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

In this paper, we study how to model taxi drivers' behaviour and geographicalinformation for an interesting and challenging task: the next destinationprediction in a taxi journey. Predicting the next location is a well studiedproblem in human mobility, which finds several applications in real-worldscenarios, from optimizing the efficiency of electronic dispatching systems topredicting and reducing the traffic jam. This task is normally modeled as amulticlass classification problem, where the goal is to select, among a set ofalready known locations, the next taxi destination. We present a RecurrentNeural Network (RNN) approach that models the taxi drivers' behaviour andencodes the semantics of visited locations by using geographical informationfrom Location-Based Social Networks (LBSNs). In particular, RNNs are trained topredict the exact coordinates of the next destination, overcoming the problemof producing, in output, a limited set of locations, seen during the trainingphase. The proposed approach was tested on the ECML/PKDD Discovery Challenge2015 dataset - based on the city of Porto -, obtaining better results withrespect to the competition winner, whilst using less information, and onManhattan and San Francisco datasets.

Modeling Taxi Drivers' Behaviour for the Next Destination Prediction