An Improved K-nearest Neighbor Model for Short-term Traffic Flow Prediction
TL;DR: A short-term traffic prediction based on k-NN nonparametric regression model is developed in the Matlab platform and results show that the accuracy of the proposed method is over 90 percent and it also rereads that the feasibility of the methods is used in short- term traffic flow prediction.
About: This article is published in Procedia - Social and Behavioral Sciences.The article was published on 2013-11-06 and is currently open access. It has received 212 citations till now. The article focuses on the topics: Traffic flow & Nonparametric regression.
Citations
More filters
TL;DR: In this article, a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is combined with the graph convolutionsal network and the gated recurrent unit (GRU), is proposed.
Abstract: Accurate and real-time traffic forecasting plays an important role in the intelligent traffic system and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an “open” scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time. To capture the spatial and temporal dependences simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is combined with the graph convolutional network (GCN) and the gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures for capturing spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data for capturing temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at https://www.github.com/lehaifeng/T-GCN .
1,188 citations
TL;DR: This research provides strong evidence suggesting that the proposed non-parametric and data-driven approach for short-term traffic forecasting provides promising results and can be easily incorporated with real-time traffic control for proactive freeway traffic management.
Abstract: The ability to timely and accurately forecast the evolution of traffic is very important in traffic management and control applications. This paper proposes a non-parametric and data-driven methodology for short-term traffic forecasting based on identifying similar traffic patterns using an enhanced K-nearest neighbor (K-NN) algorithm. Weighted Euclidean distance, which gives more weight to recent measurements, is used as a similarity measure for K-NN. Moreover, winsorization of the neighbors is implemented to dampen the effects of dominant candidates, and rank exponent is used to aggregate the candidate values. Robustness of the proposed method is demonstrated by implementing it on large datasets collected from different regions and by comparing it with advanced time series models, such as SARIMA and adaptive Kalman Filter models proposed by others. It is demonstrated that the proposed method reduces the mean absolute percent error by more than 25%. In addition, the effectiveness of the proposed enhanced K-NN algorithm is evaluated for multiple forecast steps and also its performance is tested under data with missing values. This research provides strong evidence suggesting that the proposed non-parametric and data-driven approach for short-term traffic forecasting provides promising results. Given the simplicity, accuracy, and robustness of the proposed approach, it can be easily incorporated with real-time traffic control for proactive freeway traffic management.
234 citations
Cites methods from "An Improved K-nearest Neighbor Mode..."
..., 2009; Wang and Shi, 2013), k-nearest neighbor (Lin et al., 2013; Zhang et al., 2013; Zheng et al., 2006)....
[...]
...Pattern recognition methods were also applied for short-term traffic forecast, e.g., cluster analysis (Xia et al., 2012), support vector machines (SVM) (Castro-Neto et al., 2009; Wang and Shi, 2013), k-nearest neighbor (Lin et al., 2013; Zhang et al., 2013; Zheng et al., 2006)....
[...]
TL;DR: A novel deep learning framework named attention graph convolutional sequence-to-sequence model (AGC-Seq2Seq) is proposed to capture the complex non-stationary temporal dynamics and spatial correlations in multistep traffic-condition prediction and further capture the temporal heterogeneity of traffic pattern.
Abstract: Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial correlations in multistep traffic-condition prediction, we propose a novel deep learning framework named attention graph convolutional sequence-to-sequence model (AGC-Seq2Seq). In the proposed deep learning framework, spatial and temporal dependencies are modeled through the Seq2Seq model and graph convolution network separately, and the attention mechanism along with a newly designed training method based on the Seq2Seq architecture is proposed to overcome the difficulty in multistep prediction and further capture the temporal heterogeneity of traffic pattern. We conduct numerical tests to compare AGC-Seq2Seq with other benchmark models using two real-world datasets. The results indicate that our model yields the best prediction performance in terms of various prediction error measures. Furthermore, the variations of spatio-temporal correlations of traffic conditions under different perdition steps and road segments are revealed.
188 citations
Posted Content•
12 Nov 2018
TL;DR: Experiments demonstrate that the T-GCN model can obtain the spatiotemporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets.
Abstract: Accurate and real-time traffic forecasting plays an important role in the Intelligent Traffic System and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence. To capture the spatial and temporal dependence simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is in combination with the graph convolutional network (GCN) and gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures to capture spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data to capture temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at this https URL.
177 citations
Cites methods from "An Improved K-nearest Neighbor Mode..."
...There are many existing traffic forecasting methods, some of which consider temporal dependence, including the ARIMA model[5, 6], the Kalman filtering model[7], the support vector regression machine model[8, 9], the k-nearest neighbor model[10], the Bayesian model[11] and partial neural network model[12, 13]....
[...]
...The common nonparametric model includes: the k-nearest neighbor model[10], the support vector regression model[8, 9, 35], the Fuzzy Logic model[36], the Bayesian network model[11], the neural network model and so on....
[...]
TL;DR: The support vector machine model with spatial‐temporal parameters exhibits good performance compared with an artificial neural network, a k‐nearest neighbor model, a historical data‐ based model, and a moving average data‐based model.
Abstract: Short-term traffic speed prediction is one of the most critical components of an intelligent transportation system ITS. The accurate and real-time prediction of traffic speeds can support travellers' route choices and traffic guidance/control. In this article, a support vector machine model single-step prediction model composed of spatial and temporal parameters is proposed. Furthermore, a short-term traffic speed prediction model is developed based on the single-step prediction model. To test the accuracy of the proposed short-term traffic speed prediction model, its application is illustrated using GPS data from taxis in Foshan city, China. The results indicate that the error of the short-term traffic speed prediction varies from 3.31% to 15.35%. The support vector machine model with spatial-temporal parameters exhibits good performance compared with an artificial neural network, a k-nearest neighbor model, a historical data-based model, and a moving average data-based model.
166 citations
Cites background from "An Improved K-nearest Neighbor Mode..."
...…popular methods because of its simple nature and wide applicability, and it has been successfully applied by many scholars for short-term traffic flow prediction (Smith et al., 2002; Zuo et al., 2008; Akbari et al., 2011; Turochy, 2006; Lam et al., 2006; Chang et al., 2012; Zhang et al., 2013)....
[...]
References
More filters
TL;DR: This research effort seeks to examine the theoretical foundation of nonparametric regression and to answer the question of whether non parametric regression based on heuristically improved forecast generation methods approach the single interval traffic flow prediction performance of seasonal ARIMA models.
Abstract: Single point short-term traffic flow forecasting will play a key role in supporting demand forecasts needed by operational network models. Seasonal autoregressive integrated moving average (ARIMA), a classic parametric modeling approach to time series, and nonparametric regression models have been proposed as well suited for application to single point short-term traffic flow forecasting. Past research has shown seasonal ARIMA models to deliver results that are statistically superior to basic implementations of nonparametric regression. However, the advantages associated with a data-driven nonparametric forecasting approach motivate further investigation of refined nonparametric forecasting methods. Following this motivation, this research effort seeks to examine the theoretical foundation of nonparametric regression and to answer the question of whether nonparametric regression based on heuristically improved forecast generation methods approach the single interval traffic flow prediction performance of seasonal ARIMA models.
926 citations
TL;DR: Using 3-min volume measurements from urban arterial streets near downtown Athens, models were developed that feed on data from upstream detectors to improve on the predictions of downstream locations and it appears that the use of multivariate state space models improves on the prediction accuracy over univariate time series ones.
Abstract: Urban traffic congestion is one of the most severe problems of everyday life in Metropolitan areas. In an effort to deal with this problem, intelligent transportation systems (ITS) technologies have concentrated in recent years on dealing with urban congestion. One of the most critical aspects of ITS success is the provision of accurate real-time information and short-term predictions of traffic parameters such as traffic volumes, travel speeds and occupancies. The present paper concentrates on developing flexible and explicitly multivariate time-series state space models using core urban area loop detector data. Using 3-min volume measurements from urban arterial streets near downtown Athens, models were developed that feed on data from upstream detectors to improve on the predictions of downstream locations. The results clearly suggest that different model specifications are appropriate for different time periods of the day. Further, it also appears that the use of multivariate state space models improves on the prediction accuracy over univariate time series ones.
504 citations
TL;DR: In this article, a comparison of the forecasting performance of these four models is undertaken with data sets from 25 loop detectors located in major arterials in the city of Athens, Greece, where the variable under study is the relative velocity, which is the traffic volume divided by the road occupancy.
Abstract: Several univariate and multivariate models have been proposed for performing short-term forecasting of traffic flow. Two different univariate [historical average and ARIMA (autoregressive integrated moving average)] and two multivariate [VARMA (vector autoregressive moving average) and STARIMA (space-time ARIMA)] models are presented and discussed. A comparison of the forecasting performance of these four models is undertaken with data sets from 25 loop detectors located in major arterials in the city of Athens, Greece. The variable under study is the relative velocity, which is the traffic volume divided by the road occupancy. Although the specification of the network's neighborhood structure for the STARIMA model was relatively simple and can be further refined, the results obtained indicate a comparable forecasting performance for the ARIMA, VARMA, and STARIMA models. The historical average model could not cope with the variability of the data sets at hand.
352 citations
Journal Article•
TL;DR: In a comparison of a backpropagation neural network model with the more traditional approaches of an historical, data-based algorithm and a time-series model, the back Propagation model was clearly superior, although all three models did an adequate job of predicting future traffic volumes.
Abstract: Much of the current activity in the area of intelligent vehicle-highway systems (IVHSs) focuses on one simple objective: to collect more data. Clearly, improvements in sensor technology and communication systems will allow transportation agencies to more closely monitor the condition of the surface transportation system. However, monitoring alone cannot improve the safety or efficiency of the system. It is imperative that surveillance data be used to manage the system in a proactive rather than a reactive manner. Proactive traffic management will require the ability to predict traffic conditions. Previous predictive modeling approaches can be grouped into three categories: (a) historical, data-based algorithms; (b) time-series models; and (c) simulations. A relatively new mathematical model, the neural network, offers an attractive alternative because neural networks can model undefined, complex nonlinear surfaces. In a comparison of a backpropagation neural network model with the more traditional approaches of an historical, data-based algorithm and a time-series model, the backpropagation model was clearly superior, although all three models did an adequate job of predicting future traffic volumes. The backpropagation model was more responsive to dynamic conditions than the historical, data-based algorithm, and it did not experience the lag and overprediction characteristics of the time-series model. Given these advantages and the backpropagation model's ability to run in a parallel computing environment, it appears that such neural network prediction models hold considerable potential for use in real-time IVHS applications.
331 citations
TL;DR: An examination on how realtime information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods found that the modular ANN outperformed a conventional singular ANN.
Abstract: With the advent of route guidance systems (RGS), the prediction of short-term link travel times has become increasingly important. For RGS to be successful, the calculated routes should be based on not only historical and real-time link travel time information but also anticipatory link travel time information. An examination is conducted on how real-time information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods (of 5 minutes' duration). The methodology developed consists of two steps. First, the historical link travel times are classified based on an unsupervised clustering technique. Second, an individual or modular artificial neural network (ANN) is calibrated for each class, and each modular ANN is then used to predict link travel times. Actual link travel times from Houston, Texas, collected as part of the automatic vehicle identification system of the Houston Transtar system were used as a test bed. It was found that the modular ANN outperformed a conventional singular ANN. The results of the best modular ANN were compared with existing link travel time techniques, including a Kalman filtering model, an exponential smoothing model, a historical profile, and a real-time profile, and it was found that the modular ANN gave the best overall results.
238 citations
"An Improved K-nearest Neighbor Mode..." refers methods in this paper
...…based on traditional mathematics and physics models, including the historical average model (Keith, Scherer, and Smith, 2000), time series models (Park and Rilett, 1998), Kalman filtering model (Nihan and Holmesland,1980) and exponential smoothing model etc.; the other is the mathematical model…...
[...]