Spatio-temporal Trajectories Research Articles

Wisdom of Crowds: A Human-Machine-Things Cooperative Scheduling Method for Heterogeneous Mobile Crowdsensing

Relying on the development of crowdsourcing ideas and mobile crowd sensing (MCS) technology, many tasks that originally required a lot of manpower and material resources have been solved efficiently. However, with the development of urbanization, the traditional MCS systems have gradually been unable to cope with the demands of massive sensing tasks and high spatio-temporal sensing coverage. The challenges are as follows: 1) The scarcity of participants and the limitation of human motion rules lead to the existence of spatio-temporal blind spots in the process of collecting sensing data; 2) The single type of participants limits the sensing ability of the system and the types of data that can be collected, which affects sensing precision and quality. With the emergence of various intelligent sensing terminals in the city, the heterogeneous crowd sensing that integrates human, machine and things participants has become a new generation of sensing mode. In the spatio-temporal related sensing scenarioes, this article designs a new human-machine-things cooperative scheduling (HMT-CS) algorithm framework by comprehensively considering the diverse sensing skills, spatio-temporal trajectories, sensing costs of heterogeneous participants and system total budget constraints. The algorithm can match suitable heterogeneous participants for each task, which greatly improves the sensing quality, sensing fairness and overall utility of heterogeneous MCS systems. We combined multiple public real urban datasets to conduct an in-depth comparative analysis and comprehensive evaluation of the algorithm, and the results show that our method is superior to other baselines in all indicators.

Unraveling the spatio-temporal trajectories of urban growth in Asansol city, West Bengal: A geospatial exploration of the emerging urbanlandscape

The rapid urban growth of Asansol City has led to the rise of unplanned built-up areas, disrupting natural land covers and posing challenges to sustainable resource management. Hence, this study aims to quantify spatio-temporal trajectories of urban growth in Asansol City during 1991–2021, using integrated remote sensing and GIS-based techniques. Landsat 5 TM and 8 OLI/TIRS satellite imageries were used to delineate built-up and non-built-up areas using a random forest machine-learning algorithm. The study utilized the gradient approach, urban sprawl typologies, urban expansion indices, shannon’s entropy, and landscape fragmentation metrics to analyze the pattern, direction, intensity and dynamics of urban expansion in a space-time context. The findings showed that built-up growth increased significantly from 25.49 sq. km. to 57.18 sq. km. between 1991 and 2021, with the highest growth observed in the westward direction and within 3 km from the CBD. The study highlighted the prevalence of edge expansion and scatter development as dominant typologies of urban growth. Urban expansion indices, shannon's entropy and landscape fragmentation metrics analysis revealed the increasing urban sprawl towards the periphery and the formation of clustered built-up areas near the CBD. The outcomes of this study provide a basis for sustainable urban development by quantifying spatio-temporal trajectories and highlighting challenges from unrestrained growth of Asansol municipal corporation.

Delineating three distinct spatiotemporal patterns of brain atrophy in Parkinson's disease.

The clinical manifestation of Parkinson's disease exhibits significant heterogeneity in the prevalence of non-motor symptoms and the rate of progression of motor symptoms, suggesting that Parkinson's disease can be classified into distinct subtypes. In this study, we aimed to explore this heterogeneity by identifying a set of subtypes with distinct patterns of spatiotemporal trajectories of neurodegeneration. We applied Subtype and Stage Inference (SuStaIn), an unsupervised machine learning algorithm that combined disease progression modelling with clustering methods, to cortical and subcortical neurodegeneration visible on 3 T structural MRI of a large cross-sectional sample of 504 patients and 279 healthy controls. Serial longitudinal data were available for a subset of 178 patients at the 2-year follow-up and for 140 patients at the 4-year follow-up. In a subset of 210 patients, concomitant Alzheimer's disease pathology was assessed by evaluating amyloid-β concentrations in the CSF or via the amyloid-specific radiotracer 18F-flutemetamol with PET. The SuStaIn analysis revealed three distinct subtypes, each characterized by unique patterns of spatiotemporal evolution of brain atrophy: neocortical, limbic and brainstem. In the neocortical subtype, a reduction in brain volume occurred in the frontal and parietal cortices in the earliest disease stage and progressed across the entire neocortex during the early stage, although with relative sparing of the striatum, pallidum, accumbens area and brainstem. The limbic subtype represented comparative regional vulnerability, which was characterized by early volume loss in the amygdala, accumbens area, striatum and temporal cortex, subsequently spreading to the parietal and frontal cortices across disease stage. The brainstem subtype showed gradual rostral progression from the brainstem extending to the amygdala and hippocampus, followed by the temporal and other cortices. Longitudinal MRI data confirmed that 77.8% of participants at the 2-year follow-up and 84.0% at the 4-year follow-up were assigned to subtypes consistent with estimates from the cross-sectional data. This three-subtype model aligned with empirically proposed subtypes based on age at onset, because the neocortical subtype demonstrated characteristics similar to those found in the old-onset phenotype, including older onset and cognitive decline symptoms (P < 0.05). Moreover, the subtypes correspond to the three categories of the neuropathological consensus criteria for symptomatic patients with Lewy pathology, proposing neocortex-, limbic- and brainstem-predominant patterns as different subgroups of α-synuclein distributions. Among the subtypes, the prevalence of biomarker evidence of amyloid-β pathology was comparable. Upon validation, the subtype model might be applied to individual cases, potentially serving as a biomarker to track disease progression and predict temporal evolution.

Multi-Step Continuous Decision Making and Planning in Uncertain Dynamic Scenarios Through Parallel Spatio-Temporal Trajectory Searching

Multi-Step Continuous Decision Making and Planning in Uncertain Dynamic Scenarios Through Parallel Spatio-Temporal Trajectory Searching

STdi4DMPC: Distributed Model Predictive Control for Connected and Automated Truck Platoon With Mixed Traffic Flow Based on Spatiotemporal Trajectory Prediction

STdi4DMPC: Distributed Model Predictive Control for Connected and Automated Truck Platoon With Mixed Traffic Flow Based on Spatiotemporal Trajectory Prediction

Hierarchical Semi-Supervised Approach for Classifying Activities of Workers Utilising Indoor Trajectory Data

Activity recognition refers to the process of automatically identifying or interpreting activities of objects based on the data captured from different sensing devices. While previous research on indoor activity recognition predominantly relies on visual data like images or video recordings, we present a novel approach based on spatiotemporal trajectory data recorded by IoT based sensors. The proposed approach is tailored for indoor manufacturing applications leveraging trajectory partitioning, hierarchical clustering, and convolutional neural networks. Moreover, a vast majority of activity recognition models that have been used in different industrial settings are supervised methods requiring large manually labelled datasets to be collected. This manual annotation process is unwieldly and labour-intensive, and hence, often infeasible to deploy for practical applications. In contrast, our proposed activity recognition approach is semi-supervised meaning it can be trained with far less labelled data; significantly reducing the effort and costs associated with the manual annotation process. The proposed approach is evaluated using two indoor trajectory datasets related to different manufacturing assembly processes. Experimental results demonstrate its effectiveness for activity recognition: the classification accuracy (measured using F-score) varies between 0.81 to 0.95 and 0.88 to 0.92 across indoor trajectory datasets. A comparison with a baseline model indicates that it achieves up to a 18% improvement in classification accuracy. Furthermore, the classification results enable insights into factory floor states, aiding in decision-making for operational efficiency and resource allocation.

Diagnosing Dyslexia in Early School-Aged Children Using the LSTM Network and Eye Tracking Technology

Dyslexia, often referred to as a specific reading disability, affects many students around the world. It is a neurological disorder that affects the ability to recognise words, and it causes difficulties in writing and reading comprehension. Previous computer-based methods for the automatic detection of dyslexia in children have had low efficiency due to the complexity of the test administration process and the low measurement reliability of the attention measures used. This paper proposes the use of a student’s mobile device to record the spatio-temporal trajectory of attention, which is then analysed by deep neural network long short-term memory (LSTM). The study involved 145 participants (66 girls and 79 boys), all of whom were children aged 9 years. The input signal for the neural network consisted of recorded observation sessions, which were packets containing the child’s spatio-temporal attention trajectories generated during task performance. The training set was developed using stimuli from Benton tests and an expert opinion from a specialist in early childhood psychology. The coefficients of determination of R2∼0.992 were obtained for the proposed model, giving an accuracy of 97.7% for the test set. The ease of implementation of this approach in school settings and its non-stressful nature make it suitable for use with children of different ages and developmental stages, including those who have not yet learned to read. This enables early intervention, which is essential for effective educational and emotional support for children with dyslexia.

Spatiotemporal trajectory of energy efficiency in the Guangdong-Hong Kong-Macao Greater Bay Area and implications on the route of economic transformation.

The Guangdong-Hong Kong-Macao Greater Bay Area has attracted attention for its extraordinary pace of economic development and is considered to be leading the way in China's transformation from a manufacturing to an innovation cluster. However, due to rapid economic expansion and rapid urbanization, the Great Bay Area still struggles with low energy efficiency and environmental degradation, which has slowed down the pace of development. Therefore, in order to alleviate energy pressure, promote the country's sustainable development and gain a competitive advantage in the global market, researching energy efficiency and improving energy utilization efficiency is crucial. In this study, macro-level energy efficiency indicators are constructed using energy consumption data from various cities in the Greater Bay Area for the period from 2000 to 2020, and the spatio-temporal evolution of energy efficiency is analysed. The results show that all cities in the Greater Bay Area experienced an increasing trend in energy efficiency from 2000 to 2019, with significant variation in growth rates and magnitudes between cities. Compared to the nine cities in Guangdong province, Hong Kong and Macao exhibited significantly superior energy efficiency, with Foshan recording the highest growth rate of 14%. In 2020, most cities experienced a decline in energy efficiency due to the COVID-19 pandemic, with Macao experiencing the greatest decrease at 57%. Hong Kong and Macao are both in the "low consumption and high efficiency" target region, while Guangzhou, Shenzhen and Zhuhai are consistently in the "both high" region. Changes in the industrial upgrading index correspond significantly with changes in energy efficiency trajectories, with the transition from primary to secondary and tertiary industries playing a more substantial role. There is no significant association found between the strength of environmental regulation and changes in energy efficiency. The study's findings indicate that the most effective way to achieve economic transformation in the majority of China's regions is to combine adequate environmental legislation with industrial structural adjustment.

Reconstructing Spatiotemporal Trajectories of Visual Object Memories in the Human Brain.

How the human brain reconstructs, step-by-step, the core elements of past experiences is still unclear. Here, we map the spatiotemporal trajectories along which visual object memories are reconstructed during associative recall. Specifically, we inquire whether retrieval reinstates feature representations in a copy-like but reversed direction with respect to the initial perceptual experience, or alternatively, this reconstruction involves format transformations and regions beyond initial perception. Participants from two cohorts studied new associations between verbs and randomly paired object images, and subsequently recalled the objects when presented with the corresponding verb cue. We first analyze multivariate fMRI patterns to map where in the brain high- and low-level object features can be decoded during perception and retrieval, showing that retrieval is dominated by conceptual features, represented in comparatively late visual and parietal areas. A separately acquired EEG dataset is then used to track the temporal evolution of the reactivated patterns using similarity-based EEG-fMRI fusion. This fusion suggests that memory reconstruction proceeds from anterior frontotemporal to posterior occipital and parietal regions, in line with a conceptual-to-perceptual gradient but only partly following the same trajectories as during perception. Specifically, a linear regression statistically confirms that the sequential activation of ventral visual stream regions is reversed between image perception and retrieval. The fusion analysis also suggests an information relay to frontoparietal areas late during retrieval. Together, the results shed light onto the temporal dynamics of memory recall and the transformations that the information undergoes between the initial experience and its later reconstruction from memory.

Recruited atypical Ly6G+ macrophages license alveolar regeneration after lung injury.

The lung is constantly exposed to airborne pathogens and particles that can cause alveolar damage. Hence, appropriate repair responses are essential for gas exchange and life. Here, we deciphered the spatiotemporal trajectory and function of an atypical population of macrophages after lung injury. Post-influenza A virus (IAV) infection, short-lived monocyte-derived Ly6G-expressing macrophages (Ly6G+ Macs) were recruited to the alveoli of lung perilesional areas. Ly6G+ Macs engulfed immune cells, exhibited a high metabolic potential, and clustered with alveolar type 2 epithelial cells (AT2s) in zones of active epithelial regeneration. Ly6G+ Macs were partially dependent on granulocyte-macrophage colony-stimulating factor and interleukin-4 receptor signaling and were essential for AT2-dependent alveolar regeneration. Similar macrophages were recruited in other models of injury and in the airspaces of lungs from patients with suspected pneumonia. This study identifies perilesional alveolar Ly6G+ Macs as a spatially restricted, short-lived macrophage subset promoting epithelial regeneration postinjury, thus representing an attractive therapeutic target for treating lung damage.

STTraj2Vec: A spatio-temporal trajectory representation learning approach

Computing trajectory similarity plays a critical role in various spatio-temporal applications that involve trajectory analysis. In recent years, trajectory representation learning has been extensively studied and applied for trajectory similarity calculation. However the majority of existing algorithms for trajectory representation generally have two problems. The first problem is the emphasis of spatial similarity over temporal similarity, and even to discard the temporal dimension of spatio-temporal trajectories. As a result, the outputs of these approaches cannot fully represent the similarity of spatio-temporal trajectories. The second problem is the introduction of additional information, such as the topology of the road network, which increases the uncertainty of capturing the spatio-temporal correlation of trajectories and prevents their application in scenarios where it is difficult to obtain such information. This poses a significant challenge when dealing with complex and time-varying traffic networks. This paper proposes a novel method, named STTraj2Vec (Spatio-temporal Trajectory 2 Vector), which relies only on spatio-temporal trajectories to capture their similarity without spatio-temporal separation. This takes into account the whole spatio-temporal trajectory information. In this method, an extended clustering algorithm is introduced, which maps the trajectory into a point-region quadtree, and constructs a time-varying virtual network structure based on the point-region quadtree. In this method, an extended clustering algorithm is introduced, which maps each trajectory into a point-region quadtree, and then completes density clustering through the adjacency relation of leaf nodes to construct a time-varying virtual network structure. This virtual network structure not only considers the spatial proximity, but also the time, so as to reflect the spatio-temporal characteristics of the trajectory more accurately. Then, a novel spatially and temporally integrated random walk algorithm is designed, which carries out spatiotemporal random walk on the virtual network structure, to capture the spatiotemporal characteristics of the trajectory, and thus obtains the representation of all nodes in the virtual network. Furthermore, each trajectory is converted into a sequence of vectors on the virtual road network according to the latitude, longitude, and time of the trajectory points. Finally, based on these node representations and trajectories, a transformer model with ranking loss is employed to capture the distinct contributions of the various locations and times to the similarity computation and encode each sequence of vectors into target vectors. Experiments on two public datasets show that STTraj2Vec is superior to the state-of-the-art methods in terms of effectiveness for top-k trajectory similarity search and trajectory clustering, while exhibiting low parameter sensitivity and high model robustness.

A novel method for ship carbon emissions prediction under the influence of emergency events

Accurate prediction of ship emissions aids to ensure maritime sustainability but encounters challenges, such as the absence of high-precision and high-resolution databases, complex nonlinear relationships, and vulnerability to emergency events. This study addresses these issues by developing novel solutions: a novel Spatiotemporal Trajectory Search Algorithm (STSA) based on Automatic Identification System (AIS) data; a rolling structure-based Seasonal-Trend decomposition based on the Loess technique (STL); a modular deep learning model based on Structured Components, stacked-Long short-term memory, Convolutional neural networks and Comprehensive forecasting module (SCLCC). Based on these solutions, a case study using pre and post-COVID-19 AIS data demonstrates model reliability and the pandemic’s impact on ship emissions. Numerical experiments reveal that the STSA algorithm significantly outperforms the conventional identification standard in terms of accuracy of ship navigation state identification; the SCLCC model exhibits greater resistance against emergency events and excels in comprehensively capturing global information, thus yielding higher accurate prediction results. This study sheds light on the changing dynamics of maritime transport and its impacts on carbon emissions.

Model for generating data from navigation sensors for assessing the spatial position of objects

When selecting or developing new algorithms for assessing the spatial position of objects based on data from consumer navigation equipment (CNA) of global navigation satellite systems (GNSS) and data from inertial MEMS modules, the task of generating test model input data that meets certain conditions arises. Such conditions include, for example, the requirements for limited time increments of elements of spatio-temporal trajectories and ease of formation of their characteristic sections. The characteristic sections of spatio-temporal trajectories can be sections of a stationary position – sections of “Rest” or sections of rectilinear movement. The importance of forming these areas is due to the need to test the potential capabilities of compared or developed algorithms for assessing the spatial position of objects to ensure an improvement in their accuracy characteristics in the presence of such areas in various conditions. A data generation model is proposed for comparing algorithms for estimating the spatial position of objects, which ensures that the time increments of elements of spatio-temporal trajectories are limited in time and the simple formation of their characteristic sections is met. The model is based on the selection of a set of specified parameters that would allow, on the one hand, to form characteristic sections of spatio-temporal trajectories, and, on the other hand, to obtain model output data of NAP GNSS and inertial MEMS modules. The selected set of specified model parameters is determined through a set of analytically specified functions with sequential calculation of their parameters, which is much simpler compared to traditional approaches that involve solving boundary value problems of optimal control with restrictions on the type of control functions or the construction and application of genetic models and algorithms. The use of the developed model makes it possible to generate test model input data for the selection or development of new algorithms for assessing the spatial position of objects, implemented in devices that include CNA of GNSS and inertial MEMS modules and produce results both in real time and in delayed time. The effectiveness of the proposed solution is confirmed by the criterion of suitability under the considered conditions.

Challenges of spatio-temporal trajectory datasets

ABSTRACT The rapid evolution of wireless location technologies has significantly increased the availability of mobility data, particularly spatio-temporal trajectory data, detailing object movements and locations over time. This data holds diverse applications such as predicting travel patterns, optimizing routes, analysing social interactions, and managing urban resources. However, leveraging trajectory datasets presents challenges, including data heterogeneity, volume, velocity requiring real-time processing, privacy concerns with sensitive information, and regulatory compliance. Traditional systematic reviews of literature may not fully capture industry challenges, as professionals often do not publish research. To address this gap, industry expert input is vital. Collaborating with academia, we propose using focus group discussions to explore these challenges comprehensively. Focus groups offer a qualitative platform for professionals and academics to identify practical issues and gaps in the literature. This combined approach will inform technological advancements in creating and utilizing spatio-temporal datasets. Additionally, integrating insights from focus groups with a literature review ensures a thorough analysis of data challenges. This methodology aims to provide a holistic understanding and foster innovation in managing and exploiting trajectory data effectively.

Endoplasmic Reticulum and Mitochondrial Calcium Handling Dynamically Shape Slow Afterhyperpolarizations in Vasopressin Magnocellular Neurons.

Many neurons including vasopressin (VP) magnocellular neurosecretory cells (MNCs) of the hypothalamic supraoptic nucleus (SON) generate afterhyperpolarizations (AHPs) during spiking to slow firing, a phenomenon known as spike frequency adaptation. The AHP is underlain by Ca2+-activated K+ currents, and while slow component (sAHP) features are well described, its mechanism remains poorly understood. Previous work demonstrated that Ca2+ influx through N-type Ca2+ channels is a primary source of sAHP activation in SON oxytocin neurons, but no obvious channel coupling was described for VP neurons. Given this, we tested the possibility of an intracellular source of sAHP activation, namely, the Ca2+-handling organelles endoplasmic reticulum (ER) and mitochondria in male and female Wistar rats. We demonstrate that ER Ca2+ depletion greatly inhibits sAHPs without a corresponding decrease in Ca2+ signal. Caffeine sensitized AHP activation by Ca2+ In contrast to ER, disabling mitochondria with CCCP or blocking mitochondria Ca2+ uniporters (MCUs) enhanced sAHP amplitude and duration, implicating mitochondria as a vital buffer for sAHP-activating Ca2+ Block of mitochondria Na+-dependent Ca2+ release via triphenylphosphonium (TPP+) failed to affect sAHPs, indicating that mitochondria Ca2+ does not contribute to sAHP activation. Together, our results suggests that ER Ca2+-induced Ca2+ release activates sAHPs and mitochondria shape the spatiotemporal trajectory of the sAHP via Ca2+ buffering in VP neurons. Overall, this implicates organelle Ca2+, and specifically ER-mitochondria-associated membrane contacts, as an important site of Ca2+ microdomain activity that regulates sAHP signaling pathways. Thus, this site plays a major role in influencing VP firing activity and systemic hormonal release.

Urban Traffic Dominance: A Dynamic Assessment Using Multi-Source Data in Shanghai

This study redefines the evaluation of urban traffic dominance by integrating complex network theory with multi-source spatiotemporal trajectory data, addressing the dynamic nature of various transportation modes, including public transit and shared mobility. Traditional traffic studies, which focus predominantly on static road traffic characteristics, overlook the fluid dynamics integral to urban transport systems. We introduce Relative Weighted Centrality (RWC) as a novel metric for quantifying dynamic traffic dominance, combining it with traditional static metrics to forge a comprehensive traffic dominance evaluation system. The results show the following: (1) Both static and dynamic traffic dominance display core-periphery structures centered around Huangpu District. (2) Dynamically, distinct variations in RWC emerge across different times and transport modes; during the early hours (0:00–6:00), shared bicycles show unique spatial distributions, the subway network experiences a notable decrease in RWC yet maintains its spatial pattern, and taxis exhibit intermediate characteristics. Conversely, the RWC for all modes generally increases during morning (6:00–12:00) and evening (18:00–24:00) peaks, with a pronounced decrease in subway RWC in the latter period. (3) The integration of dynamic evaluations significantly modifies conventional static results, emphasizing the impact of population movements on traffic dominance. This comprehensive analysis provides crucial insights into the strategic management and development of urban traffic infrastructure in Shanghai.

Optimization study of pruning strategy based on KNN trajectory similarity query

With the development of GPS positioning technology, a large amount of spatiotemporal trajectory data has been generated. Due to the complex structure of trajectory data, which has irregular spatial shapes and continuous temporal sequence attributes, querying massive trajectory data poses certain challenges. The pruning strategy of existing trajectory similarity query methods is not very effective. Even after pruning operations, there are still a large number of trajectories that need to undergo distance calculations to confirm whether they are similar trajectories. This paper proposes multiple local pruning optimization schemes, which maximally reduce the number of trajectories in the candidate set. Specifically, it starts with region pruning in the index space, eliminating index spaces with distances greater than the maximum similarity distance from the query trajectory. Then, it performs distance pruning between trajectories, removing trajectories that do not meet the distance conditions. Finally, it adds a termination condition: when the distance between the current index space and the query trajectory is greater than the maximum similarity distance and the number of trajectories in the result set is K, the loop is exited, and the query process ends. Tests on real datasets demonstrate that the KTSS method outperforms current algorithms of the same type.

Safe Trajectory Planning for Incremental Robots Based on a Spatiotemporal Variable-Step-Size A* Algorithm.

In this paper, a planning method based on the spatiotemporal variable-step-size A* algorithm is proposed to address the problem of safe trajectory planning for incremental, wheeled, mobile robots in complex motion scenarios with multiple robots. After constructing the known conditions, the spatiotemporal variable-step-size A* algorithm is first used to perform a collision-avoiding initial spatiotemporal trajectory search, and a variable time step is utilized to ensure that the robot completes the search at the target speed. Subsequently, the trajectory is instantiated using B-spline curves in a numerical optimization considering constraints to generate the final smooth trajectory. The results of simulation tests in a field-shaped, complex, dynamic scenario show that the proposed trajectory planning method is more applicable, and the results indicate higher efficiency compared to the traditional method in the incremental robot trajectory planning problem.

STP-KDE: A spatiotemporal trajectory protection and publishing method based on kernel density estimation

Promoted by the Internet of Thing era, the widespread use of mobile sensing devices equipped with positioning functions has led to the generation of substantial trajectory data. Mining and analyzing trajectory data has high research value, but poses a risk of user privacy leakage, resulting in fewer publicly available trajectory datasets for research and analysis. Therefore, a trajectory data publishing method that ensures high data utility while protecting user privacy has become a hot topic. In this paper, we propose a spatiotemporal trajectory data protection and publishing method based on kernel density estimation (STP-KDE), which protects the trajectory data and trajectory count values while improving data utility. In the protection process of trajectory data, we designed a kernel density clustering framework that is combined with the differential privacy exponential mechanism. In the protection process of trajectory counts value, the adaptive Laplace noise perturbation mechanism is proposed to differentially protect these counts. Experimental results show that STP-KDE can provide more useful data and stronger privacy protection than existing studies.

Research on A Ship Trajectory Classification Method Based on Deep Learning

The unrestricted development and utilization of marine resources have resulted in a series of practical problems, such as the destruction of marine ecology. The wide application of radar, satellites and other detection equipment has gradually led to a large variety of large-capacity marine spatiotemporal trajectory data from a vast number of sources. In the field of marine domain awareness, there is an urgent need to use relevant information technology means to control and monitor ships and accurately classify and identify ship behavior patterns through multisource data fusion analysis. In addition, the increase in the type and quantity of trajectory data has produced a corresponding increase in the complexity and difficulty of data processing that cannot be adequately addressed by traditional data mining algorithms. Therefore, this paper provides a deep learning-based algorithm for the recognition of four main motion types of the ship from automatic identification system (AIS) data: anchoring, mooring, sailing and fishing. A new method for classifying patterns is presented that combines the computer vision and time series domains. Experiments are carried out on a dataset constructed from the open AIS data of ships in the coastal waters of the United States, which show that the method proposed in this paper achieves more than 95\% recognition accuracy. The experimental results confirm that the method proposed in this paper is effective in classifying ship trajectories using AIS data and that it can provide efficient technical support for marine supervision departments.