Short-term traffic flow prediction with Conv-LSTM

Short-term traffic flow prediction can provide a basis for traffic management and support for travelers to make decisions. Accurate short-term traffic flow prediction also provides necessary conditions for the sustainable development of the traffic environment. Although the application of deep learning methods for traffic flow prediction has achieved good accuracy, the problem of combining multiple deep learning methods to improve the prediction accuracy of a single method still has a margin for in-depth research. In this article, a combined deep learning prediction (CDLP) model including two paralleled single deep learning models, CNN-LSTM-attention model and CNN-GRU-attention model, is established. In the model, a one-dimensional convolutional neural network (1DCNN) is used to extract traffic flow local trend features and RNN variants (LSTM and GRU) with attention mechanism are used to extract long temporal dependencies trend features. Moreover, a dynamic optimal weighted coefficient algorithm (DOWCA) is proposed to calculate the dynamic weights of CNN-LSTM-attention and CNN-GRU-attention with the goal of minimizing the sum of squared errors of the CDLP model. Then, the neuron number, loss function, optimization algorithm, and other parameters of the CDLP model are discussed and set through experiments. Finally, the training set and test set for the CDLP model are established through the processing of traffic flow data collected from the field. The CDLP model is trained and tested, and the prediction results of traffic flow are obtained and analyzed. It indicates that the CDLP model can fit the change trend of traffic flow very well and has better performance. Furthermore, under the same dataset, the results from the CDLP model are compared with baseline models. It is found that the CDLP model has higher prediction accuracy than baseline models.

In modern intelligent transportation system, traffic control and traffic congestion management are main components of it. Real-time and accurate short-term traffic flow prediction is the precondition and key to realizing traffic control and traffic congestion management. In order to improve the accuracy of short-term traffic flow prediction, a combined model prediction method is proposed in this paper which is based on Xgboost and LightGBM algorithms. First, the short-term traffic flow data is preprocessed and features are sampled. Then, according to different characteristics, different prediction models are constructed by using Xgboost and LightGBM algorithms. Finally, these models are merged to generate the final model. Appling this model for prediction, the average travel time of the road can be obtained to predict the traffic flow and reflect road congestion. Experimental results show that the combined model has higher prediction accuracy than a single model, and it is an effective short-term traffic flow prediction method.

Accurate short-term traffic flow prediction is the foundation of the efficient and proactive management of freeway networks, especially on the abnormal traffic states. The relationship between traffic flow on the current section and the upstream stations can be used for predicting short-term traffic flow. In this paper, we reveal this relationship by the traffic flow structure pattern. The structure pattern can be drawn from real freeway toll data and a few video detective cameras on the freeway segments. Based on the stability pattern, a new traffic flow prediction algorithm has been proposed. Experimental based on real data showed that the prediction method based on structure pattern is an effective approach for traffic flow prediction, especially on the abnormal traffic state.

Traffic flow forecasting is one of the key issues in smart traffic systems. The process of traffic flow changing involves a high degree of nonlinearity and randomness, environmental interference and measurement noise, which brings difficulties to accurate traffic flow prediction. Aiming at improving the accuracy of short-term traffic flow prediction, this paper proposes a method called Basis Prediction method. A raw traffic flow series can be deemed as a summation of a basis series that indicates the changeable trend of the traffic flow and a deviation series that represents the random interference information involved in the flow. The basis series comprises mainly low-frequency signals and the deviation series is composed of some high-frequency signals. Based on an appropriate extraction of the basis series, prediction merely of the basis series brings more precise prediction of the raw traffic flow. This paper suggests adopting wavelet decomposition to obtain the basis series and the deviation series from the raw traffic flow. To predict the basis series effectively, two algorithms, local weighted partial least squares (LW-PLS) and Kalman filtering, are adopted separately and a comparison between them is also provided. In this paper, real data of traffic flow of Xinbei city in Taiwan was collected and used for validation of the proposed basis prediction method. The results show that the use of that proposed method improves the accuracy of short-term traffic flow prediction by about 2% on average.

In recent years, China’s urbanization process has been accelerating, the number of motor vehicles has been increasing, and the problems of traffic congestion, traffic noise and environmental pollution have become increasingly prominent. The application of artificial intelligence system in the field of transportation provides a good idea to solve the above problems. Traffic flow prediction is to estimate the traffic flow in a period of time according to historical traffic data. This technology can provide decision-making basis for traffic guidance and path planning. In this paper, the deep learning theory of artificial intelligence technology is used to predict the short-term traffic flow, and the LSTM prediction model is constructed. On the basis of preprocessing the original data, through correlation analysis, compression matrix construction and other steps, a more accurate short-term traffic flow prediction is realized. According to the model, this paper also discriminates the actual road congestion, and the prediction results are basically consistent with the actual situation.

Construction of traffic state vector using mutual information for short-term traffic flow prediction

Timely and accurate traffic flow information is essential for the realization of intelligent transportation systems (ITS). For the existing traffic flow prediction models, only the temporal features were extracted but the spatial features were neglects. A short-term traffic flow prediction model based on Pearson Correlation Coefficient (PCC) and Bi-directional Long Short-Term Memory Network (BiLSTM) model was proposed. The PCC was used to mine the spatial dependence of the road network, and the temporal features of traffic flow were mined using BiLSTM model. The extracted temporal and spatial features were combined to achieve short-term flow prediction. The experimental results show that the PCC-BiLSTM model has higher prediction accuracy and lower error than the prediction models considering only temporal features, which verifies the effectiveness of traffic flow prediction in consideration of both temporal and spatial characteristics.

Short-term traffic flow prediction (STFP) is one of the key technologies in Intelligence Transportation System (ITS). With the development of artificial intelligence technology, deep learning has been employed to STFP and certain achievements have been obtained. However, further improvement of STFP accuracy is constrained by the presence of noise, modal aliasing in the modal components and insufficient feature extraction of neural networks. Therefore, to more accurately capture the changing trend of traffic flow in different time periods, and increase the reliability and interpretability of the prediction models, improved variational mode decomposition (IVMD) and self-attention mechanism (SAM) based hybrid convolutional neural network (CNN) and long short term memory network (LSTM) are proposed for STFP in this study, benefited from the modal decomposition of IVMD and redistribution of the neural weights in CNN-LSTM networks by SAM, the proposed IVMD-CNN-LSTM-SAM effectively suppresses the influence of randomness and volatility of traffic flow, and accurately predict the short-term lane occupancy in the designated area. Furthermore, this study analyses the mechanism of SAM and IVMD in STFP, and proves the superiority of IVMD and SAM in signal decomposition with physical significance and weight allocation respectively. Therefore, the interpretability of the proposed neural network model is significantly improved. Eleven competitive neural networks forecasting methods are used as benchmarks and numerical studies based on actual traffic flow validate the accuracy and stability of the proposed IVMD-CNN-LSTM-SAM. Mean absolute percentage error and goodness of fit of the proposed model are 0.81% and 0.9968, respectively.

Wang, H. and Yue, P., 2020. Short-term traffic flow prediction of coastal cities based on entropy weight method. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Research, Special Issue No. 103, pp. 739–743. Coconut Creek (Florida), ISSN 0749-0208.The traditional short-term traffic flow prediction method has a high prediction error, so a short-term traffic flow prediction method based on entropy weight method is designed. First, identify the lost data, use the weighted average value of historical trend data and measured data to modify, and standardize the original data to collect the short-term traffic flow data of coastal cities. Then, statistical analysis of the original data set, using the minimum maximum standardization method, linear transformation of the original data, and extract the characteristic factors that affect the traffic flow. Finally, based on the correlation of traffic flow at urban intersections, the short-term traffic flow prediction of coastal cities is completed by using entropy weight method. In the experimental part, the prediction errors of the two methods in the period of 7:00-9:00 and 22:00-24:00 are compared. The comparison results show that the prediction errors of the short-term traffic flow prediction method based on entropy weight method in the period of 7:00-9:00 and 22:00-24:00 are small, which proves that the prediction method of this design has practical application significance.

As one of the effective technical means to improve traffic management and alleviate traffic congestion, short-term traffic flow prediction on urban roads has been rapidly applied and developed with the development of machine learning algorithms, and has achieved good prediction results. Reviewed the basic characteristics of traffic flow and the classification of prediction models. On this basis, the development trajectory of deep learning technology and its application in the future field of transportation engineering were discussed. Based on the actual traffic data of Chongqing Dadukou, a deep learning model framework, overall data preprocessing method, and feature engineering idea for short-term traffic flow prediction were designed. Based on the actual collection of data in the experimental area and the establishment of relevant models, the training process of the model and the adjustment and optimization of hyperparameters were optimized to make it more stable and accurate in prediction. At the same time, quantitative analysis was conducted on different evaluation indicators, and it was concluded that the model has strong robustness and generalization ability for different traffic conditions. The conclusion indicates that the model has good accuracy and universality when applied to short-term traffic flow prediction on urban roads, and can assist in intelligent management of urban traffic. Summarized the main conclusions of this article and explored possible directions for future work: firstly, conducted in-depth research on multi-source data fusion technology and interpretability of models.

Short-term traffic speed prediction is a promising research topic in intelligent transportation systems (ITSs), which also plays an important role in the real-time decision-making of traffic control and guidance systems. However, the urban traffic speed has strong temporal, spatial correlation and the characteristic of complex nonlinearity and randomness, which makes it challenging to accurately and efficiently forecast short-term traffic speeds. We investigate the relevant literature and found that although most methods can achieve good prediction performance with the complete sample data, when there is a certain missing rate in the database, it is difficult to maintain accuracy with these methods. Recent studies have shown that deep learning methods, especially long short-term memory (LSTM) models, have good results in short-term traffic flow prediction. Furthermore, the attention mechanism can properly assign weights to distinguish the importance of traffic time sequences, thereby further improving the computational efficiency of the prediction model. Therefore, we propose a framework for short-term traffic speed prediction, including data preprocessing module and short-term traffic prediction module. In the data preprocessing module, the missing traffic data are repaired to provide a complete dataset for subsequent prediction. In the prediction module, a combined deep learning method that is an attention-based LSTM (ATT-LSTM) model for predicting short-term traffic speed on urban roads is proposed. The proposed framework was applied to the urban road network in Nanshan District, Shenzhen, Guangdong Province, China, with a 30-day traffic speed dataset (floating car data) used as the experimental sample. Results show that the proposed method outperforms other deep learning algorithms (such as recurrent neural network (RNN) and convolutional neural network (CNN)) in terms of both calculating efficiency and prediction accuracy. The attention mechanism can significantly reduce the error of the LSTM model (up to 12.4%) and improves the prediction performance.

Proactive traffic management is a subset of smart mobility applications in which traffic control strategies are implemented in advance to respond to anticipated roadway conditions. Predicted traffic flows are a key input to proactive traffic control systems, such as proactive freeway ramp metering, proactive variable speed limits, and proactive incident management systems. This paper proposes a machine learning approach for short-term traffic flow prediction where prevailing conditions, such as the traffic volume, speed, and occupancy of roadway segments, are used to predict traffic flow in short-term intervals. Four categories of predictive methods for traffic flow prediction were investigated: deep neural networks, a distributed random forest, a gradient boosting machine, and a generalized linear model. Data from Interstate 64 in St. Louis, Missouri, in the United States were used to calibrate and evaluate the models. The results obtained by the four predictive methods were very similar, with the distributed random forest model slightly outperforming the models obtained by the other three methods. The case study showed that the inclusion of traffic flow, speed, occupancy, and time of day in the traffic prediction process reduces the traffic prediction error. However, the two-sample Kolmogorov-Smirnov test did not show a statistically significant benefit from the inclusion of upstream traffic data in the distributed random forest, and gradient boosting machine models.

Accurate short-term traffic flow prediction is pivotal for intelligent transportation systems and smart city planning. This study presents a hybrid deep learning model Deep TrafficNet, which combines both Gated Recurrent Units (GRU) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks to predict the nature of the multi-junction traffic flow. The suggested model is demonstrated to have enhanced the extraction of temporal features and error in prediction is minimized with the help of massive real-world traffic data consisting of four urban intersections. To ensure the quality and stationarity of the data, the data were analysed by using the exploratory data analysis, z-score normalisation and Augmented Dickey-Fuller (ADF) test which yielded an overall RMSE value of 20.47, an improvement of 33% and 31% over LSTM and GRU baselines, respectively. The model was also suitable to model the junction-level variations with RMSEs of 31.43, 10.83, 13.51, and 17.79 in the four junctions. These results indicate that the model is efficient and scalable in its capacities to predict traffic effectively and which is important in adaptive traffic management of smart urban ecosystems.

Short-term traffic flow prediction plays an important role in intelligent transportation system. Numerous researchers have paid much attention to it in the past decades. However, the performance of traditional traffic flow prediction methods is not satisfactory, for those methods cannot describe the complicated nonlinearity and uncertainty of the traffic flow precisely. Neural networks were used to deal with the issues, but most of them failed to capture the deep features of traffic flow and be sensitive enough to the time-aware traffic flow data. In this paper, we propose a deep bi-directional long short-term memory (DBL) model by introducing long short-term memory (LSTM) recurrent neural network, residual connections, deeply hierarchical networks and bi-directional traffic flow. The proposed model is able to capture the deep features of traffic flow and take full advantage of time-aware traffic flow data. Additionally, we introduce the DBL model, regression layer and dropout training method into a traffic flow prediction architecture. We evaluate the prediction architecture on the dataset from Caltrans Performance Measurement System (PeMS). The experiment results demonstrate that the proposed model for short-term traffic flow prediction obtains high accuracy and generalizes well compared with other models.

Accurate selection of spatial-temporal features is key to the short-term traffic flow prediction model outputting higher quality results, which can effectively reduce the difficulty of constructing the prediction model. The spatial-temporal feature selection of most existing short-term traffic flow prediction models mainly relies on empirical knowledge methods and lacks interpretability. The proposed short-term traffic flow prediction network, named STFP-FGFS, utilizes a filter-genetic feature selection method to better explain the results of short-term traffic flow predictions. It consists of three stages: initial generation of temporal-spatial feature set, filtering, and feature optimization, as well as the predicted model. The initial spatial features are generated based on effective travel time, target time granularity, and vehicle type; that is, original spatial features are replaced by standardized spatial features. Four widely used feature selection methods for short-term traffic flow prediction are applied and compared, evaluating three experimental targets and four types of time granularity using four evaluation indexes. The results show that the STFP-FGFS proposed method has overall superior performance, good interpretability, and readability for selected spatial-temporal features.