Search

Location-based services have important applications in IoVs, and especially the destination-related applications have attracted more and more attention. Due to privacy consideration or operation convenience, people hesitate to share destinations to the public. Thus, these applications need to predict the destinations of moving vehicles in order to provide better services. Some existing works on destination prediction suffer from the dataset sparsity problem or the model inaccuracy problem. To overcome these problems, a Segmented Trajectory Clustering-Based Destination Prediction mechanism is proposed in this paper. First, each original trajectory is segmented to several key sub-trajectories, with the DP-based trajectory segmentation algorithm. Then, all the sub-trajectories are clustered based on the average nearest point pair distance to reveal the common characteristics or similar tracks. Finally, a deep neural network-based model is utilized to predict destinations, according to the history trajectories. Extensive simulations are conducted for destination predictions. Simulation results show that our proposed method can predict destinations with acceptable average errors and outperform other methods in most of the cases.

Indoor positioning data reflects human mobility in indoor spaces. Revealing patterns of indoor trajectories may help us understand human indoor mobility. Clustering methods, which are based on the measurement of similarity between trajectories, are important tools for identifying those patterns. However, due to the specific characteristics of indoor trajectory data, it is difficult for clustering methods to measure the similarity between trajectories. These characteristics are manifested in two aspects. The first is that the nodes of trajectories may have clear semantic attributes, for example, in a shopping mall, the node of a trajectory may contain information such as the store type and visit duration time, which may imply a customer’s interest in certain brands. The semantic information can only be obtained when the position precision is sufficiently high so that the relationship between the customer and the store can be determined, which is difficult to realize for outdoor positioning, either using GPS or mobile base station, due to the relatively large positioning error. If the tendencies of customers are to be considered, the similarity of geometrical morphology does not reflect the real similarity between trajectories. The second characteristic is the complex spatial shapes of indoor trajectory caused by indoor environments, which include elements such as closed spaces, multiple obstacles and longitudinal extensions. To deal with these challenges caused by indoor trajectories, in this article we proposed a new method called E-DBSCAN, which extended DBSCAN to trajectory clustering of indoor positioning data. First, the indoor location data were transformed into a sequence of residence points with rich semantic information, such as the type of store customer visited, stay time and spatial location of store. Second, a Weighted Edit Distance algorithm was proposed to measure the similarity of the trajectories. Then, an experiment was conducted to verify the correctness of E-DBSCAN using five days of positioning data in a shopping mall, and five shopping behavior patterns were identified and potential explanations were proposed. In addition, a comparison was conducted among E-DBSCAN, the k-means and DBSCAN algorithms. The experimental results showed that the proposed method can discover customers’ behavioral pattern in indoor environments effectively.

The aircraft trajectory clustering analysis in the terminal airspace is conducive to determining the representative route structure of the arrival and departure trajectory and extracting their typical patterns, which is important for air traffic management such as airspace structure optimization, trajectory planning, and trajectory prediction. However, the current clustering methods perform poorly due to the large flight traffic, high density, and complex airspace structure in the terminal airspace. In recent years, the continuous development of Deep Learning has demonstrated its powerful ability to extract internal potential features of large dataset. Therefore, this paper mainly tries a deep trajectory clustering method based on deep autoencoder (DAE). To this end, this paper proposes a trajectory clustering method based on deep autoencoder (DAE) and Gaussian mixture model (GMM) to mine the prevailing traffic flow patterns in the terminal airspace. The DAE is trained to extract feature representations from historical high-dimensional trajectory data. Subsequently, the output of DAE is input into GMM for clustering. This paper takes the terminal airspace of Guangzhou Baiyun International Airport in China as a case to verify the proposed method. Through the direct visualization and dimensionality reduction visualization of the clustering results, it is found that the traffic flow patterns identified by the clustering method in this paper are intuitive and separable.

The distribution of passively drifting particles within highly turbulent flows is a classic problem in marine sciences. The use of trajectory clustering on huge amounts of simulated marine trajectory data to identify main pathways of drifting particles has not been widely investigated from a data science perspective yet. In this paper, we propose a fast and computationally light method to efficiently identify main pathways in large amounts of trajectory data. It aims at overcoming some of the issues of probabilistic maps and existing trajectory clustering approaches. Our approach is evaluated against simulated larvae dispersion data based on a real-world model that have been produced as part of work in the marine science domain.

International audience; In the context of the surveillance of the maritime traffic, a major challenge is the automatic identification of traffic flows from a set of observed trajectories, in order to derive good management measures or to detect abnormal or illegal behaviours for example. In this paper, we propose a new modelling framework to cluster sequences of a large amount of trajectories recorded at potentially irregular frequencies. The model is specified within a continuous time framework, being robust to irregular sampling in records and accounting for possible heterogeneous movement patterns within a single trajectory. It partitions a trajectory into sub-trajectories, or movement modes, allowing a clustering of both individuals' movement patterns and trajectories. The clustering is performed using non parametric Bayesian methods, namely the hierarchical Dirichlet process, and considers a stochastic variational inference to estimate the model's parameters, hence providing a scalable method in an easy-to-distribute framework. Performance is assessed on both simulated data and on our motivational large trajectory dataset from the Automatic Identification System (AIS), used to monitor the world maritime traffic: the clusters represent significant, atomic motion-patterns, making the model informative for stakeholders.

Intelligent transportation brings huge benefits to humans’ life and Industrial production in terms of vehicle control and traffic management. Now, the development of edge-cloud computing has once again promoted intelligent transportation into a new era. However, the development of intelligent transportation inevitably produces a large amount of data, which brings new challenges to data privacy protection and security. In this paper, we propose to develop an improved trajectory prediction framework based on the self-adaptive trajectory prediction model (SATP), which could significantly enhance traffic safety in transportation systems. The proposed framework is capable of guaranteeing the accurate trajectory prediction of moving target under different application scenarios. In particular, to reduce the size of original trajectory point data collected by sensors, the angle change and minimum description length (MDL) principle are first combined to remove the redundant points in raw trajectories. The obtained points can then be reduced for model using the two-step clustering method. To further enhance the prediction performance, we add the “self-transfer” to the original model to solve the problems that the state of original SATP model may be discontinuous. Furthermore, we propose to develop a trajectory complementation method based on Bezier curve to improve the prediction accuracy. Finally, by comparing the two-step clustering method with the commonly-used SinglePass and density-based clustering method (DBCM) algorithms, the proposed two-step clustering policy greatly reduce the time cost of clustering. At the same time, by comparing the improved SATP model with the original model, the results show that the improved SATP method can greatly improve the speed of prediction model.

Various spatio-temporal clustering methods have been proposed to detect groups of jointly moving objects in space and time. However, such spatio-temporal clustering methods are rarely compared against each other to evaluate their performance in discovering moving clusters. Hence, in this work, we present a spatio-temporal clustering benchmark for the field of collective animal behavior. Our reproducible benchmark proposes synthetic datasets with ground truth and scalable implementations of spatio-temporal clustering methods. The benchmark reveals that temporal extensions of standard clustering algorithms are inherently useful for the scalable detection of moving clusters in collective animal behavior. published

Semen analysis is currently performed by using two techniques. Visual assessment technique is manual observation based technique and strongly depends on the experiences of the observer. Therefore, the reliability of the results is skeptical. On the other hand, computer based expert systems are more consistent and reliable. However, they are very expensive systems, therefore, cannot be utilized in many laboratories. In this study, we proposed a hybrid expert system utilizing visual assessment environment with the computerized analyzing part to eliminate the disadvantages of each technique. In the proposed system, smartphone based data acquisition approach is used to provide more modular and practical expert system for the sperm analysis. The records are, then, transferred to the server to analyze by developed software. In this analyzing software, we proposed multi-stage hybrid analyzing approach in terms of video stabilization, sperm concentration and motility analysis. Each video was initially fixed by the Speed Up Robust Features based matching technique. Then, Kalman Filter was employed for sperm tracking. After tracking step, trajectories have been divided into 3 s length to prevent possible incorrect assignments due to sudden changes in sperm motions. In the experimental tests, we combined all trajectories obtained from a total of 18 videos of 6 different subjects. We clustered a total of 89438 trajectories into 4 cluster as fast progressive, progressive, non-progressive and immotile according to extracted seven features. In order to compare the results, we also analyzed the same semen sample in another expert system, SQA-Vision. The difference was measured 3.4% and 4.8% in the determination of total and motile sperm concentration, and 2.1%, 7.4%, 5.3% for progressive, non-progressive and immotile movement type analysis respectively. The significance and impact of the proposed system are capability of reporting more detailed results in a variety of situations and having more advantages than any expert systems utilized for sperm analysis in terms of portability, cost and modularity. Additionally, to the best of our knowledge, this is the first study reporting use of the smartphone in an expert system for the sperm analysis in terms of data acquisition and result reporting. © 2021 Elsevier Ltd

In order to better mine information from the data of automatic identification system (AIS) and scientifically perceive the water traffic situation, several common clustering algorithms, such as K-means algorithm and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, are studied and analyzed, and the advantages and disadvantages of each algorithm and applicable scenarios are compared. Taking the actual ship's AIS trajectory data as an example, each algorithm is used to verify its characteristics, which provides convenience for further information mining of trajectory data.

GPS (Global Positioning System) trajectories with low sampling rates are prevalent in many applications. However, current map matching methods do not perform well for low-sampling-rate GPS trajectories due to the large uncertainty between consecutive GPS points. In this paper, a collaborative map matching method (CMM) is proposed for low-sampling-rate GPS trajectories. CMM processes GPS trajectories in batches. First, it groups similar GPS trajectories into clusters and then supplements the missing information by resampling. A collaborative GPS trajectory is then extracted for each cluster and matched to the road network, based on longest common subsequence (LCSS) distance. Experiments are conducted on a real GPS trajectory dataset and a simulated GPS trajectory dataset. The results show that the proposed CMM outperforms the baseline methods in both, effectiveness and efficiency.

In this paper, we present a Big data framework for the pre- diction of streaming trajectory data by exploiting mined patterns of tra- jectories, allowing accurate long-term predictions with low latency. In particular, to meet this goal we follow a two-step methodology. First, we efficiently identify the hidden mobility patterns in an offline manner. Subsequently, the trajectory prediction algorithm exploits these patterns in order to prolong the temporal horizon of useful predictions. The exper- imental study is based on real-world aviation and maritime datasets.

WOS:000451650400002; International audience; It is extremely helpful to be able to partition the thousands of frames produced in molecular dynamics simulations into a limited number of most dissimilar conformations. While robust clustering algorithms are already available to do so, there is a distinct need for an easy-to-use clustering program with complete user control, taking as input a trajectory from any molecular dynamics (MD) package and outputting an intuitive display of results with plots allowing at-a-glance analysis. We present TTClust (for Trusty Trajectory Clustering), a python program that uses the MDTraj package to fill this need.

Increasing geotagged social media data has become a potential repository used to find common trajectory patterns. Various spatial trajectory behaviors have been studied in previous work. In this pa...

Automatic identification systems (AISs) serve as a complement to radar systems, and they have been installed and widely used onboard ships to identify targets and improve navigational safety based on a very high-frequency data communication scheme. AIS networks have also been constructed to enhance traffic safety and improve management in main harbors. AISs record vessel trajectories, which include rich traffic flow information, and they represent the foundation for identifying locations and analyzing motion features. However, the inclusion of redundant information will reduce the accuracy of trajectory clustering; therefore, trajectory data mining has become an important research direction. To extract useful information with high accuracy and low computational costs, trajectory mapping and clustering methods are combined in this paper to explore big data acquired from AISs. In particular, the merge distance (MD) is used to measure the similarities between different trajectories, and multidimensional scaling (MDS) is adopted to construct a suitable low-dimensional spatial expression of the similarities between trajectories. An improved density-based spatial clustering of applications with noise (DBSCAN) algorithm is then proposed to cluster spatial points to acquire the optimal cluster. A fusion of the MD, MDS, and improved DBSCAN algorithms can identify the course of trajectories and attain a better clustering performance. Experiments are conducted using a real AIS trajectory database for a bridge area waterway and the Mississippi River to verify the effectiveness of the proposed method. The experiments also show that the newly proposed method presents a higher accuracy than classical ones, such as spectral clustering and affinity propagation clustering.

In this paper, we propose an automatic route design method based on simple recurrent unit (SRU) and automatic identification system (AIS) data. Laplacian eigen maps and Gaussian kernel functions are used to compress the AIS data and extract the turning points of all ships. Fuzzy adaptive density-based spatial clustering of applications with noise (FA-DBSCAN) technique is used to cluster the turning points obtained at the preprocessing stage to obtain the turning region. Optimal turn region matching is used to connect the turning regions of similar routes, and the SRU neural network algorithm is used to learn the relationship between different types, sizes, and drafts of ships in each turning region; extract the feature-turning points; and obtain the recommended coastal routes, speed, and course of each type of ship. In the experimental stage, a large variety of AIS data from two sea areas are used to compare and analyze the designed route and real-ship data through LSTM and SRU experiments. The results show that the SRU algorithm improves the training speed and accuracy in comparison to LSTM, while the generated automatic route meets the requirements of navigation practice.

It has become a new research direction to use process mining technology to mine and analyze all kinds of data generated during shipbuilding. The classification of hull segments into different clusters according to some properties in advance can make the excavation results more specific. In this paper, the process examples in ship construction are divided into different clusters based on the cohesive hierarchical clustering algorithm. Firstly, this paper introduces the advantages and disadvantages of several main clustering algorithms, selects the clustering algorithm most suitable for segmented outfield logistics, establishes the mathematical model of segmented outfield logistics process trajectory clustering, and defines the appropriate feature vectors. Euclidean distance, Hamming distance, Jekard distance and cosine distance were used to calculate the similarity distance between process instances, and the concepts of chain, single chain and group average were added to select the appropriate similarity distance between clusters. An evaluation method of clustering results based on coutour coefficient is introducedwhich can effectively evaluate the clustering results of the logistics process trajectory during segmented remote operations. Finally, the feasibility and effectiveness of the proposed algorithm are verified by experiments.

Maritime anomaly detection is a key technique in intelligent vessel traffic surveillance systems and implementation of maritime situational awareness. In this paper, we propose a method which combines vessel trajectory clustering and Naïve Bayes classifier to detect anomalous vessel behaviour in the maritime surveillance system. A similarity measurement between vessel trajectories is designed based on the spatial and directional characteristics of Automatic Identification System (AIS) data, then the method of hierarchical and k-medoids clustering are applied to model and learn the typical vessel sailing pattern within harbour waters. The Naïve Bayes classifier of vessel behaviour is built to classify and detect anomalous vessel behaviour. The proposed method has been tested and validated on the vessel trajectories from AIS data within the waters of Xiamen Bay and Chengsanjiao, China. The results indicate that the proposed method is effective and helpful, thus enhancing maritime situational awareness in coastal waters.

Center-based clustering, in particular k-means clustering, is frequently used for point data. Its advantages include that the resulting clustering is often easy to interpret and that the cluster centers provide a compact representation of the data. Recent theoretical advances have been made in generalizing center-based clustering to trajectory data. Building upon these theoretical results, we present practical algorithms for center-based trajectory clustering.

Trajectory clustering and path modelling are two core tasks in intelligent transport systems with a wide range of applications, from modeling drivers’ behavior to traffic monitoring of road intersections. Traditional trajectory analysis considers them as separate tasks, where the system first clusters the trajectories into a known number of clusters and then the path taken in each cluster is modelled. However, such a hierarchy does not allow the knowledge of the path model to be used to improve the performance of trajectory clustering. Based on the distance dependent Chinese restaurant process (DDCRP), a trajectory analysis system that simultaneously performs trajectory clustering and path modelling was proposed. Unlike most traditional approaches where the number of clusters should be known, the proposed method decides the number of clusters automatically. The proposed algorithm was tested on two publicly available trajectory datasets, and the experimental results recorded better performance and considerable improvement in both datasets for the task of trajectory clustering compared to traditional approaches. The study proved that the proposed method is an appropriate candidate to be used for trajectory clustering and path modelling.

The Automatic Identification System (AIS) of ships provides massive data for maritime transportation management and related researches. Trajectory clustering has been widely used in recent years as a fundamental method of maritime traffic analysis to provide insightful knowledge for traffic management and operation optimization, etc. This paper proposes a ship AIS trajectory clustering method based on Hausdorff distance and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN), which can adaptively cluster ship trajectories with their shape characteristics and has good clustering scalability. On this basis, a re-clustering method is proposed and comprehensive clustering performance metrics are introduced to optimize the clustering results. The AIS data of the estuary waters of the Yangtze River in China has been utilized to conduct a case study and compare the results with three popular clustering methods. Experimental results prove that this method has good clustering results on ship trajectories in complex waters.

Most of traditional trajectory clustering algorithms often cluster similar trajectories from a temporal or spatial perspective. One weak point is that the semantic relationship between the trajectories is ignored. In some cases, trajectories with spatio-temporal similarities may be semantically related, and the negligence of semantic information may result in unreasonable trajectory clustering results. In addition, the existing semantic trajectory clustering algorithms only consider the local semantic relationship between adjacent spatio-temporal trajectories, and the overall global semantic relationship between trajectories is still unknown. Considering the disadvantages of the current trajectory clustering methods, we proposed a novel algorithm for semantic trajectory clustering based on community detection (STCCD) in networks, which can better measure the semantic similarity of trajectories and capture global relationship among trajectories from the perspective of the network, and can get better trajectory clustering results compared to some traditional and recently proposed methods. Experimental results demonstrate that the proposed method can effectively mine the trajectory clustering information and related knowledge from the semantic trajectory data.

This article presents a statistical engineering approach for clustering aircraft trajectories. The clustering methodology was developed to address the need to incorporate more realistic trajectories in fast time computer simulations used to evaluate an ..

Understanding the dynamic nature of how urban neighbourhoods evolve through time has been a critical issue both in the literature and in public policy practice for decades. Methodological limitations in understanding change across the multiple attribute dimensions that define a neighbourhood, through time and for spatially situated units, have largely reduced empirical analyses to two points in time or for a singular attribute dimension. This paper demonstrates a two-layered approach to classifying neighbourhoods according to their multidimensional, temporal trajectories. The method first projects data onto a two-dimensional output space using a self-organizing map, then constructs temporal trajectories of change across this space and, finally, classifies the resulting trajectories with a k-means algorithm. The resulting typology of neighbourhood trajectories are then mapped in the geographic space to visualize the space–time, multidimensional dynamics. A case study of neighbourhood change from 19...

Wrestling against road unsafety is a mandatory issue that has very serious effect on human health. Therefore, many researches were tackled the vehicle trajectory modeling and measurement to examine the interaction between the driver, the vehicle and the infrastructure in order to identify the safe and unsafe zones of the trajectories. The aim of this study is to determine the different driving behaviors through a real trajectories analysis using unsupervised clustering based on density estimation through the variable kernel estimator. Also, we introduce a new method of data transformation for trajectory data before considering any clustering algorithm.

Anomalous taxi trajectories are those chosen by a small number of drivers that are different from the regular choices of other drivers. These anomalous driving trajectories provide us an opportunity to extract driver or passenger behaviors and monitor adverse urban traffic events. Because various trajectory clustering methods have previously proven to be an effective means to analyze similarities and anomalies within taxi GPS trajectory data, we focus on the problem of detecting anomalous taxi trajectories, and we develop our trajectory clustering method based on the edit distance and hierarchical clustering. To achieve this objective, first, we obtain all the taxi trajectories crossing the same source–destination pairs from taxi trajectories and take these trajectories as clustering objects. Second, an edit distance algorithm is modified to measure the similarity of the trajectories. Then, we distinguish regular trajectories and anomalous trajectories by applying adaptive hierarchical clustering based on an optimal number of clusters. Moreover, we further analyze these anomalous trajectories and discover four anomalous behavior patterns to speculate on the cause of an anomaly based on statistical indicators of time and length. The experimental results show that the proposed method can effectively detect anomalous trajectories and can be used to infer clearly fraudulent driving routes and the occurrence of adverse traffic events.

Quantifying dissimilarities between two trajectories is a challenging yet fundamental task in many trajectory analysis systems. Existing methods are computationally expensive to calculate. We proposed a dissimilarity measure estimate for trajectory data by using deep learning methodology. One advantage of the proposed method is that it can get executed on GPU, which can significantly reduce the execution time for processing large number of data. The proposed network is trained using synthetic data. A simulator to generate synthetic trajectories is proposed. We used a publicly available dataset to evaluate the proposed method for the task of trajectory clustering. Our experiments show the performance of our proposed method is comparable with other well-known dissimilarity measures while it is substantially faster to compute.

Analyzing trajectory data plays an important role in practical applications, and clustering is one of the most widely used techniques for this task. The clustering approach based on information bottleneck (IB) principle has shown its effectiveness for trajectory data, in which a predefined number of the clusters and an explicit distance measure between trajectories are not required. However, presenting directly the final results of IB clustering gives no clear idea of both trajectory data and clustering process. Visual analytics actually provides a powerful methodology to address this issue. In this paper, we present an interactive visual analytics prototype called IBVis to supply an expressive investigation of IB-based trajectory clustering. IBVis provides various views to graphically present the key components of IB and the current clustering results. Rich user interactions drive different views work together, so as to monitor and steer the clustering procedure and to refine the results. In this way, insights on how to make better use of IB for different featured trajectory data can be gained for users, leading to better analyzing and understanding trajectory data. The applicability of IBVis has been evidenced in usage scenarios. In addition, the conducted user study shows IBVis is well designed and helpful for users This work has been funded by Natural Science Foundation of China (61179067, 61771335) and Spanish ministry MINECO (TIN2016-75866-C3-3-R)

A method of trajectory clustering based on decision graph and data field is proposed in this paper. The method utilizes data field to describe spatial distribution of trajectory points, and uses decision graph to discover cluster centres. It can automatically determine cluster parameters and is suitable to trajectory clustering. The method is applied to trajectory clustering on taxi trajectory data, which are on the holiday (May 1st, 2014), weekday (Wednesday, May 7th, 2014) and weekend (Saturday, May 10th, 2014) respectively, in Wuhan City, China. The hotspots in four hours (8:00-9:00, 12:00-13:00, 18:00-19:00 and 23:00-24:00) for three days are discovered and visualized in heat maps. In the future, we will further research the spatiotemporal distribution and laws of these hotspots, and use more data to carry out the experiments.

The development of location-acquisition technologies has led to the emergence of massive spatial trajectory data. Recently many researchers have focused on techniques related to processing, managing and mining trajectories to extract knowledge and predictions useful for various applications. One of the first steps in processing trajectories is clustering and classification. Hash-based methods have been used and showed to be successful in clustering the large trajectory datasets. In this paper, we specifically focus on methods based on two types of hash functions: Locality-Sensitive and Distance-Based hash functions and compare them in terms of accuracy and bucket size balance. Our results suggest that, in comparison to Distance- Based hashes, Locality-Sensitive hashes results in higher accuracy but not necessarily higher bucket balance.

Clustering analysis is one of the most important issues in trajectory data mining. Trajectory clustering can be widely applied in the detection of hotspots, mobile pattern analysis, urban transportation control, and hurricane prediction, etc. To obtain good clustering performance, the existing trajectory clustering approaches need to input one or more parameters to calibrate the optimal values, which results in a heavy workload and computational complexity. To realize adaptive parameter calibration and reduce the workload of trajectory clustering, an adaptive trajectory clustering approach based on the grid and density (ATCGD) is proposed in this paper. The proposed ATCGD approach includes three parts: partition, mapping, and clustering. In the partition phase, ATCGD applies the average angular difference-based MDL (AD-MDL) partition method to ensure the partition accuracy on the premise that it decreases the number of the segments after the partition. During the mapping procedure, the partitioned segments are mapped into the corresponding cells, and the mapping relationship between the segments and the cells are stored. In the clustering phase, adopting the DBSCAN-based method, the segments in the cells are clustered on the basis of the calibrated values of parameters from the mapping procedure. The extensive experiments indicate that although the results of the adaptive parameter calibration are not optimal, in most cases, the difference between the adaptive calibration and the optimal is less than 5%, while the run time of clustering can reduce about 95%, compared with the TRACLUS algorithm.