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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Generating realistic human flows across regions is essential for ourunderstanding of urban structures and population activity patterns, enablingimportant applications in the fields of urban planning and management. However,a notable shortcoming of most existing mobility generation methodologies isneglect of prediction fairness, which can result in underestimation of mobilityflows across regions with vulnerable population groups, potentially resultingin inequitable resource distribution and infrastructure development. Toovercome this limitation, our study presents a novel, fairness-aware deeplearning model, FairMobi-Net, for inter-region human flow prediction. TheFairMobi-Net model uniquely incorporates fairness loss into the loss functionand employs a hybrid approach, merging binary classification and numericalregression techniques for human flow prediction. We validate the FairMobi-Netmodel using comprehensive human mobility datasets from four U.S. cities,predicting human flow at the census-tract level. Our findings reveal that theFairMobi-Net model outperforms state-of-the-art models (such as the DeepGravitymodel) in producing more accurate and equitable human flow predictions across avariety of region pairs, regardless of regional income differences. The modelmaintains a high degree of accuracy consistently across diverse regions,addressing the previous fairness concern. Further analysis of featureimportance elucidates the impact of physical distances and road networkstructures on human flows across regions. With fairness as its touchstone, themodel and results provide researchers and practitioners across the fields ofurban sciences, transportation engineering, and computing with an effectivetool for accurate generation of human mobility flows across regions.

FairMobi-Net: A Fairness-aware Deep Learning Model for Urban Mobility Flow Generation