Open AccessNeural Network-Based Ridesharing Policy for Reducing Rider Transportation Cost
Author(s) -
Karl Cedric U. Obias,
Elmer R. Magsino,
Edwin Sybingco
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1997/1/012011
Subject(s) - taxis , traffic congestion , transport engineering , computer science , queueing theory , artificial neural network , trace (psycholinguistics) , operations research , computer network , engineering , linguistics , philosophy , machine learning
With the increasing demand for taxis during peak hours, adding more vehicles is not always the optimal solution since this will also contribute to the increasing traffic congestion, noise, and air pollution. In this study, we propose a neural network-based ridesharing policy that will utilize the available seats in an occupied taxi to accommodate other queueing passengers. The proposed policy allows a single taxi to transport more people at the same time and reduces the passenger taxi fare. The ridesharing policy is extensively verified by studying empirical mobility trace datasets to determine its capability of reducing transportation costs for riders. Test results show that the proposed ridesharing policy can reduce the cost by approximately 120% with the implementation of ridesharing.