Search

This paper proposes a dynamic infectious disease model for COVID-19 daily counts data and estimate the model using the Langevinized EnKF algorithm, which is scalable for large-scale spatio-temporal data, converges to the right filtering distribution, and is thus suitable for performing statistical inference and quantifying uncertainty for the underlying dynamic system. Under the framework of the proposed dynamic infectious disease model, we tested the impact of temperature, precipitation, state emergency order and stay home order on the spread of COVID-19 based on the United States county-wise daily counts data. Our numerical results show that warm and humid weather can significantly slow the spread of COVID-19, and the state emergency and stay home orders also help to slow it. This finding provides guidance and support to future policies or acts for mitigating the community transmission and lowering the mortality rate of COVID-19. [ABSTRACT FROM AUTHOR]

Forest fires have frequently occurred and caused great harm to people's lives. Many researchers use machine learning techniques to predict forest fires by considering spatio-temporal data features. However, it is difficult to efficiently obtain the features from large-scale, multi-source, heterogeneous data. There is a lack of a method that can effectively extract features required by machine learning-based forest fire predictions from multi-source spatio-temporal data. This paper proposes a forest fire prediction method that integrates spatio-temporal knowledge graphs and machine learning models. This method can fuse multi-source heterogeneous spatio-temporal forest fire data by constructing a forest fire semantic ontology and a knowledge graph-based spatio-temporal framework. This paper defines the domain expertise of forest fire analysis as the semantic rules of the knowledge graph. This paper proposes a rule-based reasoning method to obtain the corresponding data for the specific machine learning-based forest fire prediction methods, which are dedicated to tackling the problem with real-time prediction scenarios. This paper performs experiments regarding forest fire predictions based on real-world data in the experimental areas Xichang and Yanyuan in Sichuan province. The results show that the proposed method is beneficial for the fusion of multi-source spatio-temporal data and highly improves the prediction performance in real forest fire prediction scenarios. [ABSTRACT FROM AUTHOR]

The Modifiable Aerial Unit Problem (MAUP) influences the interpretation of spatial data in that forms of spatial aggregation creates scale and segmentation ecological fallacies. This paper explores the extent to which similar scalar and segmentation issues affect the analysis of temporal data. The analogy of gerrymandering in spatial data, which is the purposeful segmentation of space such that the underlying aggregations prove a specific point, is used to demonstrate segmentation and aggregation effects on time series data. To do so, the paper evaluates real-time sound monitoring data for Dublin, Ireland at multiple aggregation scales and segmentations to determine their effects with respect to compliance with European Union regulations concerning acceptable decibel levels. Like the MAUP, increasing scales of temporal aggregation remove extremes at more local scales, which has the effect of reducing measurements of non-compliance. Similarly, and unlike the spatial equivalent, because of circadian human social patterns, segmentation of temporal measurements also has a predictable, and gerrymander-able, effect on the measurement of compliance with ambient sound limits. The effect is computed as the Temporal Aggregation Bias and strategies which could justify gerrymandering of sound monitoring data are presented. [ABSTRACT FROM AUTHOR]

The forecasting of electricity sales is directly related to the power generation planning of power enterprises and the progress of the generation tasks. Aiming at the problem that traditional forecasting methods cannot properly deal with the actual data offset caused by external factors, such as the weather, season, and spatial attributes, this paper proposes a method of electricity sales forecasting based on a deep spatio-temporal residual network (ST-ResNet). The method not only relies on the temporal correlation of electricity sales data but also introduces the influence of external factors and spatial correlation, which greatly enhances the fitting degree of each parameter of the model. Moreover, the residual module and the convolution module are fused to effectively reduce the damage of the deep convolutional process to the training effectiveness. Finally, the three comparison experiments of the ultra-short term, short term and medium term show that the MAPE forecasted by the ST-ResNet model is at least 2.69% lower than that of the RNN and other classical Deep Learning models, that its RMSE is at least 36.2% lower, and that its MAD is at least 34.2% lower, which is more obvious than the traditional methods. The effectiveness and feasibility of the ST-ResNet model in the short-term forecasting of electricity sales are verified. [ABSTRACT FROM AUTHOR]

With the fast development of various positioning techniques such as Global Position System (GPS), mobile devices and remote sensing, spatio-temporal data has become increasingly available nowadays. Mining valuable knowledge from spatio-temporal data is critically important to many real-world applications including human mobility understanding, smart transportation, urban planning, public safety, health care and environmental management. As the number, volume and resolution of spatio-temporal data increase rapidly, traditional data mining methods, especially statistics-based methods for dealing with such data are becoming overwhelmed. Recently deep learning models such as recurrent neural network (RNN) and convolutional neural network (CNN) have achieved remarkable success in many domains due to the powerful ability in automatic feature representation learning, and are also widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, anomaly detection and classification. In this paper, we provide a comprehensive review of recent progress in applying deep learning techniques for STDM. We first categorize the spatio-temporal data into five different types, and then briefly introduce the deep learning models that are widely used in STDM. Next, we classify existing literature based on the types of spatio-temporal data, the data mining tasks, and the deep learning models, followed by the applications of deep learning for STDM in different domains including transportation, on-demand service, climate & weather analysis, human mobility, location-based social network, crime analysis, and neuroscience. Finally, we conclude the limitations of current research and point out future research directions. [ABSTRACT FROM AUTHOR]

Spatially fine-grained urban flow data is critical for smart city efforts. Though fine-grained information is desirable for applications, it demands much more resources for the underlying storage system compared to coarse-grained data. To bridge the gap between storage efficiency and data utility, in this paper, we aim to infer fine-grained flows throughout a city from their coarse-grained counterparts. This task exhibits two challenges: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a model entitled UrbanFM which consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs that uses a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influence of different external factors. This structure provides outstanding effectiveness and efficiency for small scale upsampling. However, the single-pass upsampling used by UrbanFM is insufficient at higher upscaling rates. Therefore, we further present UrbanPy, a cascading model for progressive inference of fine-grained urban flows by decomposing the original tasks into multiple subtasks. Compared to UrbanFM, such an enhanced structure demonstrates favorable performance for larger-scale inference tasks. [ABSTRACT FROM AUTHOR]

Traffic flow prediction is of paramount importance in the field of spatio-temporal forecasting. In recent years, research efforts have primarily been directed towards developing intricate graph convolutional networks (GCNs) to capture spatial complexities. However, this has inadvertently led to the neglect of the inherent temporal correlations in traffic prediction, as well as the heterogeneity of graph structures. As a result, existing models show limited efficacy when dealing with the complex nature of traffic data. To address this issue, this paper introduces a novel traffic prediction model: the Fourier-enhanced heterogeneous graph convolution attention recurrent network (FEHGCARN). This model integrates historical information and incorporates a graph convolution attention recurrent unit (GCARU), meticulously engineered to effectively capture spatio-temporal dependencies. Additionally, it features a Fourier-enhanced heterogeneous graph learning module, which facilitates the acquisition of complex relationships among nodes in the frequency domain. Notably, this memory network excels at recognizing abrupt traffic conditions. To validate our approach, we conducted comprehensive comparisons using three authentic datasets and benchmarked our model against six state-of-the-art baseline methods. The experimental results unequivocally demonstrate the superior performance of our model across all evaluation metrics. • Fourier-enhanced heterogeneous graph convolution attention recurrent network. • Capturing spatio-temporal dependencies in graph convolution attention units. • The novel approach is the Fourier-enhanced heterogeneous graph learner. • Our model surpasses baselines, achieving state-of-the-art results in experiments. [ABSTRACT FROM AUTHOR]

Spatio-temporal data are common in practice. Existing methods for analyzing such data often employ parametric modelling with different sets of model assumptions. However, spatio-temporal data in practice often have complicated structures, including complex spatial and temporal data variation, latent spatio-temporal data correlation, and unknown data distribution. Because such data structures reflect the complicated impact of confounding variables, such as weather, demographic variables, life styles, and other cultural and environmental factors, they are usually too complicated to describe by parametric models. In this paper, we suggest a general modelling framework for estimating the mean and covariance functions of spatio-temporal data using a three-step local smoothing procedure. The suggested method can well accommodate the complicated structure of real spatio-temporal data. Under some regularity conditions, the consistency of the proposed estimators is established. Both simulation studies and a real-data application show that our proposed method could work well in practice. [ABSTRACT FROM AUTHOR]

With the rapid development of economy and the frequent occurrence of air pollution incidents, the problem of air pollution has become a hot issue of concern to the whole people. The air quality big data is generally characterized by multi-source heterogeneity, dynamic mutability, and spatial–temporal correlation, which usually uses big data technology for air quality analysis after data fusion. In recent years, various models and algorithms using big data techniques have been proposed. To summarize these methodologies of air quality study, in this paper, we first classify air quality monitoring by big data techniques into three categories, consisting of the spatial model, temporal model and spatial–temporal model. Second, we summarize the typical methods by big data techniques that are needed in air quality forecasting into three folds, which are statistical forecasting model, deep neural network model, and hybrid model, presenting representative scenarios in some folds. Third, we analyze and compare some representative air pollution traceability methods in detail, classifying them into two categories: traditional model combined with big data techniques and data-driven model. Finally, we provide an outlook on the future of air quality analysis with some promising and challenging ideas. • The air quality early warning system are systematically reviewed. • Some air quality analysis methods by big data techniques are overviewed. • The difficulties and some ideas of air quality research are discussed briefly. [ABSTRACT FROM AUTHOR]

Multivariate statistics have gained a respectable place in quantitative research, especially in the economic geography, socio-economic development, urban and regional planning and spatio-temporal analysis. The main goal is to reduce multidimensional data to simple, but meaningful representative information. One of the powerful methods in multivariate statistics is Principal Component Analysis (PCA). The aim of this paper is to define a novel Spatio-Temporal Principal Component Analysis (STPCA). It is the first solution that sensibly combines at the same time variability of the values of the observed features, time of observation of the considered features and place of observation. It is therefore a solution for spatio-temporal data and a very valuable tool for practitioners wishing to obtain useful inferences from a PCA. The inclusion of the time and place of observation, in addition to the variability of the values of features, results in more detailed division of the examined objects into homogeneous clusters. Space and time, which interact with each other, are used on equal terms in the construction of the STPCA. The definition of these principal components is based on the product of two factors. The first factor is equal to the variance of the functional principal components, and the second factor is Geary's contiguity ratio C. The proposed new method of Spatio-Temporal Principal Components was used to show the mutual location of 16 Polish regions characterized by 12 socio-economic features observed in the years 2002–2018 in the system of the first two principal components and to identify homogeneous clusters of these regions in the system of all 15 constructed principal components. • The paper extends classical Principal Component Analysis (PCA) by taking into • consideration spatio-temporal socio-economic measurements of geographical space. • It converts spatial point data into continuous functions of regions orchestrating • developments over time, based on functional PCA. • It composes and employs an advanced statistical-mathematical methodology for dealing with spatio-temporal dependencies among multivariate data using Moran's I index. • It carries out a sensitivity analysis on an extensive range of alternative spatial weight systems, with an application to Polish regions. [ABSTRACT FROM AUTHOR]

Defining a multi-target motion model, an important step of tracking algorithms, is a challenging task due to various factors, from its theoretical formulation to its computational complexity. Using fixed models (as in several generative Bayesian algorithms, such as Kalman filters) can fail to accurately predict sophisticated target motions. On the other hand, sequential learning of the motion model (for example, using recurrent neural networks) can be computationally complex and difficult due to the variable unknown number of targets. In this paper, we propose a multi-target filtering and tracking algorithm which learns the motion model, simultaneously for all targets. It does so from an implicitly represented state map and performing spatio-temporal data prediction. To this end, the multi-target state is modeled over a continuous hypothetical target space, using random finite sets and Gaussian mixture probability hypothesis density formulations. The prediction step is recursively performed using a deep convolutional recurrent neural network with a long short-term memory architecture, which is trained as a regression block, on the fly, over probability density difference maps. Our approach is evaluated over widely used pedestrian tracking benchmarks, remarkably outperforming state-of-the-art multi-target filtering algorithms, while giving competitive results when compared with other tracking approaches: The proposed approach generates an average 40.40 and 62.29 optimal sub-pattern assignment errors on MOT15 and MOT16/17 datasets, respectively, while producing 62.0%, 70.0%, and 66.9% multi-object tracking accuracy on MOT16/17, PNNL Parking Lot, and PETS09 pedestrian tracking datasets, respectively, when publicly available detectors are used. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel methodology to design optimal precoders for distributed detection of high-dimensional signals. We consider a wireless sensor network (WSN) that consists of multiple sensors that are spatially distributed in a region of interest and a fusion center (FC). The sensors observe an unknown high-dimensional signal and forward their observations to the FC after precoding. The sensors collect data over both temporal and spatial domains. The FC performs a binary hypothesis test based on the data received from the sensors over noisy channels. In this setup, we present a technique to design optimal online linear precoding strategies with transmit power constraints. We show analytically that the error exponents achieved by the proposed precoders are independent of the signal dimension. In contrast, the error exponents of the state-of-the-art precoding strategies deteriorate with the increase in signal dimension. We verify our analysis via numerical simulations and show that the proposed precoders achieve better detection performance compared to those of other state-of-the-art techniques known in the literature. [ABSTRACT FROM AUTHOR]

Driven by the GPS-enabled devices and wireless communication technologies, the researches and applications on spatio-temporal databases have received significant attentions during the past decade. Hence, large trajectory datasets are extremely necessary to test high performance algorithms for these applications and researches. However, real-world datasets are not accessible in many cases due to privacy concerns and business competition. For this reason, we propose a feature-preserving model FTS to generate new trajectories in this work. The proposed model is composed of three components: 1) Extracting data features from the original dataset. 2) Generating new trajectories. 3) Validating the result by comparing the features of generated trajectories with the given dataset. However, it is hard to make the diverse features of generated dataset consistent with those of original dataset. To tackle this challenging problem, we present several novel algorithms in this paper. Extensive experiments based on real trajectory datasets exhibit that the synthetic datasets generated by FTS preserve the features of original datasets successfully. [ABSTRACT FROM AUTHOR]

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

In team sports like soccer, utilizing tracking data for analysis is challenging due to the dynamic and multi-agent nature of the data. The biggest issue surrounds the changing of positions or “roles” between players on a frame-to-frame basis, which causes misalignment of the data and makes it difficult to perform team analysis. In this paper, we present an unsupervised method to learn a formation template which allows us to “align” the tracking data at the frame level. Not only does this approach give important contextual information to facilitate large-scale analysis (e.g., we know when a player is in the left-wing position compared to left-back), it also yields the team structure or “formation” which serves as a strong descriptor for identifying a team’s style. The utility of the approach is demonstrated on a full season of player and ball tracking data from a professional soccer league consisting of over 21.5 million frames of player tracking data. [ABSTRACT FROM PUBLISHER]

This paper will critically assess the utility of conventional and novel data sources for building fine-scale spatio-temporal estimates of the ambient population. It begins with a review of data sources employed in existing studies of the ambient population, followed by preliminary analysis to further explore the utility of each dataset. The identification and critiquing of data sources which may be useful for building estimates of the ambient population are novel contributions to the literature. This paper will provide a framework of reference for researchers within urban analytics and other areas where an accurate measurement of the ambient population is required. This work has implications for national and international applications where accurate small area estimates of the ambient population are crucial in the planning and management of urban areas, the development of realistic models and informing policy. This research highlights workday population estimates, in conjunction with footfall camera and Wi-Fi sensors data as potentially valuable for building estimates of the ambient population. [ABSTRACT FROM AUTHOR]

In recent years, with the development of various types of public transportation, they are also more and more closely connected. Among them, subway transportation has become the first choice of major cities. However, the planning of subway stations is very difficult and there are many factors to consider. Besides, few methods for selecting optimal station locations take other public transport in to consideration. In order to study the relationship between different types of public transportation, the authors collected and analyzed the travel data of subway passengers and the passenger trajectory data of taxis. In this paper, a method based on LeaderRank and Gaussian Mixed Model (GMM) is proposed to conduct subway station locations selection. In this method, the author builds a subway-passenger traffic zone weighted network and a station location prediction model. First, we evaluate the nodes in the network, then use the GPS track data of taxis to predict the location of new stations in future subway construction, and analyze and discuss the land use characteristics in the prediction area. Taking the design of the Beijing subway line as an example, the suitability of this method is illustrated. [ABSTRACT FROM AUTHOR]

Abstract: The widespread deployment of technologies with tracking capabilities, like GPS, GSM, RFID and on-line social networks, allows mass collection of spatio-temporal data about their users. As a consequence, several methods aimed at anonymizing spatio-temporal data before their publication have been proposed in recent years. Such methods are based on a number of underlying privacy models. Among these models, claims to extend the widely used k-anonymity concept by exploiting the spatial uncertainty in the trajectory recording process. In this paper, we prove that, for any (that is, whenever there is actual uncertainty), does not offer trajectory k-anonymity, that is, it does not hide an original trajectory in a set of k indistinguishable anonymized trajectories. Hence, the methods based on , like Never Walk Alone (NWA) and Wait For Me (W4M) can offer trajectory k-anonymity only when (no uncertainty). Thus, the idea of exploiting the recording uncertainty to achieve trajectory k-anonymity with information loss inversely proportional to turns out to be flawed. [Copyright &y& Elsevier]

Movement ecology is a field which places movement as a basis for understanding animal behavior. To realize this concept, ecologists rely on data collection technologies providing spatio-temporal data in order to analyze movement. Recently, wireless sensor networks have offered new opportunities for data collection from remote places through multi-hop communication and collaborative capability of the nodes. Several technologies can be used in such networks for sensing purposes and for collecting spatio-temporal data from animals. In this paper, we investigate and review technological solutions which can be used for collecting data for wildlife monitoring. Our aim is to provide an overview of different sensing technologies used for wildlife monitoring and to review their capabilities in terms of data they provide for modeling movement behavior of animals. [ABSTRACT FROM AUTHOR]

The research reported in this paper uses wireless sensor networks to provide salient information about spatially distributed dynamic fields, such as regional variations in temperature or concentration of a toxic gas. The focus is on deriving qualitative descriptions of salient changes to areas of high-activity that occur during the temporal evolution of the field. The changes reported include region merging or splitting, and hole formation or elimination. Such changes are formally characterized, and a distributed qualitative change reporting (QCR) approach is developed that detects the qualitative changes simply based on the connectivity between the sensor nodes without location information. The efficiency of the QCR approach is investigated using simulation experiments. The results show that the communication cost of the QCR approach in monitoring large-scale phenomena is an order of magnitude lower than that using the standard boundary-based data collection approach, where each node is assumed to have its location information. [ABSTRACT FROM AUTHOR]

Abstract: Urban public parks can serve an important function by contributing to urban citizens’ quality of life. At the same time, they can be the location of processes of displacement and exclusion. Despite this ambiguous role, little is known about actual park use patterns. To learn more about park use in three parks in Zurich, Switzerland, extensive data on visitor activities was collected using a new method based on direct recording via a portable GIS solution. Then, the data was analyzed using qualitative and quantitative methods. This paper examines whether geographic visualization of these data can help domain experts like landscape designers and park managers to assess park use. To maximize accessibility, the visualizations are made available through a web-interface of a common, off-the-shelf GIS. The technical limitations imposed by this choice are critically assessed, before the available visualization techniques are evaluated in respect to the needs and tasks of practitioners with limited knowledge on spatial analysis and GIS. Key criteria are each technique’s level of abstraction and graphical complexity. The utility and suitability of the visualization techniques is characterized for the distinct phases of exploration, analysis and synthesis. The findings suggest that for a target user group of practitioners, a combination of dot maps showing the raw data and surface maps showing derived density values for several attributes serves the purpose of knowledge generation best. [Copyright &y& Elsevier]

Abstract: Trajectories are spatio-temporal traces of moving objects which contain valuable information to be harvested by spatio-temporal data mining techniques. Applications like city traffic planning, identification of evacuation routes, trend detection, and many more can benefit from trajectory mining. However, the trajectories of individuals often contain private and sensitive information, so anyone who possess trajectory data must take special care when disclosing this data. Removing identifiers from trajectories before the release is not effective against linkage type attacks, and rich sources of background information make it even worse. An alternative is to apply transformation techniques to map the given set of trajectories into another set where the distances are preserved. This way, the actual trajectories are not released, but the distance information can still be used for data mining techniques such as clustering. In this paper, we show that an unknown private trajectory can be reconstructed using the available background information together with the mutual distances released for data mining purposes. The background knowledge is in the form of known trajectories and extra information such as the speed limit. We provide analytical results which bound the number of the known trajectories needed to reconstruct private trajectories. Experiments performed on real trajectory data sets show that the number of known samples is surprisingly smaller than the actual theoretical bounds. [Copyright &y& Elsevier]

Abstract: The integration of time and space is the key to the research on Temporal Geographic Information System (TGIS). This paper will do some research on the integration method of spatio-temporal data at the spatial database level combining with requirements of cadastral management. Firstly, making analysis on the widely used integration method regarding time as attribute and its corresponding query method, the author thinks that there are some disadvantages on the expression of time semantics and efficiency of querying historical data in this algorithm. Taking these disadvantages into consideration, a new integration method, a time-based integration method, is proposed. In this method, time, as the independent time sequence, becomes the organizational basis for recording changes and intuitionally records the changing process of each spatial entity as time changes. Compared to the method regarding time as attribute, the time-based integration method can express time semantics better and provides a solution for improving backtracking query efficiency by reducing times of backtracking query. [Copyright &y& Elsevier]

The efficient analysis of spatio-temporal data, generated by moving objects, is an essential requirement for intelligent location-based services. Spatio-temporal rules can be found by constructing spatio-temporal baskets, from which traditional association rule mining methods can discover spatio-temporal rules. When the items in the baskets are spatio-temporal identifiers and are derived from trajectories of moving objects, the discovered rules represent frequently travelled routes. For some applications, e.g., an intelligent ridesharing application, these frequent routes are only interesting if they are long and sharable, i.e., can potentially be shared by several users. This paper presents a database projection based method for efficiently extracting such long, sharable frequent routes. The method prunes the search space by making use of the minimum length and sharable requirements and avoids the generation of the exponential number of sub-routes of long routes. Considering alternative modelling options for trajectories, leads to the development of two effective variants of the method. SQL-based implementations are described, and extensive experiments on both real life- and large-scale synthetic data show the effectiveness of the method and its variants. [ABSTRACT FROM AUTHOR]

Road traffic congestion is a common problem in most large cities, and exploring the root causes is essential to alleviate traffic congestion. Travel behavior is closely related to the built environment, and affects road travel speed. This paper investigated the direct effect of built environment on the average travel speed of road traffic. Taxi trajectories were divided into 30 min time slot (48 time slots throughout the day) and matched to the road network to obtain the average travel speed of road segments. The Points of Interest (POIs) in the buffer zone on both sides of the road segment were used to calculate the built environment indicators corresponding to the road segment, and then a spatial panel data model was proposed to assess the influence of the built environment adjacent to the road segment on the average travel speed of the road segment. The results demonstrated that the bus stop density, healthcare service density, sports and leisure service density, and parking entrance and exit density are the key factors that positively affect the average road travel speed. The residential community density and business building density are the key factors that negatively affect the average travel speed. Built environments have spatial correlation and spatial heterogeneity in their influence on the average travel speed of road segments. Findings of this study may provide useful insights for understanding the correlation between road travel speed and built environment, which would have important implications for urban planning and governance, traffic demand forecasting and traffic system optimization. [ABSTRACT FROM AUTHOR]

In video processing, background initialization aims to obtain a scene without foreground objects. Recently, the background initialization problem has attracted the attention of researchers because of its real-world applications, such as video segmentation, computational photography, video surveillance, etc. However, the background initialization problem is still challenging because of the complex variations in illumination, intermittent motion, camera jitter, shadow, etc. This paper proposes a novel and effective background initialization method using singular spectrum analysis. Firstly, we extract the video's color frames and split them into RGB color channels. Next, RGB color channels of the video are saved as color channel spatio-temporal data. After decomposing the color channel spatio-temporal data by singular spectrum analysis, we obtain the stable and dynamic components using different eigentriple groups. Our study indicates that the stable component contains a background image and the dynamic component includes the foreground image. Finally, the color background image is reconstructed by merging RGB color channel images obtained by reshaping the stable component data. Experimental results on the public scene background initialization databases show that our proposed method achieves a good color background image compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Taxi waiting times is an important criterion for taxi passengers to choose appropriate pick-up locations in urban environments. How to predict the taxi waiting time accurately at a certain time and location is the key solution for the imbalance between the taxis' supplies and demands. Considering the life schedule of urban residents and the different functions of geogrid regions, the research developed in this paper introduces a spatio-temporal schedule-based neural network for urban taxi waiting time prediction. The approach integrates a series of multi-source data from taxi trajectories to city points of interest, different time frames and human behaviors in the city. We apply a grid-based and functional structuration of an urban space that provides a lower-level data representation. Overall, the neural network model can dynamically predict the waiting time of taxi passengers in real time under some given spatio-temporal constraints. The experimental results show that the granular-based grids and spatio-temporal neural network can effectively predict and optimize the accuracy of taxi waiting times. This work provides a decision support for intelligent travel predictions of taxi waiting time in a smart city. [ABSTRACT FROM AUTHOR]

To monitor the Earth's surface, the satellite of the NASA Landsat program provides us image sequences of any region on the Earth constantly over time. These image sequences give us a unique resource to study the Earth's surface, changes of the Earth resource over time, and their implications in agriculture, geology, forestry, and more. Besides natural sciences, image sequences are also commonly used in functional magnetic resonance imaging (fMRI) of medical studies for understanding the functioning of brains and other organs. In practice, observed images almost always contain noise and other contaminations. For a reliable subsequent image analysis, it is important to remove such contaminations in advance. This paper focuses on image sequence denoising, which has not been well-discussed in the literature yet. To this end, an edge-preserving image denoising procedure is suggested. The suggested method is based on a jump-preserving local smoothing procedure, in which the bandwidths are chosen such that the possible spatio-temporal correlations in the observed image intensities are accommodated properly. Both theoretical arguments and numerical studies show that this method works well in the various cases considered. [ABSTRACT FROM AUTHOR]

Despite pressing need, current relational database management systems (RDBMS) support for spatio-temporal data is limited and inadequate, and most existing spatio-temporal indices cannot be readily integrated into existing RDBMSs. This paper proposes a practical index for spatio-temporal (PIST) data, an indexing technique, rather than a new indexing structure, for historical spatio-temporal data points that can be fully integrated within existing RDBMSs. PIST separates the spatial and temporal components of the data. For the spatial component, we develop a formal cost model and a partitioning strategy that leads to an optimal space partitioning for uniformly distributed data and an efficient heuristic partitioning for arbitrary data distributions. For the temporal component of the data a B + -tree is used. We show that this layer’s performance can be maximized if an optimal maximal temporal range is enforced, and we present a procedure to determine such an optimal value. Being fully mapped onto a RDBMS, desirable and important properties, such as concurrency control, are immediately inherited by PIST. Using ORACLE as our implementation platform we perform extensive experiments with both real and synthetic datasets comparing its performance against other RDBMS-based options, as well as the MV3R-tree. PIST outperforms the former by at least one order of magnitude, and is competitive or better with respect to the latter, with the unarguable advantage that it can readily used on top of virtually any existing RDBMS. [ABSTRACT FROM AUTHOR]

• Review of occupant behavior modeling methods in Building Science and beyond. • Bridge the knowledge gap between Building Science and other domains. • Cross comparison of the modeling requirements in different domains. • Summary of the various metrics for model accuracy evaluation. Traditional occupant behavior modeling has been studied at the building level, and it has become an important factor in the investigation of building energy consumption. However, studies modeling occupant behaviors at the urban scale are still limited. Recent work has revealed that urban big data can enable occupant behavior modeling at the urban scale – however, utilizing the existing data sources and modeling methods in building science to model urban scale occupant behaviors can be quite challenging. Beyond building science, urban scale human behaviors have been studied in several different domains using more advanced modeling methods, including Stochastic Modeling, Neural Networks, Reinforcement Learning, Network Modeling, etc. This paper aims to bridge the gap between data sources and modeling methodologies in building science by borrowing from other domains. Based on a comprehensive review, we 1) identify the modeling challenges of the current approaches in building science, 2) discuss the modeling requirements and data sources both in building science and other domains, 3) review the current modeling methods in building science and other domains, and 4) summarize available performance evaluation metrics for evaluating the modeling methods. Finally, we present future opportunities in building science with enhanced data sources and modeling methods from other domains. [ABSTRACT FROM AUTHOR]

As mobile phone technology evolves quickly, people could use mobile phones to conduct business, watch entertainment shows, order food, and many more. These location-based services (LBS) require users' mobility data (trajectories) in order to provide many useful services. Latent patterns and behavior that are hidden in trajectory data should be extracted and analyzed to improve location-based services including routing, recommendation, urban planning, traffic control, etc. While LBSs offer relevant information to mobile users based on their locations, revealing such areas can pose user privacy violation problems. An efficient privacy preservation algorithm for trajectory data must have two characteristics: utility and privacy, i.e., the anonymized trajectories must have sufficient utility for the LBSs to carry out their services, and privacy must be intact without any compromise. Literature on this topic shows many methods catering to trajectories based on GPS data. In this paper, we propose a privacy preserving method for trajectory data based on Call Detail Record (CDR) information. This is useful as a vast number of people, particularly in underdeveloped and developing places, either do not have GPS-enabled phones or do not use them. We propose a novel framework called Privacy-Preserving Trajectory Publication Framework for CDR (PPTPF) for moving object trajectories to address these concerns. Salient features of PPTPF include: (a) a novel stay-region based anonymization technique that caters to important locations of a user; (b) it is based on Spark, thus it can process and anonymize a significant volume of trajectory data successfully and efficiently without affecting LBSs operations; (c) it is a component-based architecture where each component can be easily extended and modified by different parties. [ABSTRACT FROM AUTHOR]

Detecting change-points and trends are common tasks in the analysis of remote sensing data. Over the years, many different methods have been proposed for those purposes, including (modified) Mann–Kendall and Cox–Stuart tests for detecting trends; and Pettitt, Buishand range, Buishand U, standard normal homogeneity (Snh), Meanvar, structure change (Strucchange), breaks for additive season and trend (BFAST), and hierarchical divisive (E.divisive) for detecting change-points. In this paper, we describe a simulation study based on including different artificial, abrupt changes at different time-periods of image time series to assess the performances of such methods. The power of the test, type I error probability, and mean absolute error (MAE) were used as performance criteria, although MAE was only calculated for change-point detection methods. The study reveals that if the magnitude of change (or trend slope) is high, and/or the change does not occur in the first or last time-periods, the methods generally have a high power and a low MAE. However, in the presence of temporal autocorrelation, MAE raises, and the probability of introducing false positives increases noticeably. The modified versions of the Mann–Kendall method for autocorrelated data reduce/moderate its type I error probability, but this reduction comes with an important power diminution. In conclusion, taking a trade-off between the power of the test and type I error probability, we conclude that the original Mann–Kendall test is generally the preferable choice. Although Mann–Kendall is not able to identify the time-period of abrupt changes, it is more reliable than other methods when detecting the existence of such changes. Finally, we look for trend/change-points in land surface temperature (LST), day and night, via monthly MODIS images in Navarre, Spain, from January 2001 to December 2018. [ABSTRACT FROM AUTHOR]

Extracting features from crowd flow analysis has become an important research challenge due to its social cost and the impact of inadequate planning of high-quality services and security monitoring on the lives of citizens. This paper descriptively reviews and compares existing crowd analysis approaches based on different data sources. This survey provides the fundamentals of crowd analysis and considers three main approaches: crowd video analysis, crowd spatio-temporal analysis, and crowd social media analysis. The key research contributions in each approach are presented, and the most significant techniques and algorithms used to improve the precision of results that could be integrated into solutions to enhance the quality of services in a smart city are analyzed. [ABSTRACT FROM AUTHOR]

Sensor networks generate substantial amounts of frequently updated, highly dynamic data that are transmitted as packets in a data stream. The high frequency and continuous unbound nature of data streams leads to challenges when deriving knowledge from the underlying observations. This paper presents (1) a state of the art review into visual analytics of geospatial, spatio-temporal streaming data, and (2) proposes a framework based on the identified gaps from the review. The framework consists of (1) the data model that characterizes the sensor observation data, (2) the user model, which addresses the user queries and manages domain knowledge, (3) the design model, which handles the patterns that can be uncovered from the data and corresponding visualizations, and (4) the visualization model, which handles the rendering of the data. The conclusion from the visualization model is that streaming sensor observations require tools that can handle multivariate, multiscale, and time series displays. The design model reveals that the most useful patterns are those that show relationships, anomalies, and aggregations of the data. The user model highlights the need for handling missing data, dealing with high frequency changes, as well as the ability to review retrospective changes. [ABSTRACT FROM AUTHOR]