• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.259-260
• /
• 2024

졸음운전으로 인한 교통사고는 매년 꾸준하게 일어나 이에 대한 다방면의 해결책이 요구되고 있다. 본 논문에서는 위 문제를 개선하고자 ChatGPT와 영상처리를 이용한 졸음 감지 시스템을 구현하였다. 이 시스템은 운전자의 얼굴 부분을 영상처리로 인식하여 눈동자의 종횡비를 구해 PERCLOS 공식에 따른 운전자의 졸음을 판별시키고, 경고와 동시에 ChatGPT가 운전자에게 특정 주제를 키워드로 TTS와 STT를 통해 대화한다. 운전자의 졸음을 판별하기 위해 임베디드 보드에서 연결된 캠을 통해 졸음 판별을 하고, ChatGPT도 마찬가지로 보드에서 연결한 스피커, 마이크를 통해 운전자와 대화한다. 이를 활용하여 운전자의 졸음 자각을 통한 안전운전 및 사고 발생률의 감소를 기대할 수 있다.

• Korean Journal of Culture and Social Issue
• /
• v.18 no.3
• /
• pp.415-433
• /
• 2012

This study was conducted in order to explain the effect of driving behavior determinants such as drivers' personality and attitude that may induce risky driving behavior and to develop a valid method for discriminating risky drivers using the determinants. In the results of surveying 534 adult drivers, 5 driving behavior determinants (avoidance of problems, benefit/stimulus seeking, interpersonal anxiety, interpersonal anger, and aggression) were found to have a statistically significant effect on drivers' various risky driving behaviors. Using these factors, drivers were grouped according to risk levels (normal drivers, unintentionally risky drivers, and intentionally risky drivers). This result suggests that drivers' dangerous behavior level can be predicted using psychological factors such as their personality and attitude. Accordingly, if the driving behavior determinant model and the base score system used in this study are improved through further research, they are expected to be useful in predicting drivers' recklessness in advance, identifying problems, and providing differentiated safe driving education services based on the results.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.1
• /
• pp.1-15
• /
• 2016

This study aims to develop a model by which city bus drivers who are likely to cause an accident can be figured out based on the information about their actual driving records. For this purpose, from the information about the actual driving records of the drivers who have caused an accident and those who have not caused any, significance variables related to traffic accidents are drawn, and the accuracy between models is compared for the classification models developed, applying a discriminant analysis and logistic regression analysis. In addition, the developed models are applied to the data on other drivers' driving records to verify the accuracy of the models. As a result of developing a model for the classification of drivers who are likely to cause an accident, when deceleration ($X_{deceleration}$) and acceleration to the right ($Y_{right}$) are simultaneously in action, this variable was drawn as the optimal factor variable of the classification of drivers who had caused an accident, and the prediction model by discriminant analysis classified drivers who had caused an accident at a rate up to 62.8%, and the prediction model by logistic regression analysis could classify those who had caused an accident at a rate up to 76.7%. In addition, as a result of the verification of model predictive power of the models showed an accuracy rate of 84.1%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.75-77
• /
• 2021

다양한 원인으로 매년 수많은 사람이 교통사고로 목숨을 잃거나 크게 다치곤 한다. 최근 교통사고 통계자료에 따르면 졸음운전으로 인한 교통사고가 음주운전이나, 과속보다도 높은 비중을 차지하고 있었다. 또한, 사고가 났을 때 안전벨트를 매지 않은 운전자나 동승객은 부상 정도가 훨씬 심각한 것으로 알려져 전 좌석에 안전벨트를 꼭 착용해야 하는 법도 제정되었다. 그런데도 많은 운전자 및 동승자가 안전벨트를 착용하지 않아 크게 부상을 당하는 사고는 줄지 않고 있다. 이러한 사고와 부상을 줄이기 위하여 본 논문에서는 다중 네트워크를 이용하여 운전자의 졸음 감지 및 운전자, 동승자의 안전벨트 착용 여부까지 실시간으로 판별하는 시스템을 설계하고 구현한다.

• Journal of Korean Society of Transportation
• /
• v.28 no.6
• /
• pp.147-158
• /
• 2010

Studies on the distribution of traffic demands have been proceeding by providing traffic information for reducing greenhouse gases and reinforcing the road's competitiveness in the transport section, however, since it is preferentially required the extensive studies on the driver's behavior changing routes and its influence factors, this study has been developed a discriminant model for changing routes considering driving conditions including traffic conditions of roads and driver's preferences for information media. It is divided into three groups depending on driving conditions in group classification with the CART analysis, which is statistically meaningful. And, elements of the driving conditions and the preferred media affecting the change of paths are classified into statistical meaningful groups through the CHAID analysis, and the major factors affecting the change of paths are examined. Finally, the extent that driving conditions and preferred media affect a route change is examined through a discriminant analysis, and it is developed a discriminant model equation to predict a route change. As a result of building the discriminant model equation, it is shown that driving conditions affect a route change much more, the entire discriminant hit ratio is derived as 64.2%, and this discriminant equation shows high discriminant ability more than a certain degree.

• International Journal of Highway Engineering
• /
• v.10 no.2
• /
• pp.101-113
• /
• 2008

VMS are installed in many Korean highways in oder to give drivers informations such as travel time to destination, congestion and Incident situation. However, some guidelines for install VMS are restricted in only geometric factors although human factors considering driver behavior are very important to affect the VMS installation. Therefore, this paper are focusing on developing and verifying the discriminant model for VMS installation considering human factors. As a result, following outputs are obtained ; (1) developing the discriminant model using human factors of driving simulation experiments in oder to predict driver reading VMS messages safely detour highway. (2) proving that driving experiences in highway, personal driving history, vehicle speed orderly affects VMS installation (3) verifying predictability of developed model by comparing the real values with predicted values. (4) suggesting that VMS should be installed off 3.2Km from the I.C. of rural highway.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1228-1229
• /
• 2023

현대 도시 모빌리티의 중요한 구성 요소로 자리 잡은 전동킥보드는 편리한 이동 수단으로 인기를 얻고 있으나, 이에 따른 안전사고 증가로 운전자와 보행자의 안전이 심각하게 위협받고 있다. 본 논문에서는 전동킥보드 운전 중에 발생한 사고의 원인을 객관적으로 분석하고, 사고가 운전자의 부주의로 인한 것인지를 판별하며, 이로 인한 배상 책임을 정확하게 결정하기 위한 모델을 제안한다. 운전 중 수집된 센서 데이터를 활용하여 Deep SVDD (Deep Support Vector Data Description) 모델을 구축하고, 이상치 탐지를 통해 운전 패턴을 분류하며 운전자의 부주의로 인한 사고를 파악한다. 이를 통해, 정확하고 공정한 배상 책임 판단을 지원하며, 도시 모빌리티 분야에서 안전사고 감소에 기여할 것으로 기대된다.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1234-1239
• /
• 2006

신속하고 정확한 교통정보 서비스의 제공은 원활한 교통소통을 위하여 필수적인 요소이다. 특히, 교통사고, 도로보수 그리고 자연재해와 같은 유고가 발생할 경우, 운전자에게 즉시 통보해주어 우회할 수 있도록 조치하는 것이 필요하다. 이를 위하여 다양한 교통정보 수집기에서 수집된 교통정보를 바탕으로 실시간으로 유고상황을 판별하는 연구가 많이 진행되고 있다. 유고상황 분석은 다양한 환경요인으로 인해 판별이 어렵고, 최근에 활용되고 있는 인공지능 기법은 검지에 드는 시간 비용이 많다는 문제를 가지고 있다. 본 연구에서는 과거에 발생한 각종 돌발 상황을 분석하여 실시간으로 유고상황을 검지하는 것이 목적이다. 유고검지를 위해 GPS를 탑재한 probe car에서 수집된 차량속도와 온라인으로 제보된 유고정보를 ANFIS를 이용하여 분석 후 유고상태를 판별한다. 본 연구를 통해 실시간 도로 이용자들이 유고 발생 지역의 정보를 제공받고 그 상황에 신속하게 대처하게 함으로써 교통 혼잡 완화에 기여할 것으로 기대한다.

• Journal of Convergence for Information Technology
• /
• v.9 no.6
• /
• pp.175-182
• /
• 2019

This study was conducted to test the assessment validity and examine the cut-off scores for driving risk as a part of the Self-report Assessment Forecasting Elderly Driving Risk (SAFE-DR) development project. The 132 senior drivers were categorized as either risky of 58 or safe of 74 drivers through the Drivers 65 Plus. Based on this initial assessment, we analyzed the risk prediction cut-offs. Furthermore, we tested the construct, content, and predictive validity. The cut-off score for the prediction of driving risk was found to be 74.5 points. The positive predictive value was 88.6%, and the negative predictive value was 86.3% about the cut-off score, signifying an excellent level of discrimination. Convergent validity, nomological validity, and content validity were found to be appropriate. Therefore, this study confirms that SAFE-DR is an appropriate assessment that can be used to screen dangerous elderly drivers.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.859-864
• /
• 2022

Drowsy driving, one of the biggest causes of traffic accidents every year, is accompanied by various factors. As a general method to check whether or not there is drowsiness, a method of identifying a driver's expression and driving pattern, and a method of analyzing bio-signals are being studied. This paper proposes a driver fatigue detection system using deep learning technology and bio-signal measurement technology. As the first step in the proposed method, deep learning is used to detect the driver's eye shape, yawning presence, and body movement to detect drowsiness. In the second stage, it was designed to increase the accuracy of the system by identifying the driver's fatigue state using the pulse wave signal and body temperature. As a result of the experiment, it was possible to reliably determine the driver's drowsiness and fatigue in real-time images.