• 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.21 no.1
• /
• pp.91-102
• /
• 2003

There are two goals in this paper. The one is development of existing CA(Cellular Automata) model to explain more realistic deceleration process to stop. The other is the application of the updated CA model to forecasting simulation to predict short term link travel time that takes a key rule in finding the shortest path of route guidance system of ITS. Car following theory of CA models don't makes not response to leading vehicle's velocity but gap or distance between leading vehicles and following vehicles. So a following vehicle running at free flow speed must meet steeply sudden deceleration to avoid back collision within unrealistic braking distance. To tackle above unrealistic deceleration rule, “Slow-to-stop” rule is integrated into NaSch model. For application to interrupted traffic flow, this paper applies “Slow-to-stop” rule to both normal traffic light and random traffic light. And vehicle packet method is used to simulate a large-scale network on the desktop. Generally, time series data analysis methods such as neural network, ARIMA, and Kalman filtering are used for short term link travel time prediction that is crucial to find an optimal dynamic shortest path. But those methods have time-lag problems and are hard to capture traffic flow mechanism such as spill over and spill back etc. To address above problems. the CA model built in this study is used for forecasting simulation to predict short term link travel time in Kangnam district network And it's turned out that short term prediction simulation method generates novel results, taking a crack of time lag problems and considering interrupted traffic flow mechanism.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.10
• /
• pp.1018-1023
• /
• 2010

The CAN (Controller Area Network) system is the most dominant protocol for in-vehicle networking system because it provides bounded transmission delay among ECUs (Electronic Control Units) at data rates between 125Kbps and 1Mbps. And, many automotive companies have chosen the CAN protocol for their in-vehicle networking system such as chassis network system because of its excellent communication characteristics. However, the increasing number of ECUs and the need for more intelligent functions such as ADASs (Advanced Driver Assistance Systems) or IVISs (In-Vehicle Information Systems) require a network with more network capacity and the real-time QoS (Quality-of-Service). As one approach to enhancing the network capacity of a CAN system, this paper introduces a CAN system with dual communication channel. And, this paper presents a distributed message allocation method that allocates messages to the more appropriate channel using forecast traffic of each channel. Finally, an experimental testbed using commercial off-the-shelf microcontrollers with two CAN protocol controllers was used to demonstrate the feasibility of the CAN system with dual communication channel using the distributed message allocation method.

• The KIPS Transactions:PartC
• /
• v.10C no.1
• /
• pp.51-60
• /
• 2003

One of the most important matters in designing network and realizing service, is to grip on the traffic characteristics. Conventional traffic prediction and analysis used the models which based on the Poisson or Markovian. Recently, experimental research on the LAN, WAN and VBR traffic properties have been pointed rut that they weren't able to display actual real traffic specificities because the models based on the Poisson assumption had been underestimated the long range dependency of network traffic and self-similar peculiarities, it has been lately presented that the new approach method using self-similarity characteristics as similar as the real traffic models. Therefore, in this paper, we generated self-similar data traffic like real traffic as background load. On the existing ABR congestion control algorithm, we analyzed by classify into ACR, buffer utilization. cell drop rate, transmission throughput with the representative EFCI, ERICA, EPRCA and NIST twitch algorithm to show the efficient reaction about the burst traffic.

• Journal of Korean Society of Transportation
• /
• v.20 no.4
• /
• pp.135-150
• /
• 2002

The basic assumption of analytical Dynamic Traffic Assignment models is that traffic demand and network conditions are known as a priori and unchanging during the whole planning horizon. This assumption may not be realistic in the practical traffic situation because traffic demand and network conditions nay vary from time to time. The rolling horizon implementation recognizes a fact : The Prediction of origin-destination(OD) matrices and network conditions is usually more accurate in a short period of time, while further into the whole horizon there exists a substantial uncertainty. In the rolling horizon implementation, therefore, rather than assuming time-dependent OD matrices and network conditions are known at the beginning of the horizon, it is assumed that the deterministic information of OD and traffic conditions for a short period are possessed, whereas information beyond this short period will not be available until the time rolls forward. This paper introduces rolling horizon implementation to enable a multi-class analytical DTA model to respond operationally to dynamic variations of both traffic demand and network conditions. In the paper, implementation procedure is discussed in detail, and practical solutions for some raised issues of 1) unfinished trips and 2) rerouting strategy of these trips, are proposed. Computational examples and results are presented and analyzed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.6
• /
• pp.77-90
• /
• 2015

An increasing number of vehicles is causing various traffic problems such as chronic congestion of highways and air pollution. Local governments have been managing traffic by constructing systems such as Intelligent Transport Systems (ITS) and Advanced Traffic Management Systems (ATMS) to relieve such problems, but construction of an infrastructure-based traffic system is insufficient in resolving chronic traffic problems. A more sophisticated system with enhanced operational management capabilities added to the existing facilities is necessary at this point. As traffic patterns of the urban traffic flow is time-specific due to the different vehicle populations throughout the time of the day, a local network-wide signal operation plan that can manage such situation-specific traffic patterns is deemed to be necessary. Therefore, this study is conducted for the purpose of establishment of a plan for contextual signal control management through signal optimization at the network level after setting the Frame Signal in accordance to the traffic patterns gathered from the short-term traffic forecast data as a means to mitigate the problems with existing standardized signal operations.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.1-15
• /
• 2023

In this study, the number of truck traffic accidents was predicted by using Poisson and negative binomial regression analysis to understand what factors affect accidents using expressway data. Significant variables in the truck traffic accident prediction model were continuous driving time, link length, truck traffic volume. number of bridges and number of drowsy shelters. The calculated LOSS rating was expressed on the national expressway network to diagnose the risk of truck accidents. This is expected to be used as basic data for policy establishment to reduce truck accidents on expressways.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.395-396
• /
• 2014

최근 급증하는 교통 혼잡으로 인해 시간적/물리적 손실이 크게 발생하고 있다. 이러한 교통난 해소는 시설투자만으로는 근본적인 해결책이 될 수 없다는 판단 하에 지난 수년간 보다 정확한 교통량을 예측하기 위해 다양한 교통량 예측 모델들이 개발되어왔다. 그러나 기존 모델들은 회기분석을 통해 과거 교통량을 분석하고 과거의 교통패턴이 미래에 지속적으로 연장된다는 가정 하에 연구되었기 때문에 실시간으로 급변하는 불규칙한 교통 패턴에 대한 예측의 신뢰성을 떨어트린다. 이를 위해 본 논문에서는 큐잉 네트워크 모델 기반의 교통량 예측 모델을 설계 하고 이를 바탕으로 안드로이드 기반의 애플리케이션을 구현하였다.

• Journal of KIISE:Information Networking
• /
• v.30 no.1
• /
• pp.1-8
• /
• 2003

In this paper. we develop an analytical model to evaluate the virtual topology reconfiguration phase of optical Internet networks. To counter the continual approximation problem brought by traditional heuristic approach, we take the traffic prediction into consideration and propose a new heuristic reconfiguration algorithm called Prediction based Multi-stage Reconfiguration approach. We then use this analytical model to study the different configuration operation policies in response to the changing traffic patterns in the higher layer and the congestion level on the virtual topology. This algorithm persists to decide the optimal instant of reconfiguration easily based on the network state. Simulation results show that our virtual topology management Policy significantly outperforms the conventional one, while the required physical resources are limited.

• Journal of Korean Society of Transportation
• /
• v.32 no.5
• /
• pp.522-530
• /
• 2014

Spatio-temporal congestion evolution pattern can be reproduced using the VDS(Vehicle Detection System) historic speed dataset in the TMC(Traffic Management Center)s. Such dataset provides a pool of spatio-temporally experienced traffic conditions. Traffic flow pattern is known as spatio-temporally recurred, and even non-recurrent congestion caused by incidents has patterns according to the incident conditions. These imply that the information should be useful for traffic prediction and traffic management. Traffic flow predictions are generally performed using black-box approaches such as neural network, genetic algorithm, and etc. Black-box approaches are not designed to provide an explanation of their modeling and reasoning process and not to estimate the benefits and the risks of the implementation of such a solution. TMCs are reluctant to employ the black-box approaches even though there are numerous valuable articles. This research proposes a more readily understandable and intuitively appealing data-driven approach and developes an algorithm for identifying congestion patterns for recurrent and non-recurrent congestion management and information provision.