Discovering Mobility Patterns on Bicycle-Based Public Transportation System by Using Probabilistic Topic Models

@inproceedings{Montoliu2012DiscoveringMP,
  title={Discovering Mobility Patterns on Bicycle-Based Public Transportation System by Using Probabilistic Topic Models},
  author={Ra{\'u}l Montoliu},
  booktitle={ISAmI},
  year={2012}
}
In this work, we present a new framework to discover the daily mobility routines which are contained in a real-life dataset collected from a bike-sharing system. Our goal is the discovery and analysis of mobility patterns which characterize the behavior of the stations of a bike-sharing system based on the number of available bikes along a day. An unsupervised methodology based on probabilistic topic models has been used to achieve these goals. Topic models are probabilistic generative models… 

Exploring the Citywide Human Mobility Patterns of Taxi Trips through a Topic-Modeling Analysis

TLDR
To identify human mobility patterns, a topic model with the latent Dirichlet allocation (LDA) algorithm was proposed to infer the sixty-five key topics and it is revealed that Topic 44 exhibits dominant patterns, which means distance less than 10 km is predominant no matter what time in a day.

Spatio-temporal Analysis of Dynamic Origin-Destination Data Using Latent Dirichlet Allocation: Application to Vélib' Bike Sharing System of Paris

TLDR
An approach based on Latent Dirichlet Allocation (LDA), that extracts the main features of the spatio-temporal behavior of the BSS by extracting few OD-templates, interpreted as typical and temporally localized demand profiles is introduced in this paper.

Learning Urban Nightlife Routines from Mobile Data

TLDR
The results suggest that nightlife routine mining could be used as a complementary tool to traditional survey-based methods in public health studies, and also inform other institutional actors interested in understanding and supporting youth well-being.

Temporal decomposition and semantic enrichment of mobility flows

TLDR
The machine learning method of probabilistic topic modelling is applied for semantic enrichment of mobility data recorded in terms of trip counts by using geo-referenced social media data to explore the questions of causality and correlation, as well as predictability of the obtained semantic decompositions of mobility flows on a real dataset from a bike sharing network.

Real-Time Twitter Data Mining Approach to Infer User Perception Toward Active Mobility

TLDR
The findings from the analysis show that the proposed method can help produce more relevant information on walking and biking facilities as well as safety concerns and can be a critical part of the decision support system to understand the qualitative level of service of existing transportation facilities.

A crowdsourced dynamic repositioning strategy for public bike sharing systems

TLDR
A crowdsourced dynamic repositioning strategy that may reduce unmet rental demands by more than 30% during rush hours compared to conventional trucks is proposed.

Spatiotemporal Analysis of Bluetooth Data: Application to a Large Urban Network

TLDR
A methodological contribution to the use of Bluetooth data for the spatiotemporal analysis of a large urban network (Brisbane, Australia) is presented, which introduces the concept of the Bluetooth origin-destination (B-OD) matrix, which is built from a network of 79 Bluetooth detectors located within the Brisbane urban area.

Performance Analysis and Improvement of the Bike Sharing System Using Closed Queuing Networks with Blocking Mechanism

TLDR
This paper model a sub-graph of a Bike Sharing System using the closed queuing network with a Repetitive-Service-Random-Destination blocking mechanism and shows that the overall performance is robust enough regarding the fleet size changes but it degrades with the increase of the stations’ capacity.

References

SHOWING 1-10 OF 11 REFERENCES

Discovering routines from large-scale human locations using probabilistic topic models

TLDR
An unsupervised methodology based on two differing probabilistic topic models is developed and applied to the daily life of 97 mobile phone users over a 16-month period to achieve the discovery and analysis of human routines that characterize both individual and group behaviors in terms of location patterns.

Sensing and predicting the pulse of the city through shared bicycling

TLDR
This paper provides a spatiotemporal analysis of 13 weeks of bicycle station usage from Barcelona's shared bicycling system, called Bicing, and applies clustering techniques to identify shared behaviors across stations and shows how these behaviors relate to location, neighborhood, and time of day.

Measuring the Pulse of the City through Shared Bicycle Programs

TLDR
This paper provides a spatio-temporal analysis of six weeks of usage data from Barcelona's shared bicycling system called Bicing to show how these digital traces can be used to uncover daily routines, cultural influences and the role of time and space in city dynamics.

Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models

TLDR
A novel unsupervised learning framework to model activities and interactions in crowded and complicated scenes with many kinds of activities co-occurring, and three hierarchical Bayesian models are proposed that advance existing language models, such as LDA and HDP.

Finding scientific topics

  • T. GriffithsM. Steyvers
  • Computer Science
    Proceedings of the National Academy of Sciences of the United States of America
  • 2004
TLDR
A generative model for documents is described, introduced by Blei, Ng, and Jordan, and a Markov chain Monte Carlo algorithm is presented for inference in this model, which is used to analyze abstracts from PNAS by using Bayesian model selection to establish the number of topics.

Latent Dirichlet Allocation

Describing Visual Scenes Using Transformed Objects and Parts

TLDR
This work develops hierarchical, probabilistic models for objects, the parts composing them, and the visual scenes surrounding them and proposes nonparametric models which use Dirichlet processes to automatically learn the number of parts underlying each object category, and objects composing each scene.

Unsupervised Learning of Human Action Categories

TLDR
The approach is not only able to classify different actions, but also to localize different actions simultaneously in a novel and complex video sequence.

Agency seeks substitute for nextbike’s shelved hire fleet (2011), http://www.nzherald.co.nz/auckland-region/news/ article.cfm?l id=117&objectid=10700595

  • (accessed January
  • 2011