Risk-aware Route Recommendation

What is it about?

Multi-objective route recommendation system based on heterogeneous urban sensing open data (i.e., crime, accident, traffic flow, road network, meteorological, calendar event, and point of interest distributions). . We introduce a wide, deep, and multitask-learning (WD-MTL) framework that uses a transformer to extract spatial, temporal, and semantic correlation for predicting crime, accident, and traffic flow of particular road segment. Later, for a particular source and destination, the adaptive epsilon constraint technique is used to optimize route satisfying multiple objective functions.

Featured Image

Photo by Hendrik Morkel on Unsplash

Photo by Hendrik Morkel on Unsplash

Why is it important?

Automatic route navigation systems provide route recommendation based on shortest distance and time-aware routes, which helps traveling in unfamiliar or complex routes. These navigation systems are heavily used by tourists or visitors during traveling. Therefore, the safety of tourists is more important to any country or regional government to raise the country’s economic growth. However, the current recommendations lack in considering risk prone navigation routes, such as accident prone road segments, crime prone areas, etc. Our work addresses the issue of tourist safety and proposes a framework.

Perspectives