PURPOSES : In this study, the existence of an optimal pattern among transition methods applied during changes in traffic signal timing was investigated. We aimed to develop this pattern into an artificial intelligence reinforcement-learning model to assess its effectiveness METHODS : By developing various traffic signal transition scenarios and considering 19 different traffic signal transition situations that can be applied to these scenarios, a simulation analysis was performed to identify patterns through statistical analysis. Subsequently, a reinforcement-learning model was developed to select an optimal transition time model suitable for various traffic conditions. This model was then tested by simulating a virtual experimental center environment and conducting performance comparison evaluations on a daily basis. RESULTS : The results indicated that when the change in the traffic signal cycle length was less than 50% in the negative direction, the subtraction method was efficient. In cases where the transition was less than 15% in the positive direction, the proposed center method for traffic signal transition was found to be advantageous. By applying the proposed optimal transition model selection, we observed that the transition time decreased by approximately 70%. CONCLUSIONS : The findings of this study provide guidance for the next level of traffic signal transitions. The importance of traffic signal transition will increase in future AI-based traffic signal control methods, requiring ongoing research in this field.

기존 신호제어기법은 과거 주기에 파악된 교통상황을 바탕으로 다음 주기의 교통신호시간을 설계하는 방식으로 신호시간을 설계하기 위해 관측할 때의 교통상황과 신호시간을 제공받는 교통상황 간의 간극이 존재하였다. 또한, 설정된 주기길이 동안 차량이 교차로에 일정하게 도착하는 균일분포를 가정하지만, 실제 교차로에 도착하는 교통량의 행태는 비 균일분포로 실제 교통수요에 대응하기 어렵 다는 한계가 존재한다. 본 연구는 이러한 한계를 극복하기 위해 교차로로 진입하는 상류 교차로의 교통정보를 활용하여 단기 미래 도 착 교통량 예측모델 개발을 통해 관측 시점과 제공 시점 간의 간극을 최소화한다. 또한, 기존 주기길이 동안의 교통량 도착분포를 비 균일분포로 가정하여 주기길이가 고정되지 않는 방식(Acyclic)의 적응식 신호제어 기법(ATC) 개발한다. 제안된 단기 미래 도착 교통 량 예측모델은 실제 스마트교차로 자료를 가공하여 시뮬레이션을 통하여 학습데이터를 구축하여 장단기 메모리(LSTM) 모형과 시간 분산(TimeDistributed) 모형을 적용하여 딥러닝 모델을 개발하였다. 적응식 교통신호제어 기법은 실시간 예측 교통량을 활용하여 교통 류별 예측 지체 산출을 통하여 지체가 최소화되는 현시 종료 지점에서 현시를 종료하고 다음 시간 단계에서 예측된 교통량을 통해 최 적 현시를 재산출하는 롤링 호라이즌(Rolling Horizon)을 수행한다. 제안 신호제어 기법의 평가를 위해 미시적 교통 시뮬레이션을 활 용하여 기존 신호제어 기법인 TOD 신호제어 기법과 제안기법 간의 평가를 수행하였다.

PURPOSES : This study presents a general guideline for the initial management of traffic signal timings in response to traffic incidents, prior to the implementation of specific treatments in detail. The proposed solution includes a set of optimal reductions in the green time rates at three signalized intersections upstream. METHODS : To account for the various traffic and incident conditions that may be encountered, a total of 36 traffic-condition scenarios were prepared. These scenarios encompass a wide range of conditions, from unsaturated to near-saturated conditions, and were designed to provide a comprehensive understanding of the impact of traffic conditions on signal timing. For each of the traffic conditions, all 27 traffic signal timing combinations were subjected to testing. A total of 972 simulation analyses were conducted using the SUMO model. The results indicated that the scenario with the lowest control delay was the optimal choice. RESULTS : The results indicated that the most effective initial management for the traffic incident would be to reduce the green signal timings by 20% at the first two upstream intersections and by 40% at the third intersection. CONCLUSIONS : We propose reducing the green times by 20% at the first and second intersections and by 40% at the third intersection as the initial response of the traffic signal control center when a traffic incident occurs.

This study analyzes the seismic response of traffic light poles, considering soil-foundation effects through nonlinear static and time history analyses. Two poles are investigated, uni-directional and bi-directional, each with 9 m mast arms. Finite element models incorporate the poles, soil, and concrete foundations for analysis. Results show that the initial stiffness of the traffic light poles decreases by approximately 38% due to soil effects, and the drift ratio at which their nonlinear behavior occurs is 77% of scenarios without considering soil effects. The maximum acceleration response increases by about 82% for uni-directional poles and 73% for bi-directional poles, while displacement response increases by approximately 10% for uni-directional and 16% for bi-directional poles when considering soil-foundation effects. Additionally, increasing ground motion intensity reduces soil restraints, making significant rotational displacement the dominant response mechanism over flexural displacement for the traffic light poles. These findings underscore the importance of considering soil-foundation interactions in analyzing the seismic behavior of traffic light poles and provide valuable insights to enhance their seismic resilience and safety.

PURPOSES : This paper proposes an artificial neural network (ANN)-based real-time traffic signal time design model using real-time field data available at intersections equipped with smart intersections. The proposed model generates suitable traffic signal timings for the next cycle, which are assumed to be near the optimal values based on a set of counted directional real-time traffic volumes. METHODS : A training dataset of optimal traffic signal timing data was prepared through the CORSIM Optimal Signal Timing program developed for this study to find the best signal timings, minimizing intersection control delays estimated with CORSIM and a heuristic searching method. The proposed traffic signal timing design model was developed using a training dataset and an ANN learning process. To determine the difference between the traditional pre-time model primarily used in practice and the proposed model, a comparison test was conducted with historical data obtained for a month at a specific intersection in Uiwang, Korea. RESULTS : The test results revealed that the proposed method could reduce control delays for most of the day compared to the existing methods, excluding the peak hour periods when control delays were similar. This is because existing methods focus only on peak times in practice. CONCLUSIONS : The results indicate that the proposed method enhances the performance of traffic signal systems because it rapidly provides alternatives for all-day cycle periods. This would also reduce the management cost (repeated field data collection) required to increase the performance to that level. A robust traffic-signal timing design model (e.g., ANN) is required to handle various combinations of directional demands.

PURPOSES : This study aims to develop and validate timing transition techniques for real-time traffic signal operations, departing from conventional methods based on past commuting traffic patterns. METHODS : In this study, we propose two traffic signal transition techniques that can perform transitions while minimizing disruptions within a short period. The Proposed 1 technique involves an unconditional transition within one cycle and allows for the allocation of offset changes to both the coordinated and non-coordinated phases. The Proposed 2 technique performs transitions within 1-2 cycles based on the offset change rate and considers the non-coordinated phase for allocating offset changes. RESULTS : Functional improvements of the proposed techniques were validated. For validation, simulated traffic signal transition scenarios were created, and a comparative analysis of the transition techniques was performed based on the selected analysis approaches. The results showed that the Proposed 1 technique exhibited the lowest delay during the approximated saturated transitions, whereas the Subtract technique showed the lowest delay during the non-saturated transitions. CONCLUSIONS : These findings emphasize the importance of selecting and applying appropriate transition techniques tailored to individual traffic scenarios. The proposed transition techniques provide valuable insights for improving real-time traffic signal operations, and contribute to the overall efficiency and effectiveness of traffic management in highway corridors.

PURPOSES : This study proposes brief guidelines for traffic engineers in the field to refer to when operating tram priority signals based on the "early green" and "green extension" methods. METHODS : A set of VISSIM simulation analyses was conducted considering various traffic and control conditions in a hypothetical corridor consisting of two signalized intersections. The traffic conditions were varied at five different levels. The control conditions were varied at twenty-five levels by changing the tram priority traffic signal control parameters, i.e., the early green unit time and green extension unit time. A total of 125 simulation runs were from these combinations. A set of optimal signal timings for ordinary non-tram vehicles was prepared with TRANSYT-7F and implemented for the simulation. A tram priority signal control module based on VISVAP was exclusively developed for this study. RESULTS : As expected, no specific trend was found in the relationship between the two tram priority control parameters (early green time and green extension time). However, a trend was observed when assuming that the early green and green extension operations were mutually exclusive. Specifically, an inverse trend appeared between the tram priority control parameter values and level of congestion according to the performance measure (average network delay). CONCLUSIONS : For the early green control parameters, it is better to provide six seconds when undersaturated and four seconds when near-saturated. For the green extension control parameter, four seconds is suitable.

본 연구에서는 기존의 신호체계에서 발생하는 황색 신호 딜레마 상황에서 운전자의 상태를 파악하고 새로운 신호체계를 제안하고자 한다. 특히, 생체신호 분석을 통해 운전자 중심의 대처모형을 제안한다. 이를 위해 자동차 그래픽 시뮬레이터를 통해 교차로 도로 주행상황을 구현하여 기존의 신호체계와 본 연구에서 제안하는 신호체계에서 운전자의 생리적 반응을 관찰하여 규명하고자 한다. 따라서 대조군(기존 신호체계)과 새로운 황색 신호체계를 실험군(새로운 신호체계)으로 나누어 20대 초보 운전자를 중심으로 실험을 진행하였다. 그 결과, 대조군보다 실험군에서 교감신경의 출현이 우세하였으며 통계적으로 유의차가 인정되었다(p<0.05). 이를 통해 새로운 신호체계가 운전자가 긴장감을 유발하는 것처럼 보이지만 교감신경과 부교감신경의 비율이 6:4로 이상적인 균형으로 해석할 수 있다. 결론적으로, 본 연구에서 제안하는 대처 신호체계를 교통체계에 적용한다면 운전자가 더욱 안정적인 주행이 가능할 것으로 보인다.

PURPOSES : In this paper, pedestrian-oriented time assured traffic operation (POTATO), adopted in Korea at a single crossing pedestrianoriented operating area, is explored and applied to a simulation experiment and test site to verify the operation efficiency. METHODS : Three candidate plans are presented as a method to operate pedestrian-oriented signal operations that can overcome the restrictions on signal controllers in Korea. The selected POTATO and TOD signal operations were compared and analyzed. The delay and pedestrian queues, present length, and number of times were used as comparative indices. RESULTS : Scenario-specific simulations confirmed that the delay, compared to TOD signal operation, was reduced by up to 5 s/ped depending on the vehicle traffic volume and the number of pedestrians. For the vehicle delay, the results increased up to 8.99 s/veh, depending on the traffic volume of the vehicles and pedestrians. As a result of the test site operation, POTATO operation improved by 5.12 s/ped (approximately 46.69% improvement) compared to TOD operation in the hours commuting to school and by 2.84 s/ped in the hours commuting from school (approximately 51.13% improvement). In case of vehicle delay, the delay increased by 2.35 s/veh (approximately 64.39%) in the hours commuting to school and 1.20 s/veh (approximately 21.11%) in the hours commuting from school compared to the TOD operation. CONCLUSIONS : Through simulations and test site pilot operation verifications, the effects of pedestrian delay improvement were more positive if POTATO proposed in this study was low in vehicle traffic.

PURPOSES: This paper presents the development and evaluation of the smart hardware-in-the-loop systems (SMART-HILS) that evaluate traffic signal operations of a new real-time traffic signal control system called SMART SIGNAL at the traffic management center (TMC) level. METHODS: The layouts of the hardware and software components of the SMART-HILS were introduced in this study and its performance was tested using real-time traffic signal operation algorithms embedded in the SMART SIGNAL control server by utilizing the VISSIM simulation model. In this study, the SMART-HILS management software was developed using .NET programming language. Fewer random seed numbers were used for the test scenarios by conducting statistical tests to address the shortcomings of a longer time due to the adoption of the simulation time as the real-time by the TMC server. RESULTS : It was determined that SMART-HILS can communicate with TMC and VISSIM for both upload and download directions within acceptable time constraints and evaluate new design algorithms for traffic signal timing. CONCLUSIONS : In practice, traffic engineers can utilize SMART-HILS for testing the traffic signal operation alternatives before their selection and implementation. This application could increase the productivity of traffic signal operation.

In this study, we are developing next-generation traffic signal control system, SMART SIGNAL, which is operated using a traffic big-data. To improve urban’s chronic recurrent congestion, SMART SIGNAL conducts real-time traffic signal control based on travel time data of traffic information systems. This research project started in 2015 and is scheduled to end in 2019. This research project consists of three sub-tasks, which are traffic big-data bank system, signal operation algorithm, and field test for SMART SIGNAL. The traffic big-data bank system includes the travel time and traffic volume data from public and private sector’s traffic information systems. Additionally, this system contains taxi trajectory data, CCTV image and smartphone based traffic data. This big-data system predicts the travel time and traffic volume by intersection movement for real-time signal control. The smart signal operation algorithm of SMART SIGNAL consists three sub-algorithm of PRE-CON, CAERUS, and NIMOS. PRE-CON makes today’s signal timing plan using historical traffic data. CAERUS is traffic responsive signal control algorithm based on predicted travel time. NIMOS is spillback control algorithm for oversaturated condition. In this project, field experiment is planned in 2019 in Seoul.

This study suggested a new real-time traffic signal operation algorithm using combined data of travel time and occupancy rate. This study applied the travel time data to traffic signal control system, and developed the signal operation algorithm based on saturation degree that was calculated using the travel time data. This algorithm calculates a queue length using a delay model, and converts the queue length to the saturation degree. Moreover, it calculates signal timing variables using this combined saturation degree. This study conducted a microscopic simulation for effectiveness evaluation. We checked that the average intersection delay decreased by up to 27 percent. Moreover, we checked that this signal operation algorithm could respond to a traffic condition of oversaturation and loop detector error effectively and usefully. In korea, sectional traffic detection systems are being installed in various ITS projects, such as Advanced Transportation Management System(ATMS) and Urban Transportation Information System(UTIS). This study has important significance in the sense that it is new methodology to accept the sectional detection system in traffic signal control system.

PURPOSES : The purpose of this study is to present a linear programing optimization model for the design of lane-based lane-uses and signal timings for an isolated intersection. METHODS: For the optimization model, a set of constraints for lane-uses and signal settings are identified to ensure feasibility and safety of traffic flow. Three types of objective functions are introduced for optimizing lane-uses and signal operation, including 1) flow ratio minimization of a dual-ring signal control system, 2) cycle length minimization, and 3) capacity maximization. RESULTS : The three types of model were evaluated in terms of minimizing delay time. From the experimental results, the flow ratio minimization model proved to be more effective in reducing delay time than cycle length minimization and capacity maximization models and provided reasonable cycle lengths located between those of other two models. CONCLUSIONS : It was concluded that the flow ratio minimization objective function is the proper one to implement for lane-uses and signal settings optimization to reduce delay time for signalized intersections.

PURPOSES : This study evaluated the feasibility of implementing protected-permissive left-turn (PPLT) signals at three-leg signalized intersections. METHODS: A three-leg signalized intersection with permissive left-turn was first selected. A VISSIM simulation model was constructed using data collected from the test site. The VISSIM network was calibrated by adjusting related parameter values in order to minimize the difference between the simulated and surveyed critical gap. The calibrated network was validated by the number of waiting left-turning vehicles per cycle. Finally, the mobility and safety measures were extracted from simulation runs in which permissive, protected left turns as well as PPLTs were realized based on diverse traffic volume scenarios. RESULTS : The mobility-related measures of effectiveness (MOEs) of the case with PPLT outperformed the other two left-turn treatment scenarios. In particular, the average waiting time per cycle for the left-turn vehicles in the case with PPLT was reduced by 30 s. The safetyrelated MOEs of the case with PPLT were somewhat higher than those in the case with protected left-turns and much higher than those in the case with permissive left-turns. CONCLUSIONS : Based on the mobility- and safety-related MOEs generated from the VISSIM simulation runs, the use of PPLT seems to be feasible at three-leg signalized intersections where the left-turn is permissive and a pedestrian signal exists at the conflicting approach. However, in order to use the PPLT in earnest, it is necessary to revise the road traffic act, traffic signs, and related manuals.

회전교차로(roundabout)는 용량 이하의 상태에서 접근로별 교통류가 균등할 경우 기존 신호교차로에 비해 운영효율성이 증대되나 토지이용변화로 교통량이 증가하면서 접근로별 교통류가 불균등 해질 경우(차로 당 450대/시 이상) 주접근로에서 회전교차로 내부로의 진입이 어려워져 효율성이 떨어지게 된다. 본 연구에서는 1차로형 4지 회전교차로를 대상으로 회전교차로 설치이후 교통량 증가로 신호교차로 설치에 대한 재검토를 하기 전에 회전교차로를 효율적으로 운영할 수 있는 Signal Metering 전환기준 및 운영방법을 제시하고 효과분석(지체 및 대기행렬)은 SIDRA를 활용하였다. 본 연구결과 총 진입교통량이 1,800~2,000pcu/시 이고 주접근로의 진입교통량비가 60~70%일 때 지체는 30~40% 그리고 대기행렬은 30~60% 감소하였다. 또한 주접근로에 가장 인접한 부접근로에 Metered Approach를 설치하고 한 쌍(pair)으로 묶어서 운영하는 것이 효과적인 것으로 분석되었다.

단일로에 위치한 보행자 신호기는 지역제어기에 사전입력된 값에 의해 매주기마다 보행신호를 제공해 주고, 이로 인해 보행자 교통량이 적은 단일로의 경우 보행자가 없는 경우에도 보행자 신호를 제공함으로써 신호운영상 비효율적인 면이 존재해 왔다. 이로 인해 운전자들은 보행자가 존재하지 않는데도 불구하고, 보행자 신호가 제공됨에 따라 불필요한 신호대기시간을 겪게 되고 교통신호의 비효율적인 운영에 대한 불만이 쌓여 왔고, 그 결과 신호를 위반하고 횡단보도를 통과하는 운전자가 발생함으로써 범법자를 양산하게 되었다. 보행자 안전과 보행자 신호의 효율성을 높이기 위한 방안으로 근래에 일부지역에 보행자작동신호기를 설치하여 운영하고 있지만, 예산 등의 문제 및 보행자작동신호기의 효용성 인식이 부족한 원인 등으로 전국적으로 확대설치가 지연되고 있다. 본 연구에서는 보행자작동신호기 설치 시 비용과 편익을 현장조사 및 시뮬레이션을 이용하여 분석함으로써 이의 효과를 가시적으로 제시하였다. 4개의 연구대상지점을 선정하여 실제 차량 및 보행자교통량을 조사하여 보행자작동신호기의 효과를 검증해 본 결과, 4개소 모두 B/C가 1이 넘어 보행자작동신호기 설치가 타당하다는 결론이 나왔다. 또한 차량교통량과 보행자교통량에 따른 민감도 분석을 한 결과 보행자교통량이 90인/시 보다 많을 경우에는 보행자작동신호기의 효과가 없는 것으로 나타났으며, 보행자 교통량이 90인/시 이하이고, 차량교통량이 2,500대/시 이상일 경우에는 보행자작동신호기에 대한 B/C가 1이 넘어, 이 경우 보행자작동신호기 설치가 타당하다고 나타났다. 또한, 차량교통량이 많고 보행자교통량이 적을수록 그 효과는 더 큰 것으로 나타났다. 본 연구에서는 보행자작동신호기의 설치기준의 근거를 경제성분석을 통해서 제시하였으며, 본 연구의 결과가 향후 보행자작동신호기 확대설치방안을 뒷받침 할 수 있는 기초자료로 사용될 수 있기를 기대한다.