Trajectory Data Research Articles

Smartphone videos-driven musculoskeletal multibody dynamics modelling workflow to estimate the lower limb joint contact forces and ground reaction forces.

The estimation of joint contact forces in musculoskeletal multibody dynamics models typically requires the use of expensive and time-consuming technologies, such as reflective marker-based motion capture (Mocap) system. In this study, we aim to propose a more accessible and cost-effective solution that utilizes the dual smartphone videos (SPV)-driven musculoskeletal multibody dynamics modeling workflow to estimate the lower limb mechanics. Twelve participants were recruited to collect marker trajectory data, force plate data, and motion videos during walking and running. The smartphone videos were initially analyzed using the OpenCap platform to identify key joint points and anatomical markers. The markers were used as inputs for the musculoskeletal multibody dynamics model to calculate the lower limb joint kinematics, joint contact forces, and ground reaction forces, which were then evaluated by the Mocap-based workflow. The root mean square error (RMSE), mean absolute deviation (MAD), and Pearson correlation coefficient (ρ) were adopted to evaluate the results. Excellent or strong Pearson correlations were observed in most lower limb joint angles (ρ = 0.74 ~ 0.94). The averaged MADs and RMSEs for the joint angles were 1.93 ~ 6.56° and 2.14 ~ 7.08°, respectively. Excellent or strong Pearson correlations were observed in most lower limb joint contact forces and ground reaction forces (ρ = 0.78 ~ 0.92). The averaged MADs and RMSEs for the joint lower limb joint contact forces were 0.18 ~ 1.07 bodyweight (BW) and 0.28 ~ 1.32 BW, respectively. Overall, the proposed smartphone video-driven musculoskeletal multibody dynamics simulation workflow demonstrated reliable accuracy in predicting lower limb mechanics and ground reaction forces, which has the potential to expedite gait dynamics analysis in a clinical setting.

AnimalEnvNet: A Deep Reinforcement Learning Method for Constructing Animal Agents Using Multimodal Data Fusion

Simulating animal movement has long been a central focus of study in the area of wildlife behaviour studies. Conventional modelling methods have difficulties in accurately representing changes over time and space in the data, and they generally do not effectively use telemetry data. Thus, this paper introduces a new and innovative deep reinforcement learning technique known as AnimalEnvNet. This approach combines historical trajectory data and remote sensing images to create an animal agent using deep reinforcement learning techniques. It overcomes the constraints of conventional modelling approaches. We selected pandas as the subject of our research and carried out research using GPS trajectory data, Google Earth images, and Sentinel-2A remote sensing images. The experimental findings indicate that AnimalEnvNet reaches convergence during supervised learning training, attaining a minimal mean absolute error (MAE) of 28.4 m in single-step prediction when compared to actual trajectories. During reinforcement learning training, the agent has the capability to replicate animal locomotion for a maximum of 12 iterations, while maintaining an error margin of 1000 m. This offers a novel approach and viewpoint for mimicking animal behaviour.

Analysis of the Duration of Mandatory Lane Changes for Heavy-Duty Trucks at Interchanges

Due to the different driving characteristics of different vehicle models, inappropriate mandatory lane changes (MLCs) by heavy vehicles at interchanges often lead to serious traffic accidents. Therefore, this paper focuses on the impact of road geometric design on the MLC duration of heavy trucks by using full time-domain trajectory data. Specifically, we use the generalized additive time-varying Cox model to establish the MLC duration model of heavy trucks at interchanges, then analyze the combined influence of geometric elements. The results show that the consistency index of the model is 0.9, indicating that it has advantages in building models in complex environments. The length of the deceleration lane, ramp type, and curve radius have a significant impact on the validity and duration of MLCs. This finding provides a theoretical and methodological reference for the safety analysis of interchange areas and the refinement of road geometric design.

Evaluating the Attraction of Scenic Spots Based on Tourism Trajectory Entropy.

With the development of positioning technology and the widespread application of mobile positioning terminal devices, the acquisition of trajectory data has become increasingly convenient. Furthermore, mining information related to scenic spots and tourists from trajectory data has also become increasingly convenient. This study used the normalization results of information entropy to evaluate the attraction of scenic spots and the experience index of tourists. Tourists and scenic spots were chosen as the probability variables to calculate information entropy, and the probability values of each variable were calculated according to certain methods. There is a certain competitive relationship between scenic spots of the same type. When the distance between various scenic spots is relatively close (less than 8 km), a strong cooperative relationship can be established. Scenic spots with various levels of attraction can generally be classified as follows: cultural heritage, natural landscape, and leisure and entertainment. Scenic spots with higher attraction are usually those with a higher A-level and convenient transportation. A considerable number of tourists do not choose to visit crowded scenic destinations but choose some spots that they are more interested in according to personal preferences and based on access to free travel.

A survey on reinforcement learning-based control for signalized intersections with connected automated vehicles

ABSTRACT Recent advancements in connected automated vehicles (CAVs) and reinforcement learning (RL) hold significant promise for enhancing intelligent traffic control systems. This paper conducts a systematic review of studies on RL-based urban traffic control at signalised intersections, highlighting the significant impact of CAVs on traffic control performance improvement. We first review the fundamental concepts of RL algorithms, establishing a foundational understanding for subsequent RL-based traffic control methods. We then review recent progress in RL-based traffic signal control using CV/CAV trajectory data, RL-based CAV trajectory planning, and the cooperative control of both traffic signals and CAVs at signalised intersections. Our aim is to provide researchers with a comprehensive roadmap for future research in RL-based traffic control at signalised intersections.

A novel ship trajectory reconstruction approach based on low-rank tensor completion

The Automatic Identification System (AIS) enhances maritime safety and environmental monitoring by providing crucial ship trajectory data. However, this data is often compromised by missing or abnormal values due to signal blockage, transmission errors, and equipment failures, jeopardizing safety and the accuracy of environmental analyses. Addressing these challenges, we propose a novel Customized Tensor-Based Maritime Trajectory Reconstruction (CTMTR) framework that leverages the self-similarity of ship trajectories to reformulate trajectory reconstruction as a matrix rank minimization issue. The CTMTR framework consists of three steps: data preprocessing, trajectory matrix construction, and trajectory reconstruction. We conducted simulation experiments using a dataset comprising vessel trajectories from the east coast of Dover in the United States in 2022. To validate its effectiveness, the CTMTR is compared with four advanced methods (LRMC, LRTC-TNN, TRPCA, and TNN-DCT) under diverse missing and anomalous scenarios. The results substantiate that the performance of CTMTR outperforms other approaches, especially in anomalous cases. Our method outperforms existing methods by an order of magnitude under random missing combined with anomaly scenarios. The CTMTR framework thus has the potential to advance maritime trajectory reconstruction methodologies, providing a solid foundation for future innovations in maritime data analysis and navigation safety technologies.

Calibrating Car-Following Models Using SUMO-in-the-Loop and Vehicle Trajectories From Roadside Radar

This paper presents an innovative calibration method for car-following (CF) models in the Simulation of Urban MObility (SUMO) using real-world trajectory data from a 1.5 km signalized urban corridor, captured by roadside radars. By applying a sophisticated track-level association and fusion methodology, the study extends trajectory analysis beyond individual radar fields of view. The enhanced data is then utilized to refine the Krauss, IDM, and W99 CF models within SUMO, addressing the literature gap by integrating SUMO into the calibration loop, thereby accommodating the simulator's integration scheme and any model adaptations. The research identifies that default SUMO models tend to exhibit shorter time headways compared to real-world data, with calibration effectively reducing this discrepancy. Moreover, the W99 model, despite its unrealistic acceleration profiles when calibrated without considering acceleration, most accurately captures the higher-end energy consumption distribution. Conversely, the IDM model, with its default parameters, provides the closest approximation to observed acceleration behaviors, highlighting the nuanced performance of CF models in traffic simulation and their implications for energy consumption estimation. Detailed results of optimized parameters for each CF model are provided in appendix in addition to distribution information that may be useful for other modelers to use directly or other datasets to be compared in the future (including expansion of the work to include vehicle classification).

Calculation Model for the Exit Decision Sight Distance of Right-Turn Ramps on the Left at Interchange

Given the rapid construction of freeways in developing countries such as China, land use is constantly under strict constraints, leading to challenges in adopting conventional layouts for interchanges. Implementing right-turn ramps on the left (RTRL) at interchanges can minimize land occupancy; however, the traffic safety level in this type of diversion area design requires extra attention. This study examines the decision sight distance for right-turn exit ramps on the left side. Utilizing unmanned aerial vehicle (UAV) video and the YOLOv3 target detection algorithm, the original trajectory data of vehicles in the diversion area is extracted. Employing Kalman filtering and Frenet coordinate system conversion reveals microscopic vehicle lane-change patterns, velocities, and time headways. Furthermore, the driving simulation experiment assesses driver behaviors in RTRL, with subjective, task performance, and physiological measure indicators. Ultimately, the range of the decision sight distance is defined, and establishing a calculation model involves determining relevant parameters based on measured data and simulation outcomes. The results indicate potential insufficiencies in the decision sight distance when standardized values are applied to RTRL.

Driving risk identification of urban arterial and collector roads based on multi-scale data

Urban arterial and collector roads, while interconnected within the urban transportation network, serve distinct purposes, leading to different driving risk profiles. Investigating these differences using advanced methods is of paramount significance. This study aims to achieve this by primarily collecting and processing relevant vehicle trajectory data alongside driver-vehicle–road-environment data. A comprehensive risk assessment matrix is constructed to assess driving risks, incorporating multiple conflict and traffic flow indicators with statistically temporal stability. The Entropy weight-TOPSIS method and the K-means algorithm are employed to determine the risk scores and levels of the target arterial and collector roads. Using risk levels as the outcome variables and multi-scale features as the explanatory variables, random parameters models with heterogeneity in means and variances are developed to identify the determinants of driving risks at different levels. Likelihood ratio tests and comparisons of out-of-sample and within-sample prediction are conducted. Results reveal significant statistical differences in the risk profiles between arterial and collector roads. The marginal effects of significant parameters are then calculated separately for arterial and collector roads, indicating that several factors have different impacts on the probability of risk levels for arterial and collector roads, such as the number of movable elements in road landscape pictures, the standard deviation of the vehicle’s lateral acceleration, the average standard deviation of speed for all vehicles on the road segment, and the number of one-way lanes on the road segment. Some practical implications are provided based on the findings. Future research can be implemented by expanding the collected data to different regions and cities over longer periods.

A novel car-following model for adaptive cruise control vehicles using enhanced intelligent driver model

ABSTRACT This paper proposes Enhanced Intelligent Driver Model for Adaptive Cruise Control (EIDM-ACC) vehicles, a novel car-following model that dynamically adjusts desired speed and considers acceleration inertia. The EIDM-ACC model is compared with two widely used models for simulating ACC vehicles – the ACC model developed by the PATH Project (PATH-ACC) at the University of California Transportation Institute and Continuous Asymmetric Optimal Velocity Relative Velocity (CAOVRV) model. Three models are calibrated and cross-validated using real vehicle trajectory data from the OpenACC dataset. Results show that the EIDM-ACC outperforms the other two models in small and large fluctuation stages. In addition, EIDM-ACC has better performance in capturing the instability and energy consumption of ACC vehicles, and also has advantages over the other two models in terms of safety.

Association between outdoor jogging behavior and PM2.5 exposure: Evidence from massive GPS trajectory data in Beijing

Outdoor jogging is one of the most popular practised exercises worldwide, providing various benefits for health and wellbeing. However, PM2.5 exposure risks of jogging behaviors were rarely explored. This study aims to investigate the association between jogging behavior and PM2.5 exposure with big data. PM2.5 exposure concentration and dose inhalation of individuals were calculated by integrating hourly PM2.5 concentration data and jogging GPS trajectory recorded by a sports app during 2015 in Beijing, after which relationships between jogging behaviors and PM2.5 exposure were unpacked using statistics analysis and structural equation modelling. Experimental results on massive jogging trajectories show that: (1) the average jogging PM2.5 exposure concentration is 60.43 μg/m3, and female joggers inhaled significantly less air pollution dose (19.70 μg) than men (24.91 μg). (2) There exist significant spatiotemporal disparities in jogging exposure to PM2.5. Joggings in the city center, in the morning, on weekdays and in autumn and winter seasons were exposed to higher pollution concentrations. (3) Jogging behavior characteristics, especially distance, activity space size, duration and rotation, were systematically associated with PM2.5 exposure across space and time. (4) The role of gender directly shaped joggers' dose inhalation of PM2.5 pollution and indirectly via duration, timing choice and distance. (5) The effects of weather conditions on joggers' exposure to PM2.5 are mainly via direct effects, whereas the direct impacts of precipitation and wind speed are mitigated by indirect effects stemming from jogging behavior patterns. Our findings provide insights for personal guidance and policy intervention for the sake of promoting physical activity and reducing PM2.5 exposure.

A trajectory similarity computation method based on GAT-based transformer and CNN model

Trajectory similarity computation is very important for trajectory data mining. It is applied into many trajectory mining tasks, including trajectory clustering, trajectory classification and trajectory search etc. So efficient trajectory similarity computation method is very useful for improving trajectory mining result. Nowadays many trajectory similarity computation methods have been proposed. But most of them can not be applied into long trajectories similarity calculation efficiently. So a new algorithm called TrajGAT is proposed. This algorithm can calculate similarity for long trajectories. It treats long trajectory as a long sequence. By doing so, long-term dependency of long trajectory is considered by this algorithm while computing similarity value. But, the spatial feature of long trajectories is not considered. As long trajectory can be presented in many different shapes, if two long trajectories are judged as similar trajectories, the outline shape of these two trajectories should be similar as well. To solve this problem, a new trajectory similarity computation method is proposed in this paper. This method not only takes the long-term dependence feature into consideration, but also considers the outline feature of long trajectory. The proposed method employs GAT-based transformer to extract long-term dependence feature from long trajectory. And it applies Convolutional Neural Network to extract outline feature.

NRIMD, a Web Server for Analyzing Protein Allosteric Interactions Based on Molecular Dynamics Simulation.

Long-range allosteric communication between distant sites and active sites in proteins is central to biological regulation but still poorly characterized, limiting the development of protein engineering and drug design. Addressing this gap, NRIMD is an open-access web server for analyzing long-range interactions in proteins from molecular dynamics (MD) simulations, such as the effect of mutations at distal sites or allosteric ligand binding at allosteric sites on the active center. Based on our recent works on neural relational inference using graph neural networks, this cloud-based web server accepts MD simulation data on any length of residues in the alpha-carbon skeleton format from mainstream MD software. The input trajectory data are validated at the frontend deployed on the cloud and then processed on the backend deployed on a high-performance computer system with a collection of complementary tools. The web server provides a one-stop-shop MD analysis platform to predict long-range interactions and their paths between distant sites and active sites. It provides a user-friendly interface for detailed analysis and visualization. To the best of our knowledge, NRIMD is the first-of-its-kind online service to provide comprehensive long-range interaction analysis on MD simulations, which significantly lowers the barrier of predictions on protein long-range interactions using deep learning. The NRIMD web server is publicly available at https://nrimd.luddy.indianapolis.iu.edu/.

Coupling Hyperbolic GCN with Graph Generation for Spatial Community Detection and Dynamic Evolution Analysis

Spatial community detection is a method that divides geographic spaces into several sub-regions based on spatial interactions, reflecting the regional spatial structure against the background of human mobility. In recent years, spatial community detection has attracted extensive research in the field of geographic information science. However, mining the community structures and their evolutionary patterns from spatial interaction data remains challenging. Most existing methods for spatial community detection rely on representing spatial interaction networks in Euclidean space, which results in significant distortion when modeling spatial interaction networks; since spatial community detection has no ground truth, this results in the detection and evaluation of communities being difficult. Furthermore, most methods usually ignore the dynamics of these spatial interaction networks, resulting in the dynamic evolution of spatial communities not being discussed in depth. Therefore, this study proposes a framework for community detection and evolutionary analysis for spatial interaction networks. Specifically, we construct a spatial interaction network based on network science theory, where geographic units serve as nodes and interaction relationships serve as edges. In order to fully learn the structural features of the spatial interaction network, we introduce a hyperbolic graph convolution module in the community detection phase to learn the spatial and non-spatial attributes of the spatial interaction network, obtain vector representations of the nodes, and optimize them based on a graph generation model to achieve the final community detection results. Considering the dynamics of spatial interactions, we analyze the evolution of the spatial community over time. Finally, using taxi trajectory data as an example, we conduct relevant experiments within the fifth ring road of Beijing. The empirical results validate the community detection capabilities of the proposed method, which can effectively describe the dynamic spatial structure of cities based on human mobility and provide an effective analytical method for urban spatial planning.

ST-TrajGAN: A synthetic trajectory generation algorithm for privacy preservation

The rapid growth of large-scale trajectory data poses privacy risks for location-based services (LBS), primarily through centralized storage and processing of data, as well as insecure data transmission channels (such as the Internet and wireless networks), which can lead to unauthorized access or manipulation of users' location information by attackers. To enhance trajectory privacy protection while improving the trajectory utility, this paper proposes an efficient and secure deep learning model Semantic and Transformer-based Trajectory Generative Adversarial Networks (ST-TrajGAN) for trajectory data generation and publication. First, this article introduces a semantic trajectory encoding model for preprocessing trajectory points. Through this model, trajectory points can be transformed into vector representations with semantic information. Next, by learning the spatio-temporal and semantic features of real trajectory data, a deep learning model is used to generate synthetic trajectories with more uncertainty and practicality. Furthermore, a novel TrajLoss loss metric function was crafted to gauge the trajectory similarity loss within the trained deep learning model. Ultimately, the efficacy of the generated synthetic trajectories and the model's utility are assessed through Trajectory-User Linking (TUL) and Trajectory Sharing Percentage (TSP) values on three authentic Location-Based Services (LBS) datasets. Numerous experiments have shown that our method outperforms other methods in terms of privacy protection effectiveness and utility.

A probabilistic time geographic approach to quantifying seabird‐vessel interactions

AbstractAccounting for uncertainty is essential for precautionary approaches to managing seabird bycatch in commercial fisheries. However, there is no existing mechanism to explicitly quantify the uncertainty of seabird‐vessel interactions (i.e. co‐occurrence in space and time). Here we develop a time geographic method to measure the probability of individual birds encountering (co‐occurring within 30 km) and attending (within 5 km) individual fishing vessels. The approach involves creating voxel‐based probabilistic space–time prisms (PSTPs) to model the movements of individual birds and vessels, with trajectory data from bird‐borne GPS devices and vessel Automatic Identification Systems (AIS). We intersected these PSTPs to quantify the probability of interaction between bird‐vessel pairs over time and space. We demonstrate the approach with a case study of interactions of Endangered Toroa (Antipodean Albatross; Diomedea antipodensis antipodensis) with pelagic longline vessels in part of the South Pacific high seas. We found 15 vessels within 150 km and 3 h of two birds, yet interaction occurred with only two of those vessels. We visualised the probability of encounter and attendance over time and space and determined that interactions lasted several hours each (up to 6.2–14.1 h attendance, 20.8–26.1 h encounter for one bird‐vessel pair). Our time geographic approach adds to existing tools to quantify seabird bycatch risk by providing an explicit measure of uncertainty of seabird‐vessel interactions. We provide a flexible methodological pathway and R scripts, the application of which would allow managers to estimate interaction probability for multiple marine species and fisheries, including those with lower‐resolution positional datasets.

Deriving Verified Vehicle Trajectories from LiDAR Sensor Data to Evaluate Traffic Signal Performance

Advances and cost reductions in Light Detection and Ranging (LiDAR) sensor technology have allowed for their implementation in detecting vehicles, cyclists, and pedestrians at signalized intersections. Most LiDAR use cases have focused on safety analyses using its high-fidelity tracking capabilities. This study presents a methodology to transform LiDAR data into localized, verified, and linear-referenced trajectories to derive Purdue Probe Diagrams (PPDs). The following four performance measures are then derived from the PPDs: arrivals on green (AOG), split failures (SF), downstream blockage (DSB), and control delay level of service (LOS). Noise is filtered for each detected vehicle by iteratively projecting each sample’s future location and keeping the subsequent sample that is close enough to the estimated destination. Then, a far side is defined for the analyzed intersection’s movement to linear reference sampled trajectories and to remove those that do not cross through that point. The technique is demonstrated by using over one hour of LiDAR data at an intersection in Utah to derive PPDs. Signal performance is then estimated from these PPDs. The results are compared to those obtained from comparable PPDs derived from connected vehicle (CV) trajectory data. The generated PPDs from both data sources are similar, with relatively modest differences of 1% AOG and a 1.39 s/veh control delay. Practitioners can use the presented methodology to estimate trajectory-based traffic signal performance measures from their deployed LiDAR sensors. The paper concludes by recommending that unfiltered LiDAR data are used for deriving PPDs and extending the detection zones to cover the largest observed queues to improve performance estimation reliability.

Simulation-based personal fatality risk assessment due to the fragmentation hazard

In the military and chemical industry, modeling the fragmentation hazard field is of great significance in conducting the fatality risk assessment and calculating the safety distance for person. Although the ballistic methodology achieves the simulation of fragmentation flight trajectory, the acquisition of accurate initial projection data of fragmentation is a challenge. By coupling continuum-discontinuum element method and particle discrete element method, the fragmentation power algorithm is established, which achieves the integrated simulation of the initial projection data of fragmentation and the flight process of fragmentation. First, continuum-discontinuum element method is adopted to simulate the detonation products-driven fragmentation acceleration process by introducing the explosive detonation model, which achieves the acquisition of initial projection data of fragmentation. Then, the particle discrete element method is adopted to simulate the flight trajectory and power data of fragmentation. Based on the numerical and experimental result, the accuracy of fragmentation power algorithm is verified. In conjunction with the personal vulnerability model, a systematic numerical simulation framework is established to conduct the simulation-based personal fatality risk assessment when the metal-cased munition detonates accidentally, and the results indicate that the personal fatality risk due to the fragmentation becomes severer with the increase of munition curvature.

Analyzing foreland dynamics in China's port clusters under global major events (2019–2022) by AIS trajectory data

Port foreland, serves as the maritime mirror of the hinterland, encompasses the ports and overseas markets interconnected through shipping services. During major global events, understanding port foreland structures becomes imperative for nations and port authorities to anticipate future trade trends and potential coastal management risks. However, systematic approaches for accurately identifying foreland structures remain lacking, particularly given liner shipping complexities. In response, this paper develops two algorithms to analyze changes in the foreland structure of five port clusters in China for the years 2019 and 2022, leveraging over 2.1 billion global vessel AIS trajectory signals. We aim to understand the foreland dynamics of China's ports amidst the broader impacts of the China-US trade war, the COVID-19 pandemic, and the Russia-Ukraine (RU) conflict, and provide insights for maintaining the global trade continuity. Our findings show that geopolitical events and bilateral relations highly influence port foreland structures, yet global supply chain requirements prompt stakeholders to adopt alternative transport strategies. In 2022, China's foreland structures remain stable despite its strict epidemic control measures. Positive developments in China's port forelands with the US are driven by improving bilateral relations and reduced impacts of the US-China trade war, while conflicts in RU cause shrinkage in Europe. On this basis, we provide three constructive opinions on the development of China's port clusters.

TPRT: a trajectory publishing scheme for the Internet of Vehicles based on radix tree

Abstract The location and trajectory information generated in the Internet of Vehicles (IoV) provides sufficient data support for road network planning. However, there is much sensitive information in these data, and publishing them directly will lead to serious privacy leakage risks. Therefore, this paper proposes a trajectory publishing scheme for the Internet of Vehicles based on radix tree (TPRT). Firstly, the trajectory data are divided into multiple location planes based on timestamps and processed using clustering and generalization. This approach addresses the issue of real-life trajectory data having almost no identical prefixes, making it more suitable for storage in radix tree. Then, the directed graph and the shortest path algorithm are utilized to synthesize a new trajectory dataset for publication. Subsequently, a radix tree structure that satisfies differential privacy is defined. In comparison to the research method employing a prefix tree, the radix tree not only captures the spatiotemporal characteristics of the trajectories but also reduces space consumption. Finally, a novel method of noise addition is proposed. In contrast to the traditional layer-by-layer noise addition approach, our method reduces the cost of noise addition and enhances data availability. Experimental results demonstrate that TPRT exhibits superior data availability compared to the baseline methods.