Machine learning (ML) offers a promising avenue for international freight transportation management (IFTM) given its capability to harness the power of data that have become increasingly available to freight transportation researchers and practitioners. This paper conducts a comprehensive investigation of the state-of-the-art in developing ML models for applications to different aspects of IFTM. We start by giving an overview of various fundamental ML methods. Then, how different ML methods have been employed, adapted, and applied to a multitude of subject areas in IFTM are discussed, including demand forecast, operation and asset maintenance, and vehicle trajectory and on-time performance prediction. The potential data sources that may be used to develop ML models are further examined. Subsequently, a synthesis of the exiting work is performed to identify the specific topics addressed in the existing research, ML methods used, the trends of research, and opportunities for further explorations. Four directions for future research are proposed in the end

Machine learning for international freight transportation management: A comprehensive review

There is no definite conclusion about what the main variables that play a fundamental role in road safety are. Therefore, the identification of significant factors in road accidents has been a primary concern of the transportation safety research community for many years. Every accident is influenced by multiple variables that, in a given time interval, concur to cause a crash scenario. Information coming from crash reports is very useful in traffic safety research, and several reported crash variables can be analyzed with modern statistical methods to establish whether a classification or clustering of different crash variables is possible. Hence, this study aims to use stochastic techniques for evaluating the role of some variables in accidents with a clustering analysis. The variables that are considered in this paper are light conditions, weekday, average speed, annual average daily traffic, number of vehicles, and type of accident. For this purpose, a combination of particle swarm optimization (PSO) and the genetic algorithm (GA) with the k-means algorithm was used as the machine-learning technique to cluster and evaluate road safety data. According to a multiscale approach, based on a set of data from two years of crash records collected from rural and urban roads in the province of Cosenza, 154 accident cases were accurately investigated and selected for three categories of accident places, including straight, intersection, and other, in each urban and rural network. PSO had a superior performance, with 0.87% accuracy on urban and rural roads in comparison with GA, although the results of GA had an acceptable degree of accuracy. In addition, the results show that, on urban roads, social cost and type of accident had the most and least influence for all accident places, while, on rural roads, although the social cost was the most notable factor for all accident places, the type of accident had the least effect on the straight sections and curves, and the number of vehicles had the least influence at intersections.

https://www.mdpi.com/2071-1050/12/18/7541/pdf

Feasibility of Stochastic Models for Evaluation of Potential Factors for Safety: A Case Study in Southern Italy

Utilizing machine learning on freight transportation and logistics applications: A review

Traffic flow forecasting (TFF) is critical for constructing intelligent transportation systems and offering real-time traffic applications, and especially accurate flow forecasting based on traffic big data can drive reliable strategies for traffic management and control. To consider the weight of the influence of the spatial correlation among the road segments and capture the nonlinear characteristics of traffic flow, this paper presents a parallel Normal Distribution and Attention Mechanism Weighted Deep Bidirectional Long Short-Term Memory (NAW-DBLSTM) algorithm on Spark. Specifically, we employ the resilient distributed data set (RDD) to preprocess large-scale mobile trajectory data (e.g., taxi GPS trajectory data), and then Kalman Filter (KF) is utilized to smooth the taxi trajectory big data. Next, the parallel NAW-DBLSTM algorithm is put forward on a Spark distributed computing platform to enhance the accuracy and scalability of TFF, combined with the attention mechanism and the normal distribution, and then the time window is used for TFF. Finally, the traffic flow is forecasted successfully on Spark by our NAW-DBLSTM algorithm with the real-world GPS trajectories of taxicabs. The experimental results demonstrate that, compared with LSTM, BiLSTM, DBLSTM, DNN, SVR, KNN, SAEs, BP, CNN, GRU, and ANNs, NAW-DBLSTM can produce better performance with the MAPE value that is 85.1%, 80.1%, 85.8%, 73.1%, 78.2%, 77.9%, 78.8%, 84.6%, 96.4%, 86.2%, and 73.2% lower than that of comparable algorithms, respectively. Particularly, the MAPE value of NAW-DBLSTM is 28.3%, 20.1%, 71.1%, and 79.1% lower than that of LSTM weighted with the normal distribution and the attention mechanism (NAW-LSTM), BiLSTM weighted with the normal distribution and the attention mechanism (NAW-BiLSTM), DBLSTM weighted with the normal distribution (NW-DBLSTM), and NAW-DBLSTM weighted without the time window (NT-NAW-DBLSTM), respectively.

A parallel NAW-DBLSTM algorithm on Spark for traffic flow forecasting

Traffic flow decomposition is an alternative method to explore the composition of traffic flow and improve prediction accuracy. However, most of them suffer from the inability to fully utilize the character of traffic data. This paper presents a novel framework for traffic flow decomposition and modeling named Time Series Decomposition (TSD). The traffic flow is adaptively decomposed into periodic component, residual component and volatile component which are modeled respectively. Empirical Mode Decomposition (EMD) is applied to extract the intrinsic mode functions (IMFs) of traffic flow, the periodic patterns are intuitively presented via Hilbert transform in terms of frequencies. Then the periodic component can be described as a Fourier series based on obtained frequencies. Meanwhile, the residual component is presented by IMF with the lowest frequency. The remaining part is the volatile component modeled by supervised learning. The proposed hybrid model is evaluated on the real-world dataset and compared with classical baseline models. The results demonstrate that TSD can unearth the underlying periodic patterns and provide an explicable composition of the traffic flow. Furthermore, the volatile component ensures the accuracy of single-step prediction while periodic and residual components show promising abilities in improving the multi-step prediction accuracy of short-term traffic flow.

Short-term traffic prediction based on time series decomposition

For many intelligent transportation applications, traffic congestion prediction is quite essential. If traffic congestion on the road ahead can be accurately and promptly predicted, and routes can be planned reasonably based on the prediction results, traffic congestion can be effectively alleviated. Aiming at the spatio-temporal correlation and evolution characteristics of traffic flow data, the Conv–BiLSTM module comprising a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) is proposed, considering the spatio-temporal features. Firstly, the obtained traffic speed data is folded according to spatio-temporal features, and a three-dimensional matrix is constructed as the input of the prediction network module. After the spatial features are extracted by the CNN, the temporal features and alignment features are extracted by the BiLSTM, followed by which the prediction results are obtained as an output. Prediction and evaluation experiments on the traffic data of the highway in Shanghai prove that the traffic congestion state predicted by this method is largely consistent with the actual state. The results demonstrate that the proposed method has a higher prediction accuracy compared with the conventional and state-of-the-art methods and is an efficient method of traffic congestion prediction.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-its.2020.0406

Short-term traffic congestion prediction with Conv–BiLSTM considering spatio-temporal features

When performing microscopic traffic simulations, a premise is to have appropriately calibrated parameter values. This is often computationally expensive as it requires repeatedly running simulation...

Calibrating microscopic traffic simulators using machine learning and particle swarm optimization

The invention relates to an integrated fusion method of an urban and rural passenger line network and a hub station. The method comprises the following steps of evaluating the node level based on the importance degree of a hub station node; building a node set for connecting the urban and rural passenger line network, determining the urban and rural passenger line network, generating the urban and rural passenger line network, and joining the line network and the hub station. According to the method provided by the invention, the defects that the line network transport is not smooth, the transfer is inconvenient and the like are overcome, the generated line network node and a passenger distribution center are better linked, and passengers are favorably attracted to the utmost extent. The method has the advantages of easiness in implementation, high reliability, flexible design process and the like, and is conveniently popularized and applied in the integrated design process of the urban and rural passenger line.

Linjie Gao

Papers

Short-term traffic congestion prediction with Conv–BiLSTM considering spatio-temporal features

Calibrating microscopic traffic simulators using machine learning and particle swarm optimization

Integrated fusion method of urban and rural passenger line network and hub station