Search

Recovering the fine-grained working process of couriers is becoming one of the essential problems for improving the express delivery systems because knowing the detailed process of how couriers accomplish their daily work facilitates the analyzing, understanding, and optimizing of the working procedure. Although coarse-grained courier trajectories and waybill delivery time data can be collected, this problem is still challenging due to noisy data with spatio-temporal biases, lacking ground truth of couriers' fine-grained behaviors, and complex correlations between behaviors. Existing works typically focus on a single dimension of the process such as inferring the delivery time and can only yield results of low spatio-temporal resolution, which cannot address the problem well. To bridge the gap, we propose a digital-twin-based iterative calibration system (DTRec) for fine-grained courier working process recovery. We first propose a spatio-temporal bias correction algorithm, which systematically improves existing methods in correcting waybill addresses and trajectory stay points. Second, to model the complex correlations among behaviors and inherent physical constraints, we propose an agent-based model to build the digital twin of couriers. Third, to further improve recovery performance, we design a digital-twin-based iterative calibration framework, which leverages the inconsistency between the deduction results of the digital twin and the recovery results from real-world data to improve both the agent-based model and the recovery results. Experiments show that DTRec outperforms state-of-the-art baselines by 10.8% in terms of fine-grained accuracy on real-world datasets. The system is deployed in the industrial practices in JD Logistics with promising applications. The code is available at https://github.com/tsinghua-fib-lab/Courier-DTRec. [ABSTRACT FROM AUTHOR]

Accurate and efficient traffic information prediction is significantly important for the management of intelligent transportation systems. The traffic status (e.g., speed or flow) on one road segment is spatially affected by both its nearby neighbors and distant locations. The impending traffic status can be temporally influenced not only by its recent status but also by the randomness of its historical status change. The current state-of-the-art methods have effectively captured the spatio-temporal dependencies of road networks. However, most existing methods overlook the impact of time delay when capturing dynamic time dependencies. In addition, aggregating roads with similar traffic patterns from a wide range of spatial associations still poses challenges. In this paper, a spatial-temporal nonlinear auto-regressive multi-channel neural network (ST-NAMN) model is proposed to reveal the sophisticated nonlinear dynamic interconnections between temporal and spatial dependencies in road traffic data. Considering the temporal periodicity and spatial pattern similarity inherently in road traffic data, a divided period latent similarity correlation matrix (DLSC) first is utilized to calculate the similarity of traffic patterns from historical observation data. Then, we introduce an output feedback to the multi-layer perceptron (MLP) through a delay unit, which enables the output-layer to feedback its result data to the input layer in real-time, and further participate in the next iterative training to boost the learning capacity. Furthermore, an Enhanced-Bayesian Regularization weight updating method (EBR) is designed to better contemplate the influence of the continuous and delayed observation points compared to existing optimizers during the learning procedure. Experimental tests have been carried out on four real-world datasets and the results demonstrated that the proposed ST-NAMN method outperforms other state-of-the-art models. [ABSTRACT FROM AUTHOR]

Abstract Crowd flow prediction has been studied for a variety of purposes, ranging from the private sector such as location selection of stores according to the characteristics of commercial districts and customer-tailored marketing to the public sector for social infrastructure design such as transportation networks. Its importance is even greater in light of the spread of contagious diseases such as COVID-19. In many cases, crowd flow can be divided into subgroups by common characteristics such as gender, age, location type, etc. If we use such hierarchical structure of the data effectively, we can improve prediction accuracy of crowd flow for subgroups. But the existing prediction models do not consider such hierarchical structure of the data. In this study, we propose a deep learning model based on global–local structure of the crowd flow data, which utilizes the overall(global) and subdivided by the types of sites(local) crowd flow data simultaneously to predict the crowd flow of each subgroup. The experiment result shows that the proposed model improves the prediction accuracy of each sub-divided subgroup by 5.2% (Table 5 Cat #9)—45.95% (Table 11 Cat #5), depending on the data set. This result comes from the comparison with the related works under the same condition that use target category data to predict each subgroup. In addition, when we refine the global data composition by considering the correlation between subgroups and excluding low correlated subgroups, the prediction accuracy is further improved by 5.6–48.65%.

Crowd flow prediction has been studied for a variety of purposes, ranging from the private sector such as location selection of stores according to the characteristics of commercial districts and customer-tailored marketing to the public sector for social infrastructure design such as transportation networks. Its importance is even greater in light of the spread of contagious diseases such as COVID-19. In many cases, crowd flow can be divided into subgroups by common characteristics such as gender, age, location type, etc. If we use such hierarchical structure of the data effectively, we can improve prediction accuracy of crowd flow for subgroups. But the existing prediction models do not consider such hierarchical structure of the data. In this study, we propose a deep learning model based on global–local structure of the crowd flow data, which utilizes the overall(global) and subdivided by the types of sites(local) crowd flow data simultaneously to predict the crowd flow of each subgroup. The experiment result shows that the proposed model improves the prediction accuracy of each sub-divided subgroup by 5.2% (Table 5 Cat #9)—45.95% (Table 11 Cat #5), depending on the data set. This result comes from the comparison with the related works under the same condition that use target category data to predict each subgroup. In addition, when we refine the global data composition by considering the correlation between subgroups and excluding low correlated subgroups, the prediction accuracy is further improved by 5.6–48.65%. [ABSTRACT FROM AUTHOR]

The article presents STAR-HiT, a model for improved next Point-of-Interest (POI) recommendations in location-based social networks. It utilizes hierarchical encoders to capture spatio-temporal context and identify diverse patterns in user check-in sequences. It is reported that STAR-HiT excels in predicting the next POI, providing superior performance and interpretable recommendations based on experiments with three datasets.

Accurate and rapid prediction of monitoring parameters is an important means of proactively preventing safety accidents in tailings dams. Traditional monitoring model uses a single-point time-domain prediction method through feature selection, ignoring the correlation between monitoring point data. Multiple raw monitoring time series were used as direct input to the GCN-AGRU prediction model to estimate response changes in tailings dam operations. Firstly, the spatial location map of sensors in the tailings dam monitoring system was constructed to describe the sensor data in a multi-point arrangement. Then a graph neural network was used to capture the complex spatial dependencies of the sensor location map to obtain the overall safety level of the tailings dam. Secondly, the spatial features extracted from the graph convolutional neural network at different moments were fused with time series and input into a gated recurrent unit (GRU). The purpose was to use the fused features to capture the spatio-temporal correlation between time series of different monitoring locations. Finally, the temporal attention mechanism was combined to predict the dam monitoring data. Based on real data, the algorithm was compared with other algorithms to verify its accuracy and generalizability, which indicates that the model has great significance for improving the risk prevention and control of tailings dams. [ABSTRACT FROM AUTHOR]

Landslide is one of the most common geological hazards,it causes significant damage to people’s life and property everyyear.In order to prevent and control landslides,it is necessary to monitor the land surface extensively.However,insurmountable difficulties such as severe climate and high monitoring cost impede the collection of land surface data,resulting in incomplete local data,unbalanced data sampling and dynamic changes of monitoring points,which hinder the prevention and control research of landslide and put forward new demand to the data collection and analysis.Existing methods try to handle incomplete data from spatial perspective,which,however,ignore temporal dependencies that are important for data interpolation.To solve the above problems,the incomplete INSAR data filling is studied,the spatio-temporal dependence is modeled by using the spatio-temporal mask matrix,the multi-level spatial relationship is comprehensively studied by using multi-head attention,and a novel Kriging interpolation method using spatio-temporal attention is proposed on the basis of Kriging.It realizes the deep understanding of complex temporal and spatial features.Interpolation experiments on real-world INSAR datasets show that the proposed model is capable to learn sophisticated spatial and temporal features effectively,and achieves better performance than the state-of-the-art methods in three different data interpolation scenarios.

As a new form of public transportation, shared bikes have greatly facilitated people's travel in recent years. However, in the actual operation process, the uneven distribution of bicycles at each shared bicycle station has limited the travel experience. In this paper, we propose a deep spatio-temporal residual network model based on Region-reConStruction algorithm to predict the usage of shared bikes in the bike-sharing system. We first propose an Region-reConStruction algorithm (RCS) to partition the shared bicycle sites within a city into separate areas based on their geographic location information as well as bikes' migration trends between stations. We then combine the RCS algorithm with a deep spatio-temporal residual network to model the key factors affecting the usage of shared bicycles. RCS makes good use of the migration trend of shared bikes during user usage, thus greatly improving the accuracy of prediction. Experiments performed on New York's bike-sharing system show that our model's prediction accuracy is significantly better than that of previous models. [ABSTRACT FROM AUTHOR]

Abstract As a new form of public transportation, shared bikes have greatly facilitated people’s travel in recent years. However, in the actual operation process, the uneven distribution of bicycles at each shared bicycle station has limited the travel experience. In this paper, we propose a deep spatio-temporal residual network model based on Region-reConStruction algorithm to predict the usage of shared bikes in the bike-sharing system. We first propose an Region-reConStruction algorithm (RCS) to partition the shared bicycle sites within a city into separate areas based on their geographic location information as well as bikes’ migration trends between stations. We then combine the RCS algorithm with a deep spatio-temporal residual network to model the key factors affecting the usage of shared bicycles. RCS makes good use of the migration trend of shared bikes during user usage, thus greatly improving the accuracy of prediction. Experiments performed on New York’s bike-sharing system show that our model’s prediction accuracy is significantly better than that of previous models.

Copyright of Journal of Xinyang Normal University Natural Science Edition is the property of Journal of Xinyang Normal University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Traffic flow prediction is an integral part of an intelligent transportation system and thus fundamental for various traffic-related applications. Buses are an indispensable way of moving for urban residents with fixed routes and schedules, which leads to latent travel regularity. However, human mobility patterns, specifically the complex relationships between bus passengers, are deeply hidden in this fixed mobility mode. Although many models exist to predict traffic flow, human mobility patterns have not been well explored in this regard. To address this research gap and learn human mobility knowledge from this fixed travel behaviors, we propose a multi-pattern passenger flow prediction framework, MPGCN, based on Graph Convolutional Network (GCN). Firstly, we construct a novel sharing-stop network to model relationships between passengers based on bus record data. Then, we employ GCN to extract features from the graph by learning useful topology information and introduce a deep clustering method to recognize mobility patterns hidden in bus passengers. Furthermore, to fully utilize spatio-temporal information, we propose GCN2Flow to predict passenger flow based on various mobility patterns. To the best of our knowledge, this paper is the first work to adopt a multi-pattern approach to predict the bus passenger flow by taking advantage of graph learning. We design a case study for optimizing routes. Extensive experiments upon a real-world bus dataset demonstrate that MPGCN has potential efficacy in passenger flow prediction and route optimization. [ABSTRACT FROM AUTHOR]

The discovery of spatio-temporal co-occurrence patterns (STCPs) among multiple types of crimes whose events frequently co-occur in neighboring space and time is crucial to the joint prevention of crimes. However, the crime event occurrence time is often uncertain due to a lack of witnesses. This occurrence time uncertainty further results in the uncertainty of the spatio-temporal neighborhood relationships and STCPs. Existing methods have mostly modeled the uncertainty of events under the independent and identically distributed assumption and utilized one-sided distance information to measure the distance between uncertain events. As a result, STCPs detected from a dataset with occurrence time uncertainty (USTCPs) are likely to be erroneously assessed. Therefore, this paper proposes a probabilistic-distance-based USTCP discovery method. First, the temporal probability density functions of crime events with uncertain occurrence times are estimated by considering the temporal dependence. Second, the spatio-temporal neighborhood relationships are constructed based on the spatial Euclidean distance and the proposed temporal probabilistic distance. Finally, the prevalent USTCPs are identified. Experimental comparisons performed on twelve types of crimes from X City Public Security Bureau in China demonstrate that the proposed method can more objectively express the occurrence time of crimes and more reliably identify USTCPs. [ABSTRACT FROM AUTHOR]

Deep Learning methods have been proven to be flexible to model complex phenomena. This has also been the case of Intelligent Transportation Systems, in which several areas such as vehicular perception and traffic analysis have widely embraced Deep Learning as a core modeling technology. Particularly in short-term traffic forecasting, the capability of Deep Learning to deliver good results has generated a prevalent inertia towards using Deep Learning models, without examining in depth their benefits and downsides. This paper focuses on critically analyzing the state of the art in what refers to the use of Deep Learning for this particular Intelligent Transportation Systems research area. To this end, we elaborate on the findings distilled from a review of publications from recent years, based on two taxonomic criteria. A posterior critical analysis is held to formulate questions and trigger a necessary debate about the issues of Deep Learning for traffic forecasting. The study is completed with a benchmark of diverse short-term traffic forecasting methods over traffic datasets of different nature, aimed to cover a wide spectrum of possible scenarios. Our experimentation reveals that Deep Learning could not be the best modeling technique for every case, which unveils some caveats unconsidered to date that should be addressed by the community in prospective studies. These insights reveal new challenges and research opportunities in road traffic forecasting, which are enumerated and discussed thoroughly, with the intention of inspiring and guiding future research efforts in this field. [ABSTRACT FROM AUTHOR]

Trajectory-User Linking (TUL) aims to link anonymous trajectories to their owners, which is considered an essential task in discovering human mobility patterns. Although existing TUL studies have shown promising results, they still have specific defects in the perception of spatio-temporal properties of trajectories, which manifested in the following three problems: missing context of the original trajectory, ignorance of spatial information, and high computational complexity. To address those issues, we revisit the characteristics of the trajectory and propose a novel model called TULMGAT (TUL via Multi-Scale Graph Attention Network) based on masked self-attention graph neural networks. Specifically, TULMGAT consists of four components: construction of check-in oriented graphs, node embedding, trajectory embedding, and trajectory user linking. Sufficient experiments on two publicly available datasets have shown that TULMGAT is the state-of-the-art model in task TUL compared to the baselines with an improvement of about 8% in accuracy and only a quarter of the fastest baseline in runtime. Furthermore, model validity experiments have verified the role of each module. • A multi-scale graph attention network for effective and efficient trajectory user linking • A graph construction method preserves the original trajectory context of arbitrary length. • A spatio-temporal network mines human mobility patterns in parallel and robustly. • Sufficient experiments prove its better performance and module validity. [ABSTRACT FROM AUTHOR]

In order to improve the effect of path planning in emergencies, the missing position imputation and velocity restoration in vehicle trajectory provide data support for emergency path planning and analysis. At present, there are many methods to fill in the missing trajectory information, but they basically restore the missing trajectory after analyzing a large number of datasets. However, the trajectory reduction method with few training sets needs to be further explored. For this purpose, a novel trajectory data cube model (TDC) is designed to store time, position, and velocity information hierarchically in the trajectory data. Based on this model, three trajectory Hierarchical Trace-Back algorithms HTB-p, HTB-v, and HTB-KF are proposed in this paper. Finally, experiments verify that conduct in a different number of sample sets, it has a satisfactory performance on information restoration of individual points of the trajectory and information restoration of trajectory segments. [ABSTRACT FROM AUTHOR]

To model and forecast flight delays accurately, it is crucial to harness various vehicle trajectory and contextual sensor data on airport tarmac areas. These heterogeneous sensor data, if modelled correctly, can be used to generate a situational awareness map. Existing techniques apply traditional supervised learning methods onto historical data, contextual features and route information among different airports to predict flight delay are inaccurate and only predict arrival delay but not departure delay, which is essential to airlines. In this paper, we propose a vision-based solution to achieve a high forecasting accuracy, applicable to the airport. Our solution leverages a snapshot of the airport situational awareness map, which contains various trajectories of aircraft and contextual features such as weather and airline schedules. We propose an end-to-end deep learning architecture, TrajCNN, which captures both the spatial and temporal information from the situational awareness map. Additionally, we reveal that the situational awareness map of the airport has a vital impact on estimating flight departure delay. Our proposed framework obtained a good result (around 18 min error) for predicting flight departure delay at Los Angeles International Airport. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhengzhou University (Natural Science Edition) is the property of Journal of Zhengzhou University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Earthquake prediction is a very important problem in seismology, the success of which can potentially save many human lives. Various kinds of technologies have been proposed to address this problem, such as mathematical analysis, machine learning algorithms like decision trees and support vector machines, and precursors signal study. Unfortunately, they usually do not have very good results due to the seemingly dynamic and unpredictable nature of earthquakes. In contrast, we notice that earthquakes are spatially and temporally correlated because of the crust movement. Therefore, earthquake prediction for a particular location should not be conducted only based on the history data in that location, but according to the history data in a larger area. In this paper, we employ a deep learning technique called long short-term memory (LSTM) networks to learn the spatio-temporal relationship among earthquakes in different locations and make predictions by taking advantage of that relationship. Simulation results show that the LSTM network with two-dimensional input developed in this paper is able to discover and exploit the spatio-temporal correlations among earthquakes to make better predictions than before. [ABSTRACT FROM AUTHOR]

Legionella spp. are considered an important cause of potentially preventable morbidity and mortality, making environmental surveillance a crucial component of risk assessment plans. In this work, historical data of about 24,000 water samples collected during a series of environmental surveys in the Italian region of Friuli-Venezia Giulia in the period 2002–2019 were analysed using machine learning methods. The objective was to determine the most relevant factors linked to the Legionella spread in the considered territory, and to compare such findings to those already presented in the literature. Specifically, retrospective unsupervised spatio-temporal analyses on geocoded data were carried out to identify potential clusters with an excess of cases in the higher-risk categories. In addition, tree-based ensemble classification methods were employed to try to predict the samples serogroup and contamination levels based on climatic and geographical factors, highlighting relationships between the values of such predictors and the presence of specific serogroups. Results based on cross-validation show that it is possible to identify spatially restricted zones with unusual contamination based on data collected during routine surveillance, and that the serogroup appears to be influenced by humidity, temperature and latitude, although the interaction with environmental factors is complex and still not entirely clarified. Despite that, our analyses highlighted several relationships between environmental factors and the presence of Legionella. Most importantly, there is an indication that some Legionella strains are more tolerant to specific microclimates, suggesting that further work should be conducted in this sense when more data will become available.

This article addresses a new pattern mining problem in time series sensor data, which we call correlated attribute pattern mining. The correlated attribute patterns (CAPs for short) are the sets of attributes (e.g., temperature and traffic volume) on sensors that are spatially close to each other and temporally correlated in their measurements. Although the CAPs are useful to accurately analyze and understand spatio-temporal correlation between attributes, the existing mining methods are inefficient to discover CAPs because they extract unnecessary patterns. Therefore, we propose a mining method Miscela to efficiently discover CAPs. Miscela can discover not only simultaneous correlated patterns but also time delayed correlated patterns. Furthermore, we extend Miscela to automatically search for correlated patterns with any time delays. Through our experiments using three real sensor datasets, we show that the response time of Miscela is up to 20.84 times faster compared with the state-of-the-art method. We show that Miscela discovers meaningful patterns for urban managements and environmental studies. [ABSTRACT FROM AUTHOR]

The goal of maritime traffic management is to provide a safe and efficient maritime environment for different type of vessels facilitating port logistics and supply chain business. However, current maritime traffic management mainly relies on the massive individual vessel’s data for decision making. Lack of macro-level understanding of vessel crowd movement around port challenges maritime safety and traffic efficiency. In this paper, we describe a spatio-temporal data mining method to discover crowd movement patterns of vessels from their short-term history data. The method first captures vessels’ crowd movement features by building vessels’ tracklets with their speed and location. A movement vector clustering algorithm is developed to find different travel behaviors for different group of vessels. With nonparametric regression on the classified vessel movement vectors which represent the crowd travel behaviors, an overall vessel movement pattern can then be discovered. In this research, we tested real trajectory data of vessels near Singapore ports. Comparing with the actual massive vessel movement data, we found that this method was able to extract vessels’ crowd movement information. The hotspots on risk area in terms of vessel traffic and speed can be identified. The method can be used to provide decision-making support for maritime traffic management.

Extracting road network information including lane boundaries, lane centerlines, junctions and their relationship from AIS data plays an important role in location based services, urban computing and intelligent transportation systems, etc. However, AIS data are large scale, high noisy, the density and quality are very uneven in different areas, extracting a whole, continuous and smooth maritime road network with rich information from such data is a challenging problem. To address these issues, this paper proposes an adaptive maritime road network extraction approach that can extract both lane boundaries and centerlines for a large sea area from AIS data. Based on a road network definition including nodes, segments and segment curves, the approach designs parallel grid merging and filtering algorithms to determine if a grided area is inside lane or not. Lane boundaries are smoothed through jagged edge filtering and Simple Moving Average algorithms before centerline extraction. We evaluate our method based on real world AIS data in various area across the world's seas. Experimental results show the advantage of our method beyond the close related work.

Recent advances in stream-flow prediction using Recurrent Neural Networks (RNN) or Long Short-Term Memory (LSTM) have prompted their exploration in the field of hydrology. Predicting hydrological time series is of great importance, but is very challenging as it is influenced by many complex factors such as dynamic spatio-temporal feature correlation and nonlinear meteorological-hydrological. In this context, we propose a framework based on dynamic spatio-temporal attention (DSTA) to predict the stream-flow of a hydrological station over several days. It consists of three main modules: a spatial module, a temporal module, and a trend input module. Experiments were carried out on real data sets from four watersheds in the mainstream of the Yangtze River and proved that our method is superior to the six baseline methods.

The discovery of spatio-temporal co-occurrence patterns (STCPs) among multiple types of crimes whose events frequently co-occur in neighboring space and time is crucial to the joint prevention of crimes. However, the crime event occurrence time is often uncertain due to a lack of witnesses. This occurrence time uncertainty further results in the uncertainty of the spatio-temporal neighborhood relationships and STCPs. Existing methods have mostly modeled the uncertainty of events under the independent and identically distributed assumption and utilized one-sided distance information to measure the distance between uncertain events. As a result, STCPs detected from a dataset with occurrence time uncertainty (USTCPs) are likely to be erroneously assessed. Therefore, this paper proposes a probabilistic-distance-based USTCP discovery method. First, the temporal probability density functions of crime events with uncertain occurrence times are estimated by considering the temporal dependence. Second, the spatio-temporal neighborhood relationships are constructed based on the spatial Euclidean distance and the proposed temporal probabilistic distance. Finally, the prevalent USTCPs are identified. Experimental comparisons performed on twelve types of crimes from X City Public Security Bureau in China demonstrate that the proposed method can more objectively express the occurrence time of crimes and more reliably identify USTCPs.

Predictive modeling of large-scale spatio-temporal data is an important but challenging problem as it requires training models that can simultaneously predict the target variables of interest at multiple locations while preserving the spatial and temporal dependencies of the data. In this paper, we investigate the effectiveness of applying a multi-task learning approach based on supervised tensor decomposition to the spatio-temporal prediction problem. Our proposed framework, known as SMART, encodes the data as a third-order tensor and extracts a set of interpretable, spatial and temporal latent factors from the data. An ensemble of spatial and temporal prediction models are trained using the latent factors as their predictor variables. Outputs from the ensemble model are aggregated to make predictions on test instances. The framework also allows known patterns from the domain to be incorporated as constraints to guide the tensor decomposition and ensemble learning processes. As the data may grow over space and time, an incremental learning version of the framework is given to efficiently update the models. We perform extensive experiments using a global-scale climate dataset to evaluate the accuracy and efficiency of the models as well as interpretability of the latent factors. [ABSTRACT FROM AUTHOR]

Tremendous increase in the use of the mobile devices equipped with the GPS and other location sensors has resulted in the generation of a huge amount of movement data. In recent years, mining this data to understand the collective mobility behavior of humans, animals and other objects has become popular. Numerous mobility patterns, or their mining algorithms have been proposed, each representing a specific movement behavior. Convoy pattern is one such pattern which can be used to find groups of people moving together in public transport or to prevent traffic jams. A convoy is a set of at least m objects moving together for at least k consecutive time stamps where m and k are user-defined parameters. Existing algorithms for detecting convoy patterns do not scale to real-life dataset sizes. Therefore in this paper, we propose a generic distributed convoy pattern mining algorithm called DCM and show how such an algorithm can be implemented using the MapReduce framework. We present a cost model for DCM and a detailed theoretical analysis backed by experimental results. We show the effect of partition size on the performance of DCM. The results from our experiments on different data-sets and hardware setups, show that our distributed algorithm is scalable in terms of data size and number of nodes, and more efficient than any existing sequential as well as distributed convoy pattern mining algorithm, showing speed-ups of up to 16 times over SPARE, the state of the art distributed co-movement pattern mining framework. DCM is thus able to process large datasets which SPARE is unable to. [ABSTRACT FROM AUTHOR]

In recent years, air pollution has seriously affected people's production and life, so the air prediction has become a research hotspot in recent years. When analyzing air data, it is found that this type of data has not only temporal correlation, but also spatial correlation. For these temporal and spatial characteristics, this paper studies deep spatio-temporal learning method to global prediction. The purpose is to learn the evolution rule behind the spatio-temporal sequence, and give an estimation for future state. To be specific, we propose two novel forecasting models based on video processing technology: Spatio-temporal Orthogonal Cube model (STOR-cube) and Spatio-temporal Dynamic Advection model (ST-DA), which effectively capture the spatio-temporal correlation and accurately predict the long-term air quality. STOR-cube contains three branches, i.e., a spatial branch for capturing moving objects, a temporal branch for processing motion, and an output branch for coupling the first two mutually orthogonal branches to generate a prediction frame. ST-DA constructs a spatio-temporal reasoning network to learn the characteristics of the spatio-temporal domain, and its impact on the future is explicitly modeled by pixel motion. Experiments results on the real-world datasets demonstrate our proposed approach significantly outperforms the state-of-the-art ones. Moreover, our model can be extended to other spatio-temporal data prediction tasks. [ABSTRACT FROM AUTHOR]

Crowd flows prediction is an important problem of urban computing whose goal is to predict the number of incoming and outgoing people of regions in the future. In practice, emergency applications often require less training time. However, there is a little work on how to obtain good prediction performance with less training time. In this paper, we propose a simplified deep residual network for our problem. By using the simplified deep residual network, we can obtain not only less training time but also competitive prediction performance compared with the existing similar method. Moreover, we adopt the spatio-temporal attention mechanism to further improve the simplified deep residual network with reasonable additional time cost. Based on the real datasets, we construct a series of experiments compared with the existing methods. The experimental results confirm the efficiency of our proposed methods. [ABSTRACT FROM AUTHOR]

In order to improve the effect of path planning in emergencies, the missing position imputation and velocity restoration in vehicle trajectory provide data support for emergency path planning and analysis. At present, there are many methods to fill in the missing trajectory information, but they basically restore the missing trajectory after analyzing a large number of datasets. However, the trajectory reduction method with few training sets needs to be further explored. For this purpose, a novel trajectory data cube model (TDC) is designed to store time, position, and velocity information hierarchically in the trajectory data. Based on this model, three trajectory Hierarchical Trace-Back algorithms HTB-p, HTB-v, and HTB-KF are proposed in this paper. Finally, experiments verify that conduct in a different number of sample sets, it has a satisfactory performance on information restoration of individual points of the trajectory and information restoration of trajectory segments.

The analysis of factors influencing urban shrinkage is of great interest to spatial planners and policy makers. Population loss is usually the most relevant indicator of this shrinkage, but many other factors interact in complex ways over time. This paper proposes a multidimensional and spatio-temporal analysis of the shrinkage process in Spanish municipalities between 1991 and 2020. The method is based on the potentiality provided by self-organizing maps. The generated maps group municipalities according to hidden partial correlations among the data behind the variables characterizing the municipalities at different dates. In addition, as the number of map nodes is too big to allow for the detection of distinct types of municipalities, a Ward clustering algorithm is applied to identify homogeneous areas with a higher probability of shrinkage occurring over time. The results indicate that the municipalities with the lowest shrinkage are more stable and have a geographical concentration: they correspond to areas where peripheralization may occur (creation of surrounding districts close to main urban centers) and constitute the hinterland of large functional areas. The results also report a path of decline, with an important increase in the number of municipalities with higher shrinkage values. This approach has important implications for policy making since local governments may profit from shrinkage predictions.

The goal of spatio-temporal data mining is to discover previously unknown but useful patterns from the spatial and temporal data. However, explosive growth of the spatiotemporal data emphasizes the need for developing novel computationally efficient methods for large-scale data mining applications. Since lots of spatiotemporal data mining problems can be converted to an optimization problem, in this paper, we propose an efficient parameter-level parallel optimization algorithm for large-scale spatiotemporal data mining. In detail, most of previous optimization methods are based on gradient descent methods, which iteratively update the model and provide model-level convergence control for all parameters. Namely, they treat all parameters equally and keep updating all parameters until every parameter has converged. However, we find that during the iterative process, the convergence rates of model parameters are different from each other. This may cause redundant computation and reduce the performance. To solve this problem, we propose a parameter-level stochastic gradient descent (plpSGD), in which the convergence of each parameter is considered independently and only unconvergent parameters are updated in each iteration. Moreover, the updating of model parameters are parallelized in plpSGD to further improve the performance of SGD. We have conducted extensive experiments to evaluate the performance of plpSGD. The experimental results show that compared to previous SGD methods, plpSGD can significantly accelerate the convergence of SGD and achieve the excellent scalability with little sacrifice of the solution accuracy. [ABSTRACT FROM AUTHOR]

Traffic congestion is a direct reflection of the imbalance between supply and demand for a certain period of time. Owing to the complexity of traffic roads and the propagation of congestion, the evacuation of traffic congestion for local road sections alone cannot achieve significant results. Based on the measured data of traffic flow, this paper combines the topology of the road network and the existence time of congestion to judge the spatio-temporal correlation of congestion between road sections. We proposed a spatio-temporal co-location congestion pattern mining method to discover the orderly set of roads with congestion propagation in urban traffic, and measure its influence in congestion events. The proposed method not only reveals the process of congestion propagation but also uncovers the main propagation paths leading to the large-scale congestion. Finally, we experimented with the algorithm on the traffic dataset in Guiyang city. The experimental results reveal the traffic congestion rule in Guiyang City, including the prevalent co-occurrence of congestion propagation patterns and their influence in congestion events. [ABSTRACT FROM AUTHOR]