A5067070198- Geographic Information Systems Studies
- Human Mobility and Location-Based Analysis
- Data Management and Algorithms
- Urban Transport and Accessibility
- Data-Driven Disease Surveillance
- Semantic Web and Ontologies
- Privacy-Preserving Technologies in Data
- Privacy, Security, and Data Protection
- Biomedical Text Mining and Ontologies
- Mobile Crowdsensing and Crowdsourcing
- Data Visualization and Analytics
- COVID-19 epidemiological studies
- Data Quality and Management
- Diverse Aspects of Tourism Research
- Transportation and Mobility Innovations
- Digital Marketing and Social Media
- Land Use and Ecosystem Services
- Scientific Computing and Data Management
- Sharing Economy and Platforms
- Species Distribution and Climate Change
- COVID-19 Digital Contact Tracing
- Transportation Planning and Optimization
- Urban Design and Spatial Analysis
- Big Data Technologies and Applications
- Smart Parking Systems Research
McGill University
2018-2025
Salesforce (United States)
2023
University of Louisville
2022
University of California, Santa Barbara
2012-2021
Aalborg University
2019
University of Maryland, College Park
2016-2018
University of California System
2014
(2020). GeoAI: spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond. International Journal of Geographical Information Science: Vol. 34, Artificial discovery, pp. 625-636.
Abstract In this commentary, we describe the current state of art points interest (POIs) as digital, spatial datasets, both in terms their quality and affordings, how they are used across research domains. We argue that good coverage high-quality POI features — especially category temporality information key for creating reliable data. list challenges geolocation representation, data fidelity, attributes, address these may affect results geospatial analyses built environment applications...
The volume, velocity, and variety of data that are now becoming available allow us to study urban environments based on human behaviour with a spatial, temporal, thematic granularity was not achievable until now. Such data-driven approaches open up additional, complementary perspectives how systems function, especially if they user-generated content (UGC). While the sources, such as social media, introduce specific biases, also new possibilities for scientists broader public. For instance,...
To a large degree, the attraction of Big Data lies in variety its heterogeneous multi-thematic and multi-dimensional data sources not merely volume. fully exploit this variety, however, requires conflation. This is two-step process. First, one has to establish identity relations between information entities across different sources; second, attribute values have be merged according certain procedures that avoid logical contradictions. The first step, also called matching, can thought as...
Abstract As location‐enabled technologies are becoming ubiquitous, our location is being shared with an ever‐growing number of external services. Issues revolving around privacy—or geoprivacy —therefore concern the vast majority population, largely without knowing how underlying work and what can be inferred from individual's (especially if recorded over longer periods time). Research, on other hand, has treated this topic isolated standpoints, most prominently technological ethical points...
Cognitive regions and places are notoriously difficult to represent in geographic information science systems. The exact delineation of cognitive is challenging insofar as borders vague, membership within the varies non-monotonically, raters cannot be assumed assess consistently homogeneously. In a study published this journal 2014, researchers devised novel grid-based task which participants rated individual cells given region contrasted approach standard boundary-drawing task....
Many techniques have been proposed for visualizing uncertainty in geospatial data. Previous empirical research on the effectiveness of visualizations has focused primarily user intuitions rather than objective measures performance when reasoning under uncertainty. Framed context Google's blue dot, we examined four alternative representing positional about self-location Our task presents a mobile mapping scenario which GPS satellite location readings produce estimates with varying levels...
Ad hoc keyword search engines built using modern information retrieval methods do a good job of handling fine-grained queries. However, they perform poorly at facilitating spatial and spatially-embedded thematic exploration the results, despite fact that many queries, e.g. "civil war," refer to different documents topics in places. This is not for lack data: geographic information, such as place names, events, coordinates are common unstructured document collections on web. The associations...
Abstract Digital gazetteers play a key role in modern information systems and infrastructures. They facilitate (spatial) search, deliver contextual to recommended systems, enrich textual with geographical references, provide stable identifiers interlink actors, events, objects by the places they interact with. Hence, it is unsurprising that gazetteers, such as GeoNames, are among most densely interlinked hubs on Web of Linked Data. A wide variety digital have been developed over years serve...
Abstract. Driven by foundation models, recent progress in AI and machine learning has reached unprecedented complexity. For instance, the GPT-3 language model consists of 175 billion parameters a training-data size 570 GB. While it achieved remarkable performance generating text that is difficult to distinguish from human-authored content, single training estimated produce over 550 metric tons CO2 emissions. Likewise, we see advances GeoAI research improving large-scale prediction tasks like...
ABSTRACT GIS and GIScience education have continually evolved over the past three decades, responding to technological advances societal issues. Today, content context in which is taught continue be impacted by these disruptions, notably from technology through artificial intelligence (AI) society myriad environmental social challenges facing planet. These disruptions create a new landscape for training within discipline that affecting not only what courses but also who taught, why it being...
Abstract This article presents a new character‐level convolutional neural network model that can classify multilingual text written using any character set be encoded with UTF‐8, standard and widely used 8‐bit encoding. For geographic classification of text, we demonstrate this approach is competitive state‐of‐the‐art word‐based methods. The was tested on four crowdsourced data sets made up Wikipedia articles, online travel blogs, Geonames toponyms, Twitter posts. Unlike methods, which...
Local place names are frequently used by residents living in a geographic region. Such may not be recorded existing gazetteers, due to their vernacular nature, relative insignificance gazetteer covering large area (e.g. the entire world), recent establishment name of newly-opened shopping center) or other reasons. While always recorded, local play important roles many applications, from supporting public participation urban planning locating victims disaster response. In this paper, we...
Knowing where one is located within an environment of the most fundamental tasks humans have to master in their daily routines. Maps, as external representations offer intuitive ways extend capacities human cognitive systems. Operations such planning a route can be performed on maps instead environment. Question how design that support processes wayfinding novel environments been discussed several disciplines. The research reported here addresses question map alignment and presence landmarks...