With the increasing pervasiveness of Artificial Intelligence (AI), many visual analytics tools have been proposed to examine fairness, but they mostly focus on data scientist users. While much work on AI fairness has focused on predictive decisions, less has been done for fair allocation and planning, which require human expertise and iterative design to integrate myriad constraints. We propose an interactive visual tool, Intelligible Fair City Planner (IF-City), to help urban planners to perceive inequality across groups, identify and attribute sources of inequality, and mitigate inequality with automatic allocation simulations and constraint-satisfying recommendations.
CrowdPredictor monitors and predicts the crowd flow in indoor area of MRT stations to help with early-warning of crowd congestion and stampede. It fuses multiple heterogenous data sources including distributed surveillance cameras, passengers' tap-in-tap-out records, mmWave sensors, and etc. Domain knowledge of crowd behavior analysis is also integrated with the deep learning-based prediction model.
Imma Sort supports Interpretable, Monotonic, Multi-Attribute sorting. It sorts items by multiple attributes simultaneously by trading-off the monotonicity in the primary sorted attribute to increase the human predictability for other attributes. This is the first work to define and study the human predictability for multiple attributes of sorted results, and opens up research on optimizing sorted results for human interpretability.
OD Morphing is an interactive OD bundling technique that improves geographical faithfulness to actual trajectories while preserving visual simplicity for OD patterns. It iteratively identifies critical waypoints from the actual trajectory network with a min-cut algorithm and transitions OD bundles to pass through the identified waypoints with a smooth morphing method.
Flexi-Sharing provides flexible and personalized taxi sharing services. It considers the nearby alternative pick-up/drop-off locations and schedules a flexible sharing route with the maximum reduced travel distance by letting passengers walk a short distance. For a sharing request, Flexi-Sharing generates the sharing schedule consisting of a set of companions, the shortest sharing route and the best pick-up/drop-off locations by maximizing the satisfaction of involved passengers.
