• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.1-16
• /
• 2023

Accurate traffic information prediction is considered to be one of the most important aspects of intelligent transport systems(ITS), as it can be used to guide users of transportation facilities to avoid congested routes. Various deep learning models have been developed for accurate traffic prediction. Recently, ensemble techniques have been utilized to combine the strengths and weaknesses of various models in various ways to improve prediction accuracy and stability. Therefore, in this study, we developed and evaluated a traffic information prediction model using various deep learning models, and evaluated the performance of the developed deep learning models as a stacking ensemble. The individual models showed error rates within 10% for traffic volume prediction and 3% for speed prediction. The ensemble model showed higher accuracy compared to other models when no cross-validation was performed, and when cross-validation was performed, it showed a uniform error rate in long-term forecasting.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.1
• /
• pp.39-43
• /
• 2007

In high speed communication networks, the determination of a transmission rate is critical for the stability of a closed-loop network system with the congestion control scheme. In ATM networks, the available bit rate (ABR) service is based on a feedback mechanism, i.e., the network status is transferred to the ABR source by a resource management (RM) cell. RM cells contain the traffic information of the downstream nodes for the traffic rate control. However, the traffic status of the downstream nodes can not be directly transferred to the source node in the IP based networks. In this paper, a new rate-based congestion control scheme using an exponential weighted moving average algorithm is proposed to build an efficient feedback control law for congestion avoidance in high speed communication networks. The proposed congestion control scheme assures the stability of switch buffers and higher link utilization of the network. Moreover, we note that the proposed congestion scheme can flexibly work along with the increasing number of input sources in the network, which results in an improved scalability.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.1
• /
• pp.31-45
• /
• 2015

Existing link-based Frank-Wolfe algorithm has been widely used, thanks to its ease of simulation and stable results; however, it comes with low convergence issue towards near the optimum value. Such issue was not considered as a major drawback in the past. However, in the present, some arguments have occurred over the method's stability, analysis time, and other limits as the size and details of the fundamental data for traffic analysis have vastly improved. Therefore, this paper compared the theoretical attributes and the pros and cons between the Frank-Wolfe algorithm and the Origin-based algorithm and Path-based algorithm newly being developed. As a result of this paper, there is possibility that a problem of stability may arise depending on the convergence and exit criteria. Thus, In practice, this effort to derive the appropriate level of convergence is required to secure and stable results.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.2
• /
• pp.35-43
• /
• 2019

This paper describes the improved environment recognition algorithms using some type of sensors like LiDAR and cameras. Additionally, integrated control algorithm for an autonomous vehicle is included. The integrated algorithm was based on C++ environment and supported the stability of the whole driving control algorithms. As to the improved vision algorithms, lane tracing and traffic sign recognition were mainly operated with three cameras. There are two algorithms developed for lane tracing, Improved Lane Tracing (ILT) and Histogram Extension (HIX). Two independent algorithms were combined into one algorithm - Enhanced Lane Tracing with Histogram Extension (ELIX). As for the enhanced traffic sign recognition algorithm, integrated Mutual Validation Procedure (MVP) by using three algorithms - Cascade, Reinforced DSIFT SVM and YOLO was developed. Comparing to the results for those, it is convincing that the precision of traffic sign recognition is substantially increased. With the LiDAR sensor, static and dynamic obstacle detection and obstacle avoidance algorithms were focused. Therefore, improved environment recognition algorithms, which are higher accuracy and faster processing speed than ones of the previous algorithms, were proposed. Moreover, by optimizing with integrated control algorithm, the memory issue of irregular system shutdown was prevented. Therefore, the maneuvering stability of the autonomous vehicle in severe environment were enhanced.

• KIEAE Journal
• /
• v.9 no.6
• /
• pp.37-44
• /
• 2009

This study conducted an evaluation of the streetscape improvement project of the Gwangbok Street through analysis of correlations between psychological consciousness and physical elements in the street by comparing selected pictures of streetscape before and after the project. This work has conducted an analysis of Psychological characteristics by semantic differential method and an analysis of physical elements which influence psychological characteristics by regression analysis. According to the results of psychological analysis, the senses of interest, orderliness, esthetic and preference were highly improved in A district and the senses of openess, stability, orderliness were highly improved in B district. The results of analyzing physical elements influencing the improvement of these psychological consciousness in A district elucidated ; 1) the works of improving signboard and elevation of the building affected the whole these psychological consciousness, 2) the work of planting trees, making plant rests in the street improved the senses of orderliness, esthetic, 3) the work of changing finishing materials in the street enhanced the senses of esthetic, preference, 4) the work of adjusting the width between the road and the pavement, the work of improving traffic enhanced the senses of interest, preference. In the meantime in B district, the works of improving signboard and elevation of the building and those of planting trees, making plant rests in the street improved the senses of openess and orderliness. Also the work of improving traffic enhanced the senses of openess, stability and the work of expanding the pavement, that of changing finishing materials in the street improved the senses of openess, stability, orderliness.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.6D
• /
• pp.599-605
• /
• 2012

It is important to decide traffic opening time for construction plan of epoxy asphalt pavement. For this purpose, strength prediction model of epoxy asphalt concrete is required. In this study, Marshall stability was measured according to temperature and time for making strength properties equation. Strength prediction model was developed using chemical kinetics considering temperature variation. The traffic opening time of epoxy asphalt pavement on bridge deck has been predicted using the developed model. The prediction and actual traffic opening times were different by 17-days, because weathers of year 2009-2011 used in prediction model were different from weather of year 2012. When the prediction model used the actually measured temperatures of pavement, the difference between real opening time and prediction opening time was two days. The correlation analysis result between measured strength and prediction strength revealed that the $R^2$ using accurate temperature of pavement was 0.95. An improved precise prediction result is to be obtained if the prediction model uses accurate temperature data of pavement.

• International Journal of Highway Engineering
• /
• v.19 no.5
• /
• pp.163-171
• /
• 2017

PURPOSES : Traffic safety facilities are used to prevent traffic accidents before they occur by providing drivers with information on traffic situations and the geometric design of roads. However, some facilities not defined in guidelines do not meet installation criteria, yet are being installed and used in order to increase efficiency in traffic flow and prevent traffic accidents in a specific expressway zone. In this study, we have evaluated the effect of delineation system which are not defined in the guideline criteria. METHODS : Different virtual scenarios were created for roads using expressway median barrier chevron signs, with a driving simulator used to evaluate the installation and operational effect of such signs. Ten experiments were performed with left- and right-curved roads at curve radius intervals of 500 m, from 500 m to 2,500 m. RESULTS : For sections with a curve radius of more than 1,500 m, drivers had a clear tendency toward stable driving regardless of delineation system. When a chevron sign is installed on a protection fence in the road curving left, an expanded installation is recommended up to the section with a curve radius of 1,000 m. According to the analysis results for the RHB (Relative High Beta spectrum), driving concentration also improved up to a curve radius of 1,000 m. CONCLUSIONS :The experiment result indicates the extent of biasing within a lane and the manipulation amount of steering handle, were analyzed and found to be affected by curve radius and road alignment regardless of delineation system.

• Journal of the Korean Society of Safety
• /
• v.30 no.6
• /
• pp.122-131
• /
• 2015

Recently, starting with the deep underground road construction plan in Seobu Expressway, Korea, there area many studies on deep underground roads to be newly built. However, there is an extreme lack of safety standards, which does not consider traffic conditions and road driving characteristics. Therefore, this study reviewed safety elements to reflect in the deep underground road planning by analyzing driving stability of longitudinal tunnels with road environments, which resemble deep underground roads. For comprehensive analysis, the characteristics and causes of the accidents that have occurred in seven longitudinal tunnels with a length of 2km or over in Gangwon area, were collected. Specifically, geometric structures and facilities of each tunnel were investigated. Also, the present state of facility installation and the changes in driving speed of vehicles passing through each tunnel were observed to analyze the causes for the traffic accidents in each tunnel and accident reduction alternatives. It was revealed that the most frequent accidents in the tunnels resulted from the changes of traffic flow due to the abrupt speed reduction of forward vehicles, or the failure in speed control of following vehicles during the traffic congestion situation. Moreover, installing facilities such as plane and longitudinal curves, median strips and marginal strips seem to induce consistent driving speed. These results mean that for accident prevention, speed management must be preceded and there is a need to develop and introduce safety facilities actively to control the driving flow of forward and following vehicles.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.1
• /
• pp.73-80
• /
• 2019

Traffic Safety and efficient Road Traffic Policy of Traffic management came into effect over the certain size of the road like main road. Comparatively, Safety for Living street is deteriorated. Especially, Vehicle are usually priority to the life-zone street, even though Safety for the Passengers are essential to the life-zone street in the residential area. Improvement for the Living street has not been achieved In this study, To suggest Intersection Notifications standard of installation in Living Street, We execute on-site survey in priority to Gwangju Metropolitan City. Furthermore, After We suggest experimental value for the Intersection Notifications' standard of installation Prediction model in the Living street, Intersection Notifications compare & veritfy experimental value to the installation point's value to suggest the standard of installation in the living street. As a result, We can prevent frequent traffic accident in the Living Street. Furthermore, We are judged by installation of intersection Notifications considering stability and convenience to the passengers who are using the living street.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.1
• /
• pp.71-77
• /
• 2006

Several network attacks, such as distributed denial of service (DDoS) attack, present a very serious threat to the stability of the internet. The threat posed by network attacks on large networks, such as the internet, demands effective detection method. Therefore, a simple intrusion detection system on large-scale backbone network is needed for the sake of real-time detection, preemption and detection efficiency. In this paper, in order to discriminate attack traffic from legitimate traffic on backbone links, we suggest a relatively simple statistical measure, entropy, which can track value frequency. Den is conspicuous distinction of entropy values between attack traffic and legitimate traffic. Therefore, we can identify what kind of attack it is as well as detecting the attack traffic using entropy value.