• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.6
• /
• pp.40-48
• /
• 2012

In this paper, we suggests methods for determining optimal representative value and the optimal size of historical data for reliable travel speed prediction. To evaluate the performance of the proposed method in real world environments, we did field tests at four roadway links in Seoul on Tuesday and Sunday. According to the results of applying the methods to historical data of Central Traffic Information Center, the optimal representative value were analyzed to be average and weighted average. Second, it was analyzed that 2 months data is the optimal size of historical data used for travel speed prediction.

• Journal of Industrial Convergence
• /
• v.18 no.3
• /
• pp.53-61
• /
• 2020

Travel speed is an important parameter for measuring road traffic and incident detection system. In this paper I suggests a model developed for estimating reliable and accurate average roadway link travel speeds using image processing sensor. This method extracts the vehicles from the video image from CCTV, tracks the moving vehicles using deep neural network, and extracts traffic information such as link travel speeds and volume. The algorithm estimates link travel speeds using a robust data-fusion procedure to provide accurate link travel speeds and traffic information to the public. In the field tests, the new model performed better than existing methods.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.1-16
• /
• 2020

With the advent of the fourth industrial revolution era, there has been a growing interest in deep learning using big data, and studies using deep learning have been actively conducted in various fields. In the transportation sector, there are many advantages to using deep learning in research as much as using deep traffic big data. In this study, a short -term travel speed prediction model using LSTM, a deep learning technique, was constructed to predict the travel speed. The LSTM model suitable for time series prediction was selected considering that the travel speed data, which is used for prediction, is time series data. In order to predict the travel speed more precisely, we constructed a model that reflects both temporal and spatial effects. The model is a short-term prediction model that predicts after one hour. For the analysis data, the 5minute travel speed collected from the Seoul Transportation Information Center was used, and the analysis section was selected as a part of Gangnam where traffic was congested.

• Journal of Korean Society of Transportation
• /
• v.18 no.5
• /
• pp.57-67
• /
• 2000

Two fuzzy travel time estimators for interrupted traffic flow were developed based on field survey data and simulation data 7hat is collected from DETSIM, which is microscopic traffic simulation model that car-following theory is applied. One is FETTOS(Fuzzy Estimator of Travel Time using Occupancy and Spot speed) and the other is FETTOS(Fuzzy Estimator of Travel Speed using Volume and Occupancy). Fuzzy logic controller was applied to the estimators to deal with non-linear relationship between traffic variables and travel time. According to results of simulation and field survey. estimation of travel time can be modeled by using percent occupancy better than any other traffic variables. Detector location from storyline and signal timing Plan of intersection are affected to estimate travel time. With a few findings, the estimator was constructed and its performance was tested for observed travel time data and simulated data. FETTOS which needs signal timing plan and detector location estimates travel time with accurate better than FETSVO does. However. FETSVO has excellent transferability because the estimator needs set of input data only; volume and time mean speed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.6
• /
• pp.63-73
• /
• 2011

Travel speed is an important parameter for measuring road traffic. UTIS(Urban Traffic Information System) was developed as a mobile detector for measuring link travel speeds in South Korea. After investigation, we founded that UTIS includes some missing data caused by the lack of probe vehicles on road segments, system failures and etc. Imputation is the practice of filling in missing data with estimated values. In this paper, we suggests a new model for imputing missing data to provide accurate link travel speeds to the public. In the field test, new model showed the travel speed measuring accuracy of 93.6%. Therefore, it can be concluded that the proposed model significantly improves travel speed measuring accuracy.

• 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.

• Information and Communications Magazine
• /
• v.21 no.5
• /
• pp.70-79
• /
• 2004

최적 경로 서비스를 제공하기 위해서는 구간 통행속도, 구간 통행시간, 회전 정보, 혼잡도 등과 같은 교통정보가 필요하다. 또한, 고객에게 신뢰성 있는 최적 경로를 제공하기 위해서는 실시간 교통정보 수집은 반드시 필요하며, 이러한 실시간 교통정보 수집 방법들에 대한 고찰과 검토가 선행되어야 한다. 기존의 교통정보 수집방법을 살펴보면 지점검지 방식의 경우, 수집되는 정보가 검지기 설치 지점의 지점속도(Spot Speed)이므로 해당 링크를 주행한 통행속도(통행시간)의 대표값으로 채택하기에는 다소 무리가 있으며 구간검지 방식의 경우, 일반적으로 급격한 교통류 변동에 따른 대기행렬 검지가 늦다는 단점이 있다.(중략)

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.6
• /
• pp.1851-1861
• /
• 2014

This study aims to calculate reliable sectional travel speeds with the consideration of the characteristics of the probe data collected in the interrupted traffic flow. First, in order to analysis the characteristics of the probe data, we looked into the distribution of the sectional travel times of each probe vehicle and compared the difference in the sectional travel speeds of each probe vehicle collected by DSRC. As a result, it is shown that outliers should be removed for the distribution of the sectional travel times. However, The comparison results show that the sectional travel speeds from the DSRC probe vehicles are not significantly different. Finally, based on the distribution characteristics of the sectional travel speeds of each probe vehicle and the representative values counted during a collection period, we drew the optimal outlier removal procedure and evaluated the estimation errors. The evaluation results showed that the DSRC sectional travel speeds were found to be similar to the observed values from actually running vehicles. On the contrary, in the case of the sectional travel speeds of intra-city bus, it was analyzed that they were less accurate than the DSRC sectional travel speeds. In the future, it will be necessary to improve BIS process and make use of the travel information on intra-city buses collected in real time to find various ways of applying it as traffic information.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.949-960
• /
• 2016

This paper uses all sections of highway data (VDS) for two years (Jan. 2014-Dec. 2015), with 15 minute units. The first purpose of this study is to find clusters with similar patterns that appear repeatedly with time variables of month, week and hour. The cluster analysis results indicate a variety of patterns of average traffic speeds by time variables depending on the clusters; subsequently, these can be utilized to model for the forecast of the speed at a specific time. The second purpose is to do cluster analysis for grouping sections by effect nets that are closely related to each other. For the similarity measure we use cross-correlation functions calculated after pre-whitening the speed of each section. The cluster analysis gets 19 clusters, and sections within a cluster are geographically close. These results are expected to help to forecast a real-time speed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.142-155
• /
• 2019

This study was conducted with the aim of developing a system to collect taxi GPS probe information to prevent link defects and to improve the accuracy of the standard link-based travel speed by determining when to go into and come out the link. For this purpose, a framework and algorithm consisting of a five-step process for standard link-based map matching and individual vehicle travel speed are presented and used it to calculate the average travel speed of the service link. Two on-site surveys of Teheran and Hakdong-ro were conducted to verify the results by the methods proposed in this paper. On the basis of the overall time of the field survey, the deviation in the travel speed was 0.2 km/h and 0.6 km/h, the accuracy was 99% and 96%, and the MAPE(Mean Absolute Percentage Error) was 1% and 4% in Teheran and Hakdong-ro, respectively. These results were more accurate thand those obtained using conventional methodologies without standard links.