• The Journal of Engineering Research
• /
• v.3 no.1
• /
• pp.7-20
• /
• 1998

With our economic development and increment and increment of GNP, the number of autos has incremented. But lacking in mind for traffic safety and traffic order, many traffic accidents have occurred. So the purpose of development of traffic safety education system based on web is to advertise the importance and the need of traffic order and safety education and protect walkers and drivers from traffic accidents. The Contents and Scopes of Study Development are as follows. There are input of text, image and moving image data for traffic safety education, establishment of hierarchical relation for traffic safety education, relation analysis between traffic safety education information and design of hyper link structure between them, thesaurus implementation for traffic safety education system, design and implementation of information retrieval engine based on thesaurus, design and implementation of database schema for traffic safety education and GUI implementation for user.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2017.11a
• /
• pp.6-7
• /
• 2017

무인선박의 출현 및 운항 시기가 도래하는 시점에서, 항해사들의 경험적, 정성적 방법으로 항로를 설정하던 기존의 방식이 아니라 정량적 항로 결정 방식 필요성이 제기된다. 본 연구에서는 위험물(HNS) 적재선의 해상교통사고 리스크 기반의 침로 설정을 통해 실시간 데이터 활용에 따라 변화 추정 및 인적 오류를 최소화하여 무인선박 운항 시 활용 가능한 항로 설정 기법을 제안하였다. 항로 주변의 정적 위험(Static Hazard)을 기반한 리스크 평가 방법을 제시하고, Contour map으로 시각화 통해 무인선박뿐 아니라 현존하는 선박에도 적용 가능하여, 사용자 결정에 따라 리스크 기반으로 침로 설정 통해 선박 운항 효율성 및 안전성 확보에 기여할 것으로 기대된다. 본 연구 내용을 토대로 정적 위험뿐 만아니라 선박을 포함한 동적 위험을 반영한 실시간 리스크 기반 항로 설정까지 확장하기 위한 연구가 요구된다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2021.11a
• /
• pp.3-4
• /
• 2021

Korea government has developed Korean e-Navigation service to assist ship's collision avoidance, and is providing it since Jan. 2021 to korean vessels to reduce marine accidents caused by human error which is regarded as main reason of marine accidents. It is a huge achievement itself because it is a real-time maritime safety information service based on digital communication, but still has room for improvement to provide customized information for each vessel, such as considering ship's characteristics. This research analyzes current status and requirement of collision avoidance assistance service. Lastly, it suggests direction of improvement of service such as using data science, artificial intelligence(AI).

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.4
• /
• pp.91-100
• /
• 2010

Existing traffic safety studies have focused on identifying the relationship among roadway crashes, highway design and incremental weather condition such as rainy/ice weather. However, it is hard to find researches that studied the effect of sun glare on traffic safety although there are abundant evidences demonstrating that fatal traffic crashes are attributed to the sun glare. Affecting drivers'vision particularly during the morning or the evening time when the sun positions close to the horizon, sun glare directly deteriorate drivers'judgmental capability. In this paper, we numerically analyze the effect of sun glare on the drivers'vision in time and space domains. Applied to the roadways around St Louis area in the United States, the GIS based simulation analysis identifies the time of day in a year and the segments of highways that are potentially influenced by the sun glare. This study evidentially confirms the fact that roadway bounded for West and East directions have longer time influenced by sun glare particularly during Spring and Fall season than other roadways. The computational result provides risky time periods of day at intersections or pedestrian crossings where the sun glare potentially endangers traffic safety, which be utilized to reduce the crashes due to the sun glare.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.2
• /
• pp.149-155
• /
• 2020

The Korea Highway Traffic Authority provides statistics that analyze the causes of traffic accidents that occurred since 2015 using the Traffic Accident Analysis System (TAAS). it was reported Through TAAS that the driver's forward carelessness was the main cause of traffic accidents in 2018. As statistics on the cause of traffic accidents, 51.2 percent used mobile phones and watched DMB while driving, 14 percent did not secure safe distance, and 3.6 percent violated their duty to protect pedestrians, representing a total of 68.8 percent. In this paper, we propose a system that has improved the advanced driver assistance system ADAS (Advanced Driver Assistance Systems) by utilizing CNN (Convolutional Neural Network) among the algorithms of Deep Learning. The proposed system learns a model that classifies the movement of the driver's face and eyes using Conv2D techniques which are mainly used for Image processing, while recognizing and detecting objects around the vehicle with cameras attached to the front of the vehicle to recognize the driving environment. Then, using the learned visual steering model and driving environment data, the hazard is classified and detected in three stages, depending on the driver's view and driving environment to assist the driver with the forward and blind spots.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.5
• /
• pp.18-33
• /
• 2024

Community roads pose risks for traffic accidents, falls, crimes, and disasters, threatening pedestrian safety. However, current road management and safety systems primarily focus on arterial roads, and fail to adequately consider the unique characteristics of community roads. This study presents a methodology to more effectively predict various pedestrian accidents on community roads by categorizing risk zones based on a distribution of risk factors. Through field surveys, key risk factors for each type of accident were identified, and the frequency of these factors was used to classify risk zones, which were then visually represented using GIS. Applying this methodology to Seoul's Seocho 1-dong, a comparison with actual accident data revealed a partial correlation between the predicted risk zones and actual locations of traffic and disaster-related incidents, thereby validating the methodology. This study is expected to serve as a policy tool for preventing accidents and enhancing safety on community roads.

• Journal of Korean Society of Transportation
• /
• v.21 no.3
• /
• pp.71-83
• /
• 2003

An arterial street control is performed for the purpose of the progression of a traffic flow using the arterial. However during the progression in the arterial, the change according to the time is one of the most representative problems occurring at a signal plan. This paper intends to efficiently operate the arterial progression by applying fuzzy logic, which is thought to be the most possible one in the inference as that of the human logic, to the traffic responsive control system. Fuzzy Logic controller is appliable to the daily human language (linguistic). can be dealt with the uncertain traffic data and is useful on planning the signal control to sensitively confront the randomly changing traffic condition. This study, based on the signal control part of the isolated intersection in "A Development of a Real-time, Traffic Adaptive Control Scheme Through VIDs"(Seong Ho. Kim. 1996). suggested the strategy for the progression control in the arterial and analyzed its effect by comparing the effect of the existing control method. In addition, the study compared each effect by using TRAF-NETSIM which is the traffic simulation software to analyze each control method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.6
• /
• pp.11-20
• /
• 2023

The cost of medical treatment for motor vehicle accidents is increasing every year. In this study, we created a model to predict long-term hospitalization(more than 18 days) among minor patients, which is the main item of increasing traffic accident medical expenses, using five algorithms such as decision tree, and analyzed the factors affecting long-term hospitalization. As a result, the accuracy of the prediction models ranged from 91.377 to 91.451, and there was no significant difference between each model, but the random forest and XGBoost models had the highest accuracy of 91.451. There were significant differences between models in the importance of explanatory variables, such as hospital location, name of disease, and type of hospital, between the long-stay and non-long-stay groups. Model validation was tested by comparing the average accuracy of each model cross-validated(10 times) on the training data with the accuracy of the validation data. To test of the explanatory variables, the chi-square test was used for categorical variables.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.3D
• /
• pp.231-240
• /
• 2010

As majority of the traffic accidents in intersections is caused by human factor, a close examination is required on its contributing factors through measuring the psychological and physiological response according to the driving characteristics of the drivers and the road conditions. In this study, for the safety evaluation of individual intersection considering human factors of the drivers, electroencephalography reaction was measured utilizing cutting-edge measuring equipment and survey on drivers' cognitive characteristics in ordinary times and while driving test was conducted. The relationship between the electroencephalography response when approaching the intersection and cognitive evaluation survey data in driving test was clarified, and individual intersection safety evaluation model was built considering cognitive evaluation factor and the reaction of a bio-response electroencephalography data. As a result, I could find out that cognitive evaluation was made through the reaction of a bio-response (Electroencephalography) process because electroencephalography reaction of a bio-response showed differently by the physical characteristics of the intersection and cognitive evaluation had a difference.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.41-42
• /
• 2019

해양공간의 효율적인 활용과 해상사고 예방을 위하여 해상교통 현황 파악이 필요하다. 이를 위해서는 해상에서 운항하는 선박에 대한 면밀한 모니터링이 선행 되어야한다. 때문에 본 연구에서는 선박자동식별장치(Automatic Identification System, AIS)와 선박패스(V-Pass)를 활용하는 기존 모니터링 방법에서 나아가, 위성 자료를 활용한 연안 선박감시 방법을 해상교통관제(Vessel Traffic Service, VTS) 센터에서 활용하기 위한 방안을 제안한다. 위성 자료는 광범위한 영역에 대하여 다양한 정보를 획득할 수 있는 장점을 지니므로, 부산항 연안에서 수집한 AIS 데이터와 함께 딥 러닝 기반 선박 탐지 및 분류 모델에 활용함으로써, 보다 개선된 모니터링을 기대할 수 있다. 이를 활용하여 미식별 선박들의 출현 위치를 분석하고 나아가 선박의 종류를 예측함으로써, 상세한 해상교통 현황 파악 및 예측을 기대할 수 있다. 향후에는 선박의 종류 뿐 아니라 각 선박의 해상활동을 분석함으로써, 보다 체계적이고 실용적인 해양공간활용 계획수립에 도움이 될 수 있도록 개선할 계획이다.