A5001448076- Data Management and Algorithms
- Geographic Information Systems Studies
- Human Mobility and Location-Based Analysis
- Advanced Database Systems and Queries
- Automated Road and Building Extraction
- Traffic Prediction and Management Techniques
- Semantic Web and Ontologies
- Remote Sensing and LiDAR Applications
- Transportation Planning and Optimization
- Data Mining Algorithms and Applications
- Data Visualization and Analytics
- Web Data Mining and Analysis
- Data-Driven Disease Surveillance
- Constraint Satisfaction and Optimization
- Time Series Analysis and Forecasting
- Graph Theory and Algorithms
- Service-Oriented Architecture and Web Services
- Transportation and Mobility Innovations
- Complex Network Analysis Techniques
- Algorithms and Data Compression
- Natural Language Processing Techniques
- Urban Design and Spatial Analysis
- Data Quality and Management
- 3D Modeling in Geospatial Applications
- Mobile Crowdsensing and Crowdsourcing
George Mason University
2016-2025
Research Academic Computer Technology Institute
2003-2017
GeoInformation (United Kingdom)
2015
University of Fairfax
2015
Athena Research and Innovation Center In Information Communication & Knowledge Technologies
2011-2013
Institute of Communication and Computer Systems
2009-2011
University of Patras
2008
Aalborg University
1998-2003
University of Manchester
2002
Hella (Germany)
2002
Urban form and function have been studied extensively in urban planning geographical information science. However, gaining a greater understanding of how they merge to define the morphology remains substantial scientific challenge. Toward this goal, paper addresses opportunities presented by emergence crowdsourced data gain novel insights into spaces. We are focusing particular on harvested from social media other open-source volunteered datasets (e.g. trajectory OpenStreetMap data). These...
Road networks are important datasets for an increasing number of applications. However, the creation and maintenance such pose interesting research challenges. This work proposes automatic road network generation algorithm that takes vehicle tracking data in form trajectories as input produces a graph. effort addresses challenges evolving map sets, specifically by focusing on (i) map-attribute (weights), (ii) generation, (iii) providing quality assessment. An experimental study assesses...
The sudden outbreak of the Coronavirus disease (COVID-19) swept across world in early 2020, triggering lockdowns several billion people many countries, including China, Spain, India, U.K., Italy, France, Germany, Brazil, Russia, and U.S. transmission virus accelerated rapidly with most confirmed cases U.S., Brazil. In response to this national global emergency, NSF Spatiotemporal Innovation Center brought together a taskforce international researchers assembled implementation strategies...
Background: The recent Zika outbreak witnessed the disease evolving from a regional health concern to global epidemic. During this process, different communities across globe became involved in Twitter, discussing and key issues associated with it. This paper presents study of discussion at nexus location, actors, concepts. Objective: Our objective was demonstrate significance 3 types events: location related, actor concept for understanding how public emergency international plays out...
Social media are often heralded as offering cancer campaigns new opportunities to reach the public. However, these may not be equally successful, depending on nature of campaign itself, type being addressed, and social platform examined. This study is first compare activity Twitter Instagram across three time periods: #WorldCancerDay in February, annual month-long National Breast Cancer Awareness Month (NBCAM) October Movember November, during full year outside campaigns. Our results suggest...
Abstract Having accurate building information is paramount for a plethora of applications, including humanitarian efforts, city planning, scientific studies, and navigation systems. While volunteered geographic from sources such as OpenStreetMap (OSM) has good geometry coverage, descriptive attributes the type are sparse. To fill this gap, study proposes supervised learning-based approach to provide meaningful, semantic OSM data without manual intervention. We present basic demonstration our...
With vehicle tracking data becoming an important sensor resource for a range of applications related to traffic assessment and prediction, fast accurate mapmatching algorithms become necessary means ultimately utilize this data. This work proposes algorithm which exploits error estimates in provably correct way offers quality guarantee the computed result trajectory. A new model map-matching task is introduced takes into account. The proposed Adaptive Clipping (i) solves (ii) utilizes weak...
Despite the impressive performance of Large Language Models (LLM) for various natural language processing tasks, little is known about their comprehension geographic data and related ability to facilitate informed geospatial decision-making. This paper investigates extent knowledge, awareness, reasoning abilities encoded within such pretrained LLMs. With a focus on autoregressive models, we devise experimental approaches (i) probing LLMs geo-coordinates assess (ii) using non-geospatial...
With the proliferation of mobile computing, ability to index efficiently movements objects becomes important. Objects are typically seen as moving in two-dimensional (x,y) space, which means that their across time may be embedded three-dimensional (x,y,t) space. Further, represented trajectories, sequences connected line segments. In certain cases, movement is restricted, and specifically this paper, we aim at exploiting occur transportation networks reduce dimensionality data. Briefly, idea...
User-generated content is a valuable resource for capturing all aspects of our environment and lives, dedicated Volunteered Geographic Information (VGI) efforts such as OpenStreetMap (OSM) have revolutionized spatial data collection. While OSM widely used, considerably little attention has been paid to the quality its Point-of-interest (POI) component. This work studies accuracy, coverage, trend worthiness POI data. We assess accuracy coverage using another VGI source that utilizes editorial...
Abstract Accurately predicting commuting flows is crucial for sustainable urban planning and preventing disease spread due to human mobility. While recent advancements have produced effective models these recurrent flows, the existing methods rely on datasets exclusive a few study areas, limiting transferability other locations. This research broadens utility of state-of-the-art flow prediction with globally available OpenStreetMap data while achieving accuracy comparable location-specific...
Due to the limited availability of actual large-scale datasets, realistic synthetic trajectory data play a crucial role in various research domains, including spatiotemporal mining and management, domain-driven related transportation planning urban analytics. Existing generation methods rely on predefined heuristics cannot learn unknown underlying generative mechanisms. This work introduces two end-to-end approaches for generation. The first approach comprises deep VAE-like models that...
Urban areas get more and congested everyday due to the increasing number of moving vehicles. This imposes need for efficient analysis, modeling, processing traffic data. Moreover, extraction additional information about conditions, optional routes possible prediction troublesome situations, such as jams, becomes necessary. In this work, we describe pre-processing, storage techniques trajectory data that constitute a object database (MOD). MOD is backbone IXNH/spl Lambda/ATH/spl Sigma/...
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 sets, privacy concerns, a lack of authoritative ground-truth. To overcome these weaknesses, we leverage large-scale simulation to create framework simulate human behavior synthetic but realistic based on patterns life. Such not only captures the location users over time also their interactions via networks. Patterns...
Human mobility data science using trajectories or check-ins of individuals has many applications. Recently, we have seen a plethora research efforts that tackle these However, progress in this field is limited by lack large and representative datasets. The largest most commonly used dataset individual human captures fewer than 200 individuals, while datasets capture 100 per city day. Thus, it not clear if findings from the community would generalize to populations. Since obtaining massive,...