• 한국도로학회논문집
• /
• 제20권2호
• /
• pp.57-65
• /
• 2018

PURPOSES : The study aims to predict the service life of national highway asphalt pavements through deep learning methods by using maintenance history data of the National Highway Pavement Management System. METHODS : For the configuration of a deep learning network, this study used Tensorflow 1.5, an open source program which has excellent usability among deep learning frameworks. For the analysis, nine variables of cumulative annual average daily traffic, cumulative equivalent single axle loads, maintenance layer, surface, base, subbase, anti-frost layer, structural number of pavement, and region were selected as input data, while service life was chosen to construct the input layer and output layers as output data. Additionally, for scenario analysis, in this study, a model was formed with four different numbers of 1, 2, 4, and 8 hidden layers and a simulation analysis was performed according to the applicability of the over fitting resolution algorithm. RESULTS : The results of the analysis have shown that regardless of the number of hidden layers, when an over fitting resolution algorithm, such as dropout, is applied, the prediction capability is improved as the coefficient of determination ($R^2$) of the test data increases. Furthermore, the result of the sensitivity analysis of the applicability of region variables demonstrates that estimating service life requires sufficient consideration of regional characteristics as $R^2$ had a maximum of between 0.73 and 0.84, when regional variables where taken into consideration. CONCLUSIONS : As a result, this study proposes that it is possible to precisely predict the service life of national highway pavement sections with the consideration of traffic, pavement thickness, and regional factors and concludes that the use of the prediction of service life is fundamental data in decision making within pavement management systems.

• 한국임상수의학회지
• /
• 제31권4호
• /
• pp.282-287
• /
• 2014

The negative impacts of roads on wildlife mortality have been well documented, and one of the most significant impact is wildlife-vehicle collisions (WVCs) in most countries throughout the world. While road impacts on wildlife are a truly global concern with a large socio-economic cost, few researches in Korea have been quantified road-kill occurrence on highways or identified extensively seasonal and geographic patterns of this phenomenon. Therefore, we analyzed highway mortality of wild mammals in Korea using database from five years of nation-wide data on WVCs, and estimated road-kill density by standardizing on per km and per $10^3$ vehicle basis. During 2008 through 2012, a total of 10,940 wildlifes were reported killed on highways, with an average of 2,188 cases per year. There were 2,376 road-kills in 2012, and this equates to 0.01 road-kills per km per week or one road-kill every 88.5 km per week. For time of day, road-kills occurred more frequently in the early morning (05:00-08:00, 38.3%), and day of week did not have a significant influence in any individual year. The road-kill was highest in the spring (March- May, 33.0%) and least in the winter (December-February, 16.1%), and the most frequently killed native species were of Korean water deer (79.7%), raccoon dog (12.7%), Korean hare (3.1%), and leopard cat (1.2%). The overall standardized kill-rate (number/10 km/1,000 vehicles/month) in 2012 was 0.057 with highest on Dangjinyeongdeok highway (0.476), followed by Yeongdong (0.274), Sooncheonwanju (0.233), Iksanpohang (0.187), and Joongang (0.150). This study highlights that the frequency of WVCs are prevalent throughout the highways in Korea. Further work is needed to determine whether such a level of mortality is sustainable from an ecological point of view.

• 한국도로학회논문집
• /
• 제14권3호
• /
• pp.111-120
• /
• 2012

최근 자전거이용에 대한 관심이 증가하면서, 전국적으로 자전거도로 확충을 계획하고 자전거 이용 활성화를 위해 많은 노력이 이루어지고 있으나 대부분의 계획들은 도시부와 레저형 자전거도로에 치우쳐 있다. 따라서 본 연구에서는 지방부의 생활형 자전거도로 사업의 효율적인 투자를 위한 우선순위를 결정할 수 있는 평가기법을 개발하고자 한다. 먼저 평가지표 개발을 위해 지방부 생활형 자전거도로의 특성을 반영하고 정량화가 가능하여 객관적으로 평가할 수 있는 지표를 선정하였으며, 평가지표의 가중치를 산출하기 위하여 계층화분석법을 사용하였다. 또한, 평가항목의 결과만을 기준으로 사업의 우선순위를 평가할 경우 대도시 중심으로 우선순위가 분포되는 경우가 발생할 것으로 판단되어 지역적 형평성(지역균형발전효과)을 고려하기 위해 지역낙후도지수를 고려하였다. 지방부 생활형 자전거도로의 우선순위를 선정하기 위해 시범 적용된 일반국도 구간은 총 23개 구간 160km의 연장으로 구성되어 있다. 본 연구에서 제시된 지방부 생활형 자전거도로 우선순위 평가방법은 지금까지 없었던 생활형 자전거도로에 대한 구체적인 판단기준을 제시하고 정책적 의사결정에 도움을 줄 것으로 기대된다.

• 토지주택연구
• /
• 제2권2호
• /
• pp.171-182
• /
• 2011

본 논문에서는 북한의 인구현황, 도로현황, 도로의 기능 및 역할을 살펴보았다. 또한, 남한과 중국의 도로망 및 Asian Highway와 연계할 수 있는 도로에 대해 남북축과 동서측 $5{\times}5$로 전망하였다. 추가적으로, 도로의 투자우선순위를 결정하기 위하여 평가항목 및 가중치를 산정하고 전문가그룹의 설문조사를 바탕으로 AHP 분석방법을 활용하였다. 분석결과 축별 우선순위는 남북축은 남북2축(개성~평양~안주~중국),남북5축, 남북1축, 남북3축, 남북4축 순으로 선정되었으며 동서축은 동서2축(남포~평양~원산), 동서1축, 동서3축, 동서4축, 동서5축 구간이 투자우선순위가 높은 것으로 분석되었다.

• 대한토목학회논문집
• /
• 제34권4호
• /
• pp.1269-1278
• /
• 2014

교통문제 해결을 위해 건설된 자동차 전용도로인 도시고속도로는 신호에 의하여 단속되지 않는 연속 교통류가 주된 흐름인 관계로 주행차량들의 주행속도가 일반도로에 비해 높아 교통사고 발생 시 인명 피해의 정도가 매우 크다는 특징이 있으며, 특히 인명 피해의 정도가 큰 중상 교통사고는 전체 교통사고에 있어서 매우 중요한 위치를 점하고 있어 중상 교통사고 발생에 미치는 영향요인에 대한 분석은 중상 교통사고 감소대책 수립 시 가장 우선적으로 고려되어져야 할 것이다. 따라서 본 연구는 도시고속도로에서 발생한 중상 교통사고 발생에 있어 여러 인자들의 복합적 작용을 알아보기 위한 미시적 분석의 일환으로 영향요인의 영향정도를 판별할 수 있는 모델을 구축하였는바, 그 결과는 다음과 같이 나타났다. 첫째, 판별모델에서는 전체 적중률들이 비교적 높게 나타났고, 상관비들을 고려해 볼 때 본 모델들이 유효하다고 판단되었으며, 제반 영향요인들의 특성 역시 명확하게 구분되었다. 둘째, 판별모델을 통하여 도시고속도로에서의 중상 교통사고 발생 영향요인별 문제점을 명확하게 도출할 수 있었다. 셋째, 판별모델을 통하여 도출된 문제점에 대한 개선대책도 명확하게 제시할 수 있었다.

• 대한교통학회지
• /
• 제10권2호
• /
• pp.5-24
• /
• 1992

This research presets the method of determining basic capacity of signalized intersection using the concept of ideal saturation flow rate. Vehicle discharge rates during green time were collected and studied as part of the preparation of Korean Highway Capacity Manual. From the result of this study the ideal saturation flow rate and saturation queue position were determined. In addition, based on the ideal saturation flow rate two geometric adjustment factors(lane width and grade adjustment factors) were studied. The results were presented in this paper.

• 대한교통학회지
• /
• 제12권1호
• /
• pp.117-132
• /
• 1994

Drivers select approach lane according to various traffic situations as well as their destination. This behavior affects the utilization of lanes and capacity analysis at urban signalized intersections. This paper presents the concept, behavior of lane utilization, and the lane utilization factors which included in the study. Preparation of Korean Highway Capacity Manual (1992). Lane utilization is affected by various traffic and geometric factors which are roadway side friction, median friction, and number of lanes, etc. and it converges to an equal utilization as the degree of saturation (V/C ratio) increase. Lane utilization factor is suggested by the degree of saturation and the number of lanes, and it is presented in this paper.

• 도시과학
• /
• 제7권1호
• /
• pp.45-54
• /
• 2018

The purpose of this study is to find the factors that reduce prediction error in traffic volume using highway traffic volume data. The ARIMA model was used to predict the day, and it was confirmed that weekday and weekly characteristics were distinguished by prediction error. The forecasting results showed that weekday characteristics were prominent on Tuesdays, Wednesdays, and Thursdays, and forecast errors including MAPE and MAE on Sunday were about 15% points and about 10 points higher than weekday characteristics. Also, on Friday, the forecast error was high on weekdays, similar to Sunday's forecast error, unlike Tuesday, Wednesday, and Thursday, which had weekday characteristics. Therefore, when forecasting the time series belonging to Friday, it should be regarded as a weekly characteristic having characteristics similar to weekend rather than considering as weekday.

• 한국도로학회논문집
• /
• 제16권3호
• /
• pp.101-107
• /
• 2014

PURPOSES : This study deals with the pedestrian accidents in case of Cheongju. The goals are to develop the pedestrian accident model. METHODS : To analyze the accident, count data models, truncated count data models and Tobit regression models are utilized in this study. The dependent variable is the number of accident. Independent variables are traffic volume, intersection geometric structure and the transportation facility. RESULTS : The main results are as follows. First, Tobit model was judged to be more appropriate model than other models. Also, these models were analyzed to be statistically significant. Second, such the main variables related to accidents as traffic volume, pedestrian volume, number of Entry/exit, number of crosswalk and bus stop were adopted in the above model. CONCLUSIONS : The optimal model for pedestrian accidents is evaluated to be Tobit model.

• Smart Structures and Systems
• /
• 제2권3호
• /
• pp.275-293
• /
• 2006

For health monitoring purpose usually the structure is instrumented with a large scale and multichannel measurement system. In case of highway bridges, operating vehicle could be utilized to reduce the number of measuring devices. First this paper presents a static damage detection algorithm of using operating vehicle load. The technique has been validated by finite element simulation and simple laboratory test. Next the paper presents an approach of using this technique to field application. Here operating vehicle load data has been used by instrumenting the bridge at single location. This approach gives an upper hand to other sophisticated global damage detection methods since it has the potential of reducing the measuring points and devices. It also avoids the application of artificial loading and interruption of any traffic flow.