• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.8
• /
• pp.709-714
• /
• 2001

Recently, most vehicles has the Automatic transmission system as their transmission system. The automatic transmission system operates with fixed shift patterns. In the opposite of manual operation, it is easy and convenient for driving. Though these merit, the system can not evaluate the driver s intension because of usage of fixed shift pattern. To consider driver s intension, we must consider both the driving intensity of driver and the status of vehicle. In this paper, we developed flexible automatic transmission system by using the proposed moduled neural networks which can learn the status of th vehicle and driver s intensity. As a results, we compare the transmission system using fixed shift pattern and the proposed transmission system and show the good performance in the change of shift position.

• Journal of Korean Society of Transportation
• /
• v.21 no.1
• /
• pp.77-90
• /
• 2003

This paper explores the way and the extent to which drivers' route choice was influenced by uncertain information. In particular, this paper investigates the effect of qualitative information on route choice when drivers face a choice with different degrees of uncertain information. The SP survey was conducted and route choice legit models were estimated. We also applied Prospect Theory to the analysis of drivers' decision making under uncertain information. The main findings are firstly, drivers tend to prefer a route with information than(to) one without information. This indicated that providing charge information encouraged drivers to choose the routes for which information is provided in preference to those for which it is not provided. Secondly, drivers also prefer a route with a certain and precise information over one with uncertain and imprecise information. Thirdly, when the information is given as a range, the size of the range of the information influenced route choice slightly and as the range of the charge increases, the route becomes slightly less unattractive. Fourthly, when the information is given as a range, drivers' route choices are influenced more by the median value of the ranges than by the size of the overall ranges of the information. Application of Prospect Theory to the results explains the way drivers may be interpreting the choice situation and how they make a route choice in response to uncertain information. The results of this paper implicate that drivers' decision making under uncertainty seem to be very complicated and flexible, depending on the way drivers interpret the choice situation. Therefore, it is recommended to apply wider related theories to the analysis of the drivers' behaviour.

• Journal of Korean Society of Transportation
• /
• v.21 no.2
• /
• pp.7-16
• /
• 2003

To minimize the death and injury by a collision, the installation of an air bag is recommended as a mandatory practice together with the wearing of the seat belt. By using simulated collision experiments, this research focused on the effect of an air bag and seat belt on the driver safety. The vehicle deceleration characteristics were obtained from impact experiment. LSDYNA, a software program for vehicle collision analysis, and MADYMO. a software program for driver motion after collision, were used for simulated experiment. Four cases such as air bag installed and seat belt wearing (case A), air bag installed but seat belt not wearing (case B), air bag not installed but seat belt wearing (case C), air bag not installed and seat belt not wearing (case D) were analyzed. The impact of acceleration on the injury of driver's head was analyzed by Head Injury Criterion (HIC) as well. It was found that having air bag and wearing seat belt effectively reduced driver's head injury about 52.9% to 70.5% compared with the case of having neither air bag nor wearing seat belt.

• Journal of Korean Society of Transportation
• /
• v.29 no.5
• /
• pp.7-17
• /
• 2011

Traffic problems caused by drunk drivers have been steadily raised from the past. Even though the previous researches have focused on the development of countermeasures for preventing drunk driving, the number of drivers violating the DUI (Driving-Under-Influence) regulation is still increasing. Many studies seek countermeasures for preventing drunk driving by comparing the differences between general and drunk drivers. However, few researches have investigated focusing only on the characteristics of drunk drivers. It is well known that characteristics of general drivers are different from those of drunk drivers, and also habitual drunk drivers have different characteristics from non-habitual drunk drivers. Motivated by this fact, only the drivers who have violated DUI regulation are considered in the analysis. This study primarily aims to provide alternative solutions for reducing habitual drunk drivers who are highly inclined to do drunk driving repeatedly. For the analysis, various types of variables potentially effecting drunk driving behavior were investigated, and then truncated count data models were developed to analyze the effects of the variables selected on drunk driving. The results showed that 1) a truncated negative binomial model is better fitted to the data; and 2) five variables including experiential learning, the lack of self-control, self-reflection, the fear of crackdown, and the level of dependence on vehicles were found to be statistically significant.

• Journal of Korean Society of Transportation
• /
• v.35 no.6
• /
• pp.545-556
• /
• 2017

Various assessment indexes have been developed and utilized to evaluate the driver workload. However, existing workload assessment indexes do not fully reflect driving habits and driving patterns of individual drivers. In addition, there exists significant differences in the amount of workload experienced by a driver and the ability to overcome the driver's workload. To overcome these limitations associated with existing indexes, this study has developed a novel workload assessment index to reflect an individual driver's driving pattern. An average of the absolute values of the steering velocity for each driver are set as a threshold value in order to reflect the driving patterns of individual drivers. Further, the sum of the areas of the steering velocities exceeding the threshold value, which is defined as erratic steering area (ESA) in this study, was quantified. The developed ESA index is applied in evaluating the driver workload of manually driven vehicles in automated vehicle platooning environments. Driving simulation experiments are conducted to collect drivers' responsive behavior data which are used for exploring the relationship between the NASA-TLX score and the ESA by the correlation analysis. As a result, ESA is found to have the greatest correlation with the NASA-TLX score among the various driver workload evaluation indexes in the lane change scenario, confirming the usefulness of ESA.

• Science of Emotion and Sensibility
• /
• v.20 no.1
• /
• pp.115-132
• /
• 2017

Differences in reaction time and accuracy were compared among driver groups of middle-, old-, and stroke old-age drivers using various reaction time tasks including simple reaction task, 2-choice task, 4-choice task with different stimuli eccentricity, search task, and moving target detection task. The results can be summarized as followings. First, although overall reaction time tended to be slowed with age and stroke, stroke old drivers showed significantly slower reaction time than the other driver groups when the stimuli were presented in a large eccentricity. Second, differences in reaction time for 2-choice task and moving target detection task seemed to be determined mainly by participants' simple reaction time. Third, the search task which required temporary retention of previously presented stimuli was found to be more sensitive in discriminating difference in reaction time between middle-age drivers and old-age drivers (including stroke old drivers). Fourth, reaction accuracy of old (and stroke old) drivers decreased when more stimuli alternatives were presented and temporary retention for stimuli was required. Altogether, memory demand in reaction time task can be sensitive to evaluate performance for different age groups, whereas size of useful field of view for brain stroke.

• Korean Journal of Culture and Social Issue
• /
• v.12 no.1
• /
• pp.55-79
• /
• 2006

This study is interested in aberrant driver behaviour. The aim of this study is to investigate the effect of error and lapse on driving behaviour of elderly drivers. In order to estimate the errors and lapses, 'Driver Behaviour Questionnaire(DBQ) was used and tested with 883 drivers. Among them 175 of young drivers(younger than 25) and 150 of elderly drivers(older than 65) answered their driving patterns; driving history, annual mileage, the frequency of committing traffic violation, and experience of accident within 5 years. Elderly driver's data were collected by face to face interview. The factors of aberrant driver behaviour were analyzed and the DBQ score was compared by the age. The aberrant driver behaviour was consisted of 3 factors; violations, errors and lapses. Elderly driver's DBQ score was lower than young driver's. Elderly and young drivers showed longer driving history. were in low DBQ score group. Elderly drivers had high error score and young drivers had high violation score. Young driver's aberrant driving behaviour was associated with annual mileage, the frequency of committing traffic violation. Elderly driver's aberrant driving behaviour was associated with annual mileage, experience of accident. Specially elderly drivers, whose violation, error, lapse score was high answered more committing experience of accident within 5 years.

• Electronics and Telecommunications Trends
• /
• v.28 no.4
• /
• pp.45-52
• /
• 2013

차량용 증강현실 기술은 운전자의 신체적 인지적 부하를 최소화함으로써 운전자의 안전과 편의를 달성하기 위한 목적으로 차량에서 제공되는 정보를 운전자의 시야에 맞게 운전자 전방 실세계에 정합하여 제공하는 기술이다. 최근 차량의 지능화와 증강현실기술 접목의 다양화 및 디스플레이 기술의 급진한 발전으로 차량용 HUD(Head Up Display)기술 개발이 활발히 이루어지고 있다. 특히 최근에는 국내외 자동차 제조사 및 연구기관을 중심으로 AR(Augmented Reality)기술을 차량용 HUD에 접목한 AR-HUD 기술 개발이 진행 중이다. 본고에서는 이러한 배경을 토대로 차량용 HUD 기술 및 차량용 AR 기술의 개발 현황과 관련 이슈에 관하여 살펴보고자 한다.

• Proceedings of the Korean Reliability Society Conference
• /
• 2001.06a
• /
• pp.479-486
• /
• 2001

일시적인 행사, 도로공사 또는 교통사고로 인해 도로용량이 저하되거나 도로가 폐쇄되는 경우, 운전자들은 당초 자신이 원하는 시간에 목적지에 도달하지 못함에 따라 스케쥴 지체를 경험하게 된다. 이는 교통망의 신뢰성이 저하됨으로서 발생하는 것으로 이들 비 반복적인 혼잡요소들을 운전자의 경로선택행위에 포함시킬 필요가 있다. 이런 측면에서 본 연구에서는 기존 교통분야에서 소홀히 다루었던 신뢰성이라는 개념을 운전자 행태모형에 도입하는 방안을 제시코자 한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.7-10
• /
• 2008

자동차의 수가 점점 증가함에 따라 교통사고도 그 만큼 증가하고 있다. 교통사고의 주요 원인 중 하나가 졸음운전이나 부주의한 운전에 의한 것이다. 따라서 Real-Time으로 운전자의 제스처를 인식하여 졸음운전이나 부주의에 의한 사고를 사전에 예방하여 보다 안전한 운전을 돕는 서비스가 필요시 되고 있다. 본 논문에서는 운전자의 제스처 인식에 전처리 과정으로 운전자의 상반신에 대한 영상데이터에서 Adaboost를 이용하여 복잡한 배경과 다양한 환경에서 강인하게 얼굴 영역을 찾는 알고리즘을 소개한다.