• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.17-31
• /
• 2020

In this study, a study was conducted to analyze the factors affecting the acceptability for autonomous vehicles. The previous studies were reviewed to sturdy the acceptance factors and The PLS Structral equation model was used to analyze the acceptance factors. While the existing research focused on technical safety, this study comprehensively analyze safety, convenience, economy, environment, and ethical factors. The PLS model was analyzed to significant the factors that affect the acceptability for autonomous vehicles in the order of safety, economy, convenience and environment.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.12
• /
• pp.117-124
• /
• 2009

In this paper, we have developed communication modules for ubiquitous transportation sensor network (u-TSN). The developed module can be used for intelligent transportation services. The developed systems are based on IEEE 802.11a and IEEE 802.11g technologies for vehicle and infrastructure systems, respectively. We have found that the throughput for the developed systems is at maximum around 15 Mbps. It is reduced to 10 Mbps at a long distance and high speed condition. The performance is enough to support traffic control services in dense traffic condition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.3955-3971
• /
• 2020

Due to the significant increase in the use of autonomous car technology, it is essential to integrate this technology with high-precision digital map data containing more precise and accurate roadway information, as compared to existing conventional map resources, to ensure the safety of self-driving operations. While existing map technologies may assist vehicles in identifying their locations via Global Positioning System, it is however difficult to update the environmental changes of roadways in these maps. Roadway vision algorithms can be useful for building autonomous vehicles that can avoid accidents and detect real-time location changes. We incorporate a hybrid architectural design that combines unsupervised classification of vision data with supervised joint fusion classification to achieve a better noise-resistant algorithm. We identify, via a deep learning approach, an intelligent hybrid fusion algorithm for fusing multimodal vision feature data for roadway classifications and characterize its improvement in accuracy over unsupervised identifications using image processing and supervised vision classifiers. We analyzed over 93,000 vision frame data collected from a test vehicle in real roadways. The performance indicators of the proposed hybrid fusion algorithm are successfully evaluated for the generation of roadway digital maps for autonomous vehicles, with a recall of 0.94, precision of 0.96, and accuracy of 0.92.

• Journal of Service Research and Studies
• /
• v.9 no.4
• /
• pp.19-40
• /
• 2019

Mobility as a Service is a service conception to achieve the intelligent transportation system. Its aims to improve the travel experience. In one platform, it connects various transportation modes to offer service and users only need to pay in one time for the whole travel. But the single MaaS platform easily faces the problems such as low user traffic, low retention rate and the access to markets of the this service is still unfound. From the perspective of bicycle-sharing, this research makes the MaaS concept into bicycle-sharing to build a better service model. The bicycle-sharing combine with the MaaS concept is innovative in business model, travel model and service architecture. In addition, this research also tests users' expectations for service model. The research shows that MaaS-based bicycle-sharing could offer flexible and convenient travel experience in the aspects of combined transportation, travel, transfer and payment, and it also makes it possible to make travel services according to need, and sustainable transport.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.54-63
• /
• 2017

With the aim of promoting the use of metropolitan railways, the present research developed a mode choice model for evaluating its competitiveness against passenger cars. A case study was carried out with Gyeongeui and Joongang line, and the area of interest was the direct operating railway between Ilsan and Guri station where the two lines intersect. The mode choice model was a disaggregate behavior model which used Stated Preference (SP) survey data, and the plot of competition was between private passenger cars and express trains. As a result, the mode choice model was established, and this model was used to analyze characteristics of passengers' time value and elasticity. It was shown that reducing travel time is more efficient than reducing travel cost when it comes to operating express trains in metropolitan railways. Therefore, policies designed for activating the use of metropolitan railways should expand direct operating service of individual lines and run more express trains in order to minimize transfer and in-vehicle time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.1-12
• /
• 2017

Traffic accidents are caused by a combination of human factors, vehicle factors, and environmental factors. In the case of traffic accidents where rental cars are involved, the possibility and the severity of traffic accidents are expected to be different from those of other traffic accidents due to the unfamiliar environment of the driver. In this study, we developed a model to forecast the severity of rental car accidents by using Naive Bayes classifier for Busan, Gangneung, and Jeju city. In addition, we compared the prediction accuracy performance of two models where one model uses the variables of which statistical significance were verified in a prior study and another model uses the entire available variables. As a result of the comparison, it is shown that the prediction accuracy is higher when using the variables with statistical significance.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.107-121
• /
• 2017

This study conducted a 3-stage survey and simulation experiment to identify the impact of vehicle platoons on car-following behavior of manually-driven vehicles. Vehicle maneuvering data obtained from driving simulations was statistically analyzed based on three measures including average speed, acceleration noise, and offset to represent the deviation of lateral movements. Results indicate that MV drivers tended to have psychological burden while driving in automated vehicle platooning environments, which resulted in different vehicle maneuvers. It is expected that the outcome of this study would be useful fundamentals in developing various traffic operations strategies for managing mixed traffic stream consisting of MVs and autonomous vehicles.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.2
• /
• pp.106-112
• /
• 2017

In the paper, we propose a levitation and a propulsion controller for the magnetic levitation logistic transportation system. The levitation controller is designed considering the mutual influence of the electromagnets to minimize roll and pitch movements. In order to solve the structural disadvantages of the magnetic levitation transportation system, we improve the problem of the existing controller by applying the exponential filter to the reference input. DSP-based control hardware is developed and the levitation control method is verified by levitation experiments to the air gap goal. The propulsion controller uses the space vector voltage modulation method. The propulsion controller is designed to follow the position and velocity profile by detecting the absolute position from the bar code information attached to the rail. The position control result shows satisfactory performance through the propulsion control reciprocating motion experiment.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.29-41
• /
• 2017

In this study, we used individual trip data to estimate a macroscopic fundamental diagram (MFD) that relates flow (or production) to density (or state) in Daegu metropolitan city. The individual trip data were generated by processing data that were collected from DSRC-based (dedicated short range communication) traffic data collection system. Using the processed individual trip data, we first examined whether the assumptions for MFD are valid, and then the relation between outflow and accumulation was estimated in our study site. As a result, we found that i) the assumptions are valid to construct MFD; and ii) the reproducible and well-defined MFDs exist in the network level.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.112-123
• /
• 2017

The accurate forecasting of the public transportation's transit and arrival time has become increasingly important as more people use buses and subways instead of personal vehicles under the government's public transportation promotion policy. Using bus management system (BMS) data, which provide information on the real-time bus location, operation interval, and operation history, it is now possible to analyze the bus schedule reliability. However, the punctuality should always be considered together with the operation safety. Therefore, this study suggests a new methodology to secure both reliability and safety using the BMS data. Unlike other studies, we calculated the bus travel time between two bus stops by dividing the total travel length into 6 sections using 5 different measuring points. In addition, the optimal travel time for each bus route was proposed by analyzing the mean, standard deviation and coefficient of variation of the each section's measurement. This will ensure the reliability, safety and mobility of the bus operation.