Vehicle Data Research Articles

Development and experiment of an intelligent connected cooperative vehicle infrastructure system based on multiple V2I modes and BWM-IGR method

To increase the efficiency and safety of expressway, this paper constructed a new intelligent connected cooperative vehicle infrastructure system and its effectiveness was verifid from both data and practical applications. Firstly, considering the convenience of using intelligent networking systems for public transportation, a new intelligent connected cooperative vehicle infrastructure system architecture was proposed by incorporating mobile communication methods. Then, the new system was illustrated from road side unit (RSU), on board unit (OBU) and data interaction. Additionally, to verify the effectiveness of the system, this paper proposes a two-stage model named Transformer Embedded Clustering- Hierarchical Density-Based Spatial Clustering of Applications with Noise (TEC-HDBSCAN) model to identify outliers in the trajectory data of vehicles collected by the system and obtain the speed sequence of the vehicle. Finally, data from actual testing scenarios was collected and a Best Worst Method-Improved Gray Relational (BWM-IGR) model was built to verify the effectiveness of the system. The results show that the established intelligent networked transportation system can effectively guide vehicles and collect data with high accuracy.

Adaptive Traffic Control Using Cooperative Communication Through Visible Light

The study aims to create a Visible-Light Communication (VLC) system for secure vehicle management at intersections. This involves enabling communication between vehicles and infrastructure (V2V, V2I, and I2V) using headlights, streetlights, and traffic signals. Mobile optical receivers gather data, determine their location, and read transmitted information through joint transmission. An intersection manager coordinates traffic and communicates with vehicles through embedded Driver Agents. The system utilizes a "mesh/cellular" hybrid network configuration and encodes data into light signals emitted by transmitters. Optical sensors and filtering properties enable reception and decoding. The study demonstrates bidirectional communication, employing queue/request/response mechanisms and relative pose concepts for safe vehicle passage. A deep reinforcement learning model controls traffic light cycles, validated via simulation in a Simulation of Urban Mobility simulator. Results show that this adaptive traffic control system effectively collects detailed vehicle data and ensures secure communication within the short-range mesh network.

Prediction and Diagnosis of Electric Vehicle Battery Fault Based on Abnormal Voltage: Using Decision Tree Algorithm Theories and Isolated Forest

Battery voltage is a pivotal parameter for evaluating battery health and safety. The precise prediction of battery voltage and the implementation of anomaly detection are imperative for ensuring the secure and dependable operation of battery systems. Nevertheless, during the actual operation of electric vehicles, battery performance is subject to the influence of the vehicle's operational state and battery characteristic parameters, introducing challenges to safety alerts. In order to address these challenges and achieve precise battery voltage prediction, this paper comprehensively considers the battery characteristics and driving behavior of electric vehicles in both charging and operational states. Mathematical processing, including averaging and variance calculation, is applied to the battery characteristic parameter data and driving behavior data. By integrating historical voltage data and employing a modified gradient boosting decision tree algorithm (GBDT), a fast and accurate online voltage prediction method is proposed. Hyperparameter optimization is employed to minimize prediction voltage errors. The accuracy and timeliness of the predictions are validated through a comprehensive evaluation and comparison of the forecasted voltages. To diagnose anomalies in battery voltage, the paper proposes a fault diagnosis method that combines the Isolation Forest and Boxplot techniques. Finally, utilizing authentic electric vehicle data for validation, the research underscores the capability of the proposed method to achieve accurate voltage predictions six minutes in advance and provide effective fault diagnosis. This investigation carries substantial practical implications for fortifying battery management and optimizing the performance of electric vehicles.

Advanced topographic-geodetic surveys and GNSS methodologies in urban planning

Abstract The relevance of the problem examined is the need for research to ensure the safety and efficiency of construction and operation of utility networks, in light of the rapid development and growth of urban infrastructure. The purpose of this research is to explore and evaluate the application of topographic-geodetic studies in the context of the design and construction of utilities. The methods used include analytical method, classification method, functional method, statistical method, synthesis method. At the preparatory stage of works the schedule of all stages of project implementation was developed, coordinate and height systems accepted in the territory of the settlement, topographic and geodetic materials, general plans, detailed planning plans, and schemes of settlement development were established. Executive surveys, the territory of Aksukent settlement, and other materials and documents identified in the process of preparatory works were collected and analysed. Using an unmanned aerial vehicle (UAV) data of plan-altitude substantiation and aerial photography were obtained, orthophoto map in WGS84 and MSC coordinate system of the Aksukent settlement territory was obtained. To update the data on existing points of the state geodetic network, complexes of geodetic measurements and calculations were performed and parameters (key) of transformation between WGS84 and WCS coordinate systems were obtained. In the course of the field works, deciphering work was performed based on the obtained orthophoto. The inventory of engineering networks was conducted, which included engineering-geodetic surveys of underground and surface engineering networks (sewerage, water supply, gas supply, heating mains), and engineering-geodetic surveys of overhead and underground cable power lines. The results of the survey of the traces of engineering communications on the territory of Aksukent village were agreed with the balance holders of networks JSC “Turkestan Regional Telecommunications Directorate Kazakhtelecom”, JSC “KazTransGas Aimak”, LLP “Sairam Tazalyk”, LLP “Ontustik Zharyk Transit”. The research is of practical significance, as it contributes to the accurate determination of network parameters, identification of potential problem areas and ensuring effective planning and management of engineering projects.

Combining spectral and texture feature of UAV image with plant height to improve LAI estimation of winter wheat at jointing stage.

Leaf area index (LAI) is a critical physiological and biochemical parameter that profoundly affects vegetation growth. Accurately estimating the LAI for winter wheat during jointing stage is particularly important for monitoring wheat growth status and optimizing variable fertilization decisions. Recently, unmanned aerial vehicle (UAV) data and machine/depth learning methods are widely used in crop growth parameter estimation. In traditional methods, vegetation indices (VI) and texture are usually to estimate LAI. Plant Height (PH) unlike them, contains information about the vertical structure of plants, which should be consider. Taking Xixingdian Township, Cangzhou City, Hebei Province, China as the research area in this paper, and four machine learning algorithms, namely, support vector machine(SVM), back propagation neural network (BPNN), random forest (RF), extreme gradient boosting (XGBoost), and two deep learning algorithms, namely, convolutional neural network (CNN) and long short-term memory neural network (LSTM), were applied to estimate LAI of winter wheat at jointing stage by integrating the spectral and texture features as well as the plant height information from UAV multispectral images. Initially, Digital Surface Model (DSM) and Digital Orthophoto Map (DOM) were generated. Subsequently, the PH, VI and texture features were extracted, and the texture indices (TI) was further constructed. The measured LAI on the ground were collected for the same period and calculated its Pearson correlation coefficient with PH, VI and TI to pick the feature variables with high correlation. The VI, TI, PH and fusion were considered as the independent features, and the sample set partitioning based on joint x-y distance (SPXY) method was used to divide the calibration set and validation set of samples. The ability of different inputs and algorithms to estimate winter wheat LAI were evaluated. The results showed that (1) The addition of PH as a feature variable significantly improved the accuracy of the LAI estimation, indicating that wheat plant height played a vital role as a supplementary parameter for LAI inversion modeling based on traditional indices; (2) The combination of texture features, including normalized difference texture indices (NDTI), difference texture indices (DTI), and ratio texture indices (RTI), substantially improved the correlation between texture features and LAI; Furthermore, multi-feature combinations of VI, TI, and PH exhibited superior capability in estimating LAI for winter wheat; (3) Six regression algorithms have achieved high accuracy in estimating LAI, among which the XGBoost algorithm estimated winter wheat LAI with the highest overall accuracy and best results, achieving the highest R2 (R2=0.88), the lowest RMSE (RMSE=0.69), and an RPD greater than 2 (RPD=2.54). This study provided compelling evidence that utilizing XGBoost and integrating spectral, texture, and plant height information extracted from UAV data can accurately monitor LAI during the jointing stage of winter wheat. The research results will provide a new perspective for accurate monitoring of crop parameters through remote sensing.

CAS Landslide Dataset: A Large-Scale and Multisensor Dataset for Deep Learning-Based Landslide Detection

In this work, we present the CAS Landslide Dataset, a large-scale and multisensor dataset for deep learning-based landslide detection, developed by the Artificial Intelligence Group at the Institute of Mountain Hazards and Environment, Chinese Academy of Sciences (CAS). The dataset aims to address the challenges encountered in landslide recognition. With the increase in landslide occurrences due to climate change and earthquakes, there is a growing need for a precise and comprehensive dataset to support fast and efficient landslide recognition. In contrast to existing datasets with dataset size, coverage, sensor type and resolution limitations, the CAS Landslide Dataset comprises 20,865 images, integrating satellite and unmanned aerial vehicle data from nine regions. To ensure reliability and applicability, we establish a robust methodology to evaluate the dataset quality. We propose the use of the Landslide Dataset as a benchmark for the construction of landslide identification models and to facilitate the development of deep learning techniques. Researchers can leverage this dataset to obtain enhanced prediction, monitoring, and analysis capabilities, thereby advancing automated landslide detection.

Impact of battery electric vehicle usage on air quality in three Chinese first-tier cities.

China, the world leader in automobile production and sales, confronts the challenge of transportation emissions, which account for roughly 10% of its total carbon emissions. This study, utilizing real-world vehicle data from three major Chinese cities, assesses the impact of Battery Electric Vehicles (BEVs) on air quality. Our analysis reveals that BEVs, when replacing gasoline vehicles in their operational phase, significantly reduce emissions, with reductions ranging from 8.72 to 85.71kg of CO2 per vehicle monthly. The average monthly reduction rate is 9.47%, though this effect is less pronounced during winter. Advanced BEVs, characterized by higher efficiency and newer technology, exhibit greater emission reduction benefits. While private BEVs generally contribute positively to environmental outcomes, taxi BEVs, due to their intensive usage patterns, show less environmental advantage and may sometimes worsen air quality. Looking ahead, we project substantial emission reductions from the replacement of gasoline vehicles with electric alternatives over the next decade. Policymakers are urged to adopt proactive measures, focusing on promoting medium to large electric vehicles and fostering the use of private and ride-hailing electric vehicles.

Enhancing road safety in internet of vehicles using deep learning approach for real-time accident prediction and prevention

The paper proposes an Internet of Vehicles (IoV)-based Accident Prediction and Prevention System that leverages the Internet of Things (IoT) to tackle the road safety challenges arising from the increased rate and volume of traffic due to population growth. In order to enhance road safety and efficiency, the IoV devices enable real-time data transmission and analysis. The proposed multi-tier framework tracks vehicle and roadside unit (RSU) data, encompassing road traffic conditions and vehicle data. The framework integrates vehicles, road traffic, weather conditions, and external factors. On a cloud-based control server, the proposed Spatio-Temporal Conv-Long Short-Term Memory Autoencoder (STCLA) framework deals with and analyzes the resulting data. This research addresses road safety on the Internet of Vehicles via DL. It proposes a novel framework for real-time accident prevention and prediction, demonstrating its effectiveness and potential impact. In a year-long research in Hubei Province, China, data from two road segments demonstrated a substantial boost in predictive accuracy, achieving an Area Under the Receiver Operating Characteristic Curve (AUROC) score of 0.94.

Ridge Regressive Data Preprocessed Quantum Deep Belief Neural Network for Effective Trajectory Planning in Autonomous Vehicles

Trajectory planning is a new research topic in the field of automated vehicles (AVs). It is the process of identifying a trajectory for the vehicle to traverse its environment without obstacle collision. Trajectories are computed fast in real time as the environment constantly changes with time. To address these problems, the Ridge Regressive Data Preprocessed Quantum Deep Belief Neural Network (RRDPQDBNN) model is developed. The RRDPQDBNN model intends to carry out effective trajectory planning in autonomous vehicles through enhanced accuracy and minimum time complexity. Initially, in the RRDPQDBNN model, vehicle data are extracted and transmitted to the input layer. Secondly, Ridge Regressive Data Preprocessing is performed to eliminate noisy data from collected vehicle data. Finally, quantum data clustering is carried out in the RRDPQDBNN model to identify the severity of the risk without collision during the trajectory. This, in turn, is effective trajectory planning performed in autonomous vehicles. Experimental results are computed in terms of clustering accuracy, clustering time, error rate, precision, and recall. From experimental results, the RRDPQDBNN model increases clustering accuracy by 11%, precision by 13%, and recall by 5%, as well as reduces clustering time by 31% and error rate by 58% compared to existing methods.

Vehicle number recognition by using existing general surveillance cameras

India has a lot of cars because it is the densest-populated country in the world. Therefore, it's important to use a traffic management system to detect vehicles accurately. It detects a vehicle plate image from a camera and extracts the number. It's an embedded system that recognizes license plates in real-time. A real-time embedded system called Vehicle Plate Number Recognition (VNPR) recognizes license plate numbers automatically in this work using VGG16 algorithm. When a vehicle enters the entrance by the gate of the institution or highly restricted areas, the system records and captures video and recognizes the number plate. It will automatically recognize the license plate and search the data of the owner's vehicle and their challan details.

Machine Learning-Based Lane-Changing Behavior Recognition and Information Credibility Discrimination

Intelligent Vehicle–Infrastructure Collaboration Systems (i-VICS) put forward higher requirements for the real-time security of dynamic traffic information interaction. It is difficult to ensure the safety of dynamic traffic information interaction by means of traditional static information security. In this study, a method was proposed through machine learning-based lane-changing (LC) behavior recognition and information credibility discrimination, based on the utilization and exploitation of traffic business characteristics. The method consisted of three stages: LC behavior recognition based on Support Vector Machine (SVM), LC speed prediction based on Recurrent Neural Network (RNN), and credibility discrimination of speed information under LC states. Firstly, the labeling rules of vehicle LC behavior and the input/output of each stage model were determined, and the raw NGSIM data were processed to obtain data sets for LC behavior identification and LC speed prediction. Both the SVM classification and RNN prediction models were trained and tested, respectively. Afterwards, a model of credibility discrimination speed information under an LC state was constructed, and the real vehicle speed data were processed for model verification. The results showed that the overall accuracy of vehicle status recognition by the SVM model was 99.18%, and the precision of the RNN model was on the order of magnitude of cm/s. Considering transverse and longitudinal abnormal velocity, the accuracy credibility discrimination of LC velocity was more than 97% in most experimental groups. The model can effectively identify the abnormal speed data of LC vehicles and provide support for the real-time identification of LC vehicle speed information under i-VICS.

Sentinel-2 image based smallholder crops classification and accuracy assessment by UAV data

Timely and accurate extraction of crop planting units plays a critical role in crop yield estimation, soil management, food supplies, and disaster warnings. However, precisely mapping crop types is challenging in smallholder farming systems due to heterogeneous and mixed pixels, where field sizes are small, and crop types are very diverse. In this paper, the crop type system of Huocheng County in northwest China as an example area, crop classification feature variables are constructed using Sentinel-2 remote sensing images, and combining the ReliefF algorithm, three feature selection classification models are established by 3092 crop type sampling points data. The crop planting units are extracted using pixel-based and object-based classification methods, respectively, and unmanned aerial vehicle (UAV) data assess the accuracy as ground truth. The Sentinel-2 image based smallholder crops classification results indicate that: The effective combination of optimal input feature variables selection and classification models significantly improves crop classification accuracy. This is particularly evident when integrating this approach into pixel-based classification, addressing challenges such as low pixel classification accuracy in regions of this type. The validation results from UAV data also confirm these findings. At validation points 2, 3, and 4, pixel-based classification demonstrates significantly higher accuracy compared to object-based classification, with pixel-based classification accuracy improving by 9.16%, 7.83%, and 31.83%, respectively. Although the UAV validation accuracy does not reach a high level, pixel-based classification remains the optimal choice for smallholder crop classification. This method offers new insights and references for research related to the classification of smallholder crops with complex planting structures.

Securing electric transportation networks: A machine learning-driven cyber threat detection

The study examines the cybersecurity environment of electric transportation networks using a machine learning-based methodology. It analyzes the behaviors of electric vehicles, charging patterns, cyber threat occurrences, and the performance of machine learning models. An analysis of electric vehicle (EV) data shows that there are differences in battery capacity and distances covered, suggesting the presence of possible weaknesses across different cars. Cyber threat logs provide a comprehensive view of the various levels of threat severity and the time it takes to discover them, illustrating the ever-changing nature of cyber threats in the network. Machine learning models have varying performance; ML003 and ML005 exhibit excellent accuracy and precision in threat identification, whilst ML002 shows significantly lower metrics. These results highlight the need of implementing flexible cybersecurity solutions to handle different electric vehicle behaviors and effectively reduce cyber risks. This research emphasizes the need of using proactive threat detection tactics in order to effectively address high-severity attacks. It also highlights the need for ongoing improvement of machine learning models to strengthen network security. This study enhances our comprehension of cybersecurity obstacles in electric transportation networks, highlighting the crucial significance of machine learning-based analysis in strengthening network resilience against ever-changing cyber threats.

Evaluating the Robustness of MDSS Maintenance Forecasts Using Connected Vehicle Data

Evaluating the Robustness of MDSS Maintenance Forecasts Using Connected Vehicle Data

Data-Driven Optimal Formation Control for Multiple Nonlinear Quadrotors With Switching Topologies

This paper addresses the optimal distributed formation control of multiple quadrotor vehicles under switching topologies, where each vehicle suffers from significant nonlinearity and uncertainty, simultaneously. A distributed observer is constructed to generate the trajectory references for each vehicle. An optimal leader-following formation control protocol is then developed through the reinforcement learning method from the sampled vehicle data. Simulation results from a multiple quadrotors example under switching topologies are presented to verify the obtained results.

Verifiable and Redactable Blockchain for Internet of Vehicles Data Sharing

Verifiable and Redactable Blockchain for Internet of Vehicles Data Sharing

DNA Storage Promotes Long-term Storage of Internet of Vehicles Data

DNA Storage Promotes Long-term Storage of Internet of Vehicles Data

Evaluating the environmental impact on connected vehicles during freeway accidents using VISSIM with probe vehicle data

<abstract> <p>We evaluated emissions as an environmental effect resulting from connected vehicles (CVs) during freeway accidents. The CVs were used to determine the CV driving characteristics, whose values were used to implement the CV driving pattern using a microscopic traffic simulation. The environmental effect of implementation of CV was evaluated using the vehicle trajectory data derived from the simulation results. Implementation of CV effectively minimized the vehicle emissions regardless of the market penetration rate (MPR). In terms of vehicle type, the emissions reduction rate of passenger cars was the highest at a maximum of 33.4%. In the case of pollutants, the reduction rate of CO based on all vehicles was the highest at a maximum of 28.8%. Overall, we found that the implementation of CV positively affected vehicle emissions reductions, and an MPR of 60% could maximize the vehicle emissions reduction effect.</p> </abstract>

A Rapid and Convenient Spatiotemporal Calibration Method of Roadside Sensors Using Floating Connected and Automated Vehicle Data

A Rapid and Convenient Spatiotemporal Calibration Method of Roadside Sensors Using Floating Connected and Automated Vehicle Data

Assessment of floating car data quality for emission estimation

This paper presents a method for assessing the quality of floating car data and estimating emissions of the road network. The authors use a fundamental diagram from real probe vehicles to determine the categorization of the road network. These data are complemented by the widely used emission factors of the COPERT model to investigate the quality of the floating vehicle data to use them for the determination of emissions on individual road classes with a detailed spatiotemporal resolution. From the same data, an estimate of the emission rate of the categories is determined and it is assessed whether similar differences are exhibited. The hypothesis is that the quality of data is quite sufficient on highways and high-class roads, but unusable and insufficient on low-class roads. The results show that differences in emission estimates can be observed for the road categories of the highway network and low-class road network. For some pollutants, the urban network can also be identified. The offered categorization could lead to further possibilities of using floating vehicle data, such as the assumption of the possibility to detect atypical traffic phenomena (traffic jams, accidents, or impassable roads due to bad weather conditions).