• Proceedings of the KOR-KST Conference
• /
• 1998.10a
• /
• pp.21-30
• /
• 1998

본 연구는 기존 구간 속도 예측기법의 고찰을 통하여 검지기에서 올라오는 교통제어변수를 이용하여 구간 속도 예측모형을 연구하는데 목적이 있다. 이를 위한 교통 제어변수로는 연속류 제어에서 통상적으로 사용되는 교통량, 점유율, 밀도, 속도 등을 사용한다. 공간적 범위로는 서울 올림픽대로의 17개의 영상 검지기 중 #3과 #16검지기에서 올라오는 속도, 점유율, 교통량 자료를 토대로 1998년 6월 11일 오전 7시부터 11시까지의 4시간동안 예측을 실시하며 Historical Traffic Pattern과 시험차량, 자동차 번호판 조사를 통한 구간 실측조사 자료를 토대로 예측을 위한 자료를 구축한다. 기존의 예측기법인 시계열 분석, 신경망 이론, 평활법과 칼만필터링을 고찰하였고, 가장 좋은 예측력을 보여주는 기법은 칼만필터링 모형이었다. 이를 토대로 Case Study를 통해 여러 구간의 다주기 예측을 통해 단기간(short-term)의 구간 속도를 예측하고 각 해당 검지기별 실측자료를 통해 비교분석을 실시하였다. 결과적으로 도출된 칼만필터링 모형의 다주기 예측을 통한 구간 통행속도의 예측이 기존의 구간 통행속도 산출 방법보다 더 나은 예측력을 보여주고 있다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.86-99
• /
• 2021

One of the methods to alleviate traffic congestion is to increase the efficiency of the roads by providing traffic condition information on road user and distributing the traffic. For this, reliability must be guaranteed, and quantitative real-time traffic speed prediction is essential. In this study, and based on analysis of traffic speed related to traffic conditions, historical data correlated with traffic flow were used as input. We developed an LSTM model that predicts speed in response to normal traffic conditions, along with a CNN-LSTM model that predicts speed in response to incidents. Through these models, we try to predict traffic speeds during the hour in five-minute intervals. As a result, predictions had an average error rate of 7.43km/h for normal traffic flows, and an error rate of 7.66km/h for traffic incident flows when there was an incident.

• The Journal of the Korea Contents Association
• /
• v.20 no.4
• /
• pp.25-37
• /
• 2020

As social costs of traffic congestion increase, various studies are underway to predict road speed. In order to improve the accuracy of road speed prediction, unexpected traffic situations need to be considered. In this paper, we propose a road speed prediction scheme considering traffic incidents affecting road speed. We use not only the speed data of the target road but also the speed data of the connected roads to reflect the impact of the connected roads. We also analyze the amount of speed change to predict the traffic congestion caused by traffic incidents. We use the speed data of connected roads and target road with input data to predict road speed in the first place. To reduce the prediction error caused by breaking the regular road flow due to traffic incidents, we predict the final road speed by applying event weights. It is shown through various performance evaluations that the proposed method outperforms the existing methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.308-309
• /
• 2021

과거의 연구들은 교통 속도만을 활용하여 교통 속도 예측 문제에 접근했다. 그러나 교통 속도의 비선형성으로 인해 정확한 예측이 어려워, 최근에는 교통 속도에 영향을 미칠 수 있는 외부의 요인을 활용해 정확도를 높인 연구들이 이루어지는 추세이다. 그 중에서도 강수량은 직관적으로 교통 속도와 관련이 있을 것으로 생각되어 자주 사용된다. 다만, 실제로 교통 속도가 강수량에 얼마나 영향을 받는지는 확인되지 않고 대부분의 연구가 적은 양의 데이터로 이루어지기에 강수량이 딥 러닝모델의 정확도를 향상시킬 수 있다고 단언하기는 어렵다. 본 논문은 강수량 데이터가 교통 속도를 변화시키는 양을 정량적으로 측정하고, 딥 러닝 모델의 성능에 미치는 영향을 분석하였다. 그 결과, 강수량이 높을수록 속도가 크게 감소하고 딥 러닝 모델의 정확도 또한 향상되는 것을 확인하였다.

• 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).

• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.111-121
• /
• 2008

Using variable speed limits (VSL) is a key strategy for preventing traffic accidents and alleviating traffic congestion. This study proposes an algorithm to operate VSLs on freeways for traffic safety. The proposed algorithm consists of two components based on accident likelihood estimation and analysis of safe stopping distance under various environmental conditions. A binary logistic regression technique is used for estimating accident likelihood. It is expected that the proposed algorithm would be successfully applied in practice in support of an integrated traffic and environmental condition monitoring system. Technical issues associated with the field implementation are also discussed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.4
• /
• pp.44-55
• /
• 2013

Intelligent transportation systems allow us to have valuable opportunities for collecting reliable wide-area coverage traffic and weather data. Significant efforts have been made in many countries to apply these data. This study identifies the critical points for classifying rain intensity by analyzing the relationship between rainfall and the amount of speed reduction. Then, traffic prediction performance by rain intensity level is evaluated using relative errors. The results show that critical points are 0.4mm/5min and 0.8mm/5min for classifying rain intensity (slight, moderate, and heavy rain). The best prediction performance is observable when previous five-block speed data is used as inputs under normal weather conditions. On the other hand, previous two or three-block speed data is used as inputs under rainy weather conditions. The outcomes of this study support the development of more reliable traffic information for providing advanced traffic information service.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.342-347
• /
• 2003

It is essential to develop an algorithm for the estimate of link travel velocity and for the supply and control of travel information in the context of intelligent transportation information system. The paper proposes the fuzzy logic based prediction of link travel velocity. Three factors such as time, date and velocity are considered as major components to represent the travel situation. In the fuzzy modeling, those factors were expressed by fuzzy membership functions. We acquire position／velocity data through GPS antenna with PDA embedded probe vehicles. The link travel velocity is calculated using refined GPS data and the prediction results are compared with actual data for its accuracy.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.377-380
• /
• 2004

본 논문에서는 기존의 교통 상황 검지 장비들이 가지고 있는 문제점들을 해결하기 위해 실제 통행속도 데이터의 해당 도로 속성들을 이용하여 데이터 마이닝을 통한 합리적인 오차범위 내에서의 실시간 교통 정보 예측 알고리즘을 제안한다. 본 논문에서 제안하는 알고리즘은 데이터 파이닝의 분석 기법중 하나인 신경망(Neural Network)분석을 통하여 통행 속도 예측 근사 모델을 개발하는 것이며, 기존의 교통 상황 판단 알고리즘과의 결과 비교를 통해 비용 절감 효과와 속도 정보가 없는 도로까지의 합리적인 통행 속도 예측, 그리고 Off line상에서의 시간대별 교통 정보 제공이 가능함을 보인다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.7
• /
• pp.1312-1318
• /
• 2006

One of the common services of telematics is the car navigation that finds the shortest path from source to target. Until now, some routing algorithms of the car navigation do not consider the real-time traffic information and use the static shortest path algorithm. In this paper, we prosed the method to predict the traffic flow in the future. This prediction combines two methods. The former is an accumulated speed pattern, which means the analysis results for all past speeds of each road by classfying the same day and the same time inteval. The latter is the Kalman filter. We predicted the traffic flows of each segment by combining the two methods. By experiment, we showed our algorithm gave better precise predicition than only using accumulated speed pattern that is used commonly. The result can be applied to the car navigation to support a dynamic shortest path. In addition, it can give users the travel information to avoid the traffic congestion areas.