• Journal of Advanced Marine Engineering and Technology
• /
• 제41권1호
• /
• pp.56-61
• /
• 2017

본 논문은 시간지연이 있는 데이터의 예측기법과 햅틱기반의 원격조작시스템에서의 응용방법을 다룬다. 일반적으로 네트워크 환경은 데이터 전송에 따른 시간지연이 필수적으로 동반되며, 햅틱기반의 원격조작시스템이 이러한 네트워크 환경에 구현되는 경우 시간지연으로 인해 전체 시스템의 성능저하를 피할 수 없다. 이러한 상황을 고려하여, 본 논문은 ARMA모델을 기반으로 모델파라미터의 학습방법과 실시간 예측을 위한 재귀적 알고리즘을 제안한다. 제안된 방법은 가상공간에 놓인 물체에 대하여 양방향 햅틱 상호작용의 상황에서 5ms의 샘플링 주기로 획득한 햅틱데이터에 적용되며, 그 결과로서 100ms 이후의 값을 예측함에 있어 위치수준 오차 1mm이내의 예측성능을 보였다.

• 상하수도학회지
• /
• 제26권6호
• /
• pp.871-881
• /
• 2012

This study suggested a model that can predict a degradation condition over time of two plastic pipes, PE and PVC, which are currently used in the country. This study was analyzed physical characteristics change of plastic pipes by comparison with initial physical characteristics (on the case of new pipes). Since this is dependent on accidents that already occurred, there are limitations that it only decides a priority on improvement based on relative corrosion status rather than precautionary aspects. The comparison results between physical degradation by the deducted performance rating and a conventional numerical scoring method showed that correlation coefficient was 0.67 for PE pipes and 0.86 for PVC pipes, indicating a high correlation. According to this result, it has been decided that the performance rating suggested herein can be applied naturally to the criterion of an improvement decision, which was based on Scoring System. From results of the research, it is expected that a reliable result can be provided to an improvement decision process related to degradation of plastic pipes by comprehensively comparing and evaluating a condition of pipe materials(direct factors) and an environmental impact(indirect factors).

• 대한기계학회논문집B
• /
• 제22권2호
• /
• pp.240-252
• /
• 1998

The purpose of this study is to develop a method for predicting the aerodynamic performance of the low speed airfoils in the 2-dimensional, steady and viscous flow. For this study, the airfoil geometry is specified by adopting the longest chord line system and by considering local surface curvature. In case of the inviscid incompressible flow, the analysis is accomplished by the linearly varying strength vortex panel method and the Karman-Tsien correction law is applied for the inviscid compressible flow analysis. The Goradia integral method is adopted for the boundary layer analysis of the laminar and turbulent flows. Viscous and inviscid solutions are converged by the Lockheed iterative calculating method using the equivalent airfoil geometry. The analysis of the separated flow is performed using the Dvorak and Maskew's method as the basic method. The wake effect is also considered by expressing its geometry using the formula of Summey and Smith when no separation occurs. The computational efficiency is verified by comparing the computational results with experimental data and by the shorter execution time.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.440-449
• /
• 2022

In recent years, the air pollution and Air Quality Index (AQI) has been a pivotal point for researchers due to its effect on human health. Various research has been done in predicting the AQI but most of these studies, either lack dense temporal data or cover one or two air pollutant elements. In this paper, a hybrid Convolutional Neural approach integrated with recurrent neural network architecture (CNN-LSTM), is presented to find air pollution inference using a multivariate air pollutant elements dataset. The aim of this research is to design a robust and real-time air pollutant forecasting system by exploiting a neural network. The proposed approach is implemented on a 24-month dataset from Seoul, Republic of Korea. The predicted results are cross-validated with the real dataset and compared with the state-of-the-art techniques to evaluate its robustness and performance. The proposed model outperforms SVM, SVM-Polynomial, ANN, and RF models with 60.17%, 68.99%, 14.6%, and 6.29%, respectively. The model performs SVM and SVM-Polynomial in predicting O3 by 78.04% and 83.79%, respectively. Overall performance of the model is measured in terms of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE).

• 한국건축시공학회지
• /
• 제23권1호
• /
• pp.103-111
• /
• 2023

건설 프로젝트의 초기단계에서 공사비를 정확하게 예측하는 것은 프로젝트를 성공적으로 수행하기 위해 매우 중요하다. 본 연구에서는 ANFIS 모델을 활용하여 건설프로젝트의 초기단계에 건축공사비를 예측할 수 있는 모델을 제시하였다. 모델의 활용도를 높이기 위해 공개된 공사비 데이터를 활용하였으며 프로젝트 초기단계의 제한된 정보를 바탕으로 예측할 수 있는 모델을 제시하고자 하였다. ANFIS와 관련된 기존 연구를 분석하여 최근의 동향을 파악하였으며 ANFIS의 기본 구조를 고찰한 후 건축공사비 예측을 위한 ANFIS 모델을 제시하였다. ANFIS의 모델의 소속함수의 종류와 개수에 따라 달라지는 예측 성능을 분석하여 가장 성능이 우수한 모델을 제시하였으며, 대표적인 기계학습 모델의 예측 정확도와 비교분석하였다. 적용결과 ANFIS 모델을 다른 기계학습 모델과 비교한 결과 동등 이상으로 성능을 나타내 프로젝트 초기단계 공사비 예측에 적용 가능할 것으로 판단된다.

• 한국공간정보시스템학회 논문지
• /
• 제8권1호
• /
• pp.17-25
• /
• 2006

TPR*-트리는 효과적으로 이동 객체의 미래 위치 예측을 수행하기 위하여 가장 널리 사용되는 인덱스 구조이다. 그러나 TPR*-트리는 인덱스 생성 이후 미래 예측 시점이 증가함에 따라 사장 영역과 영역중복의 문제가 커지며, 이로 인하여 질의 처리 시 액세스되는 TPR*-트리 노드들의 수가 많아지는 성능 문제가 발생한다. 본 논문에서는 실험을 통하여 이러한 성능 저하의 문제점을 정량적으로 규명한다. 먼저, 미래 예측 시점이 증가함에 따라 질의 처리 성능이 얼마나 저하되는가를 보이고, 이동 객체의 위치 갱신 연산이 이러한 성능 저하 문제를 얼마나 완화시키는가를 보인다. 이러한 공헌은 TPR*-트리의 추가적인 성능 개선을 위한 정책을 고안하는데, 중요한 실마리를 제공할 수 있을 것이다.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.3-17
• /
• 2007

This paper provides an introduction to life-span simulation and numerical approach to support the performance design processes of reinforced concrete structures. An integrated computational system is proposed for life-span simulation of reinforced concrete. Conservation of moisture, carbon dioxide, oxygen, chloride, calcium and momentum is solved with hydration, carbonation, corrosion, ion dissolution. damage evolution and their thermodynamic/mechanical equilibrium. Coupled analysis of mass transport and damage mechanics associated with steel corrosion is presented for structural performance assessment of reinforced concrete. Multi-scale modeling of micro-pore formation and transport phenomena of moisture and ions are mutually linked for predicting the corrosion of reinforcement and volumetric changes. The interaction of crack propagation with corroded gel migration can also be simulated. Two finite element codes. multi-chemo physical simulation code (DuCOM) and nonlinear dynamic code of structural reinforced concrete (COM3) were combined together to form the integrated simulation system. This computational system was verified by the laboratory scale and large scale experiments of damaged reinforced concrete members under static loads, and has been applied to safety and serviceability assessment of existing structures. Based on the damage details predicted by the nonlinear finite element analytical system, the life-span-cost of RC structures including the original construction costs and the repairing costs for possible damage during the service life can be evaluated for design purpose.

• International Journal of Computer Science & Network Security
• /
• 제24권7호
• /
• pp.11-23
• /
• 2024

Triage is a practice of accurately prioritizing patients in emergency department (ED) based on their medical condition to provide them with proper treatment service. The variation in triage assessment among medical staff can cause mis-triage which affect the patients negatively. Developing ED triage system based on machine learning (ML) techniques can lead to accurate and efficient triage outcomes. This study aspires to develop a triage system using machine learning techniques to predict ED triage levels using patients' information. We conducted a retrospective study using Security Forces Hospital ED data, from 2021 through 2023 during Hajj period in Saudia Arabi. Using demographics, vital signs, and chief complaints as predictors, two machine learning models were investigated, naming gradient boosted decision tree (XGB) and deep neural network (DNN). The models were trained to predict ED triage levels and their predictive performance was evaluated using area under the receiver operating characteristic curve (AUC) and confusion matrix. A total of 11,584 ED visits were collected and used in this study. XGB and DNN models exhibit high abilities in the predicting performance with AUC-ROC scores 0.85 and 0.82, respectively. Compared to the traditional approach, our proposed system demonstrated better performance and can be implemented in real-world clinical settings. Utilizing ML applications can power the triage decision-making, clinical care, and resource utilization.

• 한국안전학회지
• /
• 제8권3호
• /
• pp.3-12
• /
• 1993

In reciprocating internal combustion engine, engine performance Is greatly affected by volumetric efficiency. For gas flow, the dynamic effects caused by the pressure pulsation have influence on the volumetric efficiency and correlate to the configuration and pipe length of intake-exhaust system. In this study, the analytic investigation of the unstudy flow In exhaust pipe has been carried out by using the method of characteristics to predict volumetric efficiency. In conculusion, it is possible to take account of the exhaust pipe tuning effect in predicting the engine performance, by the analytic solution of the unsteady flow in the pipes, and comparision of prediction with experimental datas show a good agreement on the pressure varision in the exhaust pipe which has Influence on the volumetric efficiency and performance of engine.

• 한국자동차공학회논문집
• /
• 제9권4호
• /
• pp.10-17
• /
• 2001

The performance of a radiator is generally determined using a wind tunnel, in which the air velocity is uniform. However, when it is installed in a car, the distribution of the air velocity becomes nonuniform due to front-end openings, cross members, and horns etc., resulting in lower performance. In this study, several underhood flow simulations have been first performed to get flow rates and velocity distributions over the radiator. Secondly heat release rates are calculated by both a performance curve and a radiator model. Finally, using an engine cooling system simulator, radiator-top-tank temperature is predicted and the variations of heat release rate and radiator-top-tank temperature with nonuniformity of air velocity distributions are analyzed. The results show that the current engine cooling model successfully accounts for the nonuniformity effects that should be considered for higher accuracy in predicting engine cooling performance.