PURPOSES : In this study, model-agnostic methods are applied for interpreting machine learning models, such as the feature global effect, the importance of a feature, the joint effects of features, and explaining individual predictions. METHODS : Model-agnostic global interpretation techniques, such as partial dependence plot (PDP), accumulated local effect (ALE), feature interaction (H-statistics), and permutation feature importance, were applied to describe the average behavior of a machine learning model. Moreover, local model-agnostic interpretation methods, individual conditional expectation curves (ICE), local surrogate models (LIME), and Shapley values were used to explain individual predictions. RESULTS : As global interpretations, PDP and ALE-Plot demonstrated the relationship between a feature and the prediction of a machine learning model, where the feature interaction estimated whether one feature depended on the other feature, and the permutation feature importance measured the importance of a feature. For local interpretations, ICE exhibited how changing a feature changes the interested instance’s prediction, LIME explained the relationship between a feature and the instance’s prediction by replacing the machine model with a locally interpretable model, and Shapley values presented how to fairly contribute to the instance’s prediction among the features. CONCLUSIONS : Model-agnostic methods contribute to understanding the general relationship between features and a prediction or debut a model from the global and/or local perspective, securing the reliability of the learning model.

The global economy has been hit hard by the COVID-19 pandemic, and countries around the world urgently need to restore economic growth. As countries in Eurasia become more and more closely connected, it is inevitable for China's Belt and Road Initiative and South Korea's new Northern policy to connect. In this context, what matters is the connection of the railway network. The purpose of this study is to analyze the impact of the integration of the Korean Terminal Railway (TKR) into the Eurasian railway network by connecting the Korean Terminal Railway (TKR) with China's China-Europe freight trains. The results show that there is an interactive positive correlation between railway freight volume and GDP, and South Korea is expected to become the logistics center of East Asia and improve its status and influence in the world center. Within the Korean peninsula, the railway connection can draw North Korea into a larger multilateral agreement system, and South Korea can use external forces within the system to push North Korea to seek more economic cooperation and actively promote the reunification process. The economic development of Northeast Asia also plays a positive role in the economic recovery of the three provinces in northeast China.

‘투키디데스 함정’(Thucydides Trap)과 ‘중진국 함정’(Middle income Trap)이라는 두 개의 수렁 앞에 직면한 중국은 이를 돌파하기 위해 지 정학에 기반한 전략인 ‘일대일로’를 내놓았다. 이에 대해 국제사회는 전 통적 실크로드의 협력 공간이 확대 및 심화됨에 따라 이에 새롭게 부여 된 시대성·선진성·개척성 등에 기대를 하면서 동시에 지정학적 긴장 야기에 대한 우려의 목소리도 있다. 본 연구는 일대일로가 중국의 국가 대외전략 변화의 맥락 속에서 어떻게 등장하고 변화하였는지를 살펴보 았고, 전통적 지정학 및 지경학, 비판지정학의 이론을 바탕으로 분석하였다. 또한 전통적 지정학이 가지는 영토주의, 국가주의의 근원적 한계 로 인한 일대일로에 대한 이분법적 관점에 대해 비판지정학이 강조해온 탈영토 및 탈국가성에 주목하여 살펴보는 동시에, 최근 사회학뿐만 아 니라 다양한 영역에서 연구되는 있는 행위자-네트워크이론(ANT)의 개 념을 다룬다. 인간과 비인간(자연) 행위자 사이에서 상호작용을 다루는 행위자-네트워크이론에 따라 일대일로는 교량, 댐 등을 도로, 철도 등 의 ‘선’으로 연결하는 ‘일대일로 1.0 버전’과 중국 중심의 유라시아 경 제블록인 ‘면’으로 확장 연결하는 ‘일대일로 2.0 버전’을 뛰어넘어 4차 산업혁명 시대의 핵심기술들이 ‘입체’적으로 상호 교차·연계될 기술표준 으로 확장 연결되는 ‘일대일로 3.0 버전’으로 진화할 것을 제안한다. 이 로써 일대일로는 지정학적 갈등과 충돌의 위험을 줄이면서, 4차 산업혁 명 시대의 첨단기술 패권 선점을 위한 선의의 경쟁과 인류기술의 비약 적 발전을 위한 진보된 플랫폼으로 전환될 것으로 전망된다.

PURPOSES: This study aims to review the concept of emergency road networks through previous studies and propose a risk and resilience evaluation method for selecting an emergency road network in the event of an earthquake disaster in major highways in Daejeon. METHODS : Risk assessment in consideration of the possibility, exposure, and vulnerability of relatively weak spots and sections in the event of an earthquake disaster on major highways in Daejeon Metropolitan City, and responsiveness, mitigation, and accessibility for urgent response to disaster recovery and management. The emergency road network selection method was proposed by taking into account resilience evaluation. Five levels of links were classified using the P-I method and the overall scores were calculated by considering the weighting factors. RESULTS : In the selected emergency road network, the main roads located near major disaster prevention facilities (public institutions) and response facilities (firefighting and emergency facilities) exhibited a high priority during the earthquake. In addition, highways that emphasized the speed and connectivity between the local emergency road network and the surrounding suburbs exhibited a high priority. CONCLUSIONS : To designate the emergency road network in advance, evaluation of vulnerable facilities and exposure points in the event of a disaster needs to be considered, which can be used to establish a disaster safety plan, thereby ensuring speed and continuity in disaster response.

PURPOSES: This study examines the performance changes of road networks according to the strength of a disaster, and proposes a method for estimating the quantitative resilience according to the road-network performance changes and damage scale. This study also selected highinfluence road sections, according to disasters targeting the road network, and aimed to analyze their hazard resilience from the network aspect through a scenario analysis of the damage recovery after a disaster occurred. METHODS: The analysis was conducted targeting Sejong City in South Korea. The disaster situation was set up using the TransCAD and VISSIM traffic-simulation software. First, the study analyzed how road-network damage changed the user’s travel pattern and travel time, and how it affected the complete network. Secondly, the functional aspects of the road networks were analyzed using quantitative resilience. Finally, based on the road-network performance change and resilience, priority-management road sections were selected. RESULTS: According to the analysis results, when a road section has relatively low connectivity and low traffic, its effect on the complete network is insignificant. Moreover, certain road sections with relatively high importance can suffer a performance loss from major damage, for e.g., sections where bridges, tunnels, or underground roads are located, roads where no bypasses exist or they exist far from the concerned road, including entrances and exits to suburban areas. Relatively important roads have the potential to significantly degrade the network performance when a disaster occurs. Because of the high risk of delays or isolation, they may lead to secondary damage. Thus, it is necessary to manage the roads to maintain their performance. CONCLUSIONS : As a baseline study to establish measures for traffic prevention, this study considered the performance of a road network, selected high-influence road sections within the road network, and analyzed the quantitative resilience of the road network according to scenarios. The road users’passage-pattern changes were analyzed through simulation analysis using the User Equilibrium model. Based on the analysis results, the resilience in each scenario was examined and compared. Sections where a road’s performance loss had a significant influence on the network were targeted. The study results were judged to become basic research data for establishing response plans to restore the original functions and performance of the destroyed and damage road networks, and for selecting maintenance priorities.

PURPOSES : This study is to investigate the relationship of socioeconomic characteristics and road network structure with traffic growth patterns. The findings is to be used to tweak traffic forecast provided by traditional four step process using relevant socioeconomic and road network data. METHODS: Comprehensive statistical analysis is used to identify key explanatory variables using historical observations on traffic forecast, actual traffic counts and surrounding environments. Based on statistical results, a multiple regression model is developed to predict the effects of socioeconomic and road network attributes on traffic growth patterns. The validation of the proposed model is also performed using a different set of historical data. RESULTS : The statistical analysis results indicate that several socioeconomic characteristics and road network structure cleary affect the tendency of over- and under-estimation of road traffics. Among them, land use is a key factor which is revealed by a factor that traffic forecast for urban road tends to be under-estimated while rural road traffic prediction is generally over-estimated. The model application suggests that tweaking the traffic forecast using the proposed model can reduce the discrepancies between the predicted and actual traffic counts from 30.4% to 21.9%. CONCLUSIONS : Prediction of road traffic growth patterns based on surrounding socioeconomic and road network attributes can help develop the optimal strategy of road construction plan by enhancing reliability of traffic forecast as well as tendency of traffic growth.

PURPOSES : The purpose of this study is to check the possibilities of traffic pattern analysis using MatSIM for urban road network operation in incident case. METHODS : One of the stochastic dynamic models is MatSIM. MatSIM is a transportation simulation tool based on stochastic dynamic model and activity based model. It is an open source software developed by IVT, ETH zurich, Switzerland. In MatSIM, various scenario comparison analyses are possible and analyses results are expressed using the visualizer which shows individual vehicle movements and traffic patterns. In this study, trip distribution in 24-hour, traffic volume, and travel speed using MatSIM are similar to those of measured values. Therefore, results of MatSIM are reasonable comparing with measured values. Traffic patterns are changed according to incident from change of individual behavior. RESULTS : The simulation results and the actual measured values are similar. The simulation results show reasonable ranges which can be used for traffic pattern analysis. CONCLUSIONS : The change of traffic pattern including trip distribution, traffic volumes and speeds according to various incident scenarios can be used for traffic control policy decision to provide effective operation of urban road network.

The following research of the road network of Jeju-Eupseong during Daehan Empire period has a twofold purpose: to study some characteristics of the road network at that time; and, to restore it to the original form of that period before a newly constructed road, called Shinjakro, has been established. As an attempt to trace the old shape of Jeju-Eupseong, this study analyzed some historical factors based on the first land cadastral map which was made in 1914, including outskirts of Jeju-Eupseong; such as castle itself, castle gate, road, bridge, lots of land, etc. Then this study also tried to restore the old road network of Jeju-Eupseong, through finding the original land-lot shape in the land cadastral map. There was five Shinjakro made between 1914 and 1917. The road network before then was composed of the double east-west axes and the single north-south axis. These axes was connected to some important place of the inside of Jeju-Eupseong; such as castle gates, fountains, Gaek-sa, etc. There were many branch lines between these main axes at about 80-120m intervals. Also there was an outer road along the outer wall of castle, connected with each castle gates. Especially, the north-west axis was the baseline which divided into two large parts, a government office area and non-government area (housing and commercial street for the people). Finally, this paper examines that the road network of Jeju-Eupseong was the true result for the efficient function of the city, especially considering natural geographical conditions and environment of living of that time.

향후 임도사업(林道事業)과 임도배치망(林道配置網) 계획(計劃)에 기초자료(基礎資料)를 제공코자 현재 개설(開設)되어 있는 임도(林道)를 중심으로 임도개설비(林道開設費)에 대한 투자효과(投資效果)를 최대로 하는 최적임도배치(最適林道配置) 및 집재기능(集材機能)을 고려한 임도배치망(林道配置網)을 평가(評價)하였다. 1. 적정(適定) 임도밀도(林道密度) 및 임도연장거리(林道延長距離)를 계산(計算) 비교(比較)한 결과(結果), 각(各) 조사지(調査地)의 유성별(流城別) 기설(旣設) 임도밀도(林道密度)가 이론적으로 계산(計算)한 임도밀도(林道密度)보다 작았으며 앞으로 좀더 많은 임도개설(林道開設)이 필요하였다. 2. 투자효과(投資效果)를 최대(最大)로 하는 임도로선배치법(林道路線配置法)에 의해 계산(計算)한 임도배치망(林道配置網)과 기설(旣設)의 임도배치망(林道配置網)을 비교분석(比較分析)한 결과(結果), 각(各) 조사지(調査地)에서 기설(旣設)의 임도망(林道網)은 공도적(公道的) 기능(機能)을 높이기 위한 임도망(林道網)으로서 우회률(迂回率)이 큰 임도로선망(林道路線網)인 반면, 투자효과(投資效果)를 최대(最大)로 하는 임도배치망(林道配置網)은 공도적(公道的) 기능(機能)이 고려(考慮)되면서 임업적(林業的) 기능(機能)이 고려된 집재기능(集材機能)이 높은 수기형상(樹技形狀)의 임도망(林道網)으로 배치(配置)되어 계획구역(計劃區域)에 골고루 배치(配置)되어 있는 것을 알 수 있었다. 따라서 기설(旣設)의 임도배치망(林道配置網)이 다소 집재기능적(集材機能的)인 면(面)과 임업적(林業的) 기능(機能)이 결여(缺如)된 임도배치망(林道配置網)이라고 하겠으며 앞으로 좀더 투자효과(投資效果)와 집재기능(集材機能)을 고려(考慮)한 임도배치망계획(林道配置網計劃) 필요(必要)하겠다. 3. 각(各) 조사지(調査地)에 대한 평균(平均) 최대집재거리(最大集材距離)와 평균(平均) 집재가능면적(集材可能面積)이 기설(旣設) 임도망(林道網)과 계산(計算)에 의한 임도배치망(林道配置網)에 대한 수평거리(水平距離)와 사거리별(斜距離別) 평균(平均) 최대집재거리(最大集材距離)와 평균(平均) 집재가능면적(集材可能面積)이 다르다는 것을 알 수 있었다. 또한 최대집재수평거리(最大集材水平距離)를 동일하게 적용(適用)했을 경우, 기설(旣設) 임도망(林道網)과 계산결과(計算結果) 임도망(林道網)의 평균(平均) 최대집재거리(最大集材距離)와 평균(平均) 집재가능면적(集材可能面積)이 다르다는 것을 알 수 있었으며, 기설(旣設) 임도망(林道網)을 기준으로 최대집재거리(最大集材距離)를 동일하게 적용(遭用)했을 경우도 최대집재거리(最大集材距離)를 수평거리(水平距離)와 사거리(斜距離)로 구별했을 때에 평균(平均) 최대집재거리(最大集材距離)와 평균(平均) 집재가능면적(集材可能面積)이 다르다는 것을 알 수 있었다. 따라서 임도배치(林道配置)를 가능하면 산능선(山陵線)이나 산복(山腹)을 중심으로 배치(配置)하는 것이 효과적(效果的)이라는 것을 알 수 있었다. 그리고 기설(旣設)의 임도(林道)와 계산(計算)하여 배치(配置)한 임도(林道)의 집재거리별(集材距離別) 평균(平均) 집재가능면적(集材可能面積), 집재면적률(集材面積率)의 수평거리(水平距離)와 사거리(斜距離)의 총 평균값도 차이가 있는 것을 알 수 있다. 이를 볼 때, 기설(旣設)의 임도(林道)보다는 투자효과(投資效果)를 최대(最大)로 하는 임도배치망(林道配置網)이 임업적(林業的) 기능(機能)과 집재기능적(集材機能的)인 면(面)에서 더욱 효과적(效果的)이고 최대집재거리(最大集材距離)를 수평거리(水平距離)보다 사거리(斜距離)로 계산(計算)했을 경우가 집재가능면적(集材可能面積)이 작으므로 임도배치망(林道配置網)을 가능하면 산복(山腹)과 산능선(山陵線)을 중심으로 배치(配置)하는 것이 집재기능(集材機能)을 더욱 높일 수 있다는 것을 알 수 있었다. 따라서 앞으로 임도로선배치계획시(林道路線配置計劃時)에 가능하면 집재기능(集材機能)을 고려(考慮)하여 집재가능면적(集材可能面積)을 크게 할 수 있도록 임도배치망(林道配置網)을 구축(構築)할 필요가 있겠다. 4. 현재(現在) 개설(開設)되어 있는 임도로선(林道路線)이 산능선부(山稜線部), 산복부(山腹部), 계곡부중(溪谷部中) 어느 구역을 중심으로 개설(開設)되어 있는지를 평가(評價)하기 위해 임도로선(林道路線)의 위치(位置)를 조사(調査)한 결과(結果), 기설(旣設)의 임도로선(林道路線)이 대부분 산복부(山腹部)와 계곡부(溪谷部) 중심으로 배치(配置)되어 있었으며, 기설(旣設)의 임도망(林道網)이 집재기능(集材機能)이 다소 결여된 임도배치망(林道配置網)이므로 향후 좀더 집재작업(集材作業)시스템을 고려(考慮)한 임도로선배치(林道路線配置)가 요망(要望)된다.

빈번한 재난이 발생하는 일본은 다양한 방법의 대응계획을 세우기 위한 노력을 하고 있다. 2011년 3월 11일 발생한 동일본 대지진 이후의 일본정부의 대응전략을 살펴보면 재해대책기본법에 따라 방재도로 선정기준을 개선하였다. 일본의 방재도로는 크게 두 가지로 ‘긴급교통로’와 ‘긴급수송로’로 분리하여 운영되고 있다. ‘긴급교통로’는 이재민의 피난 및 구출·구조 및 소화활동 등 재해 직 후의 단기적 목적으로 사용되는 긴급차량(군부대, 소방, 경찰) 및 이 활동을 지원하는 차량(복구작업차량)을 위한 교통 네트워크이다. 반면에 ‘긴급수송로’는 재해 발생 시 이재민의 피난 및 이재민의 생활안전을 위한 물자수송계획에 초점을 두고 있으며 비교적 장기적인 복구와 부흥에 초점을 두고 있다. 특히, ‘긴급수송로’는 지역내부는 공안위원회(해당지자체)가, 지역간은 중앙방재위원회(중앙정부)가 지정하며, 미시적, 거시적 관점에서 접근하게 된다. 이원화 운영되는 방재교통계획은 긴급상황 발생 직 후의 피난과 구조상황과 재해복구를 위한 기능을 분리한 것이며, 그 목적에 따라 정보수집의 우선순위와 복구우선순위를 갖게 된다. 세계적으로 재난의 거대화가 진행되고, 임의의 재난이 발생하고 있기 때문에 교통방재 실현을 위해서는 체계적 방재도로 선정이 시급하다. 특히, 재난 시 방재도로의 교통정보 수집을 위한 민,관,공사의 다차원적 협조가 필요하고, 정부와 연구기관의 노력으로 방재도로의 기능성을 높여 임의의 재난에 피해를 최소화 할 수 있어야 할 것이다.

Emission reduction program for in-use diesel vehicles(ERPDV) has been enacted since 2004 over the Seoul metropolitan area, and diesel emission reduction is forced to fulfill this regulation. This study was performed to evaluate the ERPDV using PM10 concentrations of both road-side monitoring and national background network during the period of 2004-2010. In order to assess the pure road emission, we first eliminated the long range transport effect by deducting the trend of annual national background concentrations from the road-side PM10 concentrations, and then analyzed the time series of the resultant PM10 concentrations over Seoul metropolitan area. The annual rates of variations of road-side PM10 with the deduction of trend of background level show -3.2, +0.4, and -2.4㎍/㎥/year, in Seoul, Incheon, and Gyonggi province, respectively. There are steadily decreasing trend in Seoul with all of statistic parameters such as mean, mediam, 5%ile, 10%ile, 25%ile, 75%ile, 90%ile, and 95%ile concentrations. Incheon shows some fluctuations with positive with no significant trend, and Gyonggi province shows overall decreasing but not consistent. Student-t test shows 95% significant level of ERPDV effect in Seoul, but there exists no significant level greater than 90% in both Incheon, and Kyonggi province. Total annual averaged trend over the whole Seoul metropolitan area is estimated to lie in approximately -2.9㎍/㎥/year in this study, implying the intimate involvement of ERPDV to a large extent. This is also suggesting that the further research cost-effectiveness of ERPDV with consideration of the long range transport process would be needed over the Seoul metropolitan area.

최근 사회기반시설물에 대한 공공투자는 신규건설에 대한 지출이 감소하고 유지관리분야에 대한 지출이 점진적으로 늘어나는 추세로 변화되고 있다. 이에 따라 해외 도로시설물에 대한 유지관리분야에서도 선진 개념인 자산관리 방법론이 접목되고 있으며, 보다 근본적인 시스템 개선이 요구되고 있다. 따라서 본 연구에서는 중소규모 도로관리주체에서 사용할 수 있는 자산관리개념의 유지관리 프로그램을 개발하여 예산편성의 효율성을 높이고, 도로망 전체를 고려한 네트워크 방식의 합리적인 유지보수 방안을 제시하고자 한다. 또한, 향후 다수의 시설물을 통합적으로 관리할 수 있는 체계 및 방법론을 정립하였다.