• 디지털콘텐츠학회 논문지
• /
• 제15권5호
• /
• pp.579-586
• /
• 2014

본 논문은 문맥-자유 문법 (context-free grammar)를 이용하여, 차선변경 상황에서의 운전자의 행동패턴 인식을 하는 방법을 제안하는 것을 목표로 한다. 문맥-자유-문법은 기존 패턴인식 방식과는 대조적으로 유한적 기호로는 쉽게 표현될 수 없는 특징들을 비교적 손쉽게 표현할 수 있다. 이 방식을 적용하여, 동시에 여러 특징을 각각 고려해야 하는 좌표기반 데이터 처리 대신 심볼 시퀀스 방식 (symbolic sequence)을 패턴화하기 위해 구문론적 방식을 적용한다. 이 방법은 운전자와 안전 운전 분야 연구자들에게 효율적이고 보다 직관적인 방법으로 보다 더 효과적인 수행에 도움이 된다. 본 연구의 향후과제로 보다 안정적인 인식률을 획득하기 위해 확률적 구문분석 방법을 적용할 계획이다.

• 실천공학교육논문지
• /
• 제5권2호
• /
• pp.169-176
• /
• 2013

최근 시뮬레이션 환경 구축은 모든 분야에 걸쳐서 중요한 이슈로 떠오르고 있다. 특히 비행기나 우주선과 같은 한 번 작동 하는데 많은 비용이 드는 기기의 훈련일 경우, 실제 기기와 같은 환경을 시뮬레이터로 구축하여 놓음으로써 막대한 비용의 절감과 함께, 실전에서와 같은 훈련 효과를 가져올 수가 있다. 이에 우리는 일반 운전학원에서 운전 면허 획득을 위한 연습시 차량의 부족과 많은 인원으로 인해 대기 시간이 많이 지연되고 있음에 착안하여, 운전 연습에 맞는 시뮬레이터를 개발한다. 운전 연습에 적합한 시뮬레이터인 3D 레이싱 게임에 착안하여, 운전 면허 실습을 위한 컴퓨터 3D시뮬레이션 모델을 제안하고, 이를 사용하여 사람들이 실제 운행을 하는 것처럼 핸들을 조작하는 시뮬레이션 환경을 제공한다. 본 논문은 컴퓨터 3D 시뮬레이션을 활용하여 운전 연습 모델을 모델링하고, 이 모델링을 사용하여 시뮬레이터를 제작하여 활용하는 것에 관한 연구이다.

• 한국안전학회지
• /
• 제27권3호
• /
• pp.167-175
• /
• 2012

For establishing a standard of design element of the smart highway, this study investigated driver's anxiety EEG according to running speeds and geometric designs. Also, the experiment was implemented on 60 subjects. Based on running speed data and brainwave data, which were obtained from the experiment, this study analyzes anxiety EEG according to running speeds and geometric designs, and finally draws a forecasting model of anxiety EEG by selecting affecting factors of anxiety EEG. Forecasting model shows that left curve is the most influential on anxiety EEG figure. The reason is because when driver is driving on the first-lane, his or her visibility is impeded by a median strip. For this reason, anxiety EEG figure increases. And also steep downward slope and large radius of curve are heavily influential on driver's anxiety EEG figure. It is judged that anxiety EEG figure is increased by high speed on those section. Thus, the forecasting model of anxiety EEG suggested on this study will be utilized for design phase, and will decide the design speed on the superhighway. So, it will be used to make practical and safety road.

• 디지털융복합연구
• /
• 제19권4호
• /
• pp.25-31
• /
• 2021

고령화 시대에 따라 고령운전자 역시 증가하고 있으며, 이들에 의한 교통사고 심각성에 대한 관심이 높아지고 있다. 이에 고령운전자에 의한 사고심각도 예측 모형의 필요성이 점차 요구됨에 따라, 본 연구에서는 기계학습 기법을 활용하여 고령운전자에 의한 차대사람 사고심각도 예측을 위한 모형 정립 및 분석을 수행하고자 한다. 이를 위해 4개의 기계학습 알고리즘 (Logistic Model, KNN, RF, SVM)을 활용, 예측 모형을 개발하고 각 결과를 비교하였다. 연구 결과에 따르면 Logistic과 SVM 모형이 상대적으로 높은 예측력을 보였으며, 정확도 측면에서는 RF가 높은 것으로 나타났다. 추가적으로 각 중요 변수들을 이용하여 교차분석을 수행한 후 그 결과를 제시하였다. 본 연구의 결과들은 고령화시대에 고령운전자에 의한 사고심각성을 예방하기 위한 안전정책 및 인프라 개발에 활용될 것으로 판단된다.

• 한국자동차공학회논문집
• /
• 제15권5호
• /
• pp.180-187
• /
• 2007

This paper presents a mathematical vehicle model that is designed to analyze the dynamic performance and to develop various safety control systems. Wheel slip controllers for ABS is also formulated to improve the vehicle response and to increase the safety on slippery road. Validation of the model and controller is performed by comparison with a commercial software package, CarSim. The result shows that performances of developed vehicle model are in good accordance with those of the CarSim on various driving conditions. Developed ABS controller is applied to the vehicle model and CarSim model, and it achieves good control performance. ABS controller improves lateral stability as well as longitudinal one when a vehicle is in turning maneuver on slippery road. A driver model is also designed to control steer angle of the vehicle model. It also shows good performance because the vehicle tracks the desired lane very well.

• Nuclear Engineering and Technology
• /
• 제49권5호
• /
• pp.1063-1070
• /
• 2017

This paper presents a method for forecasting future uranium prices that is used as input data to calculate the uranium cost, which is a rational key cost driver of the nuclear fuel cycle cost. In other words, the statistical autoregressive integrated moving average (ARIMA) model and existing engineering cost estimation method, the so-called escalation rate model, were subjected to a comparative analysis. When the uranium price was forecasted in 2015, the margin of error of the ARIMA model forecasting was calculated and found to be 5.4%, whereas the escalation rate model was found to have a margin of error of 7.32%. Thus, it was verified that the ARIMA model is more suitable than the escalation rate model at decreasing uncertainty in nuclear fuel cycle cost calculation.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.511-514
• /
• 2005

This paper propose an advanced control strategy to improve vehicle handling and directional stability by integrating Active Front Steering(AFS) with Electronic Stability Program(ESP) . The effect of the integrated control system on the vehicle handling characteristics and directional stability is studied through a close loop computer simulation of and eight degree of freedom nonlinear vehicle model and driver model. Simulation results confirm the effectiveness of the proposed control system and the overall improvements in vehicle handling and directional stability

• 한국정보전자통신기술학회논문지
• /
• 제6권4호
• /
• pp.249-254
• /
• 2013

In the area of computer vision, face recognition is being intensively researched. It is generally known that before a face is recognized it must be localized. Skin-color information is an important feature to segment skin-color regions. To extract skin-color regions the skin-color model based on multi-layer perceptron has been proposed. Extracted regions are analyzed to emphasize ellipsoidal regions. The results from this study show good accuracy for our vehicle driver face detection system.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.144-152
• /
• 2017

Among the technologies for implementing autonomous vehicles, advanced driver assistance system is a key technology to support driver's safe driving. In the technology using the vision sensor having a high utility, various preprocessing methods are used prior to feature extraction for lane detection. However, in the existing methods, the unnecessary lane candidates such as cars, lawns, and road separator in the road area are false positive. In addition, there are cases where the lane candidate itself can not be extracted in the area under the overpass, the lane within the dark shadow, the center lane of yellow, and weak lane. In this paper, we propose an efficient preprocessing method using k-means clustering for image division and the HSV color model. When the proposed preprocessing method is applied, the true positive region is maximally maintained during the lane detection and many false positive regions are removed.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2003년도 추계학술대회논문집
• /
• pp.72-77
• /
• 2003

In this paper, an experimental verification of system identification technique for constructing finite element model is conducted for a three-story test structure equipped with an active mass driver (AMD). Twenty Gaussian white noises were used as the input for AMD, and the corresponding accelerations of each floors are measured. Then, the complex frequency response function (FRF) for the input, the force induced by the AMD, was obtained and subsequently, the Markov parameters and system matrices were estimated. The magnitudes as well as phase of experimentally obtained FRFs match well with those of analytically obtained FRFs.