A Deep Ensemble Approach for Long-Term Traffic Flow Prediction

The increasing complexity of urban transportation systems and the growing volume of vehicles have made traffic congestion a persistent challenge in modern cities. Efficient traffic flow prediction is essential for mitigating congestion, improving road safety, optimizing traffic signal control, and enhancing overall transportation efficiency. In recent years, artificial intelligence (AI) has emerged as a transformative tool in the field of traffic management, offering sophisticated algorithms capable of modeling, analyzing, and predicting complex traffic patterns with high accuracy. The application of AI in traffic flow prediction leverages vast amounts of real-time and historical data to generate precise forecasts, supporting data-driven decision-making by urban planners and traffic control authorities. The prediction of traffic flow involves analyzing time-series data that exhibit nonlinear, dynamic, and often stochastic behavior. Traditional statistical models, such as autoregressive integrated moving average (ARIMA), have proven to be limited in handling the high dimensionality and variability inherent in traffic systems. In contrast, AI algorithms possess the capacity to learn and adapt from complex data inputs without the need for explicit programming, making them particularly suitable for traffic-related applications. AI algorithms used in traffic flow prediction can be broadly categorized into machine learning (ML) and deep learning (DL) approaches. Machine learning algorithms such as k-nearest neighbors (KNN), support vector machines (SVM), decision trees, and random forests have demonstrated effectiveness in short-term traffic prediction tasks. These algorithms are capable of identifying hidden patterns in traffic data and adjusting to changes in traffic behavior over time. Ensemble methods, which combine the strengths of multiple learning models, further enhance prediction accuracy and robustness. Deep learning algorithms, a subfield of AI inspired by the human brain’s neural architecture, have shown exceptional performance in capturing spatial-temporal dependencies in traffic data. Recurrent neural networks (RNNs), particularly long short-term memory (LSTM) networks and gated recurrent units (GRUs), are widely used for their ability to process sequential data and retain information over extended time intervals. Convolutional neural networks (CNNs) are employed to extract spatial features from traffic sensor data or road network imagery. Hybrid models that integrate CNNs with RNNs have achieved high levels of predictive precision by simultaneously learning spatial and temporal correlations. In addition to supervised learning methods, unsupervised and reinforcement learning techniques are also applied in traffic flow prediction. Clustering algorithms, such as k-means and DBSCAN, assist in identifying traffic patterns, while reinforcement learning models optimize adaptive traffic signal control systems by learning optimal actions through environmental interaction. This study explores the different types of AI algorithms used in traffic flow prediction, examining their theoretical foundations, structural differences, and practical applications. It aims to evaluate the comparative advantages of various algorithms in addressing the challenges of real-time traffic prediction in increasingly complex transportation networks. Keywords: Machine Learning, Deep Learning, Neural Networks, Regression Models, Reinforcement Learning

Traffic prediction is a critical component of intel-ligent transportation systems. However, highly non-linear and dynamical spatial-temporal correlations propose challenges for traffic prediction, especially long-term prediction. We propose a spatial-temporal channel-attention based graph convolutional network (STCAGCN) to improve the accuracy of both long-term and short-term traffic flow prediction. Firstly we design an attention mechanism to learn complex temporal and spatial correlations. Then we develop the stacked spatial-temporal convo-lution layer to model complex temporal and spatial correlations. Each spatial-temporal convolution layer is composed of a gated time convolution network and a graph convolution network. We develop a gated time convolution network to model non-linear temporal correlations, which process long sequences through stacked dilated convolution. Moreover, the graph convolution network exploits the hidden spatial correlations via learning self-adaptive adjacency matrix. Experiment results on real-world datasets demonstrate that the proposed STCAGCN model obtains improvements over the state-of-the-art, especially for long-term traffic flow prediction.

Nowadays accurate and efficient traffic flow prediction is strongly needed by individual travelers and public transport management. Traffic flow prediction, especially long-term prediction, plays an important role in the application of intelligent transportation systems (ITS). In this paper, we propose a personalized design model (ResDeconvNN) based on Convolutional Neural Network (CNN) for long-term traffic flow prediction of elevated highways in Shanghai. The next whole day flow information can be predicted using the previous day flows. Taking the correlation of traffic parameters into account, we analogy flow, speed and occupancy (FSO) to the 3 channels of RGB as the 3 inputs of model. So the raw data collected from loop detectors are transformed into a spatial-temporal matrix which has 3 channels. Our model consists of two modules: Residual net and deconvolutional neural network. First, we take advantage of the residual net in deep network to extract the features of traffic. Then, we develop a deconvolutional network module and apply it to decode the flow of the next day from the comprehensive spatial and temporal traffic features. Experimental results indicate that the proposed model is robust and can achieve a better prediction accuracy compared with the other existing popular approaches.

Smart city visions aim to offer citizens with intelligent services in various aspects of life. The services envisioned have been significantly enhanced with the proliferation of Internet-of-Things (IoT) technology offering real-time and ubiquitous monitoring capability. In this paper, we focus on the short-term traffic flow prediction problem based on real-world traffic data as one critical component of a smart city. In contrast to long-term traffic prediction, accurate prediction of short-term traffic flow facilitates timely traffic management and rapid response. We develop and study a novel ensemble model (EM) based on long short term memory (LSTM), deep autoencoder (DAE) and convolutional neural network (CNN) models. Our approach takes into account both temporal and spatial characteristics of the traffic conditions. We evaluate our proposal against well-known existing prediction models. We use two real traffic data (California and London roadways) with different characteristics to train and test the models. Our results indicate that our proposed ensemble model achieves the most accurate predictions (approx. 97.50% and approx. % accuracy) and is robust against high variance traffic flow.

Dynamic Classifier Selection (DCS) techniques aim to select the most competent classifiers from an ensemble per test sample. For each test sample, only a subset of the most competent classifiers is used to estimate its target value. The performance of the DCS highly depends on how we define the local region of competence, which is a local region in the feature space around the test sample. In this paper, we propose a new definition of region of competence based on a new proximity measure. We exploit the observed similarities between traffic profiles at different links, days and hours to obtain similarities between different values. Furthermore, long-term traffic pattern prediction is a complex problem and most of the traffic prediction literature are based on time-series and regression approaches and their prediction time is limited to next few hours or days. We tackle the long-term traffic pattern prediction as a classification of discretized traffic indicators to improve the accuracy of urban traffic pattern forecasting of next weeks by using DCS. We also employ two different link clustering methods, for grouping traffic links. For each cluster, we train a dynamic classifier system for predicting the traffic variables (flow, speed and journey time). Our results on strategic road network data shows that the proposed method outperforms the existing ensemble and baseline models in long-term traffic prediction.

<p>Accurate traffic congestion and flow prediction plays a crucial role in designing intelligent transport system (ITS) for vehicles in heterogeneous mobile networks. Traffic speed, flow and congestion prediction is a challenging task if limited attributes are used as input to predictive models or the prediction is done too late to take any appropriate action. Although several deep learning and machine learning approaches have been deployed to predict different traffic conditions, these approaches are based on the traffic observations at target location or its adjacent regions. Complex road networks, large data sets with multiple traffic features and analysis of spatial temporal dependencies of traffic data are not yet exploited in detail. In this study, a workflow consists of data acquisition, analysis, and exploitation of real-world time series traffic data is developed. We study number of data driven models namely, the long short-term memory (LSTM), gated recurrent unit (GRU) and hybrid CNN-LSTM model to predict traffic and compare it with the linear regression (LR) model. The deep learning models are capable of handling both spatial and temporal dependencies as well as the sudden changes in traffic speed and flow predicting the vehicular traffic accurately over long periods. The models are trained using the six months and three months of traffic flow, speed and occupancy data provided by the California Department of Transportation (Caltrans). The deep learning models outperform traditional linear regression method. Moreover, an architectural study of deep learning models is carried out for traffic prediction to discover the best structure for traffic congestion prediction. The performance of the models is evaluated using MSE and MAE metrics. It is concluded that the performance of deep learning models vary with the amount of historical data and sliding window size used for the traffic prediction. It is observed that a complex hybrid model like CNN-LSTM is not required for accurate prediction of the spatial and temporal tendencies when the training period is longer (six months). The GRU with much simpler architecture does not need to store road network and temporal information for long term in its memory, outperforms the LSTM and CNN- LSTM models. However, as the data size is reduced CNN-LSTM model out- performs the LSTM and GRU models for traffic congestion prediction.</p>

<p>Accurate traffic congestion and flow prediction plays a crucial role in designing intelligent transport system (ITS) for vehicles in heterogeneous mobile networks. Traffic speed, flow and congestion prediction is a challenging task if limited attributes are used as input to predictive models or the prediction is done too late to take any appropriate action. Although several deep learning and machine learning approaches have been deployed to predict different traffic conditions, these approaches are based on the traffic observations at target location or its adjacent regions. Complex road networks, large data sets with multiple traffic features and analysis of spatial temporal dependencies of traffic data are not yet exploited in detail. In this study, a workflow consists of data acquisition, analysis, and exploitation of real-world time series traffic data is developed. We study number of data driven models namely, the long short-term memory (LSTM), gated recurrent unit (GRU) and hybrid CNN-LSTM model to predict traffic and compare it with the linear regression (LR) model. The deep learning models are capable of handling both spatial and temporal dependencies as well as the sudden changes in traffic speed and flow predicting the vehicular traffic accurately over long periods. The models are trained using the six months and three months of traffic flow, speed and occupancy data provided by the California Department of Transportation (Caltrans). The deep learning models outperform traditional linear regression method. Moreover, an architectural study of deep learning models is carried out for traffic prediction to discover the best structure for traffic congestion prediction. The performance of the models is evaluated using MSE and MAE metrics. It is concluded that the performance of deep learning models vary with the amount of historical data and sliding window size used for the traffic prediction. It is observed that a complex hybrid model like CNN-LSTM is not required for accurate prediction of the spatial and temporal tendencies when the training period is longer (six months). The GRU with much simpler architecture does not need to store road network and temporal information for long term in its memory, outperforms the LSTM and CNN- LSTM models. However, as the data size is reduced CNN-LSTM model out- performs the LSTM and GRU models for traffic congestion prediction.</p>

Prediction of wind turbine blade icing fault based on selective deep ensemble model

Efficient traffic flow prediction is crucial to the operation of intelligent transportation systems and the dynamic management of traffic flow. Due to the great complexity and uncertainty of traffic flow data , a single neural network prediction model can no longer meet the needs of high-precision prediction and real-time performance in reality. This paper develops for the first time a hybrid neural network model based on Black-winged Kite Algorithm (BKA)-Convolutional Neural Network (CNN)-Gated Recurrent Unit (GRU) to analyze the time series characteristics of traffic flow for long-term traffic flow prediction. The Convolutional Neural Network (CNN) has a good ability to identify traffic flow characteristics and the Gated Recurrent Unit (GRU) has the characteristics of efficiently processing long sequence traffic flow data. The Black-winged Kite Algorithm was selected as the optimization algorithm to improve the prediction accuracy of the model due to its ability to search traffic flow globally and its fast convergence speed. The hybrid model was trained and tested using traffic data from a road in an urban area of Paris, France. After data preprocessing, we analyzed the prediction results of GRU, CNN-GRU, and BKA-CNN-GRU hybrid models. The BKA-CNN-GRU hybrid model outperforms other models, with a determination coefficient (R2) of 0.833-0.840, a root mean square error (RMSE) of 16.57-17.60, and a mean absolute percentage error (MAPE) of 7.85%-8.57%, which is fully capable of meeting accurate and efficient predictions.

An accurate and reliable traffic flow prediction is of great significance, especially the long-term traffic flow prediction e.g., 24 hours, which can help the traffic decision-makers formulate the future traffic management strategy. However, the long-term traffic flow prediction imposes great challenges for decision-makers due to the nonlinear and chaotic feature of traffic flow. Therefore, in this paper, we proposed a hybrid deep learning model based on wavelet decomposition, convolutional neural network-long and short-term memory neural network (CNN-LSTM), called W-CNN-LSTM, to prediction next-day traffic flow. The wavelet decomposition technology is used to decompose the original traffic flow data into high-frequency data and low-frequency data for the improvement of predictive accuracy. The decomposed sequences are fed into a CNN-LSTM deep learning model, where the long-term temporal features of traffic flow can be well captured and learned. The numerical experiment is carried out against five benchmarks based on England traffic flow dataset; the results show that the proposed hybrid approach can achieve superior forecasting skill over the benchmarks.

Traffic flow prediction is essential for enhancing urban mobility and facilitating effective transportation systems. The rapid increase in traffic data, along with the inherently dynamic characteristics of urban traffic, poses considerable challenges for traditional Machine Learning (ML) models, which often find it difficult to efficiently handle large-scale datasets. Although Deep Learning (DL) models demonstrate potential, their significant computational requirements and susceptibility to catastrophic forgetting limit their effectiveness in dynamic and real-time contexts, including traffic emergencies or evolving road networks. To address these challenges, this research presents an innovative framework known as the Continual Learning-based Spatial–Temporal Graph Convolutional Recurrent Neural Network (STGNN-CL) for persistent and accurate long-term traffic flow prediction. By utilizing techniques such as Elastic Weight Consolidation (EWC), Memory Aware Synapses (MAS), and Synaptic Intelligence (SI), the proposed model effectively addresses the issue of catastrophic forgetting while simultaneously enhancing its capacity to incrementally assimilate new traffic data streams. An advanced traffic pattern fusion strategy is introduced, utilizing the Kullback–Leibler Divergence (KLD) metric to measure traffic divergence across different scenarios. This approach improves the efficiency of the Continual Learning (CL) process by enabling the model to adapt to new traffic patterns more effectively over time. Extensive experiments conducted on the PeMSD3, PeMSD4, PeMSD7, and PeMSD8 datasets reveal the superiority of the proposed models, STGCN-EWC, STGCN-MAS, and STGCN-SI models achieve significant reductions in error rates compared to baseline methodologies. These results highlight the potential of continual learning in developing efficient, scalable, and adaptive traffic flow prediction systems, paving the way for advancements in transportation management and autonomous driving technologies.

Accurate traffic flow prediction plays a crucial role in designing Ad hoc vehicular mobile networks in modern Internet of things (IoT) based intelligent systems. Several deep learning techniques have been deployed to predict traffic conditions to make vehicular communication more reliable. However, not all these approaches deal with complex road networks and spatial temporal dependencies of traffic data. In this paper, we analyze this problem using long short-term memory (LSTM), gated recurrent unit (GRU) and hybrid CNN-LSTM models. We trained our models using actual traffic flow data provided by the California Department of Transportation (Caltrans) over a 6 month duration and showed that our deep learning models outperform the traditional linear regression method. Moreover, an architectural study of deep learning models is carried out for the traffic flow prediction problem. The performance of these models is evaluated using MSE and MAE metrics. It is observed that the GRU model is the best to handle the complex vehicular traffic mechanisms. Also, that a complex hybrid model like CNN-LSTM does not always outperform the much simpler architectures such as LSTM and GRU.

<p>Accurate traffic flow prediction plays a crucial role in designing Ad hoc vehicular mobile networks in modern Internet of things (IoT) based intelligent systems. Several deep learning techniques have been deployed to predict traffic conditions to make vehicular communication more reliable. However, not all these approaches deal with complex road networks and spatial temporal dependencies of traffic data. In this paper, we analyze this problem using long short-term memory (LSTM), gated recurrent unit (GRU) and hybrid CNN-LSTM models. We trained our models using actual traffic flow data provided by the California Department of Transportation (Caltrans) over a 6 month duration and showed that our deep learning models outperform the traditional linear regression method. Moreover, an architectural study of deep learning models is carried out for the traffic flow prediction problem. The performance of these models is evaluated using MSE and MAE metrics. It is observed that the GRU model is the best to handle the complex vehicular traffic mechanisms. Also, that a complex hybrid model like CNN-LSTM does not always outperform the much simpler architectures such as LSTM and GRU. </p>

<p>Accurate traffic flow prediction plays a crucial role in designing Ad hoc vehicular mobile networks in modern Internet of things (IoT) based intelligent systems. Several deep learning techniques have been deployed to predict traffic conditions to make vehicular communication more reliable. However, not all these approaches deal with complex road networks and spatial temporal dependencies of traffic data. In this paper, we analyze this problem using long short-term memory (LSTM), gated recurrent unit (GRU) and hybrid CNN-LSTM models. We trained our models using actual traffic flow data provided by the California Department of Transportation (Caltrans) over a 6 month duration and showed that our deep learning models outperform the traditional linear regression method. Moreover, an architectural study of deep learning models is carried out for the traffic flow prediction problem. The performance of these models is evaluated using MSE and MAE metrics. It is observed that the GRU model is the best to handle the complex vehicular traffic mechanisms. Also, that a complex hybrid model like CNN-LSTM does not always outperform the much simpler architectures such as LSTM and GRU. </p>

Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning