Car Data Research Articles

Basic characteristics of floating car data from the perspective of traffic loss during the COVID-19 pandemic

Data from floating vehicles is a modern technology and can be another source of data. There is a free data source available in the Czech Republic, which is relatively new. The addressed source of data from floating vehicles covers the whole Czech Republic, which is a promising source for future use e.g. in transport planning in logistics, estimation of travel times and other related issues. For this reason, it is appropriate to examine the qualitative parameters of the data to see if they characterize the traffic stream. The present paper deals with the size of the processed data. Furthermore, the paper compares the data quality and coverage. January data for four subsequent years was used. The period of the COVID19 pandemic, when traffic declined, was included. Finally, data from selected highways are compared and the period covered is evaluated.

Floating Car Data–Based Short-Term Travel Time Forecasting with Deep Recurrent Neural Networks Incorporating Weather Data

The prediction of future traffic conditions represents a main building block for traffic management. With the advent of multiple traffic and environmental sensors, diverse data for predictions are available and models may incorporate not only traffic data but also additional aspects such as local weather conditions. A review of the state-of-the art methods in short-term traffic forecasting presented in this paper reveals that machine learning (ML) algorithms from the field of deep learning are occasionally used for forecasts based on historical traffic data, but not for traffic predictions including exogenous factors. Weather conditions represent an exogenous factor, which, for example, may affect travel times. This paper investigates how short-term travel time predictions may be improved by applying deep recurrent neural networks that incorporate weather data. Therefore, two hypotheses are formulated. Hypothesis 1 tests the prediction quality of the recurrent neural network (RNN) models, long short-term memory (LSTM), and gated recurrent unit (GRU) compared to the autoregressive moving average (ARMA) prediction method. The respective results indicate that the RNN models using historical traffic data and weather data show significant improvement compared to the ARMA model using only historical traffic data. Hypothesis 2 tests the prediction quality of LSTM and GRU compared to ML-based forecast models already in place in the field of traffic predictions, namely k-nearest neighbor (kNN), support vector regression (SVR), and neural networks (NN). In this context, the LSTM and GRU models using historical traffic data and weather data show significant improvement compared to the models kNN, SVR, and NN that also consider weather data. Despite the results presented in this work, there is still further potential for improvement. Thus, further research focusing on hyperparameter tuning of the RNN algorithms and the optimized selection of (additional) input variables with significant influence on travel times can contribute to further improvements of the forecast quality.

Exploring Crowd Travel Demands Based on the Characteristics of Spatiotemporal Interaction between Urban Functional Zones

As a hot research topic in urban geography, spatiotemporal interaction analysis has been used to detect the hotspot mobility patterns of crowds and urban structures based on the origin-destination (OD) flow data, which provide useful information for urban planning and traffic management applications. However, existing methods mainly focus on the detection of explicit spatial interaction patterns (such as spatial flow clusters) in OD flow data, with less attention to the discovery of underlying crowd travel demands. Therefore, this paper proposes a framework to discover the crowd travel demands by associating the dynamic spatiotemporal interaction patterns and the contextual semantic features of the geographical environment. With urban functional zones (UFZs) as the basic units of human mobility in urban spaces, this paper gives a case study in Wuhan, China, to detect and interpret the human mobility patterns based on the characteristics of spatiotemporal interaction between UFZs. Firstly, we build the spatiotemporal interaction matrix based on the OD flows of different UFZs and analyze the characteristics of the interaction matrix. Then, hotspot poles, defined as the local areas where people gather significantly, are extracted using the Gi-statistic-based spatial hotspot detection algorithm. Next, we develop a frequent interaction pattern mining method to detect the frequent interaction patterns of the hotspot poles. Finally, based on the detected frequent interaction patterns, we discover the travel demands of crowds with semantic features of corresponding urban functional zones. The characteristics of crowd travel distance and travel time are further discussed. Experiments with floating car data, road networks, and POIs in Wuhan were conducted, and results show that the underlying travel demands can be better discovered and interpreted by the proposed framework and methods in this paper. This study helps to understand the characteristics of human movement and can provide support for applications such as urban planning and facility optimization.

Commercial floating car data application in Sub-Saharan African transport planning contexts: A critical review and research agenda

Floating car data (FCD) are a source of traffic information reported by GPS-enabled probes from within the traffic stream. FCD define speed, travel time and movement patterns, all key inputs for transport planning. FCD are readily available over the entire road network without roadside sensors and communications infrastructure, making this a particularly relevant traffic data source in low- and middle-income countries (LMICs) where resource limitations restrict the expansive distribution of traffic sensors. This review article aims to investigate the applicable use-cases of FCD in LMICs, while simultaneously sensitising transport practitioners to the potential data biases that may be present in FCD. Particularly, this paper considers whether the context of Sub-Saharan African countries allows for the application of FCD similarly to high-income country FCD use-cases, critically examining insights from literature. Sub-Saharan African countries typically differ from high-income nations with respect to urban form, population distribution (and segregation), modal choice, driver population, and technology penetration. To date, there has been no literature that concatenates the current practice of FCD use-cases in Sub-Saharan Africa, nor defines the fundamental differences between transport and land use planning in high- and low-income countries with the view to determine if these dissimilarities impact FCD collection and use. Literature revealed novel research involving the application of FCD to investigate informal public transport systems that are specific to Sub-Saharan Africa, while also determining that accuracy and potential biases of FCD are not widely understood in Sub-Saharan Africa. Findings show that biases are likely to occur in FCD in Sub-Saharan Africa because of the representation and behaviours of the sample reporting FCD, as well as the urban form of Sub-Saharan African cities. The paper concludes by developing a research agenda that will assist to further the knowledge of FCD sample bias and the applicable use-cases of FCD in Sub-Saharan Africa.

Aspect-based Sentiment Analysis on Car Reviews Using SpaCy Dependency Parsing and VADER

All businesses, including car manufacturers, need to understand what aspects of their products are perceived as positive and negative based on user reviews so that they can make improvements for the negative aspects and maintain the already positive aspects of their products. One of the available tools for this task is Sentiment Analysis. The traditional document-level and sentence-level sentiment analysis will only classify each document / sentence into a class. This approach is incapable of finding the more fine-grained sentiment for a specific aspect of interest, for example, comfort, price, engine, paint, etc. Therefore, in this case, Aspect-based Sentiment Analysis is used. A total of 22.702 rows of car review data are scraped from the Edmunds website (www.edmunds.com) for a specific car manufacturer. Dependency Parsing and noun phrase extraction were carried out using the SpaCy module in Python, and VADER sentiment analysis was used to determine the polarity of the sentiment for each noun phrase. Results showed that the vast majority of the sentiments are on the positive aspects: comfortable to drive, good fuel economy / mileage, reliability, spaciousness, value for money, helpful rear camera, quiet ride, good acceleration, well-designed, good sound system, and solid build. The results for the negative aspects have some similar aspects with those in the positive class but has a very low frequency. This finding means that the vast majority of the users are satisfied with multiple aspects of the produced cars. The limitation of this research and future research direction are discussed.

Understanding Private Car Aggregation Effect via Spatio-Temporal Analysis of Trajectory Data.

Understanding the private car aggregation effect is conducive to a broad range of applications, from intelligent transportation management to urban planning. However, this work is challenging, especially on weekends, due to the inefficient representations of spatiotemporal features for such aggregation effect and the considerable randomness of private car mobility on weekends. In this article, we propose a deep learning framework for a spatiotemporal attention network (STANet) with a neural algorithm logic unit (NALU), the so-called STANet-NALU, to understand the dynamic aggregation effect of private cars on weekends. Specifically: 1) we design an improved kernel density estimator (KDE) by defining a log-cosh loss function to calculate the spatial distribution of the aggregation effect with guaranteed robustness and 2) we utilize the stay time of private cars as a temporal feature to represent the nonlinear temporal correlation of the aggregation effect. Next, we propose a spatiotemporal attention module that separately captures the dynamic spatial correlation and nonlinear temporal correlation of the private car aggregation effect, and then we design a gate control unit to fuse spatiotemporal features adaptively. Further, we establish the STANet-NALU structure, which provides the model with numerical extrapolation ability to generate promising prediction results of the private car aggregation effect on weekends. We conduct extensive experiments based on real-world private car trajectories data. The results reveal that the proposed STANet-NALU outperforms the well-known existing methods in terms of various metrics, including the mean absolute error (MAE), root mean square error (RMSE), Kullback-Leibler divergence (KL), and R2.

Traffic congestion patterns in the urban road network: (Dammam metropolitan area)

Traffic congestion is a significant problem affecting the sustainable development of urban traffic. It is important to analyze the congestion and forecast future traffic models to prevent traffic congestion. This study is conducted with the main aim to determine the most congested area of the road network and determine how they are related to the demand of the drivers. This study uses the Floating Car Data method to find the traffic congestion and the degree to which observed congestion clusters are a meaningful representation of congestion patterns within a more extensive urban road network. Statistical calculations have been carried out to determine the correlation between clusters based on which conclusions are drawn. Findings have shown that this approach can effectively identify the traffic congestion patterns in the urban road network. The analyses of the traffic congestion behaviour have shown that congestion is more severe and widespread in evening rush hours than morning. Overall, the results can be used to develop a framework to describe potential traffic issues and a system for predicting congestion.

Road Car Accident Prediction Using a Machine-Learning-Enabled Data Analysis

Traffic accidents have become severe risks as they are one of the causes of enormous deaths worldwide. Reducing the number of incidents is critical to saving lives and achieving sustainable cities and communities. Machine learning and data analysis techniques interpret the reasons for car accidents and propose solutions to minimize them. However, this needs to take the benefits of big data solutions as the size and velocity of traffic accident data are increasingly large and rapid. This paper explores road car accident data patterns and proposes a predictive model by investigating meaningful data features, such as accident severity, the number of casualties, and the number of vehicles. Therefore, a pre-processing model is designed to convert raw data using missing and meaningless feature removal, data attribute generalization, and outlier removal using interquartile. Four classification methods, including decision trees, random forest, multinomial logistic regression, and naïve Bayes, are used and evaluated to study the performance of road accident prediction. The results address acceptable levels of accuracy for car accident prediction except for naïve Bayes. The findings are discussed through a data-driven approach to understand the factors influencing road car accidents and highlight the key ones to propose accident prevention solutions. Finally, some strategies are provided to achieve healthy and community-friendly cities.

Machine-learning-based head impact subtyping based on the spectral densities of the measurable head kinematics

BackgroundTraumatic brain injury can be caused by head impacts, but many brain injury risk estimation models are not equally accurate across the variety of impacts that patients may undergo, and the characteristics of different types of impacts are not well studied. We investigated the spectral characteristics of different head impact types with kinematics classification. MethodsData were analyzed from 3262 head impacts from lab reconstruction, American football, mixed martial arts, and publicly available car crash data. A random forest classifier with spectral densities of linear acceleration and angular velocity was built to classify head impact types (e.g., football, car crash, mixed martial arts). To test the classifier robustness, another 271 lab-reconstructed impacts were obtained from 5 other instrumented mouthguards. Finally, with the classifier, type-specific, nearest-neighbor regression models were built for brain strain. ResultsThe classifier reached a median accuracy of 96% over 1000 random partitions of training and test sets. The most important features in the classification included both low- and high-frequency features, both linear acceleration features and angular velocity features. Different head impact types had different distributions of spectral densities in low- and high-frequency ranges (e.g., the spectral densities of mixed martial arts impacts were higher in the high-frequency range than in the low-frequency range). The type-specific regression showed a generally higher R2 value than baseline models without classification. ConclusionThe machine-learning-based classifier enables a better understanding of the impact kinematics spectral density in different sports, and it can be applied to evaluate the quality of impact-simulation systems and on-field data augmentation.

Blending of Floating Car Data and Point-Based Sensor Data to Deduce Operating Speeds under Different Traffic Flow Conditions

Nowadays, smart mobility can rely on innovative tools for the knowledge of road system conditions, like operating speed data extracted from the so-called Floating Car Data (FCD). Probe vehicles in the traffic flow send to operation centres a large amount of travel information, collected through GPS detection systems, especially with regard to geolocation, date and time, direction and speed. As the sample deriving from these vehicles represents a tiny portion of the entire vehicular fleet, in this paper an analysis and a comparison with data obtained by point-based traffic sensors is proposed. Therefore, the study analyses data collected by inductive loop detectors and microwave radar sensors, that provide information on the entire traffic flow in the time domain, in particular with the aim to identify free flow speed time bands. Afterwards, by means of the fusion between the results obtained from the data coming from these point-based control units and the ones coming from the probe vehicles, a comparison of the operating speeds in the two conditions of constrained and unconstrained traffic flow is performed.

City-scale holographic traffic flow data based on vehicular trajectory resampling

Despite abundant accessible traffic data, researches on traffic flow estimation and optimization still face the dilemma of detailedness and integrity in the measurement. A dataset of city-scale vehicular continuous trajectories featuring the finest resolution and integrity, as known as the holographic traffic data, would be a breakthrough, for it could reproduce every detail of the traffic flow evolution and reveal the personal mobility pattern within the city. Due to the high coverage of Automatic Vehicle Identification (AVI) devices in Xuancheng city, we constructed one-month continuous trajectories of daily 80,000 vehicles in the city with accurate intersection passing time and no travel path estimation bias. With such holographic traffic data, it is possible to reproduce every detail of the traffic flow evolution. We presented a set of traffic flow data based on the holographic trajectories resampling, covering the whole city, including stationary average speed and flow data of 5-minute intervals and dynamic floating car data (FCD).

A bi-Level programming method for SPaT estimation at fixed-time controlled intersections using license plate recognition data

Signal phase and timing (SPaT) information is a necessary input for traffic performance evaluation. However, current SPaT estimation studies mainly focus on estimation of cycle length or green time of a certain movement, and are realized mostly by floating car data whose data quality significantly affects the estimation accuracy. As license plate recognition (LPR) systems are becoming a widely implemented and reliable data source in China, in this study, a SPaT estimation method is proposed using the LPR data for fixed-time controlled intersections. The SPaT estimation problem is formulated as a bi-level programming model to find the optimal match between the phase boundaries and the LPR passing time series in the study period. Evaluation is done with an empirical case and compared with an existing method, results show that the estimation accuracies of the phase duration can reach 90.0%, outperforming the existing method and demonstrating great potential for practical application.

Deep learning in insurance: Accuracy and model interpretability using TabNet

Generalized Linear Models (GLMs) and XGBoost are widely used in insurance risk pricing and claims prediction, with GLMs dominant in the insurance industry. The increasing prevalence of connected car data usage in insurance requires highly accurate and interpretable models. Deep learning (DL) models have outperformed traditional Machine Learning (ML) models in multiple domains; despite this, they are underutilized in insurance risk pricing. This study introduces an alternative DL architecture, TabNet, suitable for insurance telematics datasets and claim prediction. This approach compares the TabNet DL model against XGBoost and Logistic Regression on the task of claim prediction on a synthetic telematics dataset. TabNet outperformed these models, providing highly interpretable results and capturing the sparsity of the claims data with high accuracy. However, TabNet requires considerable running time and effort in hyperparameter tuning to achieve these results. Despite these limitations, TabNet provides better pricing models for interpretable models in insurance when compared to XGBoost and Logistic Regression models.

Explore urban interactions based on floating car data – a case study of Chengdu, China

ABSTRACT Transport data are important for understanding human mobility and urban interactions within a city. As China’s transportation infrastructure continues to grow, more research is needed to analyse the spatial patterns of travel flows and to understand how these patterns change over time. With the development of online car-hailing and ride sharing services, floating car data have become a new resource to facilitate the analysis of human mobility patterns and the interactions of urban mobility within a city. The detection of urban communities based on urban networks is a helpful way to represent urban interactions. However, understanding community changes using online car-hailing data remains an underexplored topic. To this end, this study applies a community detection method to explore community changes over time based on the newly available floating car data (DiDi Chuxing (‘DiDi’)) in Chengdu, China. We applied undirected graphs to examine the spatial distribution of DiDi usage and the spatial patterns of travel distance. In addition, we explored the spatial-temporal variations of the communities at the taxi zone level using Blondel’s iterative algorithm, a modularity optimization approach. Results suggest that: 1) taxi zones on the south and west sides of Chengdu have more average daily trips compared to those in other areas; 2) residential taxi zones in the northeast area have a long median travel distance, indicating people living in those areas travel longer distances; and 3) the detected community structures change at different times. These findings provide valuable information for urban planning and location-based services in Chengdu.

Research on Usage Distribution of Shared Cars Based on Visual Analysis

With the help of information technology, sharing economy came into being, developed and improved. In order to get the distribution of shared car use in Tel Aviv from the shared car location data set, this paper visually describes all the parking spots in the data set, and then analyzes the distribution of shared car use in Tel Aviv from two dimensions of time and space, and concludes that there are time-sharing differences and regional differences in shared car use in this city. The above research in this paper can provide reference for the service design of shared car parking space distribution, dispatcher distribution and car deployment time.

Comparison of methods for winter road friction estimation using systems implemented for floating car data

Comparison of methods for winter road friction estimation using systems implemented for floating car data

Comparison of methods for winter road friction estimation using systems implemented for floating car data

Comparison of methods for winter road friction estimation using systems implemented for floating car data

Dimensionality reduction using elastic measures

With the recent surge in big data analytics for hyperdimensional data, there is a renewed interest in dimensionality reduction techniques. In order for these methods to improve performance gains and understanding of the underlying data, a proper metric needs to be identified. This step is often overlooked, and metrics are typically chosen without consideration of the underlying geometry of the data. In this paper, we present a method for incorporating elastic metrics into the t‐distributed stochastic neighbour embedding (t‐SNE) and Uniform Manifold Approximation and Projection (UMAP). We apply our method to functional data, which is uniquely characterized by rotations, parameterization and scale. If these properties are ignored, they can lead to incorrect analysis and poor classification performance. Through our method, we demonstrate improved performance on shape identification tasks for three benchmark data sets (MPEG‐7, Car data set and Plane data set of Thankoor), where we achieve 0.77, 0.95 and 1.00 F1 score, respectively.

Intelligent Sound-Based Early Fault Detection System for Vehicles

An intelligent sound-based early fault detection system has been proposed for vehicles using machine learning. The system is designed to detect faults in vehicles at an early stage by analyzing the sound emitted by the car. Early detection and correction of defects can improve the efficiency and life of the engine and other mechanical parts. The system uses a microphone to capture the sound emitted by the vehicle and a machine-learning algorithm to analyze the sound and detect faults. A possible fault is determined in the vehicle based on this processed sound. Binary classification is done at the first stage to differentiate between faulty and healthy cars. We collected noisy and normal sound samples of the car engine under normal and different abnormal conditions from multiple workshops and verified the data from experts. We used the time domain, frequency domain, and time-frequency domain features to detect the normal and abnormal conditions of the vehicle correctly. We used abnormal car data to classify it into fifteen other classical vehicle problems. We experimented with various signal processing techniques and presented the comparison results. In the detection and further problem classification, random forest showed the highest results of 97% and 92% with time-frequency features.

Road Infrastructure Safety Management: Proactive Safety Tools to Evaluate Potential Conditions of Risk

The identification of highly critical sections in a road network is possible by examining the network operation, with the goal of determining the risk factors and observe the critical issues, in order to better plan possible improvements.Therefore, this study proposes a method to evaluate the coherence of existing road layouts, through the analysis of the geometric characteristics, theoretical speeds and drivers operating speeds, under different environmental and flow conditions.The analysis focuses on the road network managed by ANAS SpA in the Veneto Region, for which the reconstruction of the road axes geometry, the curvature graph and the theoretical design speed profile have been obtained, according to the indications of the Italian Ministerial Decree 05/11/2001. The theoretical design speed profile has then been compared with the information relating to the road users’ mobility, in terms of the 85th percentile speeds, obtained from the extraction and analysis of the Floating Car Data (FCD). The data were processed by reconstructing the continuous profile of operating speeds with a specific regression function known as “smoothing cubic spline”. The comparison with the theoretical design speeds allows to observe whether the users assume a behavior close to or distant from what is expected, based on the technical and geometrical characteristics of the road layout.The proposed methodology can contribute to the implementation of a proactive road safety check, aimed at recognizing and assessing the potential risk conditions for road traffic, with particular attention to the point of view of the road user.