• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2016.11a
• /
• pp.263-264
• /
• 2016

본 연구는 첨두 비첨두시간에 발생되는 교통사고의 주요 요인들을 발견하고 비교하여 각 시간대의 사고특성을 제시하고자 한다. 이에 로지스틱 회귀분석을 통해 분석한 결과 흐린 날씨의 경우 첨두시간에 발생되는 사망사고 위험도가 비첨두시간의 경우보다 더 높게 나타났고, 비첨두시간 사망사고 위험도의 경우 안개가 낀 날 증가하고 맑은 날 감소하는 모습이 나타났다. 과속의 경우 비첨두시간이 첨두시간의 경우 보다 크게 나타났고, 횡단 중인 보행자와 발생되는 사고에 대해서는 첨두시간의 사망위험도가 상대적으로 높은 것으로 나타났다. 차량단독 사고의 경우 공작물과 충돌로 인한 사망위험도는 첨두시간이 높은 것으로 나타났고, 도로 이탈로 인한 사망위험도는 비첨두시간이 높은 것으로 나타났다.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.53-58
• /
• 2024

Traffic accidents are not only a threat to human lives but also pose significant societal costs. Recently, research has been conducted to address the issue of traffic accidents by predicting the risk using deep learning technology and spatiotemporal information of roads. However, while traffic accidents are influenced not only by the spatiotemporal information of roads but also by human factors, research on the latter has been relatively less active. This paper analyzes driver groups and characteristics by applying clustering techniques to a traffic accident dataset and proposes and applies a method to calculate the Risk Level for each driver group and characteristic. In this process, the preprocessing technique suggested in this paper demonstrates a higher Silhouette Score of 0.255 compared to the commonly used One-Hot Embedding & Min-Max Scaling techniques, indicating its suitability as a preprocessing method.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_1
• /
• pp.217-229
• /
• 2020

Recently, weather changes in Korea have intensified due to global warming, and the five major natural disasters that occur mostly include heavy rains, typhoons, storms, heavy snow, and earthquakes. Busan is vulnerable to snow disaster, given that the amount of natural disaster damage in Busan accounts for more than 50% of the total amount in the entire metropolitan cities in Korea, and that the Busan area includes many hilly mountains. In this study, we attempted to identify vulnerable areas for snowfall disasters in Busan areas using the geographic information system (GIS) with the data for both geographical and anthropogenic characteristics. We produced the maps of vulnerable areas for evaluating factors that include altitude, slope, land cover, road networks, and demographics, and overlapped those maps to rank the vulnerability to snowfall disasters as the 5th levels finally. To weight each evaluating factor, we used an entropy method. The riskiest areas are characterized by being located in mountainous areas with roads, including Sansung-ro in Geumjeong-gu, Mandeok tunnel in Buk-gu, Hwangnyeongsan-ro in Suyeong-gu, and others, where road restrictions were actually enforced due to snowfall events in the past. This method is simple and easy to be updated, and thus we think this methodology can be adapted to identify vulnerable areas for other environmental disasters.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.3
• /
• pp.180-192
• /
• 2013

Recently, the development of the information-communications industry has created a new paradigm of the ubiquitous and the smart environments. An USN is a typical technology for constructing a ubiquitous environments. But the USN technologies applied in practice have a lot of problems and to solve these problems that this study was to build a test bed. For the creation of the needs of USN technology, we suggest a method and service of monitoring of road hazards combining the USN and the Geographic Information System(GIS). We conduct making the USN equipment relevant provisions surveys, making installation guidelines, construction system and real-time testing. This study is capable of the management of public facilities, real-time monitoring of accident and the environment data and is expected to be expanded to a 3D facility management combineded with BIM in the future.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.5
• /
• pp.38-48
• /
• 2010

Adverse weather (e.g. strong winds, snow and ice) will probably appear as a more serious and frequent threat to road traffic than in clear climate. Another consequence of climate change with a natural disastrous on road traffic is respond to traffic accident more the large and high-rise bridge zone, tunnel zone, inclined plane zone and de-icing zone than any other zone, which in turn calls for continuous adaption of monitoring procedures. Accident mitigating measures against this accident category may consist of intense winter maintenance, the use of road weather information systems for data collection and early warnings, road surveillance and traffic control. While hazard from reduced road friction due to snow and ice may be eliminated by snow removal and de-icing measures, the effect of strong winds on road traffic are not easily avoided. The purpose of the study described here, was to design of amber information the relationship between traffic safety, weather, user information on road weather and driving conditions in local-scale Geographic. The most applications are the optimization of the amber information definition, improvements to road surveillance, road weather monitoring and improved accuracy of user information delivery. Also, statistics on wind gust, surface condition, vehicle category and other relevant parameters for wind induced accidents provide basis for traffic control, early warning policies and driver education for improved road safety at bad weather-exposed locations.

• Annual Conference of KIPS
• /
• 2017.04a
• /
• pp.767-768
• /
• 2017

국토교통부에 따르면 2014년, 대한민국의 자동차 1대당 인구수가 2.56명으로 기록되었다고 한다. 또한, 교통안전공단에 의하면, 2015년 총 교통사고는 23만 2035건이 발생하였고 이로 인한 사망자는 4621명이라고 한다. 그 중 약 53%인 12만 3760건이 폭이 9m 미만인 이면도로에서 발생하였고 이로 인한 사망자는 전체 사망자의 약 56%인 2586명이라고 한다. 이는 상당히 수의 사고들이 이면도로에서 일어나고 있음을 알려준다. 국민 안전의 측면에서 많은 사고의 위험이 있는 이면도로에 사고를 예방할 수 있는 대책이 시급하다. 이에 본 논문에서 IoT(사물인터넷)을 기반으로 한 이면도로에서의 사고 예방 장치를 제시하여 '차량과 차량'뿐만 아니라 '차량과 보행자', '차량과 자전거' 충돌사고 문제해결에 접목하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.411-414
• /
• 2014

복지 정책의 일환으로 거동이 불편한 고령자와 장애인에게 전동 휠체어의 보급이 늘어나고 있다. 그러나 사용의 편리성에 비해 유지관리가 매우 불편하다는 사용자들의 불만이 많이 제기되고 있다. 특히 전동 휠체어의 배터리의 충전 및 정비 운영관리 문제와, 현재 야외에서의 휠체어가 운행하는데 도로상황이 좋지 않아 많은 위험성을 내포하고 있다. 이에 휠체어 및 위치와 같은 주위 상황을 실시간으로 모니터링하여 위험 상황이 발생시 즉각적인 대처가 가능하도록 하는 시스템이 필요하다. 본 논문에서는 이러한 불편을 미연에 방지하고 전동 휠체어의 효율적인 관리가 가능한 배터리 및 위치정보를 실시간 모니터링하는 시스템을 제안한다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.4
• /
• pp.1591-1601
• /
• 2013

In this study, It is conducted for novice drivers about driving behavior and psychological characteristics analysis to reduce traffic accident risk and provide the basic data of education program development. Therefore, this study classified by the category-specific characteristics and hazard prediction through survey of the novice driver and unpredictable behavior and psychological characteristics were studied. The novice and general characteristics and driving behavior with vehicle simulators, comparison and analysis of the novice driver traffic safety education basic research direction based on the statistical results. Prediction the results of this study, the Hazard of the driver, speeding, traffic violation, information providing omission, abrupt change, the number of accidents in all areas novice driver is high compared to the general driver. In addition, Novice driver showed a statistically significant level of Hazard compared to the general driver target novice drivers and the general ability to predict Hazard of violation, abrupt change, and a number of traffic accidents were omitted level of speeding and other information providing level drivers all showed similar results. Vehicle simulator. The experimental results showed that novice drivers compared to drivers poorly overall driving performance. It showed a notable difference in the number of collisions, especially novice drivers compared to drivers in complex road traffic conditions due to a lack of driving experience and learning ability are considered.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.4 s.34
• /
• pp.19-25
• /
• 2005

This study suggests a method for securing road safety by extracting the expected surface freezing section in planning a route using GIS. When planning a road construction in a mountainous area it is possible to confront surface freezing especially in the wintertime. In addition, it is required assessment data of surface freezing rates in the case of turnkey inspections of newly constructed or expanded roads. Consequently, an analysis method that can quantitatively estimate the surface freezing section and sunshine influence on each section of a road is needed. We can extract the expected surface freezing section which amounted to around 29km of the Donghae highway, with such techniques as three-dimensional modeling, sunshine simulation geographical database construction and spatial analysis using the overlay function of the GIS spatial analysis. This study can be used as a method to assess advance safety which has a direct influence on planning the blueprint that should be approved by a policy maker after efficiently understanding the expected surface freezing section in accordance with hill shade.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.47-54
• /
• 2021

The number of freeway traffic accidents in Korea is about 4,000 as of 2020, and deaths per traffic accident is about 3.7 times higher than other roads due to non-recurring congestion and high driving speed. Most of the accident types on freeways are side and rear-end collisions, and one of the main factors is hazard traffic flow caused by merge, diverge and accidents. Therefore, the hazard traffic flow, which appears in a continuous flow such as a freeway, can be said to be important information for the driver to prevent accidents. This study tried to classify hazard traffic flows, such as the speed change point and the section where the speed difference by lane, using individual vehicle information. The homogeneous segment of speed was classified using spatial separation based on geohash and space mean speed that can indicate the speed difference of individual vehicles within the same section and the speed deviation between vehicles. As a result, I could extract the diverging influence segment and the hazard traffic flow segment that can provide dangerous segments information of freeways.