Understanding individual human mobility is critical for a wide range of applications. Real-world trajectory datasets provide valuable insights into actual movement behaviors but are often constrained by data sparsity and participant bias. Synthetic data, by contrast, offer scalability and flexibility but frequently lack realism. To address this gap, we introduce a comprehensive software pipeline for generating, calibrating, and processing large-scale human mobility datasets that integrate the realism of empirical data with the control and extensibility of Patterns-of-Life simulations. Our system consists of three integrated components. First, a genetic algorithm-based calibration module fine-tunes simulation parameters to align with real-world mobility characteristics, such as daily trip counts and radius of gyration, enabling realistic behavioral modeling. Second, a data generation engine constructs geographically grounded simulations using OpenStreetMap data to produce diverse mobility logs. Third, a data processing suite transforms raw simulation logs into structured formats suitable for downstream applications, including model training and benchmarking.

Trajectory anomaly detection is essential for identifying unusual and unexpected movement patterns in applications ranging from intelligent transportation systems to urban safety and fraud prevention. Existing methods only consider limited aspects of the trajectory nature and its movement space by treating trajectories as sequences of sampled locations, with sampling determined by positioning technology, e.g., GPS, or by high-level abstractions such as staypoints. Trajectories are analyzed in Euclidean space, neglecting the constraints and connectivity information of the underlying movement network, e.g., road or transit networks. The proposed Graph Enhanced Trajectory Anomaly Detection (GETAD) framework tightly integrates road network topology, segment semantics, and historical travel patterns to model trajectory data. GETAD uses a Graph Attention Network to learn road-aware embeddings that capture both physical attributes and transition behavior, and augments these with graph-based positional encodings that reflect the spatial layout of the road network. A Transformer-based decoder models sequential movement, while a multiobjective loss function combining autoregressive prediction and supervised link prediction ensures realistic and structurally coherent representations. To improve the robustness of anomaly detection, we introduce Confidence Weighted Negative Log Likelihood (CW NLL), an anomaly scoring function that emphasizes high-confidence deviations. Experiments on real-world and synthetic datasets demonstrate that GETAD achieves consistent improvements over existing methods, particularly in detecting subtle anomalies in road-constrained environments. These results highlight the benefits of incorporating graph structure and contextual semantics into trajectory modeling, enabling more precise and context-aware anomaly detection.

We demonstrate the Patterns of Life Simulation to create realistic simulations of human mobility in a city. This simulation has recently been used to generate massive amounts of trajectory and check-in data. Our demonstration focuses on using the simulation twofold: (1) using the graphical user interface (GUI), and (2) running the simulation headless by disabling the GUI for faster data generation. We further demonstrate how the Patterns of Life simulation can be used to simulate any region on Earth by using publicly available data from OpenStreetMap. Finally, we also demonstrate recent improvements to the scalability of the simulation allows simulating up to 100,000 individual agents for years of simulation time. During our demonstration, as well as offline using our guides on GitHub, participants will learn: (1) The theories of human behavior driving the Patters of Life simulation, (2) how to simulate to generate massive amounts of synthetic yet realistic trajectory data, (3) running the simulation for a region of interest chosen by participants using OSM data, (4) learn the scalability of the simulation and understand the properties of generated data, and (5) manage thousands of parallel simulation instances running concurrently.

In urban science, understanding mobility patterns and analyzing how people move around cities helps improve the overall quality of life and supports the development of more livable, efficient, and sustainable urban areas. A challenging aspect of this work is the collection of mobility data through user tracking or travel surveys, given the associated privacy concerns, noncompliance, and high cost. This work proposes an innovative AI-based approach for synthesizing travel surveys by prompting large language models (LLMs), aiming to leverage their vast amount of relevant background knowledge and text generation capabilities. Our study evaluates the effectiveness of this approach across various U.S. metropolitan areas by comparing the results against existing survey data at different granularity levels. These levels include (i) pattern level, which compares aggregated metrics such as the average number of locations traveled and travel time, (ii) trip level, which focuses on comparing trips as whole units using transition probabilities, and (iii) activity chain level, which examines the sequence of locations visited by individuals. Our work covers several proprietary and open-source LLMs, revealing that open-source base models like Llama-2, when fine-tuned on even a limited amount of actual data, can generate synthetic data that closely mimics the actual travel survey data and, as such, provides an argument for using such data in mobility studies.

This paper presents a novel approach for trajectory anomaly detection using an autoregressive causal-attention model, termed LM-TAD. This method leverages the similarities between language statements and trajectories, both of which consist of ordered elements requiring coherence through external rules and contextual variations. By treating trajectories as sequences of tokens, our model learns the probability distributions over trajectories, enabling the identification of anomalous locations with high precision. We incorporate user-specific tokens to account for individual behavior patterns, enhancing anomaly detection tailored to user context. Our experiments demonstrate the effectiveness of LM-TAD on both synthetic and real-world datasets. In particular, the model outperforms existing methods on the Pattern of Life (PoL) dataset by detecting user-contextual anomalies and achieves competitive results on the Porto taxi dataset, highlighting its adaptability and robustness. Additionally, we introduce the use of perplexity and surprisal rate metrics for detecting outliers and pinpointing specific anomalous locations within trajectories. The LM-TAD framework supports various trajectory representations, including GPS coordinates, staypoints, and activity types, proving its versatility in handling diverse trajectory data. Moreover, our approach is well-suited for online trajectory anomaly detection, significantly reducing computational latency by caching key-value states of the attention mechanism, thereby avoiding repeated computations. The code to reproduce experiments in this paper can be found at the following link: https://github.com/jonathankabala/LMTAD.

Individual human location trajectory and check-in data have been the driving force for human mobility research in recent years. However, existing human mobility datasets are very limited in size and representativeness. For example, one of the largest and most commonly used datasets of individual human location trajectories, GeoLife, captures fewer than two hundred individuals. To help fill this gap, this Data and Resources paper leverages an existing data generator based on fine-grained simulation of individual human patterns of life to produce large-scale trajectory, check-in, and social network data. In this simulation, individual human agents commute between their home and work locations, visit restaurants to eat, and visit recreational sites to meet friends. We provide large datasets of months of simulated trajectories for two example regions in the United States: San Francisco and New Orleans. In addition to making the datasets available, we also provide instructions on how the simulation can be used to re-generate data, thus allowing researchers to generate the data locally without downloading prohibitively large files.

Despite the impressive performance of Large Language Models (LLM) for various natural language processing tasks, little is known about their comprehension of geographic data and related ability to facilitate informed geospatial decision-making. This paper investigates the extent of geospatial knowledge, awareness, and reasoning abilities encoded within such pretrained LLMs. With a focus on autoregressive language models, we devise experimental approaches related to (i) probing LLMs for geo-coordinates to assess geospatial knowledge, (ii) using geospatial and non-geospatial prepositions to gauge their geospatial awareness, and (iii) utilizing a multidimensional scaling (MDS) experiment to assess the models' geospatial reasoning capabilities and to determine locations of cities based on prompting. Our results confirm that it does not only take larger but also more sophisticated LLMs to synthesize geospatial knowledge from textual information. As such, this research contributes to understanding the potential and limitations of LLMs in dealing with geospatial information.

A growing number of research areas such as location-based social networks, intelligent transportation systems, and urban computing utilize large amounts of trajectory data for benchmarking data management approaches and analysis methods. Given the general lackness of available large datasets, realistic synthetic trajectory datasets become important. This work proposes deep generative models for trajectory data that can learn disentangled models for sophisticated latent patterns. Existing methods rely on predefined heuristics and cannot learn the unknown underlying generative mechanisms. The proposed novel deep generative VAE-like models factorize global and local semantics (habits vs. random routing change). We further develop new inference strategies based on variational inference and constrained optimization to encapsulate spatiotemporal validity. New deep neural network architectures are developed to implement generative and inference models with dynamic latent priors. The proposed methods represent significant quantitative and qualitative improvements over existing approaches as demonstrated by extensive experiments. The software is made publicly available 1.

Deep generative models for graphs have exhibited promising performance in ever-increasing domains such as design of molecules (i.e, graph of atoms) and structure prediction of proteins (i.e., graph of amino acids). Existing work typically focuses on static rather than dynamic graphs, which are actually very important in the applications such as protein folding, molecule reactions, and human mobility. Extending existing deep generative models from static to dynamic graphs is a challenging task, which requires to handle the factorization of static and dynamic characteristics as well as mutual interactions among node and edge patterns. Here, this paper proposes a novel framework of factorized deep generative models to achieve interpretable dynamic graph generation. Various generative models are proposed to characterize conditional independence among node, edge, static, and dynamic factors. Then, variational optimization strategies as well as dynamic graph decoders are proposed based on newly designed factorized variational autoencoders and recurrent graph deconvolutions. Extensive experiments on multiple datasets demonstrate the effectiveness of the proposed models.

Earth observation data is collected by ever-expanding fleets of satellites including Landsat1-8, Sentinel1 & Sentinel2, SPOT1-7 and WorldView1-3. These satellites generate at spatial resolutions (pixel size) from 30m to 31cm and provide revisit rates of as frequent as every 5 days. This allows us not only to look at high-resolution images of every corner of the Earth, but also to track events and observe change over time. During the past 5 years, medium spatial resolution satellite data (30 − 10m pixels) have developed very high temporal revisit frequencies of 5-16 days and spatial-temporal structures have been developed to manage these vast data sets. However, high resolution satellite images and rapidly increasing revisit rates create major data management and mining challenges. This work discusses six challenges of integrating observations at different times, from different sensors, at different spatial resolutions and different temporal frequencies into a unified Earth Observation Data Cube, that is, a tensor of location, time, and spectral bands. Challenges include creating a unified data cube from heterogeneous sensors, scaling geo-registration (mapping pixel between images), accounting for uncertainty across observations, imputing missing observations, broad area event detection, and ultimately, predicting the future state of our planet. With such a unified Earth Observation Data Cube in place, we describe potential application areas such as detecting anthropogenic land cover change, early warning of natural hazards, tracing movement of animals, finding missing airplanes, and rapid detection of forest fires.

Deep generative models of graph-structured data have become popular in very recent years. Although initial research has focused on static graphs in applications such as molecular design and social networks, many challenges involve temporal graphs whose topology and attribute values evolve dynamically over time. Sophisticated and unknown network processes that affect temporal graphs cannot be captured adequately by prescribed models. Application areas include social mobility networks and catastrophic cybersecurity failures. These web-scale applications challenge current deep graph generative models with the need to capture 1) time-validity constraints, 2) time and topological distributions, and 3) joint time and graph encoding and decoding. Here, we propose the “Temporal Graph Generative Adversarial Network” (TG-GAN) for continuous-time graph generation with time-validity constraints 1. TG-GAN can jointly generate the time, node, and edge information for truncated temporal walks via a novel recurrent-based model and a valid time decoder. The generated truncated temporal walks are then assembled into time-budgeted temporal walks for temporal graphs under the learned topological and temporal dependencies. In addition, a discriminator is proposed to combine time and node encoding operations over a recurrent architecture to distinguish generated sequences from real ones sampled by a truncated temporal walk sampler. Extensive experiments on both synthetic and real-world datasets confirm that TG-GAN significantly outperforms five benchmarking methods in terms of efficiency and effectiveness.

Map construction algorithms attempt to derive a spatial graph representing a road network from GPS-sampled movement trajectories. Existing methods commonly use trajectories without considering the specific sampling methodology. Hence, the movement information is not preserved in the map construction results. The proposed map-construction method considers the particularities of the sampling process and how they affect the trajectory data to improve the overall result quality. Specifically, our proposed algorithm constructs nodes by clustering turn points. We use an adaptive clustering approach that considers when a turn point was sampled in relation to the ‘true’ node location based on the trajectory geometry. As nodes are the aggregates of turn points, edges are constructed by conflating trajectories that either connect turn points or are in close proximity to inferred nodes. Experiments using trajectory datasets at different spatial scales, data complexities, and data sources in combination with several assessment methods show that the proposed movement-aware map construction method produces maps of greater accuracy than those from the existing approaches.

Ever increasing traffic and consequential congestion wastes fuel and is a significant contributor to Green House Gas (GHG) emissions. Contributors here include ride-sharing services such as Uber, Lyft, and Didi, with their drivers not only transporting passengers, but also spending a considerable time in traffic searching for new ones. To mitigate their impact, this work proposes a novel algorithm to improve the efficiency the drivers' search for passengers. Our algorithm directs unassigned drivers to locations where new passengers are expected to emerge. We use a non-negative matrix factorization approach to model the time and location of passengers given historical training data. A probabilistic search strategy then guides drivers to nearby locations for which we predict new passengers. To ensure that drivers do not over subscribe to such areas, we randomize destinations and provide each driver with a home location destination when unassigned. An experimental evaluation using real-world data from Manhattan shows that our approach actually reduces the search time of drivers and the wait time of passengers compared to baseline solutions.

Traffic sensing has been revolutionized with the commoditization of GPS technology. Smartphone navigation applications ubiquitously track vehicles as samples of the overall traffic. This so-called Probe Vehicle Data (PVD) has replaced traditional road-side sensor technologies, such as induction loops and microwave sensors, given its relative low cost, good coverage, and reliability. However, while PVD allows us to assess speed and by extension the overall traffic condition in a road network, this sample-based approach does not provide us with traffic flow, i.e., the number of vehicles passing through an edge of the road network. This paper bridges this gap by proposing and evaluating a range of methods to infer traffic flow for a road network that is ubiquitously observed using probe data but having traffic flow measurements only in very road-side sensor locations. We create Road Segment Archetypes that relate PVD speeds to flow from road-side sensors for these locations. These archetypes are then extended to the entire network covered only by PVD based on similar traffic characteristics. Using these archetypes we augment and experimentally evaluate different traffic flow estimation models using real-world traffic data. Experimental results show that the Road Archetype flow estimation is comparable to the accuracy of prediction models that would be based on actual road-side sensor flows.

Urban areas provide us with a treasure trove of available data capturing almost every aspect of a population's life. This work focuses on mobility data and how it will help improve our understanding of urban mobility patterns. Readily available and sizable farecard data captures trips in a public transportation network. However, such data typically lacks temporal signatures and as such the task of inferring trip semantics, station function, and user clustering is quite challenging. While existing approaches either focus on station-level or user-level signals only, we propose a Station-to-User (S2U) transfer learning framework, which augments user-level learning with shared temporal patterns learned from station-level signals. Our framework is based on a novel, so-called "Tidal-Regularized Non-negative Matrix Factorization" method, which incorporates a-priori tidal traffic patterns in generic Non-negative Matrix Factorization. To evaluate our model performance, a user clustering stability test based on the classical Rand Index is introduced as a metric to benchmark different unsupervised learning models. Using this metric, quantitative evaluations on three real-world datasets show that S2U outperforms two baselines methods by 7-21%. We also provide a qualitative analysis of the user clustering and station functions for the Washington D.C. metro and show how S2U can support spatiotemporal urban analytics.

Location-based social networks (LBSNs) have been studied extensively in recent years. However, utilizing real-world LBSN data sets yields several weaknesses: sparse and small data sets, privacy concerns, and a lack of authoritative ground-truth. To overcome these weaknesses, we leverage a large-scale LBSN simulation to create a framework to simulate human behavior and to create synthetic but realistic LBSN data based on human patterns of life. Such data not only captures the location of users over time but also their interactions via social networks. Patterns of life are simulated by giving agents (i.e., people) an array of “needs” that they aim to satisfy, e.g., agents go home when they are tired, to restaurants when they are hungry, to work to cover their financial needs, and to recreational sites to meet friends and satisfy their social needs. While existing real-world LBSN data sets are trivially small, the proposed framework provides a source for massive LBSN benchmark data that closely mimics the real-world. As such, it allows us to capture 100% of the (simulated) population without any data uncertainty, privacy-related concerns, or incompleteness. It allows researchers to see the (simulated) world through the lens of an omniscient entity having perfect data. Our framework is made available to the community. In addition, we provide a series of simulated benchmark LBSN data sets using different synthetic towns and real-world urban environments obtained from OpenStreetMap. The simulation software and data sets, which comprise gigabytes of spatio-temporal and temporal social network data, are made available to the research community.

Our ability to extract knowledge from evolving spatial phenomena and make it actionable is often impaired by unreliable, erroneous, obsolete, imprecise, sparse, and noisy data. Integrating the impact of this uncertainty is a paramount when estimating the reliability/confidence of any time-varying query result from the underlying input data. The goal of this advanced seminar is to survey solutions for managing, querying and mining uncertain spatial and spatio-temporal data. We survey different models and show examples of how to efficiently enrich query results with reliability information. We discuss both analytical solutions as well as approximate solutions based on geosimulation.

Fixed-route bus systems are an important part of the urban transportation mix. A considerable disadvantage of buses is their slow speed, which is in part due to frequent stops, but also due to the lack of segregation from other vehicles in traffic. As such, assessing bus routes is an important aspect of route planning, scheduling, and the creation of dedicated bus lanes. In this work, we use bus tracking data from the Washington Metropolitan Area Transit Authority to discover speed patterns in relation to bus stops throughout the day. This gives us an insight on whether the routes are affected by traffic congestion or more random events such as traffic lights. We first employ a macro-level qualitative analysis to identify patterns across different trips. A micro-level quantitative analysis further refines this approach by analyzing the speed patterns around bus stops. Our analysis is based on bus odometer data, which is a one-dimensional representation of trips that has considerable accuracy when looking at speed patterns. Exploiting route metadata in relation to stops, we use Dynamic Time Warping to cluster different stops based on their speed profiles throughout the day. The clustering can be used to generate a spatiotemporal route profile and we show how such a profile provides actionable intelligence for route planning purposes.

Zoning Improvement Plan (ZIP) Codes provide a sub-division of space. Interestingly, the ZIP code area polygons for different data sources do not match, resulting in uncertainty for a range of services that rely on such data. This paper presents a system that employs traditional classification methods to map a given spatial coordinate to a distribution of ZIP-codes using various public available ZIP-code maps as predictors, and using the (not publicly available) United States Postal Service (USPS) map as an authoritative ground truth. We show that large sets of microblog data, from which we extract potential ZIP-codes, can significantly improve classification accuracy despite the noise of such data. The demonstrator allows users to select locations on a map of Orlando, FL, view the resulting distribution of ZIP-codes predicted for this location, compare the results to the ground-truth, and view the microblogs that have enriched the result. A focus will be on showing that the signal present in large, noisy, and 99.99% unrelated microblog data can indeed be used to improve reverse ZIP code geo-coding.

Data generators have been heavily used in creating massive trajectory datasets to address common challenges of real-world datasets, including privacy, cost of data collection, and data quality. However, such generators often overlook social and physiological characteristics of individuals and as such their results are often limited to simple movement patterns. To address these shortcomings, we propose an agent-based simulation framework that facilitates the development of behavioral models in which agents correspond to individuals that act based on personal preferences, goals, and needs within a realistic geographical environment. Researchers can use a drag-and-drop interface to design and control their own world including the geospatial and social (i.e. geo-social) properties. The framework is capable of generating and streaming very large data that captures the basic patterns of life in urban areas. Streaming data from the simulation can be accessed in real time through a dedicated API.

Congested traffic wastes billions of liters of fuel and is a significant contributor to Green House Gas (GHG) emissions. Although convenient, ride sharing services such as Uber and Lyft are becoming a significant contributor to these emissions not only because of added traffic but by spending time on the road while waiting for passengers. To help improve the impact of ride sharing, we propose an algorithm to optimize the efficiency of drivers searching for customers. In our model, the main goal is to direct drivers represented as idle agents, i.e., not currently assigned a customer or resource, to locations where we predict new resources to appear. Our approach uses non-negative matrix factorization (NMF) to model and predict the spatio-temporal distributions of resources. To choose destinations for idle agents, we employ a greedy heuristic that strikes a balance between distance greed, i.e., to avoid long trips without resources and resource greed, i.e., to move to a location where resources are expected to appear following the NMF model. To ensure that agents do not oversupply areas for which resources are predicted and under supply other areas, we randomize the destinations of agents using the predicted resource distribution within the local neighborhood of an agent. Our experimental evaluation shows that our approach reduces the search time of agents and the wait time of resources using real-world data from Manhattan, New York, USA.

Location-based social networks (LBSNs) have been studied extensively in recent years. However, utilizing real-world LBSN datasets in such studies has severe weaknesses: sparse and small datasets, privacy concerns, and a lack of authoritative ground-truth. Our vision is to create a large scale geo-simulation framework to simulate human behavior and to create synthetic but realistic LBSN data that captures the location of users over time as well as social interactions of users in a social network. While existing LBSN datasets are trivially small, such a framework would provide the first source of massive LBSN benchmark data which would closely mimic the real world, containing high-fidelity information of location, and social connections of millions of simulated agents over several years of simulated time. Therefore, it would serve the research community by revitalizing and reshaping research on LBSNs by allowing researchers to see the (simulated) world through the lens of an omniscient entity having perfect data. These evaluations will guide future research enabling us to develop solutions to improve LBSN applications such as user-location recommendation, friend recommendation, location prediction, and location privacy.

An inherent challenge arising in any dataset containing information of space and/or time is uncertainty due to various sources of imprecision. Integrating the impact of the uncertainty is a paramount when estimating the reliability (confidence) of any query result from the underlying input data. To deal with uncertainty, solutions have been proposed independently in the geo-science and the data-science research community. This interdisciplinary tutorial bridges the gap between the two communities by providing a comprehensive overview of the different challenges involved in dealing with uncertain geo-spatial data, by surveying solutions from both research communities, and by identifying similarities, synergies and open research problems.

Urban form and function have been studied extensively in urban planning and geographical information science. However, gaining a greater understanding of how they merge to define the urban morphology remains a substantial scientific challenge. Toward this goal, this paper addresses the opportunities presented by the emergence of crowdsourced data to gain novel insights into form and function in urban spaces. We are focusing in particular on information harvested from social media and other open-source and volunteered datasets (e.g. trajectory and OpenStreetMap data). These data provide a first-hand account of form and function from the people who define urban space through their activities. This novel bottom-up approach to study these concepts complements traditional urban studies to provide a new lens for studying urban activity. By synthesizing recent advancements in the analysis of open-source data, we provide a new typology for characterizing the role of crowdsourcing in the study of urban morphology. We illustrate this new perspective by showing how social media, trajectory, and traffic data can be analyzed to capture the evolving nature of a city’s form and function. While these crowd contributions may be explicit or implicit in nature, they are giving rise to an emerging research agenda for monitoring, analyzing, and modeling form and function for urban design and analysis.

Our work focuses around a Web application that retrieves user-generated geospatial content from multiple popular Web sources, and applies schema mapping and entity matching techniques to obtain an integrated dataset. Moreover, density-based clustering of the obtained data is performed to reveal of interest for various data categories. An analysis and overview of the underlying data are also provided by computing various statistics that are visualized in a series of charts. Further data exploration and navigation is enabled via keyword search and faceted browsing. This demonstration covers all the steps of the process, from selecting an area and the sources for data collection, to visualizing and navigating the integrated results.

Directions and paths, as commonly provided by navigation systems, are usually derived considering absolute metrics, e.g., finding the shortest path within an underlying road network. With the aid of crowdsourced geospatial data we aim at obtaining paths that do not only minimize distance but also lead through more popular areas using knowledge generated by users. We extract spatial relations such as "nearby" or "next to" from geo-textual travel blogs, that define closeness between pairs of points of interest (POIs) and quantify each of these relations using a probabilistic model. Using Bayesian inference, we obtain a probabilistic measure of spatial closeness according to the crowd. Applying this measure to the corresponding road network, we derive an altered cost function taking crowdsourced spatial relations into account. We propose two routing algorithms on the enriched road networks. To evaluate our approach, we use Flickr photo data as a ground truth for popularity. Our experimental results -- based on real world datasets -- show that the computed paths yield competitive solutions in terms of path length while also providing more "popular" paths, making routing easier and more informative for the user.

Catchment area and reachability analysis, i.e., the area from which a location attracts visitors and the minimum distance to a target location, respectively, are interesting problems when studied in the context of time-parameterized networks, such as road networks affected by traffic. This work utilizes live-traffic assessment results produced by Floating Car Data and their application to such crucial geomarketing test cases. We combine state-of-the-art isochrone computation utilizing live-traffic and demographics data to provide efficient catchment area and reachability calculations. The online demo presented here, showcases the critical impact of live-traffic assessment on business intelligence decisions related to space.

This work proposes a novel method that converts movement trajectories into a hierarchical transportation network. It utilizes an improved map construction algorithm on segmented input data based on types of movement. The produced hierarchical road network layers are then combined into a single network. This segmentation addresses the challenges imposed by noisy, low sampling rate trajectories and provides for a mechanism to accommodate automatic map maintenance on updates. An experimental evaluation is conducted using trajectories derived from GPS tracking taxi fleets and utility vehicles in Berlin, Vienna and Athens.

Crowdsourcing road network data, i.e., involving users to collect data including the detection and assessment of changes to the road network graph, poses a challenge to shortest-path algorithms that rely on preprocessing. Hence, current research challenges lie with improving performance by adequately balancing preprocessing with respect to fast-changing road networks. In this work, we take the crowdsourcing approach further in that we solicit the help of users not only for data collection, but also to provide us their computing resources. A promising approach is parallelization, which splits the graph into chunks of data that may be processed separately. This work extends this approach in that small-enough chunks allow us to use browser-based computing to solve the pre-computation problem. Essentially, we aim for a Web-based navigation service that whenever users request a route, the service uses their browsers for partially preprocessing a large, but changing road network. The paper gives performance studies that highlight the potential of the browser as a computing platform and showcases a scalable approach, which almost eliminates the computing load on the server.

Road networks are important datasets for an increasing number of applications. However, the creation and maintenance of such datasets pose interesting research challenges. This work proposes an automatic road network generation algorithm that takes vehicle tracking data in the form of trajectories as input and produces a road network graph. This effort addresses the challenges of evolving map data sets, specifically by focusing on (i) automatic map-attribute generation (weights), (ii) automatic road network generation, and (iii) by providing a quality assessment. An experimental study assesses the quality of the algorithms by generating a part of the road network of Athens, Greece, using trajectories derived from GPS tracking a school bus fleet.

The ever-increasing stream of Web and mobile applications addressing geospatial data creation has been producing a large number of user-contributed geospatial datasets. This work proposes a means to query such data using a collaborative Web-based approach. We employ crowdsourcing to the fullest in that used-generated point-cloud data will be mined by the crowd not only by providing feature names, but also by contributing computing resources. We employ browser-based collaborative search for deriving the extents of geospatial objects (Points of Interest) from point-cloud data such as Flickr image locations and tags. The data is aggregated by means of a hierarchical grid in connection with an exploratory and a refinement search phase. A performance study establishes the effectiveness of our approach with respect to the amount of data that needs to be retrieved from the sources and the quality of the derived spatial features.

Geospatial data has become an important resource in today's Web applications not only as type of content, but also as metadata. Despite its undisputed usefulness, issues need to be addressed with respect to the availability, the accuracy, and the cost of the data. The advent of Web2.0 created several creative-commons initiatives addressing geospatial dataset creation and countless (mobile) applications have been producing large amounts of point cloud datasets. In this work, we demonstrate how to query user-contributed point-cloud data using a collaborative Web-based approach.

One cannot deny that space and time are important to us. We perceive our world with respect to where and when we do things. We advocate geoblogging as a tool to capture such experiences by means of collecting and organizing notes, images, and in relation to space and time as well as to link them to other geospatial datasets. This demo showcases a Web application that allows for (i) a simple upload of content, geocoding, and map-based authoring of geoblogs as well (ii) querying and linking other geospatial datasets in relation to the geoblog entry.

The essential elements of any navigation system are a shortest-path algorithm and accurate map data. The contribution of this work is two-fold. First, the HBA* algorithm, an efficient shortest-path algorithm is presented that mimics human driving behavior by exploiting road network hierarchies. Second, in a thorough performance study dynamic travel times are introduced to replace the unreliable static speed types currently used in connection with road network datasets.

Information and specifically Web pages may be organized, indexed, searched, and navigated using various metadata aspects, such as keywords, categories (themes), and also space. While categories and keywords are up for interpretation, space represents an unambiguous aspect to structure information. The basic problem of providing spatial references to content is solved by geocoding; a task that relates identifiers in texts to geographic co-ordinates. This work presents a methodology for the semiautomatic geocoding of persistent Web pages in the form of collaborative human intervention to improve on automatic geocoding results. While focusing on the Greek language and related Web pages, the developed techniques are universally applicable. The specific contributions of this work are (i) automatic geocoding algorithms for phone numbers, addresses and place name identifiers and (ii) a Web browser extension providing a map-based interface for manual geocoding and updating the automatically generated results. With the geocoding of a Web page being stored as respective annotations in a central repository, this overall mechanism is especially suited for persistent Web pages such as Wikipedia. To illustrate the applicability and usefulness of the overall approach, specific geocoding examples of Greek Web pages are presented.

The application domain of intelligent transportation is plagued by a shortage of data sources that adequately assess traffic situations. Typically, to provide routing and navigation solutions map attributes in the form of static weights as derived from road categories and speed limits used for road networks. With the advent of Floating Car Data (FCD) and specifically the GPS-based tracking data component, a means was found to derive accurate and up-to-date travel times, i.e., qualitative traffic information. FCD is a by-product in fleet management applications and given a minimum number and uniform distribution of vehicles, this data can be used for accurate traffic assessment and also prediction. This work showcases a system that facilitates the collection of FCD, produces dynamic travel time information, and provides value-added services based on the dynamic travel times. The essential components that will be discussed are a Web-services-based data collection approach, sophisticated map-matching algorithms, a data management architecture and an online visualization platform.

Routing plays an ever-important role in a society that relies heavily on individual means of transportation. Although efficient algorithmic solutions for navigation exist, an accurate and reliable weight database that forms the basis of an acceptable algorithmic solution is missing. This work defines algorithms and data management techniques that allow the derivation of dynamic weights from collected floating car data (FCD). Weights reflect the speed associated with a piece of road at a certain time. A collection of such historical data is used to capture trends in travel time behavior according to temporal variations. Based on large amounts of travel time data, edge-based weights in the form of time-varying characteristic travel times are derived. Since the available tracking data does not cover the entire road network, several methods are defined to compensate for the lack of data and to guarantee complete coverage. A dynamic weight database, the dynamic travel time map (DTTM) is defined and implemented as a spatio-temporal data warehouse to manage the characteristic travel times and to compute dynamic weights efficiently. An experimental evaluation establishes not only the efficiency of the proposed approach but also shows its applicability in a realistic context, using actual GPS vehicle tracking data for the road network of Athens, Greece

With vehicle tracking data becoming an important sensor data resource for a range of applications related to traffic assessment and prediction, fast and accurate mapmatching algorithms become a necessary means to ultimately utilize this data. This work proposes a fast mapmatching algorithm which exploits tracking data error estimates in a provably correct way and offers a quality guarantee for the computed result trajectory. A new model for the map-matching task is introduced which takes tracking error estimates into account. The proposed Adaptive Clipping algorithm (i) provably solves this map-matching task and (ii) utilizes the weak Fr´echet distance to measure similarity between curves. The algorithm uses the error estimates in the trajectory data to reduce the search space (error-aware pruning), while offering the quality guarantee of finding a curve which minimizes the weak Fr´echet distance to the vehicle trajectory among all possible curves in the road network. Moreover, this work introduces an outputsensitive variant of an existing weak Fr´echet map-matching algorithm, which is also employed in the Adaptive Clipping algorithm. Output-sensitiveness paired with error-aware pruning makes Adaptive Clipping the first map-matching algorithm that provably solves a well-defined map-matching task. An experimental evaluation establishes further that Adaptive Clipping is also in a practical setting a fast algorithm that at the same time produces high-quality matching results.

A novel data source for assessing traffic conditions is floating car data (FCD) in the form of vehicle tracking data, or, in database terms, trajectory data. This work proposes practical data management techniques including data pre-processing, data modeling and indexing to support the analysis and the data mining of vehicle tracking data.

With the proliferation of mobile computing, the ability to index efficiently the movements of mobile objects becomes important. Objects are typically seen as moving in two-dimensional (x,y) space, which means that their movements across time may be embedded in the three-dimensional (x,y,t) space. Further, the movements are typically represented as trajectories, sequences of connected line segments. In certain cases, movement is restricted, and specifically in this paper, we aim at exploiting that movements occur in transportation networks to reduce the dimensionality of the data. Briefly, the idea is to reduce movements to occur in one spatial dimension. As a consequence, the movement data becomes two-dimensional (x,t). The advantages of considering such lower-dimensional trajectories are the reduced overall size of the data and the lower-dimensional indexing challenge. Since off-the-shelf systems typically do not offer higher-dimensional indexing, this reduction in dimensionality allows us to use such DBMSes to store and index trajectories. Moreover, we argue that, given the right circumstances, indexing these dimensionality-reduced trajectories can be more efficient than using a three-dimensional index. This hypothesis is verified by an experimental study that incorporates trajectories stemming from real and synthetic road networks.

Data warehouses as well as a wide range of other databases exhibit a strong temporal orientation: it is important to track the temporal variation of data over several months or years. In addition, databases often exhibit append-only characteristics where old data is retained while new data is appended. Performing joins efficiently on large databases such as these is essential to obtain good overall query processing performance. The paper presents a sort-merge based incremental algorithm for time oriented data. While incremental computation techniques have proven competitive in many settings, they also introduce a space overhead in the form of differential files. For the temporal data explored here, this overhead is avoided because the differential files are already part of the database. In addition, data is naturally sorted, leaving only merging. The incremental algorithm works in a partitioned storage environment and does not assume the availability of indices, making it a competitor to sort based and nested-loop joins. The paper presents analytical as well as simulation based characterizations of the performance of the join.