Taxi-aware map: identifying and predicting vacant taxis in the city

Authors:
Santi Phithakkitnukoon;Marco Veloso;Carlos Bento;Assaf Biderman;Carlo Ratti
Affiliations:
SENSEable City Lab, Massachusetts Institute of Technology, Cambridge, MA;Departamento de Engenharia Informática, Universidade de Coimbra, Portugal and Escola Superior de Tecnologia e Gestão de Oliveira do Hospital, Instituto Politécnico de Coimbra, Portu ...;Departamento de Engenharia Informática, Universidade de Coimbra, Portugal;SENSEable City Lab, Massachusetts Institute of Technology, Cambridge, MA;SENSEable City Lab, Massachusetts Institute of Technology, Cambridge, MA
Venue:
AmI'10 Proceedings of the First international joint conference on Ambient intelligence
Year:
2010

Citing 9
Cited 12

Elements of information theory

Elements of information theory
Machine Learning

Machine Learning
Intelligent Spaces: The Application of Pervasive ICT (Computer Communications and Networks)

Intelligent Spaces: The Application of Pervasive ICT (Computer Communications and Networks)
Navigate like a cabbie: probabilistic reasoning from observed context-aware behavior

UbiComp '08 Proceedings of the 10th international conference on Ubiquitous computing
Cellular Census: Explorations in Urban Data Collection

IEEE Pervasive Computing
Context-aware taxi demand hotspots prediction

International Journal of Business Intelligence and Data Mining
Adaptive routing of multiple taxis by mutual exchange of pathways

International Journal of Knowledge Engineering and Soft Data Paradigms
Activity-aware map: identifying human daily activity pattern using mobile phone data

HBU'10 Proceedings of the First international conference on Human behavior understanding
The geography of taste: analyzing cell-phone mobility and social events

Pervasive'10 Proceedings of the 8th international conference on Pervasive Computing

Urban mobility study using taxi traces

Proceedings of the 2011 international workshop on Trajectory data mining and analysis
iBAT: detecting anomalous taxi trajectories from GPS traces

Proceedings of the 13th international conference on Ubiquitous computing
Where to find my next passenger

Proceedings of the 13th international conference on Ubiquitous computing
Towards reducing taxicab cruising time using spatio-temporal profitability maps

SSTD'11 Proceedings of the 12th international conference on Advances in spatial and temporal databases
Sensing urban mobility with taxi flow

Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Location-Based Social Networks
Prediction of urban human mobility using large-scale taxi traces and its applications

Frontiers of Computer Science in China
Interacting with the steering wheel: potential reductions in driver distraction

AmI'11 Proceedings of the Second international conference on Ambient Intelligence
Where to wait for a taxi?

Proceedings of the ACM SIGKDD International Workshop on Urban Computing
Urban traffic modelling and prediction using large scale taxi GPS traces

Pervasive'12 Proceedings of the 10th international conference on Pervasive Computing
Exploring relationship between taxi volume and flue gases' concentrations

Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication
Real Time Anomalous Trajectory Detection and Analysis

Mobile Networks and Applications
From taxi GPS traces to social and community dynamics: A survey

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Knowing where vacant taxis are and will be at a given time and location helps the users in daily planning and scheduling, as well as the taxi service providers in dispatching. In this paper, we present a predictive model for the number of vacant taxis in a given area based on time of the day, day of the week, and weather condition. The history is used to build the prior probability distributions for our inference engine, which is based on the naïve Bayesian classifier with developed error-based learning algorithm and method for detecting adequacy of historical data using mutual information. Based on 150 taxis in Lisbon, Portugal, we are able to predict for each hour with the overall error rate of 0.8 taxis per 1×1 km2 area.