• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제10권6호
• /
• 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.

• Journal of Intelligence and Information Systems
• /
• 제4권2호
• /
• pp.23-34
• /
• 1998

Travel time forecasting, especially public bus travel time forecasting in urban areas, is a difficult and complex problem which requires a prohibitively large computation time and years of experience. As the network of target area grows with addition of streets and lanes, computational burden of the forecasting systems exponentially increases. Even though the travel time between two neighboring intersections is known a priori, it is still difficult, if not impossible, to compute the travel time between every two intersections. For the reason, previous approaches frequently have oversimplified the transportation network to show feasibilities of the problem solving algorithms. In this paper, forecasting of the travel time between every two intersections is attempted based on travel time data between two neighboring intersections. The time stamps data of public buses which recorded arrival time at predetermined bus stops was extensively collected and forecast. At first, the time stamp data was categorized to eliminate white noise, uncontrollable in forecasting, based on wavelet conversion. Then, the radial basis neural networks was applied to remaining data, which showed relatively accurate results. The success of the attempt was confirmed by the drastically reduced relative error when the nodes between the target intersections increases. In general, as the number of the nodes between target intersections increases, the relative error shows the tendency of sharp increase. The experimental results of the novel approaches, based on wavelet conversion and neural network teaming mechanism, showed the forecasting methodology is very promising.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제7권5호
• /
• pp.13-25
• /
• 2008

This study analyzed errors of data received from GPS which showed different reception characteristics based on chipset at poor reception area. The digital map made from National Police Agency shows 4% errors of length on the average. The comparison of three different algorithms - Average Spot Speed, Cumulative Travel Length from GPS with Actual Travel Time, Travel Length from Digital Map with Actual Travel Time have been conducted to find significant difference estimating travel time from GPS Data. The algorithm to estimate travel time from travel length and travel time showed the most reliable results from the others.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제2권1호
• /
• pp.101-108
• /
• 2003

When drivers encounter multiple available routes, they may evaluate the utility of each route. Two important factors in the evaluation are travel time and travel cost. Without hewing the current travel time of each route, drivers' decisions are not necessarily optimum. It is called 'transparency issue' that drivers are blinded to choose the optimum route among the others because of the limited travel time information. As a result of this, competing route travel times tend to fluctuate. This case study to utilize the data of Namsan traffic information system confirms that this travel time fluctuation can be lessened as real time traffic information is provided.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제12권4호
• /
• pp.1-10
• /
• 2013

This study was conducted to investigate that bus information was used as an information of travel speed. To determine the travel speed on the road, bus information and the information collected from the point detector and the interval detection installed were compared. If bus information has the function of traffic information detector, can provide the travel speed information to road users. To this end, the model of recognizing the traffic patterns is necessary. This study used simple moving-average method, simple exponential smoothing method, Double moving average method, Double exponential smoothing method, ARIMA(Autoregressive integrated moving average model) as the existing methods rather than new approach methods. This study suggested the possibility to replace bus information system into other information collection system.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제9권6호
• /
• pp.33-42
• /
• 2010

Travel speed is an important parameter in measurement of road traffic. UTIS(Urban Traffic Information System) was developed as a type of section detector. However, UTIS incur errors caused by irregular vehicle trajectories, wireless communication range and so on. This paper suggests a new model that use an error-filtering algorithm to improve the accuracy of travel speed measurements. In the field test, the variance of the percent errors measured by the new model was reduced. Therefore, it can be concluded that the proposed model significantly improves travel speed measuring accuracy.

• Journal of Korea Spatial Information System Society
• /
• 제10권3호
• /
• pp.31-43
• /
• 2008

Travel time prediction is an indispensable to many advanced traveler information systems(ATIS) and intelligent transportation systems(ITS). In this paper we propose a method to predict travel time using $Na{\ddot{i}}ve$ Bayesian classification method which has exhibited high accuracy and processing speed when applied to classily large amounts of data. Our proposed prediction algorithm is also scalable to road networks with arbitrary travel routes. For a given route, we consider time-varying average segment velocity to perform more accuracy of travel time prediction. We compare the proposed method with the existing prediction algorithms like link-based prediction algorithm [1] and Micro T* algorithm [2]. It is shown from the performance comparison that the proposed predictor can reduce MARE (mean absolute relative error) significantly, compared with the existing predictors.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제2권2호
• /
• pp.23-29
• /
• 2003

This study is the empirical research about application and evaluation of AVI that is an essential technology for calculating and providing the travel time. Travel time calculation and provision is one of the technique for information collecting and providing in the ITS. Through the field test on a national highway, we proposed the travel time calculation technique from the data by non-contact vehicle detecting method and validated field application performance with field data. We proposed the technique of evaluating field application performance, then using this, analyzed recognition rate, detection rate and travel time with field data.

• Journal of Korean Society of Transportation
• /
• 제13권4호
• /
• pp.5-29
• /
• 1995

Advanced Traveler Inoformation Systems*ATIS) , as a subsystem of ITS influence the travel choices of dreivers by providing them with historical, real-time and predictive information to supprot travel decisions and consequently improves the speed and quality of travel. For thesuccessul accomplishment of ATIS, the time-dependent variations of traffic in a road network and travel times of vehicles during their journey must be predicted . The purpose of this study is to evaluate the past developments in the dynamic route choice models and to apply the instantaneous dynamic user optimal route choice model. recently formulated with flow propagation constraints by Ran, Boyce and LeBlanc, to the real transportation network of Seocho-Ku in Seoul. As input data for this application, the time-dependent travel rates are estimated and the link travel time function is derived. The modelis validated from three view points : the efficiency of model itself the ability to predict traffic volume and travel time on links, and the optimal traffic control.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제6권2호
• /
• pp.34-44
• /
• 2007

Many urban cities deployed ITS technologies to improve the efficiency of traffic operation and management including a real-time franc control system (i.e., COSMOS). The system adopted loop detector system to collect traffic information such as volume, occupancy time, degree of saturation, and queue length. This paper investigated the applicability of detector information within COSMOS to represent the congestion level of the links. Initially, link travel times obtained from the field study were related with each of detector information. Results showed that queue length was highly correlated with link travel time, and direct link travel time estimation using the spot speed data produced high estimation error rates. From this analysis, a procedure was proposed to estimate congestion level of the links using both degree of saturation and queue length information.