• 한국시뮬레이션학회논문지
• /
• 제26권3호
• /
• pp.13-22
• /
• 2017

본 연구는 시뮬레이션을 진행하면서 그 결과를 실시간으로 시각화하는 경우에 파이프라이닝 병렬처리 기법을 적용하여 성능을 개선할 수 있음을 보인다. 일반적으로 실시간 시각화를 포함한 시뮬레이션에서는 모델을 실행하는 프로세스와, 시뮬레이션 결과를 시각화 도구로 전송하는 프로세스, 결과를 받아서 시각화 하는 3개의 프로세스가 있다. 만약 이 프로세스들을 직렬화해서 실행하면 전체 실행시간이 매우 길어져서 시각화의 성능이 저하될 수밖에 없다. 본 연구에서는 기존의 직렬 방식 대신에 파이프라이닝 병렬처리 기법을 적용하여 성능을 개선하고자 한다. 추가적으로 각 프로세스에 다중 스레드 기능을 더하여 더 큰 성능의 개선이 있음을 보인다. 이를 위해 본 논문은 제안된 기법에 대한 이론적 성능모델을 세우고 최대, 최소 성능 향상 조건을 이론적으로 해석하였으며 모의실험하였다. 이 이론을 바탕으로 실시간으로 시각화하는 실시간 공중전 시뮬레이션에 적용한 결과 기존의 직렬화된 실행 성능보다 제안된 이론을 적용한 후의 실행 성능이 크게 향상되었음을 보였다.

• International journal of advanced smart convergence
• /
• 제11권1호
• /
• pp.19-27
• /
• 2022

Across the world, 'housing' comprises a significant portion of wealth and assets. For this reason, fluctuations in real estate prices are highly sensitive issues to individual households. In Korea, housing prices have steadily increased over the years, and thus many Koreans view the real estate market as an effective channel for their investments. However, if one purchases a real estate property for the purpose of investing, then there are several risks involved when prices begin to fluctuate. The purpose of this study is to design a real estate price 'return rate' prediction model to help mitigate the risks involved with real estate investments and promote reasonable real estate purchases. Various approaches are explored to develop a model capable of predicting real estate prices based on an understanding of the immovability of the real estate market. This study employs the LSTM method, which is based on artificial intelligence and deep learning, to predict real estate prices and validate the model. LSTM networks are based on recurrent neural networks (RNN) but add cell states (which act as a type of conveyer belt) to the hidden states. LSTM networks are able to obtain cell states and hidden states in a recursive manner. Data on the actual trading prices of apartments in autonomous districts between January 2006 and December 2019 are collected from the Actual Trading Price Disclosure System of the Ministry of Land, Infrastructure and Transport (MOLIT). Additionally, basic data on apartments and commercial buildings are collected from the Public Data Portal and Seoul Metropolitan Government's data portal. The collected actual trading price data are scaled to monthly average trading amounts, and each data entry is pre-processed according to address to produce 168 data entries. An LSTM model for return rate prediction is prepared based on a time series dataset where the training period is set as April 2015~August 2017 (29 months), the validation period is set as September 2017~September 2018 (13 months), and the test period is set as December 2018~December 2019 (13 months). The results of the return rate prediction study are as follows. First, the model achieved a prediction similarity level of almost 76%. After collecting time series data and preparing the final prediction model, it was confirmed that 76% of models could be achieved. All in all, the results demonstrate the reliability of the LSTM-based model for return rate prediction.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.433-433
• /
• 2000

In this paper, we propose a development of internet teleoperation method applying QoS model, which has the real time control capability and the time-delay predicting capability, The QoS model gives a constant bandwidth to a specified application and makes the dynamically irregular time-delay to be predictable and fined so that it can have real-time capability.

• 대한의용생체공학회:의공학회지
• /
• 제6권1호
• /
• pp.55-64
• /
• 1985

The cardiac activation process using three dimensional ventricular model is simulated.To study this theme, we constructed a cardiac ventricular model and simulated the cardiac activation process using the action potential duration and the activation time. The cardiac ventricular model is generated by the logical combination of the elliptic equations. The action potential duration could be obtained from the fact that it is linearly distributed between model cells. The cardiac activation process was simulated by the law of "all-or-none" Based on the activation time and the action potential do-ration the cardiac potential at the arbitrary time after the activation of the model cell was computed. To test the validity of model, the comparison of the results of model simulation with the physiological data was performed. In conclusion, this model shows the simular results which is comparable to the real conduction of the cardiac excitation.xcitation.

• 산업기술연구
• /
• 제23권A호
• /
• pp.41-46
• /
• 2003

Because the quality of a radio link in real environment is generally varied with time, there is a difference between the delay in the real environment and one obtained from the analytic model where a time-varying link model is not used as a link model for a Bluetooth. This paper analyzes the transmission delay of a message in the time-varying radio link model for the Bluetooth. The time-varying radio link is modeled with a two-state Markov model. The mean transmission delay of the message is analytically obtained in terms of the arrival rate of the message, the state transition probability in the Markov model, and the packet error rate.

• 경영과학
• /
• 제21권3호
• /
• pp.101-113
• /
• 2004

In the rapidly propagating Internet based electronic transaction environment. the importance of real time order confirmation has been more emphasized, In this paper, using data mining techniques, we develop intelligent operations decision model to allow real time order confirmation at the time the customer places an order with required delivery terms. Among various operation plannings used for order fulfillment. mill routing is the first interface decision point to link the order receiving at the marketing with the production planning for order fulfillment. Though linear programming based mathematical optimization techniques are mostly used for mill routing problems, some early orders should wait until sufficient orders are gathered for optimization. And that could effect longer order fulfillment lead-time, and prevent instant order confirmation of delivery terms. To cope with this problem, we provide the intelligent decision model to allow instant order based mill routing decisions. Data mining techniques of decision trees and neural networks. which are more popular in marketing and financial applications, are used to develop the model. Through diverse computational trials with the industrial data from the steel company. we have reported that the performance of the proposed approach is effective compared to the present heuristic only mill routing results. Various issues of data mining techniques application to the mill routing problems having linear programming characteristics are also discussed.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2001년도 Proceedings ICPE 01 2001 International Conference on Power Electronics
• /
• pp.546-551
• /
• 2001

This paper considers the design technique of the real-time control algorithm to implement the electronic interlocking system which is the most important station control system in railway signal field. The proposed technique consists of the structure design and the detail design which are based on the ROOM(Real-Time Object-Oriented Modeling) This proposed technique is applied to the typical station model in order to prove the validity as verifying the performance of the modeled station.

• 한국지진공학회논문집
• /
• 제15권5호
• /
• pp.11-24
• /
• 2011

고정반복법에 의한 암시적 HHT 시간적분법을 이용하여 3층 3경간 철근콘크리트 골조구조물을 수치해석모형과 물리적 분구조모형으로 나누어 실시간 하이브리드실험을 실시하였다. 물리적 부분구조모형으로는 1층 내부 비연성기둥 1개소가 선택되었고, 수치해석모형에 일축 방향의 지진하중을 시편이 심한 손상에 의하여 파괴에 이를 때까지 작용시켰다. 비선형 유한요소해석 프로그램인 Mercury가 실시간 하이브리드실험을 위하여 새로이 개발 및 적용되었다. 실험결과는 물리적 부분구조모형의 상부 수평방향 층간변위비를 OpenSees에 의한 수치해석시뮬레이션과 진동대실험의 그것과 비교하였다. 본 실험은 가장 복잡한 실시간 하이브리드실험 중의 하나이고, 하드웨어, 알고리즘 그리고 모형에 대한 기술적인 내용을 본 논문에 자세히 설명하였다. 수치해석모형의 개선, 물리적 부분구조 모형 접선강성행렬의 유한요소해석 프로그램에서의 평가 그리고 하중기반 보-요소의 요소상태결정의 연산시간을 줄이기 위한 소프트웨어의 개선이 이루어진다면 실시간 하이브리드실험과 진동대실험결과의 비교는 권장할 만하다. 그리고 "지진과 같은 동적하중하의 복잡한 구조물의 수치해석시뮬레이션"이라는 목적을 위하여 실시간 하이브리드실험은 동적하중에 대한 실험적 검증을 점진적으로 수치해석모형으로 대체하기 위한 저비용-고효율 실험법으로서의 가치를 충분히 가지고 있다고 할 수 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.535-538
• /
• 2005

Today, most fixed-wing aircrafts are equipped with the antiskid brake system. It can modulate braking moments in the wheels optimally, when an aircraft is landing. So it can reduce landing distance and increase safeties. The antiskid brake system for an aircraft are mainly composed of braking moment modulators (hydraulic control valves) and brake control unit. In this paper, a Mark IV type - fully digital - brake controller is studied. For the development of its control algorithms, a 5-DOF (Degree of Freedom) aircraft landing model is composed in the form of matlab/simulink model at first. Then, braking moment control algorithms using wheel decelerations and slips are made. The developed algorithms are tested in software simulations using state-flow toolboxes in matlab/simulink model. Also, a real-time simulation systems are made, which use hydraulic brake systems of a real aircraft, pressure control valves and its controller as hardware components of HIL(Hardware In-the-Loop) simulation. Algorithms tested in software simulations are coded into the controller and the real-time landing simulations are made in very severe road conditions. The real-time simulation results are presented.

• 부동산연구
• /
• 제27권3호
• /
• pp.71-86
• /
• 2017

본 연구의 목적은 딥 러닝 방법을 부동산가격지수 예측에 적용해보고, 기존의 시계열분석 방법과의 비교를 통해 부동산 시장 예측의 새로운 방법으로서 활용가능성을 확인하는 것이다. 딥 러닝(deep learning)방법인 DNN(Deep Neural Networks)모형 및 LSTM(Long Shot Term Memory networks)모형과 시계열분석 방법인 ARIMA(autoregressive integrated moving average)모형을 이용하여 여러 가지 부동산가격지수에 대한 예측을 시도하였다. 연구결과 첫째, 딥 러닝 방법의 예측력이 시계열분석 방법보다 우수한 것으로 나타났다. 둘째, 딥 러닝 방법 중에서는 DNN모형의 예측력이 LSTM모형의 예측력보다 우수하나 그 정도는 미미한 수준인 것으로 나타났다. 셋째, 딥 러닝 방법과 ARIMA모형은 부동산 가격지수(real estate price index) 중 아파트 실거래가격지수(housing sales price index)에 대한 예측력이 가장 부족한 것으로 나타났다. 향후 딥 러닝 방법을 활용함으로써 부동산 시장에 대한 예측의 정확성을 제고할 수 있을 것으로 기대된다.