Trajectory Characteristics Research Articles

Automated Approach for Computer Vision-Based Vehicle Movement Classification at Traffic Intersections

Movement-specific vehicle classification and counting at traffic intersections is a crucial component of various traffic management activities. In this context, with recent advancements in computer-vision-based techniques, cameras have emerged as a reliable data source for extracting vehicular trajectories from traffic scenes. However, classifying these trajectories by movement type is quite challenging, as characteristics of motion trajectories obtained this way vary depending on camera calibrations. Although some existing methods have addressed such classification tasks with decent accuracies, the performance of these methods significantly relied on the manual specification of several regions of interest. In this study, we proposed an automated classification method for movement-specific classification (such as right-turn, left-turn and through movements) of vision-based vehicle trajectories. Our classification framework identifies different movement patterns observed in a traffic scene using an unsupervised hierarchical clustering technique. Thereafter, a similarity-based assignment strategy is adopted to assign incoming vehicle trajectories to identified movement groups. A new similarity measure was designed to overcome the inherent shortcomings of vision-based trajectories. Experimental results demonstrated the effectiveness of the proposed classification approach and its ability to adapt to different traffic scenarios without any manual intervention.

Neural mass framework for decoding amyloid and Tau impact on neuronal activity under Alzheimer’s Disease

AbstractBackgroundWe introduce a computational brain network model to understand the effect of abnormal microscopical processes into non‐invasive macroscopic neuronal activity observations and cognitive impairment across the Alzheimer’s disease (AD) spectrum. Amyloid‐beta (Aβ) plaques and tau protein aggregates (τ) modulate neuronal firing with the former likely increasing firing (hyperactivity) and the latter inhibiting activity (hypoactivity), especially in the abundant pyramidal populations ‐see (Maestu et al., 2021) for more details. We assume that such interactions scale up to macroscopic regions in humans, specifically influencing resting‐state fMRI signals.MethodMultimodal data, including amyloid ([18F]Florbetapir) and tau ([18F]flortaucipir) PET, baseline resting‐state fMRI, structural and diffusion MRI, and clinical/cognitive indicators were obtained from the Alzheimer’s Disease Neuroimaging Initiative. The imaging modalities were processed to produce values for a parcellation consisting of 66 brain regions. We considered four neural masses interacting within a region. The regional excitatory and inhibitory activities then transform into BOLD signals (Valdes‐Sosa et al., 2009) ‐see Fig. 1A. Pyramidal excitabilities (v0E,k) contain the Aβ‐ and τ‐ parameters of interest, and their combined effect (Fig. 1B), which we estimated by minimizing the spectral distance between simulated signals and observations.ResultThe synergy between disease factors seems to change with disease states and subjects (Fig. 1C). Most of the considered healthy controls (HC) presented relatively low excitability change by Aβ and by τ, albeit having a greater, generally positive or ‘towards hypoactivity’ combined action. Mild cognitive impairment subjects appeared in two sub‐groups, one significantly close to the HC and another with stronger individual effects and smaller joined action. All AD patients presented positive synergistic effects and relatively high independent contributions to pyramidal population firing, as estimated from the data.ConclusionThe obtained significant, subject‐specific influences of pathological factors on neural activity verify the interactions reported by (Busche et al., 2020) in animal models experiments at the mesoscopic scale. There exist causal relationships between the amyloid and tau influence parameters and clinical variables. Further research must be performed to clarify characteristic disease trajectories as effective sub‐typing in early stages could improve therapeutic interventions.

An investigation on the wake vortex structure and trajectory characteristics of the vehicle launched underwater

ABSTRACT The Improved Delayed Detached Eddy Simulation (IDDES), VOF (Volume of Fluid) multiphase flow model, and overlapping grid technology were adopted in this paper. The results show that the interaction between the high-speed regions and the low-speed flow increases, as the Kelvin–Helmholtz instability phenomenon occurs in the mixing fluid during traveling underwater. Under the effect of the inertial force, the tail bubble expands successively, resulting in an increase in cavity volume and a decrease in pressure. In addition, the wake vortex is composed of the main vortex and secondary vortex, which is a cone of the major influencing factors causing the disturbance of the flow field. As the vehicle continuously passes through the free surface, the buoyancy center of the vehicle successively moves downward, resulting in a change in the direction of buoyancy moment and aggravating the deflection amplitude of the vehicle.

Numerical study on the influence of floating ice on the water-exit hydrodynamic characteristics of a trans-media vehicle

In low-temperature combat conditions, the strong interference of floating ice on the water-exit process of trans-media weapons must be considered. The evolution of the cavity shape, hydrodynamic and ballistic characteristics during the water-exit process of a high-speed vehicle penetrating water (without floating ice) and ice-water mixture were studied in comparison based on computational fluid dynamics (CFD) and the discrete element method (DEM). The results revealed that the floating ice accelerates the collapse of the attached cavity, delays the collapse time of the tail cavity, and changes the vehicle’s wet degree. The floating ice causes the vehicle to be subjected to a severe fluctuating alternating load and lasts for a longer time, which changes the trajectory characteristics of the vehicle, reducing its motion stability and intensifying trajectory deviation. The findings can provide a reference for the design and development of cross-media weapons in low-temperature environments in winter.

The environmental impact assessment of greener trajectories: the GreAT project

GreAT (Greener Air Traffic Operations) is a project funded by the European Commission under the H2020 framework programme. The overall objective is to reduce the fuel consumption and gas emissions during “gate-to-gate” flight phases through developing and assessing environment-friendly air traffic operational concept, adaptive airspace and green trajectory optimization technologies, and supporting avionic systems. Based on the scientific description of the impact of aviation emissions on the climate, the work within GreAT is seeking the key factors of the impact about aviation emissions on climate change characteristics by using sensitivity analysis, such as greenhouse gases, pollutant gases and condensation, and then select these factors as environmental impact assessment indicators, including fuel consumption, aviation emissions, air quality and greenhouse effect, establishing a calculation model for evaluation indicators using the fuel consumption model, gas emission model and climate change model. System analysis methods are used to build an aviation emission environmental impact (EIA) assessment index system structure, apply environmental impact assessment indicators, construct a general environmental impact assessment index system, and propose a comprehensive assessment method for aviation environmental impact. The following step in the project is the environmental impact assessment of air traffic operations to determine how green air traffic performs. According to the existing air traffic operation patterns, the flight characteristics and trajectory characteristics of the aircraft are determined, and the environmental impact assessment index system is used to evaluate the environmental impact under the air traffic operation plan and the impact and improvement effect on climate change.

Failing categorization of severe COVID-19 ARDS into ventilatory subphenotypes studied via the clinical-histopathologic relationship

BackgroundCategorization of severe COVID-19 related acute respiratory distress syndrome (CARDS) into subphenotypes does not consider the trajectories of respiratory mechanoelastic features and histopathologic patterns. This study aimed to assess the correlation between mechanoelastic ventilatory features and lung histopathologic findings in critically ill patients who died because of CARDS. MethodsMechanically ventilated patients with severe CARDS who had daily ventilatory data were considered. The histopathologic assessment was performed through full autopsy of deceased patients. Patients were categorized into two groups according to the median worst respiratory system compliance during ICU stay (CrsICU). ResultsEighty-seven patients admitted to ICU had daily ventilatory data. Fifty-one (58.6%) died in ICU, 41 (80.4%) underwent full autopsy and were considered for the clinical-histopathological correlation analysis. Respiratory system compliance at ICU admission and its trajectory were not different in survivors and non-survivors. Median CrsICU in the deceased patients was 22.9 ml/cmH2O. An inverse correlation was found between the CrsICU and late-proliferative diffuse alveolar damage (DAD) (r = −0.381, p = 0.026). Late proliferative DAD was more extensive (p = 0.042), and the probability of stay in ICU was higher (p = 0.004) in the “low” compared to the “high” CrsICU group. Cluster analysis further endorsed these findings. ConclusionsIn critically ill mechanically ventilated patients, worsening of the respiratory system compliance correlated pathologically with the transition from early damage to late fibroproliferative patterns in non-survivors of CARDS. Categorization of CARDS into ventilatory subphenotypes by mechanoelastic properties at ICU admission does not account for the complexity of the histopathologic features.

An adaptive threshold fast DBSCAN algorithm with preserved trajectory feature points for vessel trajectory clustering

Vessel navigation pattern recognition plays an important role in the research of intelligent transportation on water. Clustering using the data stored in The Automatic Identification System (AIS) is a current research hotspot. However, there are three problems in the past clustering analysis. First, the traditional Douglas-Peucker (DP) Compression Algorithm exists feature point loss and trajectory distortion when compressing trajectories. Second, Dynamic Time Warping (DTW) and the density-based spatial clustering of applications with noise (DBSCAN) algorithm require high time cost. Finally, most of the studies ignore the interaction between parameters when choosing the parameters of DBSCAN. These problems seriously affect the efficiency and accuracy of clustering. To solve these problems, this paper improves the existing methods by (1) Adaptive selection of compression thresholds and trajectory feature points for each trajectory when using the DP algorithm ensures the realism of the compressed trajectory; (2) using the Fast-DTW algorithm to improve the computation speed and ensure the accuracy of trajectory similarity; (3) Self-selection of parameter combinations based on Silhouette Coefficient (SC) scores was achieved using the similarity distribution of the trajectories in combination with an improved K-Adaptive Nearest Neighbors (KANN). The experiments show that the proposed method can greatly reduce the time cost of clustering compared to the original method and significantly outperforms the three compared algorithms in terms of clustering effect images.

Mobile user identification based on road networks and multiple distance measures

AbstractMobile user identification aims at matching different mobile devices of the same user using trajectory data, which has attracted extensive research in recent years. Most of the previous work extracted trajectory features based on regular grids, which will lead to incorrect feature representation due to lack of geographic information. Besides, most trajectory similarity models only considered one single distance measure to calculate the similarity between users, which ignore the connection between different distance measures and may lead to some false matches. In light of this, we present a novel user identification method based on road networks and multiple distance measures in this article. The proposed method segments a city map into several grids and road segments based on road networks. Then it extracts location and road information of trajectories to jointly construct user features. Multiple distance measures are fused by a discriminant model to improve the effect of user identification. Experiments on real GPS trajectory datasets show that our proposed method outperforms related similarity measure methods and is stable for mobile user identification. Meanwhile, our method can also achieve good identification results even on sparse trajectory datasets.

The Study of Fishing Vessel Behavior Identification Based on AIS Data: A Case Study of the East China Sea

The goal of this paper is to strengthen the supervision of fishing behavior in the East China Sea and effectively ensure the sustainable development of fishery resources. Based on AIS data, this paper analyzes three types of fishing boats (purse seine operation, gill net operation and trawl operation) and uses the cubic spline interpolation algorithm to optimize the ship trajectory and construct high-dimensional features. It proposes a new coding method for fishing boat trajectory sequences. This method uses the Geohash algorithm to divide the East China Sea into grids and generate corresponding numbers. Then, the ship trajectory is mapped to the grid, the fishing boat trajectory points are associated with the divided grid, and the ship trajectory ID is extracted from the corresponding grid. The extracted complete trajectory sequence passes through the CBOW (continuous bag of words) model, and the correlation of trajectory points is fully learned. Finally, the fishing boat trajectory is converted from coordinate sequence to trajectory vector, and the processed trajectory sequence is trained by the LightGBM algorithm. In order to obtain the optimal classification effect, the optimal superparameter combination is selected. We put forward a LightGBM algorithm based on the Bayesian optimization algorithm, and obtained the classification results of three kinds of fishing boats. The final result was evaluated using the F1_score. Experimental results show that the F1_score trained with the proposed trajectory vectorization method is the highest, with a training accuracy of 0.925. Compared to XgBoost and CatBoost, the F1_score increased by 1.8% and 1.2%, respectively. The results show that this algorithm demonstrates strong applicability and effectiveness in fishery area evaluations and is significant for strengthening fishery resource management.

Simulation Analysis of Spreading Process and Electron Beam Melting of Ti6Al4V Powder

Forming process control of powder bed fusion (PBF) additive manufacturing (AM) is the key to produce high-quality qualified parts. In this paper, spreading powder process and electron-beam melting (EBM) of Ti6Al4V powder were simulated based on simulation technology, and the state of powder bed powder and melting trajectory characteristics were characterized. Firstly, the particle size distribution of Ti6Al4V powder was tested, and the particle diameter of normal distribution for simulation was determined. Then, the simulation models of spreading powder and EBM model were established. Finally, based on the simulation results, the effect of processing parameters on the quality of powder laying is analyzed, and the morphology of EBM melting trajectory is characterized.

Trajectory feature extraction and multi‐criteria k nearest neighbour based job‐to‐crowd matching for the crowdshipping last mile delivery

AbstractSustainable freight transportation is one of the essential concepts in the smart city. Under this concept, many people connected with mobile devices produce location data and potential opportunities for transporting small objects in a more environmentally friendly and sustainable way. Crowdshipping, which utilises public people as transportation, is one of the terminal solutions in the last mile delivery scenario. Nevertheless, precisely assigning the delivery to the right crowd willing to accept the job is challenging because the solution space is too large to perform a full search. This article proposes a trajectory feature extraction algorithm and a task‐to‐crowd matching (T2CM) algorithm for coping with the job‐to‐crowd assignment problem. A simulation based on the real‐world dataset is conducted on three different scenarios to justify the outcome from our proposed method to the job assignment results.

Selecting Features for Markov Modeling: A Case Study on HP35.

Markov state models represent a popular means to interpret molecular dynamics trajectories in terms of memoryless transitions between metastable conformational states. To provide a mechanistic understanding of the considered biomolecular process, these states should reflect structurally distinct conformations and ensure a time scale separation between fast intrastate and slow interstate dynamics. Adopting the folding of villin headpiece (HP35) as a well-established model problem, here we discuss the selection of suitable input coordinates or "features", such as backbone dihedral angles and interresidue distances. We show that dihedral angles account accurately for the structure of the native energy basin of HP35, while the unfolded region of the free energy landscape and the folding process are best described by tertiary contacts of the protein. To construct a contact-based model, we consider various ways to define and select contact distances and introduce a low-pass filtering of the feature trajectory as well as a correlation-based characterization of states. Relying on input data that faithfully account for the mechanistic origin of the studied process, the states of the resulting Markov model are clearly discriminated by the features, describe consistently the hierarchical structure of the free energy landscape, and─as a consequence─correctly reproduce the slow time scales of the process.

Morphodynamical cell state description via live-cell imaging trajectory embedding

Time-lapse imaging is a powerful approach to gain insight into the dynamic responses of cells, but the quantitative analysis of morphological changes over time remains challenging. Here, we exploit the concept of “trajectory embedding” to analyze cellular behavior using morphological feature trajectory histories—that is, multiple time points simultaneously, rather than the more common practice of examining morphological feature time courses in single timepoint (snapshot) morphological features. We apply this approach to analyze live-cell images of MCF10A mammary epithelial cells after treatment with a panel of microenvironmental perturbagens that strongly modulate cell motility, morphology, and cell cycle behavior. Our morphodynamical trajectory embedding analysis constructs a shared cell state landscape revealing ligand-specific regulation of cell state transitions and enables quantitative and descriptive models of single-cell trajectories. Additionally, we show that incorporation of trajectories into single-cell morphological analysis enables (i) systematic characterization of cell state trajectories, (ii) better separation of phenotypes, and (iii) more descriptive models of ligand-induced differences as compared to snapshot-based analysis. This morphodynamical trajectory embedding is broadly applicable to the quantitative analysis of cell responses via live-cell imaging across many biological and biomedical applications.

Trajectory‐BERT: Pre‐training and fine‐tuning bidirectional transformers for crowd trajectory enhancement

AbstractTo address the issue of trajectory fragments and ID switches caused by occlusion in dense crowds, we propose a space‐time trajectory encoding method and a point‐line‐group division method to construct Trajectory‐BERT in this paper. Leveraging the spatiotemporal context‐dependent features of trajectories, we introduce pre‐training and fine‐tuning Trajectory‐BERT tasks to repair occluded trajectories. Experimental results show that data augmented with Trajectory‐BERT outperforms raw annotated data on the MOTA metric and reduces ID switches in raw labeled data, demonstrating the feasibility of our method.

Design and analysis of direct abort trajectory for a crewed lunar mission based on the quasi-lambert problem

A direct design method for direct abort trajectory based on the quasi-lambert problem is proposed. The re-entry constraint is analytically addressed via a quasi-lambert problem instead of variables iteration and optimization method in the past. Then a new parameter is introduced to determine the plane. The exact solution is determined by differential correction based on the initial solution. Numerical simulation is carried out to test the validity and efficiency of the method. The comparison with STK verifies its reliability. Additionally, the characteristics of direct abort trajectory and their application in the option strategy for different abort ways are studied. The flight time and abort point affect the abort trajectories’ velocity increment and the latitude of the landing area.

The High-speed Aircraft Trajectory Prediction Method Based on Deep Learning Network

This paper applies deep learning technology to the trajectory prediction research of high-speed aircraft in order to predict the medium- and long-term trajectory. Hence, a hybrid model combining the time series convolution neural network (TSCNN) and the long short-term memory (LSTM) is put forward to predict position and velocity of high-speed aircraft. In the TSCNN, convolution operations are used to extract trajectory features of time and space to predict the future trajectory. However, the error will be generated during prediction the process, so the LSTM network can be tapped to correct it by analyzing why it is produced in a bid to address error accumulation. According to simulations conducted, the model can lead to high-precision prediction.

Fixed-time cooperative trajectory optimisation strategy for multiple hypersonic gliding vehicles based on neural network and ABC algorithm

AbstractCollaborative planning for multiple hypersonic vehicles can effectively improve operational effectiveness. Time coordination is one of the main forms of cooperation among multi-hypersonic glide vehicles, and time cooperation trajectory optimisation is a key technology that can significantly increase the success rate of flight missions. However, it is difficult to obtain satisfactory time as a constraint condition during trajectory optimisation. To solve this problem, a multilayer Perceptrona is trained and adopted in a time-decision module, whose input is a four-dimensional vector selected according to the trajectory characteristics. Additionally, the MLP will be capable of determining the optimal initial heading angle of each aircraft to reduce unnecessary manoeuvering performance consumption in the flight mission. Subsequently, to improve the cooperative flight performance of hypersonic glide vehicles, the speed-dependent angle-of-attack and bank command were designed and optimised using the Artificial Bee Colony algorithm. The final simulation results show that the novel strategy proposed in this study can satisfy terminal space constraints and collaborative time constraints simultaneously. Meanwhile, each aircraft saves an average of 13.08% flight range, and the terminal speed is increased by 315.6m/s compared to the optimisation results of general purpose optimal control software (GPOPS) tools.

Single-cell transcriptional uncertainty landscape of cell differentiation

Background: Single-cell studies have demonstrated the presence of significant cell-to-cell heterogeneity in gene expression. Whether such heterogeneity is only a bystander or has a functional role in the cell differentiation process is still hotly debated. Methods: In this study, we quantified and followed single-cell transcriptional uncertainty – a measure of gene transcriptional stochasticity in single cells – in 10 cell differentiation systems of varying cell lineage progressions, from single to multi-branching trajectories, using the stochastic two-state gene transcription model. Results: By visualizing the transcriptional uncertainty as a landscape over a two-dimensional representation of the single-cell gene expression data, we observed universal features in the cell differentiation trajectories that include: (i) a peak in single-cell uncertainty during transition states, and in systems with bifurcating differentiation trajectories, each branching point represents a state of high transcriptional uncertainty; (ii) a positive correlation of transcriptional uncertainty with transcriptional burst size and frequency; (iii) an increase in RNA velocity preceding the increase in the cell transcriptional uncertainty. Conclusions: Our findings suggest a possible universal mechanism during the cell differentiation process, in which stem cells engage stochastic exploratory dynamics of gene expression at the start of the cell differentiation by increasing gene transcriptional bursts, and disengage such dynamics once cells have decided on a particular terminal cell identity. Notably, the peak of single-cell transcriptional uncertainty signifies the decision-making point in the cell differentiation process.

Multi-AUV Formation Predictive Control Based on CNN-LSTM under Communication Constraints

For the problem of hydroacoustic communication constraints in multi-AUV leader follower formation, this paper designs a formation control method combining CNN-LSTM prediction and backstepping sliding mode control. First, a feedback linearization method is used to transform the AUV nonlinear model into a second-order integral model; then, the influence of hydroacoustic communication constraints on the multi-AUV formation control problem is analyzed, and a sliding window-based formation prediction control strategy is designed; for the characteristics of AUV motion trajectory with certain temporal order, the CNN-LSTM prediction model is selected to predict the trajectory state of the leader follower and compensate the effect of communication delay on formation control, and combine the backstepping method and sliding mode control to design the formation controller. Finally, the simulation experimental results show that the proposed CNN-LSTM prediction and backstepping sliding mode control can improve the effect of hydroacoustic communication constraints on formation control.

Forecasting tropical cyclone tracks in the northwestern Pacific based on a deep-learning model

Abstract. Tropical cyclones (TCs) are one of the most severe meteorological disasters, making rapid and accurate track forecasts crucial for disaster prevention and mitigation. Because TC tracks are affected by various factors (the steering flow, the thermal structure of the underlying surface, and the atmospheric circulation), their trajectories present highly complex nonlinear behavior. Deep learning has many advantages in simulating nonlinear systems. In this paper, based on deep-learning technology, we explore the movement of TCs in the northwestern Pacific from 1979 to 2021, divided into training (1979–2014), validation (2015–2018), and test sets (2019–2021), and we create 6–72 h TC track forecasts. Only historical trajectory data are used as input for evaluating the forecasts of the following three recurrent neural networks utilized: recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU) models. The GRU approach performed best; to further improve forecast accuracy, a model combining GRU and a convolutional neural network (CNN) called GRU_CNN is proposed to capture the characteristics that vary with time. By adding reanalysis data of the steering flow, sea surface temperatures, and geopotential height around the cyclone, we can extract sufficient information on the historical trajectory features and three-dimensional spatial features. The results show that GRU_CNN outperforms other deep-learning models without CNN layers. Furthermore, by analyzing three additional environmental factors through control experiments, it can be concluded that the historical steering flow of TCs plays a key role, especially for short-term predictions within 24 h, while sea surface temperatures and geopotential height can gradually improve the 24–72 h forecast. The average distance errors at 6 and 12 h are 17.22 and 43.90 km, respectively. Compared with the 6 and 12 h forecast results (27.57 and 59.09 km) of the Central Meteorological Observatory, the model proposed herein is suitable for short-term forecasting of TC tracks.