Eungcheol Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Eungcheol Kim has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
Paul Schonfeld
Department of Civil and Environmental Engineering, University of Maryland, College Park, MD, USA
5 shared publications- Manoj K. Jha
Assistant Professor, Dept. of Civil and Environmental System Engineering, Univ. of Incheon, South Korea
4 shared publications Manoj K. Jha
Morgan State University, USA
3 shared publicationsBongsoo Son
Department of Urban Planning and Engineering, Yonsei University, 262, Sungsan-ro, Seodaemun-gu, Seoul 120-749, South Korea
2 shared publications- David J. Lovell
Department of Civil and Environmental Engineering and Institute for Systems Research, University of Maryland, College Park, MD, USA
2 shared publications - Hong Sok Kim
Department of Urban Planning and Engineering, Yonsei University, Seoul, South Korea
2 shared publications
Latest Publications
- 5 January 2023
- Published by Taylor & Francis in Transportation Planning and Technology
- Vol. 46 (2) , 182-199
Development of LSTM-MLR hybrid model for radar detector missing and outlier traffic volume correction
Traffic volume data collected by radar detector contain inherent types of errors that are hard to observe. Therefore, the identification of missing data and outliers based on reliable verification volume data is essential, and the development of a methodology for correcting detector traffic data while considering various specificities at the detector installation sites is required. This study proposed a deep-learning-based long short-term memory–multiple linear regression (LSTM–MLR) hybrid model. First, the corrected detector traffic volume was calculated via the MLR model after the preprocessing of the missing and outlier detector traffic volumes. Second, the corrected radar detector traffic volume was learned via the LSTM model to predict the detector traffic volume for the target time periods. The results confirmed a correction effect in terms of radar detector traffic volume data at most of the 30 target sites. The results of this study provide three contributions. First, the missing and outlier traffic volume correction algorithm is easy to apply and can be applied to traffic volume data collected from various detectors. Second, the MLR model developed in this study derived a causal relationship between the traffic volume of the detector and the complex factors that could not reveal the obvious cause, such as the undetected small car driving next to a large vehicle and the radio transmission/reception problem. Third, complex neural networks and dropout techniques to avoid overfitting do not necessarily improve prediction accuracy.
- 5 January 2023
- Published by Taylor & Francis in Transportation Planning and Technology
- Vol. 46 (2) , 182-199
Development of LSTM-MLR hybrid model for radar detector missing and outlier traffic volume correction
Traffic volume data collected by radar detector contain inherent types of errors that are hard to observe. Therefore, the identification of missing data and outliers based on reliable verification volume data is essential, and the development of a methodology for correcting detector traffic data while considering various specificities at the detector installation sites is required. This study proposed a deep-learning-based long short-term memory–multiple linear regression (LSTM–MLR) hybrid model. First, the corrected detector traffic volume was calculated via the MLR model after the preprocessing of the missing and outlier detector traffic volumes. Second, the corrected radar detector traffic volume was learned via the LSTM model to predict the detector traffic volume for the target time periods. The results confirmed a correction effect in terms of radar detector traffic volume data at most of the 30 target sites. The results of this study provide three contributions. First, the missing and outlier traffic volume correction algorithm is easy to apply and can be applied to traffic volume data collected from various detectors. Second, the MLR model developed in this study derived a causal relationship between the traffic volume of the detector and the complex factors that could not reveal the obvious cause, such as the undetected small car driving next to a large vehicle and the radio transmission/reception problem. Third, complex neural networks and dropout techniques to avoid overfitting do not necessarily improve prediction accuracy.
- Open Access
- 10 August 2019
- Published by Faculty of Transport and Traffic Sciences in Promet - Traffic&Transportation
- Vol. 31 (4) , 387-395
A Threshold Policy for Dispatching Vehicles in Demand-responsive Transit Systems
This paper considers vehicle dispatching for a flexible transit system providing doorstep services from a terminal. The problem is tackled with an easy-to-implement threshold policy, where an available vehicle is dispatched when the number of boarded passengers reaches or exceeds a certain threshold. A simulation-based approach is applied to find the threshold that minimizes the expected system-wide cost. Results show that the optimal threshold is a function of demand, which is commonly stochastic and time-varying. Consequently, the dispatching threshold should be adjusted for different times of the day. In addition, the simulation-based approach is used to simultaneously adjust dispatching threshold and fleet size. The proposed approach is the first work to analyse threshold dispatching policy. It could be used to help improve efficiency of flexible transit systems, and thereby make this sustainable travel mode more economical and appealing to users.
- 10 August 2019
- Published by Faculty of Transport and Traffic Sciences in Promet - Traffic&Transportation
- Vol. 31 (4) , 387-395
Open AccessA Threshold Policy for Dispatching Vehicles in Demand-responsive Transit Systems
This paper considers vehicle dispatching for a flexible transit system providing doorstep services from a terminal. The problem is tackled with an easy-to-implement threshold policy, where an available vehicle is dispatched when the number of boarded passengers reaches or exceeds a certain threshold. A simulation-based approach is applied to find the threshold that minimizes the expected system-wide cost. Results show that the optimal threshold is a function of demand, which is commonly stochastic and time-varying. Consequently, the dispatching threshold should be adjusted for different times of the day. In addition, the simulation-based approach is used to simultaneously adjust dispatching threshold and fleet size. The proposed approach is the first work to analyse threshold dispatching policy. It could be used to help improve efficiency of flexible transit systems, and thereby make this sustainable travel mode more economical and appealing to users.
- 25 June 2018
- Published by Taylor & Francis in Transportation Planning and Technology
- Vol. 41 (6) , 617-643
Switching service types for multi-region bus systems
Conventional fixed-route bus services are generally preferred to flexible-route services at high demand densities, and vice versa. This paper formulates the problem of integrating conventional and flexible services that connect a main terminal to multiple local regions over multiple time periods. The system’s vehicle size, route spacing (for conventional services), service area (for flexible services), headways and fleet sizes are jointly optimized to minimize the sum of supplier costs and user costs. The route spacing for conventional bus services and service area for flexible bus services are also optimized for each region. The proposed solution method, which uses a genetic algorithm and analytic optimization, finds good solutions quickly. Numerical examples and sensitivity analyses confirm that the single fleet variable-type bus service may outperform either the single fleet conventional bus service or the single fleet flexible bus service when demand densities vary substantially among regions and time periods.
- 25 June 2018
- Published by Taylor & Francis in Transportation Planning and Technology
- Vol. 41 (6) , 617-643
Switching service types for multi-region bus systems
Conventional fixed-route bus services are generally preferred to flexible-route services at high demand densities, and vice versa. This paper formulates the problem of integrating conventional and flexible services that connect a main terminal to multiple local regions over multiple time periods. The system’s vehicle size, route spacing (for conventional services), service area (for flexible services), headways and fleet sizes are jointly optimized to minimize the sum of supplier costs and user costs. The route spacing for conventional bus services and service area for flexible bus services are also optimized for each region. The proposed solution method, which uses a genetic algorithm and analytic optimization, finds good solutions quickly. Numerical examples and sensitivity analyses confirm that the single fleet variable-type bus service may outperform either the single fleet conventional bus service or the single fleet flexible bus service when demand densities vary substantially among regions and time periods.
- 1 January 2016
- Published by IGI Global Scientific Publishing
- p. 863-880
A Sensitivity Analysis of Critical Genetic Algorithm Parameters
Genetic Algorithms (GAs) have been applied in many complex combinatorial optimization problems and have been proven to yield reasonably good solutions due to their ability of searching in continuous spaces and avoiding local optima. However, one issue in GA application that needs to be carefully explored is to examine sensitivity of critical parameters that may affect the quality of solutions. The key critical GA parameters affecting solution quality include the number of genetic operators, the number of encoded decision variables, the parameter for selective pressure, and the parameter for non-uniform mutation. The effect of these parameters on solution quality is particularly significant for complex problems of combinatorial nature. In this paper the authors test the sensitivity of critical GA parameters in optimizing 3-dimensional highway alignments which has been proven to be a complex combinatorial optimization problem for which an exact solution is not possible warranting the application of heuristics procedures, such as GAs. If GAs are applied properly, similar optimal solutions should be expected at each replication. The authors perform several example studies in order to arrive at a general set of conclusions regarding the sensitivity of critical GA parameters on solution quality. The first study shows that the optimal solutions obtained for a range of scenarios consisting of different combinations of the critical parameters are quite close. The second study shows that different optimal solutions are obtained when the number of encoded decision variables is changed.
- 1 January 2016
- Published by IGI Global Scientific Publishing
- p. 863-880
A Sensitivity Analysis of Critical Genetic Algorithm Parameters
Genetic Algorithms (GAs) have been applied in many complex combinatorial optimization problems and have been proven to yield reasonably good solutions due to their ability of searching in continuous spaces and avoiding local optima. However, one issue in GA application that needs to be carefully explored is to examine sensitivity of critical parameters that may affect the quality of solutions. The key critical GA parameters affecting solution quality include the number of genetic operators, the number of encoded decision variables, the parameter for selective pressure, and the parameter for non-uniform mutation. The effect of these parameters on solution quality is particularly significant for complex problems of combinatorial nature. In this paper the authors test the sensitivity of critical GA parameters in optimizing 3-dimensional highway alignments which has been proven to be a complex combinatorial optimization problem for which an exact solution is not possible warranting the application of heuristics procedures, such as GAs. If GAs are applied properly, similar optimal solutions should be expected at each replication. The authors perform several example studies in order to arrive at a general set of conclusions regarding the sensitivity of critical GA parameters on solution quality. The first study shows that the optimal solutions obtained for a range of scenarios consisting of different combinations of the critical parameters are quite close. The second study shows that different optimal solutions are obtained when the number of encoded decision variables is changed.
- 28 February 2015
- Published by Korean Society of Transportation in Journal of Korean Society of Transportation
- Vol. 33 (1) , 40-49
Effectiveness and Characteristics Analysis of Inertia Driving on Fuel-Cut Zones in Urban Highway
- 28 February 2015
- Published by Korean Society of Transportation in Journal of Korean Society of Transportation
- Vol. 33 (1) , 40-49
Effectiveness and Characteristics Analysis of Inertia Driving on Fuel-Cut Zones in Urban Highway
- 1 January 2015
- Published by IGI Global Scientific Publishing in International Journal of Operations Research and Information Systems
- Vol. 6 (1) , 30-48
A Sensitivity Analysis of Critical Genetic Algorithm Parameters
Genetic Algorithms (GAs) have been applied in many complex combinatorial optimization problems and have been proven to yield reasonably good solutions due to their ability of searching in continuous spaces and avoiding local optima. However, one issue in GA application that needs to be carefully explored is to examine sensitivity of critical parameters that may affect the quality of solutions. The key critical GA parameters affecting solution quality include the number of genetic operators, the number of encoded decision variables, the parameter for selective pressure, and the parameter for non-uniform mutation. The effect of these parameters on solution quality is particularly significant for complex problems of combinatorial nature. In this paper the authors test the sensitivity of critical GA parameters in optimizing 3-dimensional highway alignments which has been proven to be a complex combinatorial optimization problem for which an exact solution is not possible warranting the application of heuristics procedures, such as GAs. If GAs are applied properly, similar optimal solutions should be expected at each replication. The authors perform several example studies in order to arrive at a general set of conclusions regarding the sensitivity of critical GA parameters on solution quality. The first study shows that the optimal solutions obtained for a range of scenarios consisting of different combinations of the critical parameters are quite close. The second study shows that different optimal solutions are obtained when the number of encoded decision variables is changed.
- 1 January 2015
- Published by IGI Global Scientific Publishing in International Journal of Operations Research and Information Systems
- Vol. 6 (1) , 30-48
A Sensitivity Analysis of Critical Genetic Algorithm Parameters
Genetic Algorithms (GAs) have been applied in many complex combinatorial optimization problems and have been proven to yield reasonably good solutions due to their ability of searching in continuous spaces and avoiding local optima. However, one issue in GA application that needs to be carefully explored is to examine sensitivity of critical parameters that may affect the quality of solutions. The key critical GA parameters affecting solution quality include the number of genetic operators, the number of encoded decision variables, the parameter for selective pressure, and the parameter for non-uniform mutation. The effect of these parameters on solution quality is particularly significant for complex problems of combinatorial nature. In this paper the authors test the sensitivity of critical GA parameters in optimizing 3-dimensional highway alignments which has been proven to be a complex combinatorial optimization problem for which an exact solution is not possible warranting the application of heuristics procedures, such as GAs. If GAs are applied properly, similar optimal solutions should be expected at each replication. The authors perform several example studies in order to arrive at a general set of conclusions regarding the sensitivity of critical GA parameters on solution quality. The first study shows that the optimal solutions obtained for a range of scenarios consisting of different combinations of the critical parameters are quite close. The second study shows that different optimal solutions are obtained when the number of encoded decision variables is changed.
- 19 September 2013
- Published by Taylor & Francis in International Journal of Urban Sciences
- Vol. 18 (1) , 61-75
Development of a Korea highway safety evaluation proto type model on the concept of IHSDM crash prediction module
This study tries to develop a Korea highway safety evaluation proto type model for quantified safety evaluation. We develop a base model and crash modification factors (CMFs) through reviewing the procedures and methodologies in Highway Safety Manual. At the same time, we try to carefully consider collectable data and roadway environment of Korea that are different from the USA. CMFs are developed through models and expert's judgement. Developed CMFs are for driveway density, pedestrian crosswalk, existence of median, terrain types, and land-use types. Also, verification of the developed base model and CMFs were performed using two routes of Korea's rural two-lane highways while comparing with roadway safety design synthesis and Crash Prediction Module (CPM) of Interactive Highway Safety Design Model (IHSDM). Applicability analysis was then performed in two aspects of predictability and adaptability of the proto type model. As a result, CMFs and predicted accident estimates of CPM are similar with the developed Korea proto type model. However, the base model and CMFs of the developed proto type for Korea are more precise than the others when evaluating sections where the number of actual accidents is higher. It is found that considering CMF for land-use type is justifiable when developing a Korea highway safety evaluation proto type model. This study validates the possibility of developing a full scale of Korea highway safety evaluation model.
- 19 September 2013
- Published by Taylor & Francis in International Journal of Urban Sciences
- Vol. 18 (1) , 61-75
Development of a Korea highway safety evaluation proto type model on the concept of IHSDM crash prediction module
This study tries to develop a Korea highway safety evaluation proto type model for quantified safety evaluation. We develop a base model and crash modification factors (CMFs) through reviewing the procedures and methodologies in Highway Safety Manual. At the same time, we try to carefully consider collectable data and roadway environment of Korea that are different from the USA. CMFs are developed through models and expert's judgement. Developed CMFs are for driveway density, pedestrian crosswalk, existence of median, terrain types, and land-use types. Also, verification of the developed base model and CMFs were performed using two routes of Korea's rural two-lane highways while comparing with roadway safety design synthesis and Crash Prediction Module (CPM) of Interactive Highway Safety Design Model (IHSDM). Applicability analysis was then performed in two aspects of predictability and adaptability of the proto type model. As a result, CMFs and predicted accident estimates of CPM are similar with the developed Korea proto type model. However, the base model and CMFs of the developed proto type for Korea are more precise than the others when evaluating sections where the number of actual accidents is higher. It is found that considering CMF for land-use type is justifiable when developing a Korea highway safety evaluation proto type model. This study validates the possibility of developing a full scale of Korea highway safety evaluation model.
- 1 February 2013
- Published by American Society of Civil Engineers (ASCE) in Journal of Transportation Engineering
- Vol. 139 (2) , 230-238
Comparison of Vertical Alignments for Rail Transit
In this paper two vertical alignment profiles (labeled dipped and undipped) connecting rail transit stations with different elevations are compared. A deterministic simulation model is developed and used to analyze train motion and energy use for three different vertical alignments. To minimize the cost of rail transit operation for both directions, cruising speed is optimized as a decision variable while train operations are simulated on the proposed vertical alignments. The numerical analysis and sensitivity studies show that the developed deterministic simulation model is useful for comparing vertical alignments, and that the proposed alignment concepts can significantly reduce travel time, energy use, brake wear, operating cost, and total cost compared with the baseline alignment profile.
- 1 February 2013
- Published by American Society of Civil Engineers (ASCE) in Journal of Transportation Engineering
- Vol. 139 (2) , 230-238
Comparison of Vertical Alignments for Rail Transit
In this paper two vertical alignment profiles (labeled dipped and undipped) connecting rail transit stations with different elevations are compared. A deterministic simulation model is developed and used to analyze train motion and energy use for three different vertical alignments. To minimize the cost of rail transit operation for both directions, cruising speed is optimized as a decision variable while train operations are simulated on the proposed vertical alignments. The numerical analysis and sensitivity studies show that the developed deterministic simulation model is useful for comparing vertical alignments, and that the proposed alignment concepts can significantly reduce travel time, energy use, brake wear, operating cost, and total cost compared with the baseline alignment profile.
- 1 January 2013
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2374 (1) , 143-153
Simulation-Based Rail Transit Optimization Model
A proposed bilevel optimization process determines the depth of a dipped vertical alignment between rail transit stations as well as the cruising speed for each direction. This model also considers how regenerative braking may affect vertical alignment decisions. The optimized depth and directional cruising speeds were jointly obtained in a numerical example. A sensitivity analysis showed that regenerative braking reduced the total cost but did not significantly change the optimized depth of the dipped vertical alignment. The developed model is more realistic and useful than previous ones because it allows unequal station elevations, jointly optimizes decision variables, and considers regenerative braking.
- 1 January 2013
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2374 (1) , 143-153
Simulation-Based Rail Transit Optimization Model
A proposed bilevel optimization process determines the depth of a dipped vertical alignment between rail transit stations as well as the cruising speed for each direction. This model also considers how regenerative braking may affect vertical alignment decisions. The optimized depth and directional cruising speeds were jointly obtained in a numerical example. A sensitivity analysis showed that regenerative braking reduced the total cost but did not significantly change the optimized depth of the dipped vertical alignment. The developed model is more realistic and useful than previous ones because it allows unequal station elevations, jointly optimizes decision variables, and considers regenerative braking.
- Open Access
- 1 May 2012
- Published by Elsevier in KSCE Journal of Civil Engineering
- Vol. 16 (4) , 627-632
Critical factors associated with bicycle accidents at 4-legged signalized urban intersections in South Korea
- 1 May 2012
- Published by Elsevier in KSCE Journal of Civil Engineering
- Vol. 16 (4) , 627-632
Open AccessCritical factors associated with bicycle accidents at 4-legged signalized urban intersections in South Korea