Search

The goal of the growing discipline of neuro-symbolic artificial intelligence (AI) is to develop AI systems with more human-like reasoning capabilities by combining symbolic reasoning with connectionist learning. We survey the literature on neuro-symbolic AI during the last two decades, including books, monographs, review papers, contribution pieces, opinion articles, foundational workshops/talks, and related PhD theses. Four main features of neuro-symbolic AI are discussed, including representation, learning, reasoning, and decision-making. Finally, we discuss the many applications of neuro-symbolic AI, including question answering, robotics, computer vision, healthcare, and more. Scalability, explainability, and ethical considerations are also covered, as well as other difficulties and limits of neuro-symbolic AI. This study summarizes the current state of the art in neuro-symbolic artificial intelligence. [ABSTRACT FROM AUTHOR]

More accurate traffic prediction can further improve the efficiency of intelligent transportation systems. However, the complex spatiotemporal correlation issues in transportation networks pose great challenges. In the past, people have carried out a great deal of research to solve this problem. Most studies are based on graph neural networks to model traffic graphs and attempt to use fixed graph structures to obtain relationships between nodes. However, due to the time-varying spatial correlation of the transportation network, there is no stable node relationship. To address the above issues, we propose a new traffic prediction framework called the Dynamic Graph Spatial-Temporal Neural Network (DGSTN). Unlike other models that use predefined graphs, this model represents stable node relationships and time-varying node relationships by constructing static topology maps and dynamic information maps during the training and testing stages, to capture hidden node relationships and time-varying spatial correlations. In terms of network architecture, we designed multi-scale causal convolution and adaptive spatial self-attention mechanisms to capture temporal and spatial features, respectively, and assisted learning through static and dynamic graphs. The proposed framework has been tested on two real-world traffic datasets and can achieve state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Accurate traffic flow forecasting is very important for urban planning and traffic management. However, this is a huge challenge due to the complex spatial–temporal relationships. Although the existing methods have researched spatial–temporal relationships, they neglect the long periodic aspects of traffic flow data, and thus cannot attain a satisfactory result. In this paper, we propose a novel model Attention-Based Spatial–Temporal Convolution Gated Recurrent Unit (ASTCG) to solve the traffic flow forecasting problem. ASTCG has two core components: the multi-input module and the STA-ConvGru module. Based on the cyclical nature of traffic flow data, the data input to the multi-input module are divided into three parts, near-neighbor data, daily-periodic data, and weekly-periodic data, thus enabling the model to better capture the time dependence. The STA-ConvGru module, formed by CNN, GRU, and attention mechanism, can capture both temporal and spatial dependencies of traffic flow. We evaluate our proposed model using real-world datasets and experiments show that the ASTCG model outperforms the state-of-the-art model. [ABSTRACT FROM AUTHOR]

Accurate PM 2.5 forecasting is significant for improving quality of life and human health. However, it is very challenging to capture the high spatiotemporal correlations and the complex diffusion processes of PM 2.5 . Most existing PM 2.5 prediction methods only focus on spatiotemporal dependencies. In addition, the PM 2.5 diffusion process with domain knowledge in deep learning is rarely considered. Therefore, how to simultaneously capture comprehensive spatiotemporal dependencies and model the complicated diffusion process of PM 2.5 is still a challenge. To address this problem, we propose a dual-channel spatial–temporal difference graph neural network (DC-STDGN) to forecast future PM 2.5 concentrations. DC-STDGN first constructs a dual-channel structure to obtain distance-based local neighboring information and the global hidden spatial correlation of the data. Then, a temporal convolution layer is designed to handle the long-term dependency. Finally, the spatial difference with domain knowledge is introduced to model the complex diffusion process and capture more comprehensive spatiotemporal correlations. The extensive experiments with three real-world datasets demonstrate the improved prediction performance of DC-STDGN over state-of-the-art baselines. DC-STDGN outperforms the second-best model by up to 16.9% improvement in mean absolute error, 8.9% improvement in root mean square error and 18.2% improvement in mean absolute scaled error. [ABSTRACT FROM AUTHOR]

Detecting anomalous edges and/or nodes is a challenging problem for dynamic networks, due to the spatio-temporal (ST) patterns and randomness underneath the time-varying topology and node attributes. Existing methods commonly ignore randomness, and the anomaly detectors would be sensitive, especially in highly variable dynamic networks. In this paper, a new reconstruction method, the multi-scale variational graph recurrent autoencoder (M-VGRAE), is designed to detect anomalies in stochastic dynamic networks. Overall, upon the framework of Learning from Pure Normal (LPN), the M-VGRAE is trained to reconstruct the normal nodes and edges, and is used to detect the anomalies that cannot be reconstructed well by the trained M-VGRAE. To reduce sensitivity against the high variability, the reconstruction of stochastic dynamic networks is performed in a multi-scale manner. Specifically, the randomness is modeled by introducing multiple latent random variables at each node, each of which models the local randomness of attributes and connectivity within the temporal neighborhoods in a specific hop and historical interval. Then, the local randomness is approximated by employing the variational autoencoder (VAE) with a designed multi-scale ST feature extractor based on graph neural networks and recurrent neural networks. By such design, the capture of ST patterns and the modeling of randomness are jointly achieved. To show the effectiveness of the M-VGRAE in detecting anomalous edges and nodes, experiments are conducted on four real-world datasets of dynamic networks. The results demonstrate that the M-VGRAE consistently outperforms the existing baselines in terms of AUC score on anomaly detection. [ABSTRACT FROM AUTHOR]

Traffic forecasting is highly challenging due to its complex spatial and temporal dependencies in the traffic network. Graph Convolutional Neural Network (GCN) has been effectively used for traffic forecasting due to its excellent performance in modelling spatial dependencies. In most existing approaches, GCN models spatial dependencies in the traffic network with a fixed adjacency matrix. However, the spatial dependencies change over time in the actual situation. In this paper, we propose a graph learning-based spatial-temporal graph convolutional neural network (GLSTGCN) for traffic forecasting. To capture the dynamic spatial dependencies, we design a graph learning module to learn the dynamic spatial relationships in the traffic network. To save training time and computation resources, we adopt dilated causal convolution networks with a gating mechanism to capture long-term temporal correlations in traffic data. We conducted extensive experiments using two real-world traffic datasets. Experimental results demonstrate that the proposed GLSTGCN achieves superior performance than all state-of-art baselines. [ABSTRACT FROM AUTHOR]

Trajectory outlier detection is one of the fundamental data mining techniques used to analyze the trajectory data of the Global Positioning System. A comprehensive literature review of trajectory outlier detectors published between 2000 and 2022 led to a conclusion that conventional trajectory outlier detectors suffered from drawbacks, either due to the detectors themselves or the pre-processing methods for the variable-length trajectory inputs utilized by detectors. To address these issues, we proposed a feature extraction method called middle polar coordinates (MiPo). MiPo extracted tabular features from trajectory data prior to the application of conventional outlier detectors to detect trajectory outliers. By representing variable-length trajectory data as fixed-length tabular data, MiPo granted tabular outlier detectors the ability to detect trajectory outliers, which was previously impossible. Experiments with real-world datasets showed that MiPo outperformed all baseline methods with 0.99 AUC on average; however, it only required approximately 10% of the computing time of the existing industrial best. MiPo exhibited linear time and space complexity. The features extracted by MiPo may aid other trajectory data mining tasks. We believe that MiPo has the potential to revolutionize the field of trajectory outlier detection. [ABSTRACT FROM AUTHOR]

With the increasing accumulation of spatial-temporal trajectory data, location-based data mining has recently been extensively studied. A fundamental research topic in this field is learning the embedding vectors of locations through self-supervised pre-training. Pre-trained embedding vectors can utilize the highly available unlabeled trajectory data, and benefit downstream tasks in multiple aspects. However, most existing methods ignore the temporal information hidden in the visited time of locations in trajectories. Considering that human activities are highly regulated by specific periods of a day, temporal information can reflect some intrinsic characteristics of locations, so it is necessary to fuse them into location embedding vectors. In this paper, we propose a Time-Aware Location Embedding (TALE) pre-training method based on the CBOW framework, which is able to incorporate temporal information into the learned embedding vectors of locations. A novel temporal tree structure is designed to extract temporal information during the calculation of Hierarchical Softmax. In order to verify the effectiveness of TALE, we apply the learned embedding vectors into three downstream location-based prediction tasks, i.e., location classification, location visitor flow prediction and user next location prediction. Experiments are conducted on four real-world user trajectory datasets, and the experimental results demonstrate that our TALE model can obviously help downstream tasks gain better performance. [ABSTRACT FROM AUTHOR]

We extend the existing group-based trajectory modeling by proposing the network-based trajectory modeling based on judicious design and analysis of a spatio-temporal parse network (STPN) as a representation of neighborhood structure that evolves in time. The STPN offers a principled qualitative specification for an explicit paradigm framework to deal with complex real-world problems. The framework is completed by developing a quantitative specification of latent field representation to merge seamlessly on or alongside the established STPN via hierarchical modeling. The models adopt spatial random effects to characterize the heterogeneity and autocorrelation over the locations where nonlinear trajectories were observed. The trajectories are then investigated in the presence of the operational constraints of the dependence structure induced by the spatial and temporal dimensions. With the framework, complex developmental trajectory problems can be discerned, communicated, diagnosed and modeled in a relatively simple way that interpretation is accessible to nontechnical audiences and quickly comprehensible to technically sophisticated audiences. The proposed modeling is applied to address the challenges of the trajectory modeling of nonlinear dynamics arising from a motivating criminal justice empirical process. [ABSTRACT FROM AUTHOR]

Urban traffic status (e.g., traffic speed and volume) is highly dynamic in nature, namely, varying across space and evolving over time. Thus, predicting such traffic dynamics is of great importance to urban development and transportation management. However, it is very challenging to solve this problem due to spatial-temporal dependencies and traffic uncertainties. In this article, we solve the traffic dynamics prediction problem from Bayesian meta-learning perspective and propose a novel continuous spatial-temporal meta-learner (cST-ML), which is trained on a distribution of traffic prediction tasks segmented by historical traffic data with the goal of learning a strategy that can be quickly adapted to related but unseen traffic prediction tasks. cST-ML tackles the traffic dynamics prediction challenges by advancing the Bayesian black-box meta-learning framework through the following new points: (1) cST-ML captures the dynamics of traffic prediction tasks using variational inference, and to better capture the temporal uncertainties within tasks, cST-ML performs as a rolling window within each task; (2) cST-ML has novel designs in architecture, where CNN and LSTM are embedded to capture the spatial-temporal dependencies between traffic status and traffic-related features; (3) novel training and testing algorithms for cST-ML are designed. We also conduct experiments on two real-world traffic datasets (taxi inflow and traffic speed) to evaluate our proposed cST-ML. The experimental results verify that cST-ML can significantly improve the urban traffic prediction performance and outperform all baseline models especially when obvious traffic dynamics and temporal uncertainties are presented. [ABSTRACT FROM AUTHOR]

Traffic forecasting is highly challenging due to its complex spatial and temporal dependencies in the traffic network. Graph Convolutional Neural Network (GCN) has been effectively used for traffic forecasting due to its excellent performance in modelling spatial dependencies. In most existing approaches, GCN models spatial dependencies in the traffic network with a fixed adjacency matrix. However, the spatial dependencies change over time in the actual situation. In this paper, we propose a graph learning-based spatial-temporal graph convolutional neural network (GLSTGCN) for traffic forecasting. To capture the dynamic spatial dependencies, we design a graph learning module to learn the dynamic spatial relationships in the traffic network. To save training time and computation resources, we adopt dilated causal convolution networks with a gating mechanism to capture long-term temporal correlations in traffic data. We conducted extensive experiments using two real-world traffic datasets. Experimental results demonstrate that the proposed GLSTGCN achieves superior performance than all state-of-art baselines. [ABSTRACT FROM AUTHOR]

Sensor networks composed of static and mobile sensors are applicable for situation monitoring. In this paper, we propose SensorAware, an interactive system for visualizing and exploring spatial–temporal data from static and mobile sensors. Our system follows the procedure starting with an overview, then zoom and filter, and finally details-on-demand. We use pixel-based time-series visualization to show overall readings from individual sensors, and the readings of mobile sensors are aggregated spatially to display the distribution of sensor readings. SensorAware provides cross-filtering and details-on-demand interactions, which allow users to investigate data at different levels of details from both spatial and temporal aspects. [ABSTRACT FROM AUTHOR]

The extensive distribution of portable digital devices brings demands of adapting media to restricted display spaces or various aspect ratios. Most existing content-aware visualization resizing approaches introduce nonlinear deformation to enhance or preserve salient areas while squeezing non-salient ones. Their deformation on image-based geographic context could cause confusion and make it harder to interpret by the general mobile user. In this paper, we describe a deformation-free approach to resize the geovisualization using density map, resulting in a collage layout of sub-maps, called map collage. We show our technique of constructing a collage layout for one frame of geospatial data and a strategy of extending it to the temporal dimension. We demonstrate the results on two sets of geotemporal data and conducted a survey comparing our method, the seam carving, and the uniform scaling, which shows that ours is more preferred than the other two. [ABSTRACT FROM AUTHOR]

Abstract Air quality has drawn much attention in the recent years because it seriously affects people’s health. Nowadays, monitoring stations in a city can provide real-time air quality, but people also strongly desire air quality prediction, which is a challenging problem as it depends on several complicated factors, such as weather patterns and spatial-temporal dependencies of air quality. In this paper, we design a data-driven approach that utilizes historical air quality and meteorological data to predict air quality in the future. We propose a deep spatial-temporal ensemble(STE) model which is comprised of three components. The first component is an ensemble method with a weather-pattern-based partitioning strategy. It trains multiple individual models and combines them dynamically. The second one is to discover spatial correlation by analyzing Granger causalities among stations and generating spatial data as relative stations and relative areas. The last one is a temporal predictor based on deep LSTM to learn both long-term and short-term dependencies of air quality. We evaluate our model with data from 35 monitoring stations in Beijing, China. The experiments show that each component of our model makes contribution to the improvement in prediction accuracy and the model is superior to baselines. [ABSTRACT FROM AUTHOR]

Vecchia’s approximate likelihood for Gaussian process parameters depends on how the observations are ordered, which has been cited as a deficiency. This article takes the alternative standpoint that the ordering can be tuned to sharpen the approximations. Indeed, the first part of the article includes a systematic study of how ordering affects the accuracy of Vecchia’s approximation. We demonstrate the surprising result that random orderings can give dramatically sharper approximations than default coordinate-based orderings. Additional ordering schemes are described and analyzed numerically, including orderings capable of improving on random orderings. The second contribution of this article is a new automatic method for grouping calculations of components of the approximation. The grouping methods simultaneously improve approximation accuracy and reduce computational burden. In common settings, reordering combined with grouping reduces Kullback-Leibler divergence from the target model by more than a factor of 60 compared to ungrouped approximations with default ordering. The claims are supported by theory and numerical results with comparisons to other approximations, including tapered covariances and stochastic partial differential equations. Computational details are provided, including the use of the approximations for prediction and conditional simulation. An application to space-time satellite data is presented. [ABSTRACT FROM AUTHOR]

Deep learning models have emerged as a promising way for traffic prediction. However, the requirement for large amounts of training data remains a significant issue for achieving well-performing models. Data scarcity in real-world scenarios, caused by costly collection or privacy policies, can severely impede the performance of existing deep learning models. Transfer learning aims to leverage knowledge learned from data-sufficient cities to improve prediction performance in data-scarce cities. Unfortunately, most existing methods solely focus on transferring knowledge at the city level, neglecting fine-grained node-level correlations and distribution discrepancies between cities. In this paper, we propose DAGN, a domain adversarial graph neural network that mines inter-city spatial–temporal correlations and alleviates domain distribution discrepancies to address the data scarcity problem in traffic prediction. Specifically, DAGN comprises three key modules: (1) A cross-city graph structure learning module is developed to capture node-pair adjacent relationships across cities, enabling the dynamic aggregation of inter-city spatial–temporal information. Additionally, a graph reconstruction loss is proposed to enforce structural consistency between the learned and priori graphs. (2) A domain adversarial strategy is integrated with a spatial–temporal module, which jointly extracts domain-invariant spatial and temporal features to reduce the distribution discrepancies between cities. (3) To adaptively extract transferable knowledge from a global perspective, a global spatial–temporal attention module is designed. Extensive experiments on six traffic flow and traffic speed prediction benchmarks demonstrate that DAGN consistently outperforms state-of-the-art methods. • A novel DAGN with cross-city graph structure learning is proposed. • First to consider inter-city node-wise adjacencies for knowledge transfer. • CCGSL captures cross-city node correlations, guided by reconstruction loss. • STA extracts domain-invariant features, GSTA adapts global aggregation. • Experiments show our model surpasses SOTA in traffic flow and speed prediction. [ABSTRACT FROM AUTHOR]

Spatio-temporal data are critical for intelligent systems, such as smart transportation and smart cities. However, due to sensor failure or power failure, the spatiotemporal data missing tends to have a big impact on downstream tasks. Meanwhile, if sensors are scarce, some spatial positions without sensors need data enhancement through intelligent methods. Existing workarounds focus on modeling temporal information (such as time series), often ignoring spatial dependency, or modeling the spatial and temporal domain separately for imputation. In this paper, we propose a Long-term Multi-dimensional Spatial–Temporal Graph Convolution Network (LMSTGCN), which not only inductively estimates some missing data, but also achieves data augmentation of target locations. It contains a periodic temporal encoding mechanism, a gated temporal capture module, and a multi-dimensional spatial–temporal GCN module. The long-term temporal dependencies are captured by the periodic temporal encoding mechanism. The spatial and extra-short-term temporal dependencies are simultaneously modeled by the multi-dimensional GCN module, which can achieve exponential growth in the range of receptive fields. Corresponding to this module, we designed a spatiotemporal adjacency matrix construction method. It generates spatiotemporal adjacency matrices of corresponding time length as needed. The short-term dependencies in sequences are captured by the gated temporal capture module. In experimental analysis, results demonstrate that the proposed model outperforms the state-of-the-art baselines on real-world data sets. [ABSTRACT FROM AUTHOR]

• Introduces a new spatial-temporal graph product convolutional framework. • Unifies various existing approaches to spatial-temporal graph learning. • Captures multi-scale spatial-temporal features that were previously neglected. • Achieves better performance in capturing complex spatial-temporal patterns in two real-world applications. Earlier works on dynamic spatial-temporal data modelling prefer using spatial-temporal factorized graph convolutional networks (GCNs), which are easy to interpret but fail to capture joint spatial-temporal correlations. Thus, lots of subsequent research focus on constructing a localized adjacent matrix to capture joint features from both spatial and temporal dimension simultaneously. However, their ways of building the adjacent matrices are usually heuristic, which makes the models difficult to interpret. Meanwhile, the lack of theoretical explanations hinders the model's generalization. We introduce a general framework to model dynamic spatial-temporal graph data from the view of graph product. With the power of graph product, we propose a systematical way of constructing the spatial-temporal adjacent graphs, which can not only improve the model's interpretability but increase the spatial-temporal receptive field. Under the novel framework, the existing methods can be taken as special cases of our model. Extensive experiments on multiple large-scale real-world datasets, NTU-RGB+D60, NTU-RGB+D120, UAV-Human, PEMS03, PEMS04, PEMS07, and PEMS08, demonstrate that the proposed model can generalize to most of the scenarios with a performance improvement in a significant margin compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Exploiting deep spatial–temporal features for traffic prediction has become growing widespread. Accurate traffic prediction is still challenging due to the complex spatial dependencies and time varying temporal dependencies, especially for long-term prediction tasks. Existing studies usually employ pre-defined spatial graphs or learned fixed adjacency graphs and design models to capture spatial and temporal features. However, the pre-defined or fixed graph cannot accurately model the complex hidden structure. In this paper, a novel deep learning framework called Spatial–Temporal Multi-Feature Fusion Network (STMFFN) is proposed to address these challenges. Specifically, a multi-scale attention module with temporal convolution is designed to capture the temporal dependencies from different scales. Then, a gated graph convolution module is proposed, which constructs adaptive adjacency matrices, and integrates graph convolution and graph aggregation modules to capture spatial dependencies from different ranges. Moreover, a multi-feature fusion layer is presented to fuse the extracted spatial and temporal dependencies by obtaining the attention vectors of temporal and spatial features. Experimental results on real-world datasets show a consistent improvement of 6%–9% over state-of-the-art baselines. • Capturing complex spatial–temporal correlations for short and long term prediction. • A multi-scale attention is presented to capture temporal corrections. • A gated graph convolution is proposed to model time varying spatial correlations. • A multi-feature fusion is used to fuse the extracted spatial and temporal features. [ABSTRACT FROM AUTHOR]

Abstract When analyzing human behaviors, we need to construct the human behaviors from multiple sources of data, e.g. trajectory data, transaction data, identity data, etc. The problems we're facing are the data conflicts, different resolution, missing and conflicting data, which together lead to the uncertainty in the spatial temporal data. Such uncertainty in data leads to difficulties and even failure in the visual analytics task for analyzing people behavior, pattern and outliers. However, traditional automatic methods can not solve the problems in such complex scenario, where the uncertain and conflicting patterns are not well-defined. To solve the problems, we proposed a semi-automatic approach, for users to solve the conflicts and identify the uncertainties. To be general, we summarized five types of uncertainties and solutions to conduct the tasks of behavior analysis. Combined with the uncertainty-aware methods, we proposed a visual analytics system to analyze human behaviors, detect patterns and find outliers. Case studies from the IEEE VAST Challenge 2014 dataset confirm the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Big Geo Data promises tremendous benefits to the GIS Science community in particular and the broader scientific community in general, but has been primarily of use to the relatively small body of GIScientists who possess the specialized knowledge and methods necessary for working with this class of data. Much of the greater scientific community is not equipped with the expert knowledge and techniques necessary to fully take advantage of the promise of big spatial data. IPUMS-Terra provides integrated spatiotemporal data to these scholars by simplifying access to thousands of raster and vector datasets, integrating them and providing them in formats that are useable to a broad array of research disciplines. IPUMS-Terra exemplifies a new class of National Spatial Data Infrastructure because it connects a large spatial data repository to advanced computational resources, allowing users to access the needle of information they need from the haystack of big spatial data. The project is trailblazing in its commitment to the open sharing of spatial data and spatial tool development, including describing its architecture, process development workflows, and openly sharing its products for the general use of the scientific community. [ABSTRACT FROM AUTHOR]

Numerical climate model simulations run at high spatial and temporal resolutions generate massive quantities of data. As our computing capabilities continue to increase, storing all of the data is not sustainable, and thus it is important to develop methods for representing the full datasets by smaller compressed versions. We propose a statistical compression and decompression algorithm based on storing a set of summary statistics as well as a statistical model describing the conditional distribution of the full dataset given the summary statistics. We decompress the data by computing conditional expectations and conditional simulations from the model given the summary statistics. Conditional expectations represent our best estimate of the original data but are subject to oversmoothing in space and time. Conditional simulations introduce realistic small-scale noise so that the decompressed fields are neither too smooth nor too rough compared with the original data. Considerable attention is paid to accurately modeling the original dataset—1 year of daily mean temperature data—particularly with regard to the inherent spatial nonstationarity in global fields, and to determining the statistics to be stored, so that the variation in the original data can be closely captured, while allowing for fast decompression and conditional emulation on modest computers. Supplementary materials for this article are available online. [ABSTRACT FROM AUTHOR]

Central to many location-based service applications is the task of processing k-nearest neighbor ( k-NN) queries over moving objects. Many existing approaches adapt different index structures and design various search algorithms to deal with this problem. In these works, tree-based indexes and grid index are mainly utilized to maintain a large volume of moving objects and improve the performance of search algorithms. In fact, tree-based indexes and grid index have their own flaws for supporting processing k-NN queries over an ocean of moving objects. A tree-based index (such as R-tree) needs to constantly maintain the relationship between nodes with objects continuously moving, which usually causes a high maintenance cost. Grid index is widely used to support k-NN queries over moving objects, but the approaches based on grid index almost require an uncertain number of iterative calculations, which makes the performance of these approaches not predictable. To address this problem, we present a dynamic Strip Rectangle Index (SRI), which can reach a good balance between the maintenance cost and the performance of supporting k-NN queries over moving objects. SRI supplies two different index granularities that makes it better adapt to handle different data distributions than existing index structures. Based on SRI, we propose a search algorithm called SR-KNN that can rapidly calculate a final region with a filter-and-refine strategy to enhance the efficiency of process k-NN queries, rather than iteratively enlarging the search space like the grid-index-based approaches. Finally, we conduct experiments to fully evaluate the performance of our proposal. [ABSTRACT FROM AUTHOR]

Location prediction has attracted much attention due to its important role in many location-based services, such as food delivery, taxi-service, real-time bus system, and advertisement posting. Traditional prediction methods often cluster track points into regions and mine movement patterns within the regions. Such methods lose information of points along the road and cannot meet the demand of specific services. Moreover, traditional methods utilizing classic models may not perform well with long location sequences. In this paper, a spatial-temporal-semantic neural network algorithm (STS-LSTM) has been proposed, which includes two steps. First, the spatial-temporal-semantic feature extraction algorithm (STS) is used to convert the trajectory to location sequences with fixed and discrete points in the road networks. The method can take advantage of points along the road and can transform trajectory into model-friendly sequences. Then, a long short-term memory (LSTM)-based model is constructed to make further predictions, which can better deal with long location sequences. Experimental results on two real-world datasets show that STS-LSTM has stable and higher prediction accuracy over traditional feature extraction and model building methods, and the application scenarios of the algorithm are illustrated. [ABSTRACT FROM AUTHOR]

With the rapid spread of built-in GPS handheld smart devices, the trajectory data from GPS sensors has grown explosively. Trajectory data has spatio-temporal characteristics and rich information. Using trajectory data processing techniques can mine the patterns of human activities and the moving patterns of vehicles in the intelligent transportation systems. A trajectory similarity measure is one of the most important issues in trajectory data mining (clustering, classification, frequent pattern mining, etc.). Unfortunately, the main similarity measure algorithms with the trajectory data have been found to be inaccurate, highly sensitive of sampling methods, and have low robustness for the noise data. To solve the above problems, three distances and their corresponding computation methods are proposed in this paper. The point-segment distance can decrease the sensitivity of the point sampling methods. The prediction distance optimizes the temporal distance with the features of trajectory data. The segment-segment distance introduces the trajectory shape factor into the similarity measurement to improve the accuracy. The three kinds of distance are integrated with the traditional dynamic time warping algorithm (DTW) algorithm to propose a new segment–based dynamic time warping algorithm (SDTW). The experimental results show that the SDTW algorithm can exhibit about 57%, 86%, and 31% better accuracy than the longest common subsequence algorithm (LCSS), and edit distance on real sequence algorithm (EDR) , and DTW, respectively, and that the sensitivity to the noise data is lower than that those algorithms. [ABSTRACT FROM AUTHOR]

The efficient sharing of spatio-temporal trajectory data is important to understand traffic congestion in mass data. However, the data volumes of bus networks in urban cities are growing rapidly, reaching daily volumes of one hundred million datapoints. Accessing and retrieving mass spatio-temporal trajectory data in any field is hard and inefficient due to limited computational capabilities and incomplete data organization mechanisms. Therefore, we propose an optimized and efficient spatio-temporal trajectory data retrieval method based on the Cloudera Impala query engine, called ESTRI, to enhance the efficiency of mass data sharing. As an excellent query tool for mass data, Impala can be applied for mass spatio-temporal trajectory data sharing. In ESTRI we extend the spatio-temporal trajectory data retrieval function of Impala and design a suitable data partitioning method. In our experiments, the Taiyuan BeiDou (BD) bus network is selected, containing 2300 buses with BD positioning sensors, producing 20 million records every day, resulting in two difficulties as described in the Introduction section. In addition, ESTRI and MongoDB are applied in experiments. The experiments show that ESTRI achieves the most efficient data retrieval compared to retrieval using MongoDB for data volumes of fifty million, one hundred million, one hundred and fifty million, and two hundred million. The performance of ESTRI is approximately seven times higher than that of MongoDB. The experiments show that ESTRI is an effective method for retrieving mass spatio-temporal trajectory data. Finally, bus distribution mapping in Taiyuan city is achieved, describing the buses density in different regions at different times throughout the day, which can be applied in future studies of transport, such as traffic scheduling, traffic planning and traffic behavior management in intelligent public transportation systems. [ABSTRACT FROM AUTHOR]

This work uses a probabilistic method to combine two unique datasets of real world electric vehicle charging profiles and residential smart meter load demand. The data was used to study the impact of the uptake of Electric Vehicles (EVs) on electricity distribution networks. Two real networks representing an urban and rural area, and a generic network representative of a heavily loaded UK distribution network were used. The findings show that distribution networks are not a homogeneous group with a variation of capabilities to accommodate EVs and there is a greater capability than previous studies have suggested. Consideration of the spatial and temporal diversity of EV charging demand has been demonstrated to reduce the estimated impacts on the distribution networks. It is suggested that distribution network operators could collaborate with new market players, such as charging infrastructure operators, to support the roll out of an extensive charging infrastructure in a way that makes the network more robust; create more opportunities for demand side management; and reduce planning uncertainties associated with the stochastic nature of EV charging demand. [ABSTRACT FROM AUTHOR]

With the explosion of digital data, the need for advanced visual analytics, including coordinated multiple views (CMV), is rapidly increasing. CMV enable users to discover patterns and examine relationships across multiple visualizations of one or multiple datasets. CMV have been implemented in a web-based environment through the Australian Urban Research Infrastructure Network (AURIN) project. AURIN offers a platform providing seamless and secure access to an extensive range of distributed urban datasets across Australia. Visual exploration of these datasets is essential to support research endeavors. This paper focuses on the challenges in dealing with complexity and multidimensionality of datasets used in CMV. We rely on the concept of multidimensional data cubes as the theoretical framework for coordination across visualizations. Using the concept of data cubes and hierarchical dimensions, we present strategies to automatically build render groups. This provides an implicit coordination based on cube structures and a framework to establish links between a dataset with its aggregates in a one-to-many fashion. The CMV approach is demonstrated using aggregate-level data, which is provided through federated data services. The paper discusses the issues around our CMV implementation and concludes by reflecting on the challenges in supporting spatio-temporal urban data exploration. [ABSTRACT FROM AUTHOR]

Magnetoencephalography (MEG) is a common noninvasive imaging modality for instantly measuring whole brain activities. One challenge in MEG data analysis is how to minimize the impact of the outliers that commonly exist in the images. In this article, we propose a robust two-way regularization approach to solve the important MEG inverse problem, that is, reconstructing neuronal activities using the measured MEG signals. The proposed method is based on the distributed source model and produces a spatio-temporal solution for all the dipoles simultaneously. Unlike the traditional methods that use the squared error loss function, our proposal uses a robust loss function, which improves the robustness of the results against outliers. To impose desirable spatial focality and temporal smoothness, we then penalize the robust loss through appropriate spatial–temporal two-way regularization. Furthermore, an alternating reweighted least-squares algorithm is developed to optimize the penalized model fitting criterion. Extensive simulation studies and a real-world MEG study clearly demonstrate the advantages of the proposed method over three nonrobust methods. [ABSTRACT FROM PUBLISHER]

Abstract: The goal of this paper is to compare the performance of two estimation approaches, the quasi-likelihood estimating equation and the pseudo-likelihood equation, against model mis-specification for non-separable binary data. This comparison, to the authors’ knowledge, has not been done yet. In this paper, we first extend the quasi-likelihood work on spatial data to non-separable binary data. Some asymptotic properties of the quasi-likelihood estimate are also briefly discussed. We then use the techniques of a truncated Gaussian random field with a quasi-likelihood type model and a Gibbs sampler with a conditional model in the Markov random field to generate spatial–temporal binary data, respectively. For each simulated data set, both of the estimation methods are used to estimate parameters. Some discussion about the simulation results are also included. [Copyright &y& Elsevier]

Abstract: This paper presents a new density-based clustering algorithm, ST-DBSCAN, which is based on DBSCAN. We propose three marginal extensions to DBSCAN related with the identification of (i) core objects, (ii) noise objects, and (iii) adjacent clusters. In contrast to the existing density-based clustering algorithms, our algorithm has the ability of discovering clusters according to non-spatial, spatial and temporal values of the objects. In this paper, we also present a spatial–temporal data warehouse system designed for storing and clustering a wide range of spatial–temporal data. We show an implementation of our algorithm by using this data warehouse and present the data mining results. [Copyright &y& Elsevier]

With the development of ocean exploration technology and the rapid growth in the amount of marine science observation data, people are faced with a great challenge to identify valuable data from the massive ocean observation data. A recommendation system is an effective method to improve retrieval capabilities to help users obtain valuable data. The two most popular recommendation algorithms are collaborative filtering algorithms and content-based filtering algorithms, which may not work well for marine science observation data given the complexity of data attributes and lack of user information. In this study, an approach was proposed based on data similarity and data correlation. Data similarity was calculated by analyzing the subject, source, spatial, and temporal attributes to obtain the recommendation list. Then, data correlation was calculated based on the literature on marine science data and ranking of the recommendation list to obtain the re-rank recommendation list. The approach was tested by simulated datasets collected from multiple marine data sharing websites, and the result suggested that the proposed method exhibits better effectiveness. [ABSTRACT FROM AUTHOR]

Mobile social networking services provide efficient and easy communication, enabling users to create, retrieve and disseminate messages on the go while making their messages widely available. Despite growing evidence suggesting that geographic location and distance restrict online communication and interaction patterns, the role of geographic factors on the information dissemination in mobile social networks is often overlooked. We conducted a large-scale analysis on how the geographic factors influence the information dissemination in mobile social networks, by using two different datasets which recorded billions of users’ viewing and forwarding activities corresponding as well as the temporal and geographic information. The effects of two geographic factors, namely location and distance, on the probability and velocity of information dissemination were explored by measuring the geographic distribution of the four key indicators, namely viewing probability, forwarding probability, response time, and decision-making time. The results verify the distance decay effect of the information dissemination probability, and demonstrate that the velocity of information dissemination is not dependent on geographic distance. Furthermore, both the probability and velocity of information dissemination show heterogeneity and diversity of geographic location. Our research makes up for the gap in the relationship between geographic factors and information dissemination in mobile social networks. Our findings can provide suggestions for mobile social services, public opinion regulation and precision marketing. [ABSTRACT FROM AUTHOR]

As one of the most popular social networking services in the world, Twitter allows users to post messages along with their current geographic locations. Such georeferenced or geo-tagged Twitter datasets can benefit location-based services, targeted advertising and geosocial studies. Our study focused on the detection of small-scale spatial-temporal events and their textual content. First, we used Spatial-Temporal Density-Based Spatial Clustering of Applications with Noise (ST-DBSCAN) to spatially-temporally cluster the tweets. Then, the word frequencies were summarized for each cluster and the potential topics were modeled by the Latent Dirichlet Allocation (LDA) algorithm. Using two years of Twitter data from four college cities in the U.S., we were able to determine the spatial-temporal patterns of two known events, two unknown events and one recurring event, which then were further explored and modeled to identify the semantic content about the events. This paper presents our process and recommendations for both finding event-related tweets as well as understanding the spatial-temporal behaviors and semantic natures of the detected events. [ABSTRACT FROM AUTHOR]