PULSE: A Real Time System for Crowd Flow Prediction at Metropolitan Subway Stations

@inproceedings{Toto2016PULSEAR,
  title={PULSE: A Real Time System for Crowd Flow Prediction at Metropolitan Subway Stations},
  author={Ermal Toto and Elke A. Rundensteiner and Yanhua Li and Richard Jordan and Mariya Ishutkina and Kajal T. Claypool and Jun Luo and Fan Zhang},
  booktitle={ECML/PKDD},
  year={2016}
}
The fast pace of urbanization has given rise to complex transportation networks, such as subway systems, that deploy smart card readers generating detailed transactions of mobility. Predictions of human movement based on these transaction streams represents tremendous new opportunities from optimizing fleet allocation of on-demand transportation such as UBER and LYFT to dynamic pricing of services. However, transportation research thus far has primarily focused on tackling other challenges from… 

Modeling urban trip demands in cloud-commuting system: A holistic approach

TLDR
Generative models to capture fundamental demand arrival and service patterns are developed, and a novel model to estimate the total number of vehicles needed to serve all urban demands are introduced.

Forecasting Pedestrian Movements Using Recurrent Neural Networks: An Application of Crowd Monitoring Data

TLDR
To design, train and benchmark a data-driven procedure to forecast crowd movements, which can in real-time predict crowd movement, the RNN-GRU is found to outperform the other tested models.

Urban Traffic Dynamics Prediction—A Continuous Spatial-temporal Meta-learning Approach

TLDR
The experimental results verify that cST-ML can significantly improve the urban traffic prediction performance and outperform all baseline models especially when obvious traffic dynamics and temporal uncertainties are presented.

PANGO: Prediction Model Based on Clustering of Time Series for Traffic Flow to Venues

  • Huayi ZhouPeng Xu
  • Computer Science
    2022 IEEE 2nd International Conference on Computer Communication and Artificial Intelligence (CCAI)
  • 2022
TLDR
A Long Short Term Memory network (LSTM) combined with clustering of time series named PANGO is proposed, and the temporal clustering is proposed to solve the short-term dependence of traffic flow data and the long-term cycle prediction model is applied to obtain the longterm cycle characteristics, so as to improve the accuracy of prediction.

An efficient technique for event location identification using multiple sources of urban data

TLDR
This paper proposes "fEEL" (Efficient Event Location identification), a novel algorithm to identify affected areas from social events using multiple heterogeneous sources of urban data and shows that fEEL is efficient and practical.

SCCS: Smart Cloud Commuting System With Shared Autonomous Vehicles

TLDR
It is demonstrated that the proposed SCCS framework can serve the trip demands with 22 percent fewer vehicles and 37 percent more vehicle utilization, which shed lights on the design feasibility of future smart transportation systems.

Off-Deployment Traffic Estimation — A Traffic Generative Adversarial Networks Approach

TLDR
This paper defines the off-deployment traffic estimation problem as a traffic generation problem, and develops a novel deep generative model TrafficGAN that captures the shared patterns across spatial regions of how traffic conditions evolve according to travel demand changes and underlying road network structures.

CityLines: Designing Hybrid Hub-and-Spoke Transit System with Urban Big Data

TLDR
The proposed CityLines system routes urban trips among spokes through a few hubs or direct paths, with travel time as short as private transits and fare as low as public transits, allowing both point-to-point connection to improve the passenger QoE, and hub-and-spoke connection to reduce the system operation cost.

Sensing and Forecasting Crowd Distribution in Smart Cities: Potentials and Approaches

TLDR
The objective of this survey is to overview the many potential application areas of crowd sensing and prediction, the technologies that can be exploited to sense crowd along with their potentials and limitations, and the data analysis techniques that could be effectively used to forecast crowd distribution.

Curb-GAN: Conditional Urban Traffic Estimation through Spatio-Temporal Generative Adversarial Networks

TLDR
A novel Conditional Urban Traffic Generative Adversarial Network (Curb-GAN), which provides traffic estimations in consecutive time slots based on different travel demands, thus enables urban planners to accurately evaluate urban plans before deploying them and outperforms major baseline methods in estimation accuracy under various conditions.

References

SHOWING 1-10 OF 28 REFERENCES

Predicting Taxi–Passenger Demand Using Streaming Data

TLDR
A novel methodology for predicting the spatial distribution of taxi-passengers for a short-term time horizon using streaming data and demonstrates that the proposed framework can provide effective insight into the spatiotemporal distribution of Taxi-passenger demand for a 30-min horizon.

Traffic prediction in a bike-sharing system

TLDR
A hierarchical prediction model to predict the number of bikes that will be rent from/returned to each station cluster in a future period so that reallocation can be executed in advance and its advantage beyond baseline approaches is confirmed.

Predicting Travel Times with Context-Dependent Random Forests by Modeling Local and Aggregate Traffic Flow

  • Benjamin Hamner
  • Computer Science
    2010 IEEE International Conference on Data Mining Workshops
  • 2010
TLDR
A methodology developed to predict future travel times based on GPS reports of 1% of the cars on the road in a simulation framework, which performed best in one track of the 2010 IEEE ICDM Contest: Tom Tom Traffic Prediction for Intelligent GPS Navigation.

Short-term freeway traffic flow prediction : Bayesian combined neural network approach

TLDR
A neural network model is introduced that combines the prediction from single neural network predictors according to an adaptive and heuristic credit assignment algorithm based on the theory of conditional probability and Bayes' rule and is found that most of the time, the combined model outperforms the singular predictors.

Short Term Traffic Forecasting Using the Local Linear Regression Model

TLDR
This paper proposes and applies local linear regression models to short-term traffic prediction and finds that the local linear methods consistently outperform the nearest neighborhood and kernel smoothing methods.

OpenStreetCab: Exploiting Taxi Mobility Patterns in New York City to Reduce Commuter Costs

TLDR
This study takes advantage of a publicly available longitudinal dataset that describes the mobility of yellow taxis in New York City to provide a first head to head comparison between the iconic yellow taxi and its modern competitor, Uber, in one of the world's largest metropolitan centres.

Measuring Centralities for Transportation Networks Beyond Structures

TLDR
New centrality measures that incorporate travel time delay and commuter flow volume are proposed that are applied on Singapore’s subway network involving 89 stations and about 2 million commuter trips per day, and compared with traditional topology basedcentrality measures.

Understanding individual and collective mobility patterns from smart card records: A case study in Shenzhen

TLDR
The analytical methodologies to spatially and temporally quantify, visualize, and examine urban mobility patterns developed in this paper could provide decision support for transport planning and management.