Seung-Young Kho

Publications

4 Missing Link Data Estimation with Recurrent Neural Network: An Application Using Speed Data of Daegu Metropolitan Area

Authors: JaeHwan Yang, Da-Woon Jeong, Seung-Young Kho, Dong-Kyu Kim

Abstract:

In terms of ITS, information on link characteristic is an essential factor for plan or operation. But in practical cases, not every link has installed sensors on it. The link that does not have data on it is called “Missing Link”. The purpose of this study is to impute data of these missing links. To get these data, this study applies the machine learning method. With the machine learning process, especially for the deep learning process, missing link data can be estimated from present link data. For deep learning process, this study uses “Recurrent Neural Network” to take time-series data of road. As input data, Dedicated Short-range Communications (DSRC) data of Dalgubul-daero of Daegu Metropolitan Area had been fed into the learning process. Neural Network structure has 17 links with present data as input, 2 hidden layers, for 1 missing link data. As a result, forecasted data of target link show about 94% of accuracy compared with actual data.

Keywords: Machine Learning, road network, data estimation, link data

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 892
3 Quantifying Freeway Capacity Reductions by Rainfall Intensities Based on Stochastic Nature of Flow Breakdown

Authors: Hoyoung Lee, Dong-Kyu Kim, Seung-Young Kho, R. Eddie Wilson

Abstract:

This study quantifies a decrement in freeway capacity during rainfall. Traffic and rainfall data were gathered from Highway Agencies and Wunderground weather service. Three inter-urban freeway sections and its nearest weather stations were selected as experimental sites. Capacity analysis found reductions of maximum and mean pre-breakdown flow rates due to rainfall. The Kruskal-Wallis test also provided some evidence to suggest that the variance in the pre-breakdown flow rate is statistically insignificant. Potential application of this study lies in the operation of real time traffic management schemes such as Variable Speed Limits (VSL), Hard Shoulder Running (HSR), and Ramp Metering System (RMS), where speed or flow limits could be set based on a number of factors, including rainfall events and their intensities.

Keywords: Rainfall, capacity randomness, flow breakdown, freeway capacity

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 941
2 Latent Factors of Severity in Truck-Involved and Non-Truck-Involved Crashes on Freeways

Authors: Shin-Hyung Cho, Dong-Kyu Kim, Seung-Young Kho

Abstract:

Truck-involved crashes have higher crash severity than non-truck-involved crashes. There have been many studies about the frequency of crashes and the development of severity models, but those studies only analyzed the relationship between observed variables. To identify why more people are injured or killed when trucks are involved in the crash, we must examine to quantify the complex causal relationship between severity of the crash and risk factors by adopting the latent factors of crashes. The aim of this study was to develop a structural equation or model based on truck-involved and non-truck-involved crashes, including five latent variables, i.e. a crash factor, environmental factor, road factor, driver’s factor, and severity factor. To clarify the unique characteristics of truck-involved crashes compared to non-truck-involved crashes, a confirmatory analysis method was used. To develop the model, we extracted crash data from 10,083 crashes on Korean freeways from 2008 through 2014. The results showed that the most significant variable affecting the severity of a crash is the crash factor, which can be expressed by the location, cause, and type of the crash. For non-truck-involved crashes, the crash and environment factors increase severity of the crash; conversely, the road and driver factors tend to reduce severity of the crash. For truck-involved crashes, the driver factor has a significant effect on severity of the crash although its effect is slightly less than the crash factor. The multiple group analysis employed to analyze the differences between the heterogeneous groups of drivers.

Keywords: Structural Equation Modeling, crash severity, truck-involved crashes, multiple group analysis, crash on freeway

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 985
1 A Study of Mode Choice Model Improvement Considering Age Grouping

Authors: Young-Hyun Seo, Hyunwoo Park, Dong-Kyu Kim, Seung-Young Kho

Abstract:

The purpose of this study is providing an improved mode choice model considering parameters including age grouping of prime-aged and old age. In this study, 2010 Household Travel Survey data were used and improper samples were removed through the analysis. Chosen alternative, date of birth, mode, origin code, destination code, departure time, and arrival time are considered from Household Travel Survey. By preprocessing data, travel time, travel cost, mode, and ratio of people aged 45 to 55 years, 55 to 65 years and over 65 years were calculated. After the manipulation, the mode choice model was constructed using LIMDEP by maximum likelihood estimation. A significance test was conducted for nine parameters, three age groups for three modes. Then the test was conducted again for the mode choice model with significant parameters, travel cost variable and travel time variable. As a result of the model estimation, as the age increases, the preference for the car decreases and the preference for the bus increases. This study is meaningful in that the individual and households characteristics are applied to the aggregate model.

Keywords: Aging, multinomial logit model, age grouping, mode choice model

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1269

Abstracts

9 Relationship between Driving under the Influence and Traffic Safety

Authors: Eun Hak Lee, Young-Hyun Seo, Hosuk Shin, Seung-Young Kho

Abstract:

Among traffic crashes, driving under the influence (DUI) of alcohol is the most dangerous behavior in Seoul, South Korea. In 2016 alone 40 deaths occurred on of 2,857 cases of DUI. Since DUI is one of the major factors in increasing the severity of crashes, the intensive management of DUI required to reduce traffic crash deaths and the crash damages. This study aims to investigate the relationship between DUI and traffic safety in order to establish countermeasures for traffic safety improvement. The analysis was conducted on the habitual drivers who drove under the influence. Information of habitual drivers is matched to crash data and fine data. The descriptive statistics on data used in this study, which consists of driver license acquisition, traffic fine, and crash data provided by the Korean National Police Agency, are described. The drivers under the influence are classified by statistically significant criteria, such as driver’s age, license type, driving experience, and crash reasons. With the results of the analysis, we propose some countermeasures to enhance traffic safety.

Keywords: Traffic Safety, driving under influence, traffic crash, traffic fine

Procedia PDF Downloads 69
8 Predicting Seoul Bus Ridership Using Artificial Neural Network Algorithm with Smartcard Data

Authors: Hosuk Shin, Young-Hyun Seo, Eunhak Lee, Seung-Young Kho

Abstract:

Currently, in Seoul, users have the privilege to avoid riding crowded buses with the installation of Bus Information System (BIS). BIS has three levels of on-board bus ridership level information (spacious, normal, and crowded). However, there are flaws in the system due to it being real time which could provide incomplete information to the user. For example, a bus comes to the station, and on the BIS it shows that the bus is crowded, but on the stop that the user is waiting many people get off, which would mean that this station the information should show as normal or spacious. To fix this problem, this study predicts the bus ridership level using smart card data to provide more accurate information about the passenger ridership level on the bus. An Artificial Neural Network (ANN) is an interconnected group of nodes, that was created based on the human brain. Forecasting has been one of the major applications of ANN due to the data-driven self-adaptive methods of the algorithm itself. According to the results, the ANN algorithm was stable and robust with somewhat small error ratio, so the results were rational and reasonable.

Keywords: ANN, bus, Ridership, smartcard data

Procedia PDF Downloads 49
7 Visualization of the Mobility Patterns of Public Bike Sharing System in Seoul

Authors: Young-Hyun Seo, Hosuk Shin, Eun-Hak Lee, Seung-Young Kho

Abstract:

This study analyzed and visualized the rental and return data of the public bike sharing system in Seoul, Ttareungyi, from September 2015 to October 2017. With the surge of system users, the number of times of collection and distribution in 2017 increased by three times compared to 2016. The city plans to deploy about 20,000 public bicycles by the end of 2017 to expand the system. Based on about 3.3 million historical data, we calculated the average trip time and the number of trips from one station to another station. The mobility patterns between stations are graphically displayed using R and Tableau. Demand for public bike sharing system is heavily influenced by day and weather. As a result of plotting the number of rentals and returns of some stations on weekdays and weekends at intervals of one hour, there was a difference in rental patterns. As a result of analysis of the rental and return patterns by time of day, there were a lot of returns at the morning peak and more rentals at the afternoon peak at the center of the city. It means that stock of bikes varies largely in the time zone and public bikes should be rebalanced timely. The result of this study can be applied as a primary data to construct the demand forecasting function of the station when establishing the rebalancing strategy of the public bicycle.

Keywords: Visualization, Demand forecasting, mobility patterns, public bike sharing system

Procedia PDF Downloads 70
6 Using Open Source Data and GIS Techniques to Overcome Data Deficiency and Accuracy Issues in the Construction and Validation of Transportation Network: Case of Kinshasa City

Authors: Christian Kapuku, Seung-Young Kho

Abstract:

An accurate representation of the transportation system serving the region is one of the important aspects of transportation modeling. Such representation often requires developing an abstract model of the system elements, which also requires important amount of data, surveys and time. However, in some cases such as in developing countries, data deficiencies, time and budget constraints do not always allow such accurate representation, leaving opportunities to assumptions that may negatively affect the quality of the analysis. With the emergence of Internet open source data especially in the mapping technologies as well as the advances in Geography Information System, opportunities to tackle these issues have raised. Therefore, the objective of this paper is to demonstrate such application through a practical case of the development of the transportation network for the city of Kinshasa. The GIS geo-referencing was used to construct the digitized map of Transportation Analysis Zones using available scanned images. Centroids were then dynamically placed at the center of activities using an activities density map. Next, the road network with its characteristics was built using OpenStreet data and other official road inventory data by intersecting their layers and cleaning up unnecessary links such as residential streets. The accuracy of the final network was then checked, comparing it with satellite images from Google and Bing. For the validation, the final network was exported into Emme3 to check for potential network coding issues. Results show a high accuracy between the built network and satellite images, which can mostly be attributed to the use of open source data.

Keywords: geographic information system (GIS), network construction, transportation database, open source data

Procedia PDF Downloads 66
5 Estimating Destinations of Bus Passengers Using Smart Card Data

Authors: Hasik Lee, Seung-Young Kho

Abstract:

Nowadays, automatic fare collection (AFC) system is widely used in many countries. However, smart card data from many of cities does not contain alighting information which is necessary to build OD matrices. Therefore, in order to utilize smart card data, destinations of passengers should be estimated. In this paper, kernel density estimation was used to forecast probabilities of alighting stations of bus passengers and applied to smart card data in Seoul, Korea which contains boarding and alighting information. This method was also validated with actual data. In some cases, stochastic method was more accurate than deterministic method. Therefore, it is sufficiently accurate to be used to build OD matrices.

Keywords: Validation, kernel density estimation, smart card data, destination estimation

Procedia PDF Downloads 239
4 Missing Link Data Estimation with Recurrent Neural Network: An Application Using Speed Data of Daegu Metropolitan Area

Authors: JaeHwan Yang, Da-Woon Jeong, Seung-Young Kho, Dong-Kyu Kim

Abstract:

In terms of ITS, information on link characteristic is an essential factor for plan or operation. But in practical cases, not every link has installed sensors on it. The link that does not have data on it is called “Missing Link”. The purpose of this study is to impute data of these missing links. To get these data, this study applies the machine learning method. With the machine learning process, especially for the deep learning process, missing link data can be estimated from present link data. For deep learning process, this study uses “Recurrent Neural Network” to take time-series data of road. As input data, Dedicated Short-range Communications (DSRC) data of Dalgubul-daero of Daegu Metropolitan Area had been fed into the learning process. Neural Network structure has 17 links with present data as input, 2 hidden layers, for 1 missing link data. As a result, forecasted data of target link show about 94% of accuracy compared with actual data.

Keywords: Machine Learning, road network, data estimation, link data

Procedia PDF Downloads 366
3 A Study of Mode Choice Model Improvement Considering Age Grouping

Authors: Young-Hyun Seo, Hyunwoo Park, Dong-Kyu Kim, Seung-Young Kho

Abstract:

The purpose of this study is providing an improved mode choice model considering parameters including age grouping of prime-aged and old age. In this study, 2010 Household Travel Survey data were used and improper samples were removed through the analysis. Chosen alternative, date of birth, mode, origin code, destination code, departure time, and arrival time are considered from Household Travel Survey. By preprocessing data, travel time, travel cost, mode, and ratio of people aged 45 to 55 years, 55 to 65 years and over 65 years were calculated. After the manipulation, the mode choice model was constructed using LIMDEP by maximum likelihood estimation. A significance test was conducted for nine parameters, three age groups for three modes. Then the test was conducted again for the mode choice model with significant parameters, travel cost variable and travel time variable. As a result of the model estimation, as the age increases, the preference for the car decreases and the preference for the bus increases. This study is meaningful in that the individual and households characteristics are applied to the aggregate model.

Keywords: Aging, multinomial logit model, age grouping, mode choice model

Procedia PDF Downloads 186
2 Quantifying Freeway Capacity Reductions by Rainfall Intensities Based on Stochastic Nature of Flow Breakdown

Authors: Hoyoung Lee, Dong-Kyu Kim, Seung-Young Kho, R. Eddie Wilson

Abstract:

This study quantifies a decrement in freeway capacity during rainfall. Traffic and rainfall data were gathered from Highway Agencies and Wunderground weather service. Three inter-urban freeway sections and its nearest weather stations were selected as experimental sites. Capacity analysis found reductions of maximum and mean pre-breakdown flow rates due to rainfall. The Kruskal-Wallis test also provided some evidence to suggest that the variance in the pre-breakdown flow rate is statistically insignificant. Potential application of this study lies in the operation of real time traffic management schemes such as Variable Speed Limits (VSL), Hard Shoulder Running (HSR), and Ramp Metering System (RMS), where speed or flow limits could be set based on a number of factors, including rainfall events and their intensities.

Keywords: Rainfall, capacity randomness, flow breakdown, freeway capacity

Procedia PDF Downloads 199
1 Latent Factors of Severity in Truck-Involved and Non-Truck-Involved Crashes on Freeways

Authors: Shin-Hyung Cho, Dong-Kyu Kim, Seung-Young Kho

Abstract:

Truck-involved crashes have higher crash severity than non-truck-involved crashes. There have been many studies about the frequency of crashes and the development of severity models, but those studies only analyzed the relationship between observed variables. To identify why more people are injured or killed when trucks are involved in the crash, we must examine to quantify the complex causal relationship between severity of the crash and risk factors by adopting the latent factors of crashes. The aim of this study was to develop a structural equation or model based on truck-involved and non-truck-involved crashes, including five latent variables, i.e. a crash factor, environmental factor, road factor, driver’s factor, and severity factor. To clarify the unique characteristics of truck-involved crashes compared to non-truck-involved crashes, a confirmatory analysis method was used. To develop the model, we extracted crash data from 10,083 crashes on Korean freeways from 2008 through 2014. The results showed that the most significant variable affecting the severity of a crash is the crash factor, which can be expressed by the location, cause, and type of the crash. For non-truck-involved crashes, the crash and environment factors increase severity of the crash; conversely, the road and driver factors tend to reduce severity of the crash. For truck-involved crashes, the driver factor has a significant effect on severity of the crash although its effect is slightly less than the crash factor. The multiple group analysis employed to analyze the differences between the heterogeneous groups of drivers.

Keywords: crash severity, structural structural equation modeling (SEM), truck-involved crashes, multiple group analysis, crash on freeway

Procedia PDF Downloads 193