system.

• 한국물환경학회지
• /
• 제22권6호
• /
• pp.982-990
• /
• 2006

Generally CSOs (Combined Sewer Overflows) are regarded as one of the most serious nonpoint pollution source in the urban watershed, Particularly, the water quality of the Oncheon stream is seriously affected by CSOs because the capacity of interception sewer system connected to the Suyoung wastewater treatment plant is too small to intercept most storm water discharges. The objective of this study is to evaluate the effect of nonpoint source on an urban stream with regards to combined sewer system and separate sewer system using GIS (Geographic Information System) and SWMM (Storm Water Management Model), and to provide an insight for the management of urban stream water quality. In order to consider the effect of CSOs on the receiving water quality, the flow divider element in SWMM was applied. The model calibration and verification were performed by the measured data of quantity and quality on the Oncheon stream. The quantity data acquired from the Suyoung wastewater treatment plant were also used for this procedure. In case of separate sewer system, the modeling results showed the increased tendency in streamflow compared with the combined system in dry weather, In addition, the water quality is remarkably improved in rainfall events at the separate condition. The results imply that the construction of separate sewer system should be taken into first consideration to restore the quality and quantity of water in urban streams.