• Journal of Korean Society of Transportation
• /
• v.18 no.1
• /
• pp.47-59
• /
• 2000

The purpose of this study is to develop travel-time estimation model using neural networks and prediction model using neural networks and kalman-filtering technique. The data used in this study are travel speed collected from inductive loop vehicle detection systems(VDS) and travel time collected from the toll collection system (TCS) between Seoul and Osan toll Plaza on the Seoul-Pusan Expressway. Two models, one for travel-time estimation and the other for travel-time Prediction were developed. Application cases of each model were divided into two cases, so-called, a single-region and a multiple-region. because of the different characteristics of travel behavior shown on each region. For the evaluation of the travel time estimation and Prediction models, two Parameters. i.e. mode and mean were compared using five-minute interval data sets. The test results show that mode was superior to mean in representing the relationship between speed and travel time. It is, however shown that mean value gives better results in case of insufficient data. It should be noted that the estimation and the Prediction of travel times based on the VDS data have been improved by using neural networks, because the waiting time at exit toll gates can be included for the estimation of travel time based on the VDS data by considering differences between VDS and TCS travel time Patterns in the models. In conclusion, the results show that the developed models decrease estimation and prediction errors. As a result of comparing the developed model with the existing model using the observed data, the equality coefficients of the developed model was average 88% and the existing model was average 68%. Thus, the developed model was improved minimum 17% and maximum 23% rather then existing model .

• Journal of the Ergonomics Society of Korea
• /
• v.24 no.2
• /
• pp.51-56
• /
• 2005

Human perceptional speed is different from its real speed. There is lack of research that the perceptional speed is different from real speed in 2-dimension, because most research of speed perception has concentrated on points and lines. This research investigates the effects of object size on speed perception. In this research, we used 2-D circular objects of the different size, 0.9, 1.8 and $3.6^{\circ}$. The objects moved 9.0, 13.5 and $18.0^{\circ}$ with three different speeds, 6.0, 9.0 and $18.0^{\circ}$/s. Six participants were exposed to the environment with standard scene(size: $1.8^{\circ}$, speed: $9.0^{\circ}$/s and travel distance: $13.5^{\circ}$). After the first scene, another scene in which the object had changed to different sizes, speeds and distances, was shown to the participants. A magnitude estimation method was used to construct a scale of the perceived speed level. The relationship between the perceived and the actual speed level was explained by Stevens's power law that the value was 0.978 with the exponent of 0.992. The size of object had an effect on the speed perception but travel distance was not. The perceptional speed of bigger object was lower than of smaller object. It showed that the degrees of perceptional speed decreased as size of object increased.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1D
• /
• pp.43-50
• /
• 2011

The monitoring system for link travel speed using taxi probe is one of key sub-systems of ITS. Link travel speed collected by taxi probe has been widely employed for both monitoring the traffic states of urban road network and providing real-time travel time information. When sample size of taxi probe is small and link travel time is longer than a length of time interval to collect travel speed data, and in turn the missing state is inevitable. Under this missing state, link travel speed data is real-timely not collected. This missing state changes from single to multiple time intervals. Existing single interval prediction techniques can not generate multiple future states. For this reason, it is necessary to replace multiple missing states with the estimations generated by multi-interval prediction method. In this study, a multi-interval prediction method to generate the speed estimations of single and multiple future time step is introduced overcoming the shortcomings of short-term techniques. The model is developed based on Non-Parametric Regression (NPR), and outperformed single-interval prediction methods in terms of prediction accuracy in spite of multi-interval prediction scheme.

• International Journal of Railway
• /
• v.7 no.1
• /
• pp.24-33
• /
• 2014

The Korean high-speed rail (HSR) began its commercial service in 2004. This service has been created significant changes in the system of intercity passenger travels of Korea. However, the actual ridership was approximately half of the estimated one in the planning stage. In this background, this paper presents the difference between the stated preference (SP) before the HSR service and the revealed preference (RP) after it using the intercity travel mode choice models. Several meaningful differences are found in terms of the factors affecting the travel mode choice, the estimation results of model, the monetary values of time, and elasticities. While the access/egress travel time of high-speed rail is less important than in-vehicle travel time in the SP sample, they have same weight in the RP sample. Also the RP models show that the probability of choosing HSR can be decreased by the increase of the number of vehicles in household contrary to the results from the SP models. The monetary values of travel time are relatively high and the direct and cross elasticities in response to changes in level-of-service of HSR are relatively low in the RP sample. This Korean case is expected to offer referable material for preparing high-speed rail services in other countries by showing the difference between the SP and RP before/after the actual service, identifying the importance of access/egress travel time and lower direct elasticities of HSR demand.

• Proceedings of the KSR Conference
• /
• 2009.05a
• /
• pp.721-729
• /
• 2009

Recently, there has been growing necessity to estimate the future travel demand of high speed train because the circumstance of high speed train service is rapidly changing with the launching of 2011 second stage of Gyeongbu high speed railway(Dongdaegu-Busan) and the completion of 2014 first stage of Honam high speed railway(Yongsan-Gwangju), etc. This study was designed to estimate future travel demand by analyzing the transport performance and train service characteristics of Gyeongbu and Honam line. This study presents the maximum load section and the changed future travel demand, which will be applied to establish a train operation plan.

• Journal of the Korean Society of Industry Convergence
• /
• v.6 no.4
• /
• pp.339-345
• /
• 2003

The purpose of this thesis is to develop a simulation model to estimate link travel speed applicable to urban street transportation planning for interrupted traffic flow, influenced by signalized intersection. This link travel speed model is expected to be a better and more than previous studies.

• Journal of Cadastre & Land InformatiX
• /
• v.51 no.1
• /
• pp.97-110
• /
• 2021

This study estimated the delay factor, which is the ratio of travel time at the speed limit and travel time at the actual speed using real-time traffic information in Seoul. The actual travel speed on the road was lower than the maximum speed of the road and the travel speed was the slowest during the rush hour. As a result of accessibility analysis based on travel speed during the rush hour, the travel time at the actual speed was 37.49 minutes on average. However, the travel time at the speed limit was 15.70 minutes on average. This result indicated that the travel time at the actual speed is 2.4 times longer than that at the speed limit. In addition, this study proposedly defined the delay factor as the ratio of accessibility by the speed limit and accessibility to actual travel speed. As a result of delay factor analysis, the delay factor of Seoul was 2.44. The results by the administrative district showed that the delay factor in the north part areas of the Han River is higher than her south part areas. Analysis results after applying the relationship between road density and traffic volume showed that as the traffic volume with road density increased, the delay factor decreased. These results indicated that it could not be said that heavy traffic caused longer travel time. Therefore, follow-up research is needed based on more detailed information such as road system shape, road width, and signal system for finding the exact cause of increased travel time.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.12
• /
• pp.1373-1380
• /
• 2014

In order to calculate accurate traffic and traffic speed, qualified and sufficient GPS data should be provided. However, it is difficult to provide accurate traffic information using restricted GPS data from probe vehicles because of communication costs. This paper developed a algorithm that recovers links omitted by restricted GPS data with topology information, and calculate traffic speed with original links and recovered links. T traffic information service of city with a new algorithm can provide more accurate traffic and traffic speed than the original system.

• Journal of Korean Society of Transportation
• /
• v.21 no.5
• /
• pp.83-95
• /
• 2003

This study aims to develop travel time estimation and prediction models on the freeway using measurements from vehicle detectors. In this study, we established a travel time estimation model using traffic volume which is a principle factor of traffic flow changes by reviewing existing travel time estimation techniques. As a result of goodness of fit test. in the normal traffic condition over 70km/h, RMSEP(Root Mean Square Error Proportion) from travel speed is lower than the proposed model, but the proposed model produce more reliable travel times than the other one in the congestion. Therefore in cases of congestion the model uses the method of calculating the delay time from excess link volumes from the in- and outflow and the vehicle speeds from detectors in the traffic situation at a speed of over 70km/h. We also conducted short term prediction of Kalman Filtering to forecast traffic condition and more accurate travel times using statistical model The results of evaluation showed that the lag time occurred between predicted travel time and estimated travel time but the RMSEP values of predicted travel time to observations are as 1ow as that of estimation.

• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.4
• /
• pp.306-314
• /
• 2000

In this paper we present a new approach to estimate link travel speed based on the hybrid neuro-fuzzy network. It combines the fuzzy ART algorithm for structure learning and the backpropagation algorithm for parameter adaptation. At first, the fuzzy ART algorithm partitions the input/output space using the training data set in order to construct initial neuro-fuzzy inference network. After the initial network topology is completed, a backpropagation learning scheme is applied to optimize parameters of fuzzy membership functions. An initial neuro-fuzzy network can be applicable to any other link where the probe car data are available. This can be realized by the network adaptation and add/modify module. In the network adaptation module, a CBR(Case-Based Reasoning) approach is used. Various experiments show that proposed methodology has better performance for estimating link travel speed comparing to the existing method.