Network-Scale Traffic Modeling and Forecasting with Graphical Lasso and Neural Networks

Identifying the latent relationships between factors associated with traffic crashes through graphical models

Traffic safety field has been oriented toward finding the relationships between crash outcomes and predictor variables to understand crash phenomena and/or predict future crashes. In the literature, the main framework established for this purpose is based on constructing a modelling equation in which crash outcome (e.g., frequencies) is examined in relation to explanatory variables chosen based on the problem at hand. Despite the importance and success of this approach, there are two issues that are generally not discussed: 1) the latent relationships between factors associated with crashes are oftentimes not the focus of analysis or not observed; and 2) there are not many tools to make informed decisions on which variables might have an impact on the crash outcome and should be included in a safety model, particularly when observations are limited. To address these issues, this paper proposes the use of graphical models, namely a Markov random field (MRF) modelling, Bayesian network modelling, and a graphical XGBoost approach, to disclose relationship topologies of explanatory variables leading to fatal and incapacitating injury pedestrian crashes. The application of graph learning models in traffic safety has a high potential because they are not only useful to understand the mechanism behind the crash occurrence but also can assist in devising accurate and reliable prevention measures by identifying the true variable structure and essential factors jointly acting towards crash occurrence, similar to a pathological examination.

Convolutional Long-Short Term Memory Network with Multi-Head Attention Mechanism for Traffic Flow Prediction

Accurate predictive modeling of traffic flow is critically important as it allows transportation users to make wise decisions to circumvent traffic congestion regions. The advanced development of sensing technology makes big data more affordable and accessible, meaning that data-driven methods have been increasingly adopted for traffic flow prediction. Although numerous data-driven methods have been introduced for traffic flow predictions, existing data-driven methods cannot consider the correlation of the extracted high-dimensional features and cannot use the most relevant part of the traffic flow data to make predictions. To address these issues, this work proposes a decoder convolutional LSTM network, where the convolutional operation is used to consider the correlation of the high-dimensional features, and the LSTM network is used to consider the temporal correlation of traffic flow data. Moreover, the multi-head attention mechanism is introduced to use the most relevant portion of the traffic data to make predictions so that the prediction performance can be improved. A traffic flow dataset collected from the Caltrans Performance Measurement System (PeMS) database is used to demonstrate the effectiveness of the proposed method.

Traffic Missing Data Imputation: A Selective Overview of Temporal Theories and Algorithms

A great challenge for intelligent transportation systems (ITS) is missing traffic data. Traffic data are input from various transportation applications. In the past few decades, several methods for traffic temporal data imputation have been proposed. A key issue is that temporal information collected by neighbor detectors can make traffic missing data imputation more accurate. This review analyzes traffic temporal data imputation methods. Research methods, missing patterns, assumptions, imputation styles, application conditions, limitations, and public datasets are reviewed. Then, five representative methods are tested under different missing patterns and missing ratios. California performance measurement system (PeMS) data including traffic volume and speed are selected to conduct the test. Probabilistic principal component analysis performs the best under the most conditions.

Forecasting Subway Passenger Flow for Station-Level Service Supply

Demand forecasting is one of the managers' concerns in service supply chain management. With accurate passenger flow forecasting, the station-level service suppliers can make better service plans accordingly. However, the existing forecasting model cannot identify the different future passenger flow at different types of stations. As a result, the service suppliers cannot make service plans according to the demands of different stations. In this article, we propose a deep learning architecture called DeepSPF (Deep Learning for Subway Passenger Forecasting) to predict subway passenger flow considering the different functional types of stations. We also propose the sliding long short-term memory (LSTM) neural networks as an important component of our model, combining LSTM and one-dimensional convolution. In the experiments of the Beijing subway, DeepSPF outperforms the baseline models in three-time granularities (10, 15, and 30 minutes). Moreover, a comparison between variants of DeepSPF indicates that, with the information of stations' functional types, DeepSPF has strong robustness when an abnormal situation happens.

Urban Safety: An Image-Processing and Deep-Learning-Based Intelligent Traffic Management and Control System

With the rapid growth and development of cities, Intelligent Traffic Management and Control (ITMC) is becoming a fundamental component to address the challenges of modern urban traffic management, where a wide range of daily problems need to be addressed in a prompt and expedited manner. Issues such as unpredictable traffic dynamics, resource constraints, and abnormal events pose difficulties to city managers. ITMC aims to increase the efficiency of traffic management by minimizing the odds of traffic problems, by providing real-time traffic state forecasts to better schedule the intersection signal controls. Reliable implementations of ITMC improve the safety of inhabitants and the quality of life, leading to economic growth. In recent years, researchers have proposed different solutions to address specific problems concerning traffic management, ranging from image-processing and deep-learning techniques to forecasting the traffic state and deriving policies to control intersection signals. This review article studies the primary public datasets helpful in developing models to address the identified problems, complemented with a deep analysis of the works related to traffic state forecast and intersection-signal-control models. Our analysis found that deep-learning-based approaches for short-term traffic state forecast and multi-intersection signal control showed reasonable results, but lacked robustness for unusual scenarios, particularly during oversaturated situations, which can be resolved by explicitly addressing these cases, potentially leading to significant improvements of the systems overall. However, there is arguably a long path until these models can be used safely and effectively in real-world scenarios.

Principles and open questions in functional brain network reconstruction

Graph theory is now becoming a standard tool in system-level neuroscience. However, endowing observed brain anatomy and dynamics with a complex network representation involves often covert theoretical assumptions and methodological choices which affect the way networks are reconstructed from experimental data, and ultimately the resulting network properties and their interpretation. Here, we review some fundamental conceptual underpinnings and technical issues associated with brain network reconstruction, and discuss how their mutual influence concurs in clarifying the organization of brain function.

Multi-Step Traffic Speed Prediction Based on Ensemble Learning on an Urban Road Network

Short-term traffic speed prediction plays an important role in the field of Intelligent Transportation Systems (ITS). Usually, traffic speed forecasting can be divided into single-step-ahead and multi-step-ahead. Compared with the single-step method, multi-step prediction can provide more future traffic condition to road traffic participants for guidance decision-making. This paper proposes a multi-step traffic speed forecasting by using ensemble learning model with traffic speed detrending algorithm. Firstly, the correlation analysis is conducted to determine the representative features by considering the spatial and temporal characteristics of traffic speed. Then, the traffic speed time series is split into a trend set and a residual set via a detrending algorithm. Thirdly, a multi-step residual prediction with direct strategy is formulated by the ensemble learning model of stacking integrating support vector machine (SVM), CATBOOST, and K-nearest neighbor (KNN). Finally, the forecasting traffic speed can be reached by adding predicted residual part to the trend one. In tests that used field data from Zhongshan, China, the experimental results indicate that the proposed model outperforms the benchmark ones like SVM, CATBOOST, KNN, and BAGGING.

Data-driven analysis and forecasting of highway traffic dynamics

The unpredictable elements involved in a vehicular traffic system, like human interaction and weather, lead to a very complicated, high-dimensional, nonlinear dynamical system. Therefore, it is difficult to develop a mathematical or artificial intelligence model that describes the time evolution of traffic systems. All the while, the ever-increasing demands on transportation systems has left traffic agencies in dire need of a robust method for analyzing and forecasting traffic. Here we demonstrate how the Koopman mode decomposition can offer a model-free, data-driven approach for analyzing and forecasting traffic dynamics. By obtaining a decomposition of data sets collected by the Federal Highway Administration and the California Department of Transportation, we are able to reconstruct observed data, distinguish any growing or decaying patterns, and obtain a hierarchy of previously identified and never before identified spatiotemporal patterns. Furthermore, it is demonstrated how this methodology can be utilized to forecast highway network conditions.

The demands on transportation systems continue to grow while the methods for analyzing and forecasting traffic conditions remain limited. Here the authors show a parameter-independent approach for an accurate description, identification and forecasting of spatio-temporal traffic patterns directly from data.

Self-Organizing Traffic Flow Prediction with an Optimized Deep Belief Network for Internet of Vehicles

To assist in the broadcasting of time-critical traffic information in an Internet of Vehicles (IoV) and vehicular sensor networks (VSN), fast network connectivity is needed. Accurate traffic information prediction can improve traffic congestion and operation efficiency, which helps to reduce commute times, noise and carbon emissions. In this study, we present a novel approach for predicting the traffic flow volume by using traffic data in self-organizing vehicular networks. The proposed method is based on using a probabilistic generative neural network techniques called deep belief network (DBN) that includes multiple layers of restricted Boltzmann machine (RBM) auto-encoders. Time series data generated from the roadside units (RSUs) for five highway links are used by a three layer DBN to extract and learn key input features for constructing a model to predict traffic flow. Back-propagation is utilized as a general learning algorithm for fine-tuning the weight parameters among the visible and hidden layers of RBMs. During the training process the firefly algorithm (FFA) is applied for optimizing the DBN topology and learning rate parameter. Monte Carlo simulations are used to assess the accuracy of the prediction model. The results show that the proposed model achieves superior performance accuracy for predicting traffic flow in comparison with other approaches applied in the literature. The proposed approach can help to solve the problem of traffic congestion, and provide guidance and advice for road users and traffic regulators.

TIMSS 2011 Student and Teacher Predictors for Mathematics Achievement Explored and Identified via Elastic Net

A substantial body of research has been conducted on variables relating to students' mathematics achievement with TIMSS. However, most studies have employed conventional statistical methods, and have focused on selected few indicators instead of utilizing hundreds of variables TIMSS provides. This study aimed to find a prediction model for students' mathematics achievement using as many TIMSS student and teacher variables as possible. Elastic net, the selected machine learning technique in this study, takes advantage of both LASSO and ridge in terms of variable selection and multicollinearity, respectively. A logistic regression model was also employed to predict TIMSS 2011 Korean 4th graders' mathematics achievement. Ten-fold cross-validation with mean squared error was employed to determine the elastic net regularization parameter. Among 162 TIMSS variables explored, 12 student and 5 teacher variables were selected in the elastic net model, and the prediction accuracy, sensitivity, and specificity were 76.06, 70.23, and 80.34%, respectively. This study showed that the elastic net method can be successfully applied to educational large-scale data by selecting a subset of variables with reasonable prediction accuracy and finding new variables to predict students' mathematics achievement. Newly found variables via machine learning can shed light on the existing theories from a totally different perspective, which in turn propagates creation of a new theory or complement of existing ones. This study also examined the current scale development convention from a machine learning perspective.

Estimation of Discriminative Feature Subset Using Community Modularity

Feature selection (FS) is an important preprocessing step in machine learning and data mining. In this paper, a new feature subset evaluation method is proposed by constructing a sample graph (SG) in different k-features and applying community modularity to select highly informative features as a group. However, these features may not be relevant as an individual. Furthermore, relevant in-dependency rather than irrelevant redundancy among the selected features is effectively measured with the community modularity Q value of the sample graph in the k-features. An efficient FS method called k-features sample graph feature selection is presented. A key property of this approach is that the discriminative cues of a feature subset with the maximum relevant in-dependency among features can be accurately determined. This community modularity-based method is then verified with the theory of k-means cluster. Compared with other state-of-the-art methods, the proposed approach is more effective, as verified by the results of several experiments.

3D Markov Process for Traffic Flow Prediction in Real-Time

Recently, the correct estimation of traffic flow has begun to be considered an essential component in intelligent transportation systems. In this paper, a new statistical method to predict traffic flows using time series analyses and geometric correlations is proposed. The novelty of the proposed method is two-fold: (1) a 3D heat map is designed to describe the traffic conditions between roads, which can effectively represent the correlations between spatially- and temporally-adjacent traffic states; and (2) the relationship between the adjacent roads on the spatiotemporal domain is represented by cliques in MRF and the clique parameters are obtained by example-based learning. In order to assess the validity of the proposed method, it is tested using data from expressway traffic that are provided by the Korean Expressway Corporation, and the performance of the proposed method is compared with existing approaches. The results demonstrate that the proposed method can predict traffic conditions with an accuracy of 85%, and this accuracy can be improved further.