• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.4
• /
• pp.86-98
• /
• 2018

Since 2015, the Korea Expressway Corporation has provided predicted travel time information, which is reproduced from DSRC systems over the extended expressway network in Korea. When it is open for public information, it helps travelers decide optimal routes while minimizing traffic congestions and travel cost. Although, sutiable evaluations to investigate the reliability of travel time forecast information have not been conducted so far. First of all, this study seeks to find out a measure of effectiveness to evaluate the reliability of travel time forecast via various literatures. Secondly, using the performance measurement, this study evaluates concurrent travel time forecast information in highway quantitatively and examines the forecast error by exploratory data analysis. It appears that most of highway lines provided reliable forecast information. However, we found significant over/under-forecast on a few links within several long lines and it turns out that such minor errors reduce overall reliability in travel time forecast of the corresponding highway lines. This study would help to build a priority for quality control of the travel time forecast information system, and highlight the importance of performing periodic and sustainable management for travel time forecast information.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.164-175
• /
• 2019

Installation of digital tachograph, black box, and ADAS have been enforced to commercial vehicles for preventing violent driving and accidents by the Traffic Safety Act in Korea. Nevertheless, the damage caused by road hazards has increased 1.5 times in 2016 compared to 2013. So, developing new technologies that can identify road hazard using the sensors installed in commercial vehicles are conducting by the Ministry of Land, Infrastructure and Transport. As a part of the technologies, this research analyze the error range of GPS installed in commercial vehicles that vary according to the driving speed. As a result, the average error was 9.72m at the driving speed of 100km/h, and the error was 2.1 times larger than the average error of 4.69m at the driving speed of 40km/h. The event point proper integration/separation range(m) was analyzed to be 20m with a recognition rate of 90% or more at the same point regardless of driving speed. The results of this research can be used as basic data for improving the accuracy of location-based data would be collected using commercial vehicles.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.121-131
• /
• 2014

Traffic speed is an important measure in transportation. It can be employed for various purposes, including traffic congestion detection, travel time estimation, and road design. Consequently, accurate speed prediction is essential in the development of intelligent transportation systems. In this paper, we present an analysis and speed prediction of a certain road section in Busan, South Korea. In previous works, only historical data of the target link are used for prediction. Here, we extract features from real traffic data by considering the neighboring links. After obtaining the candidate features, linear regression, model tree, and k-nearest neighbor (k-NN) are employed for both feature selection and speed prediction. The experiment results show that k-NN outperforms model tree and linear regression for the given dataset. Compared to the other predictors, k-NN significantly reduces the error measures that we use, including mean absolute percentage error (MAPE) and root mean square error (RMSE).

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.16-30
• /
• 2019

In this study, we calculated the driving duration of individual vehicles according to the availability of rest facility on highway, and suggested indicators indicating the potential risk of accidents caused by long-term driving with weights based on the number of vehicles by driving duration of individual links. Based on this, the methodology for estimating the appropriate location of the highway rest facility considering the driving duration of individual vehicles was presented. Using the DSRC individual vehicle data collected from the highways, the appropriate location of the rest facility was calculated by considering the driving duration by classifying weekdays and weekends for the Gyeongbu Expressway. The results showed that the weekly and weekend high risk indicators were different. In the case of weekdays, the risk indicators of Gimchun JC to Kumho JC for Busan were high, while for weekends, the risk indicators of Ansung JC to Dongtan JC for Seoul and Ansung IC to Bukchunan IC for Busan were high. This study has great significance in that it provides a framework for detailed analysis of link units by using non-aggregated data of individual vehicle units. In addition, it is significant that the reasonable driving duration reflecting the behavior of individual vehicles was calculated by analyzing the use of rest facilities.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.64-78
• /
• 2019

This paper explores key factors affecting taxi travel using global positioning system(GPS) data in Seoul, Korea, considering spatial dependence. We first analyzed the travel characteristics of taxis such as average travel time, average travel distance, and spatial distribution of taxi trips according to the time of the day and the day of the week. As a result, it is found that the most taxi trips were generated during the morning peak time (8 a.m. to 9 a.m.) and after the midnight (until 1 a.m.) on weekdays. The average travel distance and travel time for taxi trips were 5.9 km and 13 minutes, respectively. This implies that taxis are mainly used for short-distance travel and as an alternative to public transit after midnight in a large city. In addition, we identified that taxi trips were spatially correlated at the traffic analysis zone(TAZ) level through the Moran's I test. Thus, spatial regression models (spatial-lagged and spatial-error models) for taxi trips were developed, accounting for socio-demographics (such as the number of households, the number of elderly people, female ratio to the total population, and the number of vehicles), transportation services (such as the number of subway stations and bus stops), and land-use characteristics (such as population density, employment density, and residential areas) as explanatory variables. The model results indicate that these variables are significantly associated with taxi trips.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.2
• /
• pp.64-79
• /
• 2023

This study reviewed the process of applying the Monte Carlo simulation technique to the traffic allocation problem of metropolitan subways. The analysis applied the assumption of a normal distribution in which the travel time information of the inter-station sample is the basis of the probit model. From this, the average and standard deviation are calculated by separating the traffic between stations. A plan was proposed to apply the simulation with the weights of the in-vehicle time of individual links and the walking and dispatch interval of transfer. Long-distance traffic with a low number of samples of 50 or fewer was evaluated as a way to analyze the characteristics of similar traffic. The research results were reviewed in two directions by applying them to the Seoul Metropolitan Subway Network. The travel time between single stations on the Seolleung-Seongsu route was verified by applying random sampling to the in-vehicle time and transfer time. The assumption of a normal distribution was accepted for sample sizes of more than 50 stations according to the inter-station traffic sample of the entire Seoul Metropolitan Subway. For long-distance traffic with samples numbering less than 50, the minimum distance between stations was 122Km. Therefore, it was judged that the sample deviation equality was achieved and the inter-station mean and standard deviation of the transport card data for stations at this distance could be applied.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.73-87
• /
• 2023

Furnishing traffic safety information can contribute to providing hazard warnings to drivers, thereby avoiding crashes. A smart road lighting platform that instantly recognizes road conditions using various sensors and provides appropriate traffic safety information has therefore been developed. This study analyzes the short-term traffic safety improvement effects of the smart road lighting's tunnel traffic safety information service using surrogate safety measures (SSM). Individual driving behavior was investigated by applying the vehicle trajectory data collected with RADAR in the Anin Avalanche 1 and 2 tunnel sections in Gangneung. Comparing accumulated speeding, speed variation, time-to-collision, and deceleration rate to avoid the crash before and after providing traffic safety information, all SSMs showed significant improvement, indicating that the tunnel traffic safety information service is beneficial in improving traffic safety. Analyzing potential crash risk in the subdivided tunnel and access road sections revealed that providing traffic safety information reduced the probability of traffic accidents in most segments. The results of this study will be valuable for analyzing the short-term quantitative effects of traffic safety information services.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.163-181
• /
• 2023

Improving the detection performance of facilities corresponding to the sensors of autonomous vehicles helps driving safety. In the road and transportation field, research is being conducted to improve the detection performance of sensors by road infrastructure or facilities. As part of this on the development of autonomous driving support infrastructure, the shape of traffic cones and drums to ensure sufficient LiDAR detection performance even rainy conditions and maintain the line-of-sight guidance function in construction zones improvement effect. The principle was to increase reflection performance and ensure no significant difference in shape from existing facilities. Traffic cones were manufactured in square pyramid shapes instead of cones, and drums were manufactured in hexagonal and octagonal pillar shapes instead of cylinders. LiDAR detection data for the facility was confirmed on a clear day and with 20 mm/h and 40 mm/h rainfall. The detection performance of the square pyramid-shaped traffic cone and octagonal column-shaped drum was to the existing facility. On the other hand, deviations occurred due to repeated measurements, and significance could not be confirmed through statistical analysis. By reflecting these results, future studies will seek a form in which data can be obtained uniformly despite the diversity of measurement environments.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.45-52
• /
• 2014

The Ubiquitous-City (U-City) is a smart or intelligent city to satisfy human beings' desire to enjoy IT services with any device, anytime, anywhere. It is a future city model based on Internet of everything or things (IoE or IoT). It includes a lot of video cameras which are networked together. The networked video cameras support a lot of U-City services as one of the main input data together with sensors. They generate huge amount of video information, real big data for the U-City all the time. It is usually required that the U-City manipulates the big data in real-time. And it is not easy at all. Also, many times, it is required that the accumulated video data are analyzed to detect an event or find a figure among them. It requires a lot of computational power and usually takes a lot of time. Currently we can find researches which try to reduce the processing time of the big video data. Cloud computing can be a good solution to address this matter. There are many cloud computing methodologies which can be used to address the matter. MapReduce is an interesting and attractive methodology for it. It has many advantages and is getting popularity in many areas. Video cameras evolve day by day so that the resolution improves sharply. It leads to the exponential growth of the produced data by the networked video cameras. We are coping with real big data when we have to deal with video image data which are produced by the good quality video cameras. A video surveillance system was not useful until we find the cloud computing. But it is now being widely spread in U-Cities since we find some useful methodologies. Video data are unstructured data thus it is not easy to find a good research result of analyzing the data with MapReduce. This paper presents an analyzing system for the video surveillance system, which is a cloud-computing based video data management system. It is easy to deploy, flexible and reliable. It consists of the video manager, the video monitors, the storage for the video images, the storage client and streaming IN component. The "video monitor" for the video images consists of "video translater" and "protocol manager". The "storage" contains MapReduce analyzer. All components were designed according to the functional requirement of video surveillance system. The "streaming IN" component receives the video data from the networked video cameras and delivers them to the "storage client". It also manages the bottleneck of the network to smooth the data stream. The "storage client" receives the video data from the "streaming IN" component and stores them to the storage. It also helps other components to access the storage. The "video monitor" component transfers the video data by smoothly streaming and manages the protocol. The "video translator" sub-component enables users to manage the resolution, the codec and the frame rate of the video image. The "protocol" sub-component manages the Real Time Streaming Protocol (RTSP) and Real Time Messaging Protocol (RTMP). We use Hadoop Distributed File System(HDFS) for the storage of cloud computing. Hadoop stores the data in HDFS and provides the platform that can process data with simple MapReduce programming model. We suggest our own methodology to analyze the video images using MapReduce in this paper. That is, the workflow of video analysis is presented and detailed explanation is given in this paper. The performance evaluation was experiment and we found that our proposed system worked well. The performance evaluation results are presented in this paper with analysis. With our cluster system, we used compressed $1920{\times}1080(FHD)$ resolution video data, H.264 codec and HDFS as video storage. We measured the processing time according to the number of frame per mapper. Tracing the optimal splitting size of input data and the processing time according to the number of node, we found the linearity of the system performance.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.365-373
• /
• 1999

Recently, numerous studies have demonstrated that artificial intelligence such as neural networks can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. In building neural network model, the selection of independent and dependent variables should be approached with great care and should be treated as a model construction process. Irrespective of the efficiency of a learning procedure in terms of convergence, generalization and stability, the ultimate performance of the estimator will depend on the relevance of the selected input variables and the quality of the data used. Approaches developed in statistical methods such as correlation analysis and stepwise selection method are often very useful. These methods, however, may not be the optimal ones for the development of neural network models. In this paper, we propose a genetic algorithms approach to find an optimal or near optimal input variables for neural network modeling. The proposed approach is demonstrated by applications to bankruptcy prediction modeling. Our experimental results show that this approach increases overall classification accuracy rate significantly.