English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent researches have shown the increasing use of machine learn-ing methodsin geography and urban analytics, primarily to extract features and patternsfrom spatial and temporal data using a supervised approach. Researchesintegrating geographical processes in machine learning models and the use ofunsupervised approacheson geographical data for knowledge discovery had beensparse. This research contributes to the ladder, where we show how latentvariables learned from unsupervised learning methods on urbanimages can be usedfor geographic knowledge discovery. In particular, we propose a simple approachcalled Convolutional-PCA(ConvPCA) which are applied on both street level andstreet network images to find a set of uncorrelated and ordered visuallatentcomponents. The approach allows for meaningful explanations using acombination of geographical and generative visualisations to explore the latentspace, and to show how the learned representation can be used to predict urbancharacteristics such as streetquality and street network attributes. Theresearch also finds that the visual components from the ConvPCA model achievessimilaraccuracy when compared to less interpretable dimension reductiontechniques.

An unsupervised approach to Geographical Knowledge Discovery using street level and street network images