Search

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]

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]

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]

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]

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]

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]

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]

Spatio-temporal co-occurrence patterns represent subsets of object-types that are often located together in space and time. The aim of the discovery of partial spatio-temporal co-occurrence patterns (PACOPs) is to find co-occurrences of the object-types that are partially present in the database. Discovering PACOPs is an important problem with many applications such as discovering interactions between animals in ecology, identifying tactics in battlefields and games, and identifying crime patterns in criminal databases. However, mining PACOPs is computationally very expensive because the interest measures are computationally complex, databases are larger due to the archival history, and the set of candidate patterns is exponential in the number of object-types. Previous studies on discovering spatio-temporal co-occurrence patterns do not take into account the presence period (i.e., lifetime) of the objects in the database. This paper defines the problem of mining PACOPs, proposes a new monotonic composite interest measure, and proposes novel PACOP mining algorithms. The experimental results show that the proposed algorithms are computationally more efficient than the naïve alternatives. [ABSTRACT FROM AUTHOR]

Spatio-temporal clustering has been a hot topic in the field of spatio-temporal data mining and knowledge discovery. It can be employed to uncover and interpret developmental trends of geographic phenomenon in the real world. However, existing spatio-temporal clustering methods seldom consider both spatiotemporal autocorrelations and heterogeneities among spatio-temporal entities, and the coupling in space and time has not been well highlighted. In this paper, a unified framework for the clustering analysis of spatio-temporal data is proposed, and a novel spatio-temporal clustering algorithm is developed by means of a spatio-temporal statistics methodology and intelligence computation technology. Our method is applied successfully to finding spatio-temporal cluster in China's annual temperature database for the period 1951-1992. [ABSTRACT FROM AUTHOR]

The latent behavior of a physical system that can exhibit extreme events such as hurricanes or rainfalls, is complex. Recently, a very promising means for studying complex systems has emerged through the concept of complex networks. Networks representing relationships between individual objects usually exhibit community dynamics. Conventional community detection methods mainly focus on either mining frequent subgraphs in a network or detecting stable communities in time-varying networks. In this paper, we formulate a novel problem- detection of predictive and phase-biased communities in contrasting groups of networks, and propose an efficient and effective machine learning solution for finding such anomalous communities. We build different groups of networks corresponding to different system's phases, such as higher or low hurricane activity, discover phase-related system components as seeds to help bound the search space of community generation in each network, and use the proposed contrast-based technique to identify the changing communities across different groups. The detected anomalous communities are hypothesized (1) to play an important role in defining the target system's state(s) and (2) to improve the predictive skill of the system's states when used collectively in the ensemble of predictive models. When tested on the two important extreme event problems-identification of tropical cyclone-related and of African Sahel rainfall-related climate indices-our algorithm demonstrated the superior performance in terms of various skill and robustness metrics, including 8-16 % accuracy increase, as well as physical interpretability of detected communities. The experimental results also show the efficiency of our algorithm on synthetic datasets. [ABSTRACT FROM AUTHOR]

Detecting spatio-temporal clusters, i.e. clusters of objects similar to each other occurring together across space and time, has important real-world applications such as climate change, drought analysis, detection of outbreak of epidemics (e.g. bird flu), bioterrorist attacks (e.g. anthrax release), and detection of increased military activity. Research in spatio-temporal clustering has focused on grouping individual objects with similar trajectories, detecting moving clusters, or discovering convoys of objects. However, most of these solutions are based on using a piece-meal approach where snapshot clusters are formed at each time stamp and then the series of snapshot clusters are analyzed to discover moving clusters. This approach has two fundamental limitations. First, it is point-based and is not readily applicable to polygonal datasets. Second, its static analysis approach at each time slice is susceptible to inaccurate tracking of dynamic cluster especially when clusters change over both time and space. In this paper we present a spatio-temporal polygonal clustering algorithm known as the Spatio- Temporal Polygonal Clustering (STPC) algorithm. STPC clusters spatial polygons taking into account their spatial and topological properties, treating time as a first-class citizen, and integrating density-based clustering with moving cluster analysis. Our experiments on the drought analysis application, flu spread analysis and crime cluster detection show the validity and robustness of our algorithm in an important geospatial application. [ABSTRACT FROM AUTHOR]

Planning travel to unfamiliar regions is a difficult task for novice travelers. The burden can be eased if the resident of the area offers to help. In this paper, we propose a social itinerary recommendation by learning from multiple user-generated digital trails, such as GPS trajectories of residents and travel experts. In order to recommend satisfying itinerary to users, we present an itinerary model in terms of attributes extracted from user-generated GPS trajectories. On top of this itinerary model, we present a social itinerary recommendation framework to find and rank itinerary candidates. We evaluated the efficiency of our recommendation method against baseline algorithms with a large set of user-generated GPS trajectories collected from Beijing, China. First, systematically generated user queries are used to compare the recommendation performance in the algorithmic level. Second, a user study involving current residents of Beijing is conducted to compare user perception and satisfaction on the recommended itinerary. Third, we compare mobile-only approach with Mobile+Cloud architecture for practical mobile recommender deployment. Lastly, we discuss personalization and adaptation factors in social itinerary recommendation throughout the paper. [ABSTRACT FROM AUTHOR]

The technologies of mobile communications pervade our society and wireless networks sense the movement of people, generating large volumes of mobility data, such as mobile phone call records and Global Positioning System (GPS) tracks. In this work, we illustrate the striking analytical power of massive collections of trajectory data in unveiling the complexity of human mobility. We present the results of a large-scale experiment, based on the detailed trajectories of tens of thousands private cars with on-board GPS receivers, tracked during weeks of ordinary mobile activity. We illustrate the knowledge discovery process that, based on these data, addresses some fundamental questions of mobility analysts: what are the frequent patterns of people's travels? How big attractors and extraordinary events influence mobility? How to predict areas of dense traffic in the near future? How to characterize traffic jams and congestions? We also describe M-Atlas, the querying and mining language and system that makes this analytical process possible, providing the mechanisms to master the complexity of transforming raw GPS tracks into mobility knowledge. M-Atlas is centered onto the concept of a trajectory, and the mobility knowledge discovery process can be specified by M-Atlas queries that realize data transformations, data-driven estimation of the parameters of the mining methods, the quality assessment of the obtained results, the quantitative and visual exploration of the discovered behavioral patterns and models, the composition of mined patterns, models and data with further analyses and mining, and the incremental mining strategies to address scalability. [ABSTRACT FROM AUTHOR]

We examine the application of spectral clustering for breaking up the behavior of a multi-agent system in space and time into smaller, independent elements. We propose clustering observations of individual entities in order to identify significant changes in the parameter space (like spatial position) and detect temporal alterations of behavior within the same framework. Available knowledge of important interactions (events) between entities is also considered. We describe a novel algorithm utilizing iterative subdivisions where clusters are pre-processed at each step to counter spatial scaling, rotation, replay speed, and varying sampling frequency. A method is presented to balance spatial and temporal segmentation based on the expected group size, and a validity measure is introduced to determine the optimal number of clusters. We demonstrate our results by analyzing the outcomes of computer games and compare our algorithm to K-means and traditional spectral clustering. [ABSTRACT FROM AUTHOR]

With the increasing use of wireless communication devices and the ability to track people and objects cheaply and easily, the amount of spatio-temporal data is growing substantially. Many of these applications cannot easily locate the exact position of objects, but they can determine the region in which each object is contained. Furthermore, the regions are fixed and may vary greatly in size. Examples include mobile/cell phone networks, RFID tag readers and satellite tracking. This demands techniques to mine such data. These techniques must also correct for the bias produced by different sized regions. We provide a comprehensive definition of Spatio-Temporal Association Rules (STARs) that describe how objects move between regions over time. We also present other patterns that are useful for mobility data; stationary regions and high traffic regions. The latter consists of sources, sinks and thoroughfares. These patterns describe important temporal characteristics of regions and we show that they can be considered as special STARs. We define spatial support to effectively deal with the problem of different sized regions. We provide an efficient algorithm--STAR-Miner--to find these patterns by exploiting several pruning properties. [ABSTRACT FROM AUTHOR]