Haram Oh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haram Oh has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Donggyun Ku
Department of Transportation Engineering, University of Seoul, Seoul, Republic of Korea
2 shared publications - Minje Choi
Department of Transportation Engineering, University of Seoul, Seoul, Republic of Korea
2 shared publications - Seungjae Lee
University of Seoul Department of Transportation Engineering Seoul, Republic of
2 shared publications - Seungheon Shin
BS student, Department of Transportation Engineering, University of Seoul, Seoul, Republic of Korea
1 shared publication - Sungyoung Na
Department of Construction Policy Research, Korea Institute of Civil Engineering and Building Technology, Gyeonggi, Republic of Korea
1 shared publication
Latest Publications
- 14 September 2022
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2677 (3) , 1033-1047
Stated Preference Analysis With Latent Variables for Higher Speed Rail
Recently, the necessity to redefine the mode selection model (modal split model) has emerged owing to the diversification of transportation systems. In addition to socio-economic factors, preference factors and user characteristics significantly affect the selection of transportation mode. Therefore, user preferences are reflected in the modal split model. The latent class model is highly descriptive, and its suitability can be improved. With the advent of high-speed rail (Great Train eXpress [GTX]), Seoul has established a competitive and complementary relationship for the demand of passengers between general and great express rail. Therefore, a modal split model reflecting the characteristics of the GTX, which is redefined by applying a latent variable to the stated preference analysis, is necessary. Latent class analysis uses the Bayesian information criterion and log-likelihood to distinguish the travel property (Cluster1), station property (Cluster2), and transfer property (Cluster 3). After comparing the time values for each cluster, the GTX preference is analyzed based on the inner and outer circle situations. A model that accurately reflects the characteristics and preferences of passengers is proposed in this paper. In the future, strategies can be established for the inner and outer circle situations, and higher operational efficiency can be achieved by combining the GTX and subway.
- 14 September 2022
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
- Vol. 2677 (3) , 1033-1047
Stated Preference Analysis With Latent Variables for Higher Speed Rail
Recently, the necessity to redefine the mode selection model (modal split model) has emerged owing to the diversification of transportation systems. In addition to socio-economic factors, preference factors and user characteristics significantly affect the selection of transportation mode. Therefore, user preferences are reflected in the modal split model. The latent class model is highly descriptive, and its suitability can be improved. With the advent of high-speed rail (Great Train eXpress [GTX]), Seoul has established a competitive and complementary relationship for the demand of passengers between general and great express rail. Therefore, a modal split model reflecting the characteristics of the GTX, which is redefined by applying a latent variable to the stated preference analysis, is necessary. Latent class analysis uses the Bayesian information criterion and log-likelihood to distinguish the travel property (Cluster1), station property (Cluster2), and transfer property (Cluster 3). After comparing the time values for each cluster, the GTX preference is analyzed based on the inner and outer circle situations. A model that accurately reflects the characteristics and preferences of passengers is proposed in this paper. In the future, strategies can be established for the inner and outer circle situations, and higher operational efficiency can be achieved by combining the GTX and subway.
- 1 September 2022
- Published by Emerald Publishing in Proceedings of the Institution of Civil Engineers - Municipal Engineer
- Vol. 175 (3) , 135-147
Assessment of the resilience of pedestrian roads based on image deep learning models
Currently, the evaluation of pedestrian paths is very time consuming. Additionally, disabled pedestrians do not tend to change their routes, even if pedestrian conditions are poor, resulting in reduced convenience and safety. Therefore, it is important to identify and act on the statuses of pedestrian paths quickly. Therefore, this study aimed to identify and process the conditions of pedestrian paths quickly to achieve high resilience. A resilience triangle was calculated according to the discrimination automation to analyse the corresponding values. Pedestrian path discrimination automation applies convolutional neural networks and ‘you only look once’ analysis to identify the road surface conditions of walkways and the presence of obstacles. Quantitative analyses for the safety and economic problems associated with transportation vulnerabilities through discrimination algorithms using deep image learning were carried out. As a result of the analyses, it was possible to determine the extent of damage with 94% accuracy if only damaged sidewalk photographs are captured. When this result was applied in Seoul, the benefits of improving pedestrian paths were quantitatively calculated to be South Korean Won (KRW) 41.2 billion (1 KRW=US$0.00085). This study may secure pedestrian resilience and improve convenience in the current scenario of a rapidly ageing population.
- 1 September 2022
- Published by Emerald Publishing in Proceedings of the Institution of Civil Engineers - Municipal Engineer
- Vol. 175 (3) , 135-147
Assessment of the resilience of pedestrian roads based on image deep learning models
Currently, the evaluation of pedestrian paths is very time consuming. Additionally, disabled pedestrians do not tend to change their routes, even if pedestrian conditions are poor, resulting in reduced convenience and safety. Therefore, it is important to identify and act on the statuses of pedestrian paths quickly. Therefore, this study aimed to identify and process the conditions of pedestrian paths quickly to achieve high resilience. A resilience triangle was calculated according to the discrimination automation to analyse the corresponding values. Pedestrian path discrimination automation applies convolutional neural networks and ‘you only look once’ analysis to identify the road surface conditions of walkways and the presence of obstacles. Quantitative analyses for the safety and economic problems associated with transportation vulnerabilities through discrimination algorithms using deep image learning were carried out. As a result of the analyses, it was possible to determine the extent of damage with 94% accuracy if only damaged sidewalk photographs are captured. When this result was applied in Seoul, the benefits of improving pedestrian paths were quantitatively calculated to be South Korean Won (KRW) 41.2 billion (1 KRW=US$0.00085). This study may secure pedestrian resilience and improve convenience in the current scenario of a rapidly ageing population.