Potential of eye-tracking for interactive geovisual exploration aided by machine learning

M Keskin, P Kettunen - International Journal of Cartography, 2023 - Taylor & Francis
This review article collects knowledge on the use of eye-tracking and machine learning
methods for application in automated and interactive geovisualization systems. Our focus is …

Towards general-purpose representation learning of polygonal geometries

G Mai, C Jiang, W Sun, R Zhu, Y Xuan, L Cai… - GeoInformatica, 2023 - Springer
Neural network representation learning for spatial data (eg, points, polylines, polygons, and
networks) is a common need for geographic artificial intelligence (GeoAI) problems. In …

A survey on spatial, temporal, and spatio-temporal database research and an original example of relevant applications using SQL ecosystem and deep learning

K Jitkajornwanich, N Pant, M Fouladgar… - Journal of information …, 2020 - Taylor & Francis
Spatio-temporal data serves as a foundation for most location-based applications
nowadays. To handle spatio-temporal data, an appropriate methodology needs to be …

MultiLineStringNet: a deep neural network for linear feature set recognition

P Li, H Yan, X Lu - Cartography and Geographic Information …, 2024 - Taylor & Francis
Pattern recognition of linear feature sets, such as river networks, road networks, and contour
clusters, is essential in cartography and geographic information science. Previous studies …

Spatial Representation Learning in GeoAI

G Mai, Z Li, N Lao - Handbook of Geospatial Artificial Intelligence, 2023 - taylorfrancis.com
Spatial representation learning (SRL) refers to a set of techniques that use deep neural
networks (DNNs) to encode and featurize various types of spatial data in the forms of points …

Logistic facility identification from spatial time series data

DJ De Beer, JW Joubert - Computers, Environment and Urban Systems, 2024 - Elsevier
Vehicle telemetry data is becoming more ubiquitous with increasingly sensorised vehicles,
but making sense of the vehicles' purpose remains challenging without additional context …

Learning from vector data: enhancing vector-based shape encoding and shape classification for map generalization purposes

M Knura - Cartography and Geographic Information Science, 2024 - Taylor & Francis
Map generalization is a complex task that requires a high level of spatial cognition, and
deep learning techniques have shown in numerous research fields that they could match or …

Two-dimensional polygon classification and pairwise clustering for pairing in ship parts nesting

GY Na, J Yang - Journal of Intelligent Manufacturing, 2024 - Springer
In the shipbuilding industry, nesting is arranging the cutting patterns of ship parts to increase
the utilization rate of steel sheets and reduce the scrap rate. The nesting complexity is high …

Encoding geospatial vector data for deep learning: LULC as a use case

M Mc Cutchan, I Giannopoulos - Remote Sensing, 2022 - mdpi.com
Geospatial vector data with semantic annotations are a promising but complex data source
for spatial prediction tasks such as land use and land cover (LULC) classification. These …

Learning Geometric Invariant Features for Classification of Vector Polygons with Graph Message-passing Neural Network

Z Huang, K Khoshelham, M Tomko - arxiv preprint arxiv:2407.04334, 2024 - arxiv.org
Geometric shape classification of vector polygons remains a non-trivial learning task in
spatial analysis. Previous studies mainly focus on devising deep learning approaches for …