Reproduce “InclusiViz: Visual Analytics of Human Mobility Data for Understanding and Mitigating Urban Segregation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yue Yu, Yifang Wang, Yongjun Zhang, Huamin Qu, Dongyu Liu
InclusiViz is a visual analytics system that leverages human mobility data, deep learning, and explainable AI to enable urban planners and social scientists to understand and mitigate urban segregation. It provides multi-level analysis of activity spaces and offers interactive "what-if" simulations, demonstrating superior mobility flow prediction (e.g., Houston CPC 0.6197) and predicting up to a 6.44% change in segregation after simulated interventions.
Key insights
- Segregation extends beyond residential areas into daily "activity spaces," and its patterns are influenced by a complex interplay of environmental features and social group behaviors.
- Specific urban features, such as types of Points of Interest (POIs), can have varying positive or negative impacts on the mobility of different social groups, contributing to or alleviating segregation.
- "What-if" analysis with real-time feedback is crucial for designing effective interventions, as exemplified by how a combined POI strategy can synergistically reduce segregation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.