jaein song - Academia.edu (original) (raw)

Papers by jaein song

Sustainability

The problem of structural imbalance in terms of supply and demand due to changes in traffic patte... more The problem of structural imbalance in terms of supply and demand due to changes in traffic patterns by time zone has been continuously raised in the mobility market. In Korea, unlike large overseas cities, the waiting time tolerance increases during the daytime when supply far exceeds demand, resulting in a large loss of operating profit. The purpose of this study is to increase taxi demand and further improve driver’s profits through real-time fare discounts during off-peak daytime hours in Seoul, Korea. To this end, we propose a real-time fare bidding system among taxi drivers based on a dynamic pricing scheme and simulate the appropriate fare discount level for each regional time zone. The driver-to-driver fare competition system consists of simulating fare competition based on the multi-agent Deep Q-Network method after developing a fare discount index that reflects the supply and demand level of each region in 25 districts in Seoul. According to the optimal fare discount level...

Sustainability

As new mobility called automated vehicles (AVs) appears on the road, positive effects are expecte... more As new mobility called automated vehicles (AVs) appears on the road, positive effects are expected, but in fact, unexpected adverse effects may arise due to the mixed traffic situation with human-driven vehicles (HVs). Prior to the commercialization of AVs, a preliminary review and preventive measures are required, and among them, the interaction between the existing vehicle and the new mobility and the interaction with the infrastructure must be considered. Therefore, we propose (i) the positive–negative effect of introducing AVs in a mixed traffic situation and (ii) the optimal operation plan for the dedicated lane for AVs. First, the effect of introducing AVs considering the interaction between vehicles in the mixed traffic situation showed mostly positive such as speed increase, delay time reduction, and capacity increase. However, in a 75% Market Penetration Rate (MPR) environment of all levels of Service (LOS), the effect was diminished compared to the previous MPR. This is co...

Electronics

As automated vehicles have been considered one of the important trends in intelligent transportat... more As automated vehicles have been considered one of the important trends in intelligent transportation systems, various research is being conducted to enhance their safety. In particular, the importance of technologies for the design of preventive automated driving systems, such as detection of surrounding objects and estimation of distance between vehicles. Object detection is mainly performed through cameras and LiDAR, but due to the cost and limits of LiDAR’s recognition distance, the need to improve Camera recognition technique, which is relatively convenient for commercialization, is increasing. This study learned convolutional neural network (CNN)-based faster regions with CNN (Faster R-CNN) and You Only Look Once (YOLO) V2 to improve the recognition techniques of vehicle-mounted monocular cameras for the design of preventive automated driving systems, recognizing surrounding vehicles in black box highway driving videos and estimating distances from surrounding vehicles through ...

Journal of Korean Society of Transportation

The Korea Institute Of Intelligent Transport Systems, Dec 1, 2020

The Journal of The Korea Institute of Intelligent Transport Systems, 2022

SSRN Electronic Journal, 2022

Fusion Engineering and Design, 2021

Abstract Shattered pellet injection (SPI) is the technology chosen for the ITER Disruption Mitiga... more Abstract Shattered pellet injection (SPI) is the technology chosen for the ITER Disruption Mitigation System and is explored at several fusion research devices, like DIII-D and JET and J-TEXT. The ITER disruption mitigation strategy relies on multiple injections to achieve RE (runaway electron) avoidance with optimum TQ (thermal quench), CQ (current quench) durations to adequately reduce wall loads. To demonstrate the feasibility of the multiple injection and to extrapolate to ITER, experiments with two identical injectors toroidally opposite to each other are needed urgently. KSTAR (Korea Superconducting Tokamak Advanced Research) can be a unique testbed to study the plasma disruption mitigation for ITER. KSTAR has installed two identical injectors in 180 degrees of toroidal opposite positions in 2019. For this system, ORNL (Oak Ridge National Laboratory) provided the two injectors, the shatter tubes, and auxiliary systems. NFRI (National Fusion Research Institute) provided the infrastructure of a vacuum pumping system, control & data acquisition system, and installed additional diagnostic systems for SPI in collaboration with the ITER Organization. This paper describes the engineering achievements during installation on KSTAR and the initial results of single and multiple SPI experiments in the 2019 campaign.

2020 International Conference on Computational Science and Computational Intelligence (CSCI), 2020

Black ice is recognized as the main cause of major accidents in winter because it has characteris... more Black ice is recognized as the main cause of major accidents in winter because it has characteristics that are difficult to identify with the naked eye. This is expected to be a potential cause of accidents in the era of automated vehicles as well. Accordingly, this study presents a CNN-based black ice detection plan to prevent traffic accidents caused by black ice. Due to the characteristic of black ice that is formed only in a certain environment, the data was augmented and the image of road environment in various environments was learned. Test results show that the proposed CNN model detected black ice with 96% accuracy and reproducibility(recall).

Journal of Korea Planning Association, 2021

The Journal of The Korea Institute of Intelligent Transport Systems, 2021

The Journal of The Korea Institute of Intelligent Transport Systems, 2020

Electronics, 2020

Automated Vehicles (AVs) are under development to reduce traffic accidents to a great extent. The... more Automated Vehicles (AVs) are under development to reduce traffic accidents to a great extent. Therefore, safety will play a pivotal role to determine their social acceptability. Despite the fast development of AVs technologies, related accidents can occur even in an ideal environment. Therefore, measures to prevent traffic accidents in advance are essential. This study implemented a traffic accident context analysis based on the Deep Neural Network (DNNs) technique to design a Preventive Automated Driving System (PADS). The DNN-based analysis reveals that when a traffic accident occurs, the offender’s injury can be predicted with 85% accuracy and the victim’s case with 67%. In addition, to find out factors that decide the degree of injury to the offender and victim, a random forest analysis was implemented. The vehicle type and speed were identified as the most important factors to decide the degree of injury of the offender, while the importance for the victim is ordered by speed, ...

Fusion Engineering and Design, 2020

Shattered pellet injection is of the most attractive way to mitigate the plasma disruption in fus... more Shattered pellet injection is of the most attractive way to mitigate the plasma disruption in fusion research facilities up to now. DIII-D has already utilized it and achieved very positive results. ITER has decided to adopt this technology for the DMS (disruption mitigation system) for PFPO-1 (Pre-Fusion Power Operation phase 1). The validation between simulation code and experiment, and continuous engineering development need to be carried out to meet the DMS's requirement and reliability. KSTAR (Korea Superconducting Tokamak Advanced Research) is a possible candidate to test the urgent issues of plasma disruption for ITER. KSTAR can install two injectors in toroidal opposite positions. For this work, ORNL (Oak Ridge National Laboratory) will provide the two injectors, the shatter tubes and auxiliary systems. NFRI (National Fusion Research Institute) is preparing the infrastructure of a pumping system, control and data acquisition system, and arranging the location of diagnostic and the heating systems. This presentation describes the basic requirements and the engineering challenges to be solved for successful deployment and operation of multiple SPI injectors in 2019.

Fusion Engineering and Design, 2019

A pellet injection system operating at 20 Hz has been operated in KSTAR (Korea Superconducting To... more A pellet injection system operating at 20 Hz has been operated in KSTAR (Korea Superconducting Tokamak Advanced Research) since 2016. This system can inject pellets with various size, velocity, and frequency to the KSTAR vacuum vessel during plasma experiments. Various experiments such as peak density control, enhancement of confinement by increasing core beta, and NTM stabilization were carried out with the pellet injection system in 2018. Most of all, the characteristics of the pellet should be studied to better understand the interaction with plasma. The pellet trajectory is one of the interesting topics in KSTAR and therefore a related investigation was carried out outside of the tokamak first. We introduce the preliminary results of the trajectory test, the pellet velocity tendency, and a plasma experiment in this paper.

Fusion Engineering and Design, 2018

Hz pellet injection system was installed for improving a fueling system of KSTAR (Korea Supercond... more Hz pellet injection system was installed for improving a fueling system of KSTAR (Korea Superconducting Tokamak Advanced Research) in 2016. Several things of hardware such as a liquid helium transfer line, an extruder nozzle and an extension part of pellet guide tube are changed for 2017 campaign. For plasma experiments, the pellet injection system uses the smallest pellet (1.5 mm of length, 2 mm of diameter). The pellet velocity can be variable from 150 m/s to over 200 m/s by controlling of propellant gas pressure. The clear increase of plasma density observed during KSTAR experiments is also presented in this paper.

Fusion Engineering and Design, 2016

The tungsten (W) brazed flat type mock-up which consists of W, OFHC-Cu (oxygen-free high conducti... more The tungsten (W) brazed flat type mock-up which consists of W, OFHC-Cu (oxygen-free high conductive copper) and CuCrZr alloy has been designed for KSTAR divertor in preparation for KSTAR upgrade with 17 MW heating power. For verification of the W brazed mock-up, the high heat flux test is performed at KoHLT-EB (Korea High Heat Load Test Facility-Electron Beam) in KAERI (Korea Atomic Energy Research Institute). Three mock-ups are tested for several thousand thermal cycles with absorbed heat flux up to 5 MW/m 2 for 20 s duration. There is no evidence of the failure at the bonding joints of all mock-ups after HHF test. Finite element analysis (FEA) is performed to interpret the result of the test. As a result, it is considered that the local area in the water is in the subcooled boiling regime.

In the traditional four-step travel demand models, each step is sequentially conducted following ... more In the traditional four-step travel demand models, each step is sequentially conducted following the model estimation at the previous step. The accuracy of the following model is partly dependent on whether the model at the former stage was properly established or not. Therefore, trip generation, which is the first step in this conventional model, has great effects on the modeling process and forecasting results. Linear regression models for trip generation of Seoul Metropolitan Area might increase the forcasting errors, since a variety of land-use characteristics are not considered. Hence, in this study, zonal factors such as socioeconomic and land use variables are included to improve the elaboration of trip generation. Comparing the %RMSE with the existing models, which contain bigger errors in the zones highly based on the secondary and tertiary industries than residence-based, the trip generation models including those variables seem more appropriate overall.

Sustainability

The problem of structural imbalance in terms of supply and demand due to changes in traffic patte... more The problem of structural imbalance in terms of supply and demand due to changes in traffic patterns by time zone has been continuously raised in the mobility market. In Korea, unlike large overseas cities, the waiting time tolerance increases during the daytime when supply far exceeds demand, resulting in a large loss of operating profit. The purpose of this study is to increase taxi demand and further improve driver’s profits through real-time fare discounts during off-peak daytime hours in Seoul, Korea. To this end, we propose a real-time fare bidding system among taxi drivers based on a dynamic pricing scheme and simulate the appropriate fare discount level for each regional time zone. The driver-to-driver fare competition system consists of simulating fare competition based on the multi-agent Deep Q-Network method after developing a fare discount index that reflects the supply and demand level of each region in 25 districts in Seoul. According to the optimal fare discount level...

Sustainability

As new mobility called automated vehicles (AVs) appears on the road, positive effects are expecte... more As new mobility called automated vehicles (AVs) appears on the road, positive effects are expected, but in fact, unexpected adverse effects may arise due to the mixed traffic situation with human-driven vehicles (HVs). Prior to the commercialization of AVs, a preliminary review and preventive measures are required, and among them, the interaction between the existing vehicle and the new mobility and the interaction with the infrastructure must be considered. Therefore, we propose (i) the positive–negative effect of introducing AVs in a mixed traffic situation and (ii) the optimal operation plan for the dedicated lane for AVs. First, the effect of introducing AVs considering the interaction between vehicles in the mixed traffic situation showed mostly positive such as speed increase, delay time reduction, and capacity increase. However, in a 75% Market Penetration Rate (MPR) environment of all levels of Service (LOS), the effect was diminished compared to the previous MPR. This is co...

Electronics

As automated vehicles have been considered one of the important trends in intelligent transportat... more As automated vehicles have been considered one of the important trends in intelligent transportation systems, various research is being conducted to enhance their safety. In particular, the importance of technologies for the design of preventive automated driving systems, such as detection of surrounding objects and estimation of distance between vehicles. Object detection is mainly performed through cameras and LiDAR, but due to the cost and limits of LiDAR’s recognition distance, the need to improve Camera recognition technique, which is relatively convenient for commercialization, is increasing. This study learned convolutional neural network (CNN)-based faster regions with CNN (Faster R-CNN) and You Only Look Once (YOLO) V2 to improve the recognition techniques of vehicle-mounted monocular cameras for the design of preventive automated driving systems, recognizing surrounding vehicles in black box highway driving videos and estimating distances from surrounding vehicles through ...

Journal of Korean Society of Transportation

The Korea Institute Of Intelligent Transport Systems, Dec 1, 2020

The Journal of The Korea Institute of Intelligent Transport Systems, 2022

SSRN Electronic Journal, 2022

Fusion Engineering and Design, 2021

Abstract Shattered pellet injection (SPI) is the technology chosen for the ITER Disruption Mitiga... more Abstract Shattered pellet injection (SPI) is the technology chosen for the ITER Disruption Mitigation System and is explored at several fusion research devices, like DIII-D and JET and J-TEXT. The ITER disruption mitigation strategy relies on multiple injections to achieve RE (runaway electron) avoidance with optimum TQ (thermal quench), CQ (current quench) durations to adequately reduce wall loads. To demonstrate the feasibility of the multiple injection and to extrapolate to ITER, experiments with two identical injectors toroidally opposite to each other are needed urgently. KSTAR (Korea Superconducting Tokamak Advanced Research) can be a unique testbed to study the plasma disruption mitigation for ITER. KSTAR has installed two identical injectors in 180 degrees of toroidal opposite positions in 2019. For this system, ORNL (Oak Ridge National Laboratory) provided the two injectors, the shatter tubes, and auxiliary systems. NFRI (National Fusion Research Institute) provided the infrastructure of a vacuum pumping system, control & data acquisition system, and installed additional diagnostic systems for SPI in collaboration with the ITER Organization. This paper describes the engineering achievements during installation on KSTAR and the initial results of single and multiple SPI experiments in the 2019 campaign.

2020 International Conference on Computational Science and Computational Intelligence (CSCI), 2020

Black ice is recognized as the main cause of major accidents in winter because it has characteris... more Black ice is recognized as the main cause of major accidents in winter because it has characteristics that are difficult to identify with the naked eye. This is expected to be a potential cause of accidents in the era of automated vehicles as well. Accordingly, this study presents a CNN-based black ice detection plan to prevent traffic accidents caused by black ice. Due to the characteristic of black ice that is formed only in a certain environment, the data was augmented and the image of road environment in various environments was learned. Test results show that the proposed CNN model detected black ice with 96% accuracy and reproducibility(recall).

Journal of Korea Planning Association, 2021

The Journal of The Korea Institute of Intelligent Transport Systems, 2021

The Journal of The Korea Institute of Intelligent Transport Systems, 2020

Electronics, 2020

Automated Vehicles (AVs) are under development to reduce traffic accidents to a great extent. The... more Automated Vehicles (AVs) are under development to reduce traffic accidents to a great extent. Therefore, safety will play a pivotal role to determine their social acceptability. Despite the fast development of AVs technologies, related accidents can occur even in an ideal environment. Therefore, measures to prevent traffic accidents in advance are essential. This study implemented a traffic accident context analysis based on the Deep Neural Network (DNNs) technique to design a Preventive Automated Driving System (PADS). The DNN-based analysis reveals that when a traffic accident occurs, the offender’s injury can be predicted with 85% accuracy and the victim’s case with 67%. In addition, to find out factors that decide the degree of injury to the offender and victim, a random forest analysis was implemented. The vehicle type and speed were identified as the most important factors to decide the degree of injury of the offender, while the importance for the victim is ordered by speed, ...

Fusion Engineering and Design, 2020

Shattered pellet injection is of the most attractive way to mitigate the plasma disruption in fus... more Shattered pellet injection is of the most attractive way to mitigate the plasma disruption in fusion research facilities up to now. DIII-D has already utilized it and achieved very positive results. ITER has decided to adopt this technology for the DMS (disruption mitigation system) for PFPO-1 (Pre-Fusion Power Operation phase 1). The validation between simulation code and experiment, and continuous engineering development need to be carried out to meet the DMS's requirement and reliability. KSTAR (Korea Superconducting Tokamak Advanced Research) is a possible candidate to test the urgent issues of plasma disruption for ITER. KSTAR can install two injectors in toroidal opposite positions. For this work, ORNL (Oak Ridge National Laboratory) will provide the two injectors, the shatter tubes and auxiliary systems. NFRI (National Fusion Research Institute) is preparing the infrastructure of a pumping system, control and data acquisition system, and arranging the location of diagnostic and the heating systems. This presentation describes the basic requirements and the engineering challenges to be solved for successful deployment and operation of multiple SPI injectors in 2019.

Fusion Engineering and Design, 2019

A pellet injection system operating at 20 Hz has been operated in KSTAR (Korea Superconducting To... more A pellet injection system operating at 20 Hz has been operated in KSTAR (Korea Superconducting Tokamak Advanced Research) since 2016. This system can inject pellets with various size, velocity, and frequency to the KSTAR vacuum vessel during plasma experiments. Various experiments such as peak density control, enhancement of confinement by increasing core beta, and NTM stabilization were carried out with the pellet injection system in 2018. Most of all, the characteristics of the pellet should be studied to better understand the interaction with plasma. The pellet trajectory is one of the interesting topics in KSTAR and therefore a related investigation was carried out outside of the tokamak first. We introduce the preliminary results of the trajectory test, the pellet velocity tendency, and a plasma experiment in this paper.

Fusion Engineering and Design, 2018

Hz pellet injection system was installed for improving a fueling system of KSTAR (Korea Supercond... more Hz pellet injection system was installed for improving a fueling system of KSTAR (Korea Superconducting Tokamak Advanced Research) in 2016. Several things of hardware such as a liquid helium transfer line, an extruder nozzle and an extension part of pellet guide tube are changed for 2017 campaign. For plasma experiments, the pellet injection system uses the smallest pellet (1.5 mm of length, 2 mm of diameter). The pellet velocity can be variable from 150 m/s to over 200 m/s by controlling of propellant gas pressure. The clear increase of plasma density observed during KSTAR experiments is also presented in this paper.

Fusion Engineering and Design, 2016

The tungsten (W) brazed flat type mock-up which consists of W, OFHC-Cu (oxygen-free high conducti... more The tungsten (W) brazed flat type mock-up which consists of W, OFHC-Cu (oxygen-free high conductive copper) and CuCrZr alloy has been designed for KSTAR divertor in preparation for KSTAR upgrade with 17 MW heating power. For verification of the W brazed mock-up, the high heat flux test is performed at KoHLT-EB (Korea High Heat Load Test Facility-Electron Beam) in KAERI (Korea Atomic Energy Research Institute). Three mock-ups are tested for several thousand thermal cycles with absorbed heat flux up to 5 MW/m 2 for 20 s duration. There is no evidence of the failure at the bonding joints of all mock-ups after HHF test. Finite element analysis (FEA) is performed to interpret the result of the test. As a result, it is considered that the local area in the water is in the subcooled boiling regime.

In the traditional four-step travel demand models, each step is sequentially conducted following ... more In the traditional four-step travel demand models, each step is sequentially conducted following the model estimation at the previous step. The accuracy of the following model is partly dependent on whether the model at the former stage was properly established or not. Therefore, trip generation, which is the first step in this conventional model, has great effects on the modeling process and forecasting results. Linear regression models for trip generation of Seoul Metropolitan Area might increase the forcasting errors, since a variety of land-use characteristics are not considered. Hence, in this study, zonal factors such as socioeconomic and land use variables are included to improve the elaboration of trip generation. Comparing the %RMSE with the existing models, which contain bigger errors in the zones highly based on the secondary and tertiary industries than residence-based, the trip generation models including those variables seem more appropriate overall.