A Graph Signal Processing Approach For Real-Time Traffic Prediction In Transportation Networks
@article{Hasanzadeh2017AGS, title={A Graph Signal Processing Approach For Real-Time Traffic Prediction In Transportation Networks}, author={Arman Hasanzadeh and Xi Liu and Nick G. Duffield and Krishna R. Narayanan and Byron T Chigoy}, journal={arXiv: Signal Processing}, year={2017} }
Accurate real-time traffic prediction has a key role in traffic management strategies and intelligent transportation systems. [] Key Method First, we introduce a novel spatio-temporal clustering algorithm in order to split the large graph into multiple connected disjoint subgraphs. Then within each subgraph, we propose to use a Graph Signal Processing (GSP) approach to decouple spatial dependencies and obtain independent time series in graph frequency domain.
3 Citations
Deep Sequence Learning with Auxiliary Information for Traffic Prediction
- Computer ScienceKDD
- 2018
This paper intends to improve traffic prediction by appropriate integration of three kinds of implicit but essential factors encoded in auxiliary information within an encoder-decoder sequence learning framework that integrates the following data: offline geographical and social attributes.
Anomaly Detection in Smart City Traffic Based on Time Series Analysis
- Computer Science2019 International Conference on Software, Telecommunications and Computer Networks (SoftCOM)
- 2019
The proposed Occupancy based anomaly detection algorithm (OBADA) is analyzing occupancy data of the roads, by searching for subsequence of major changes in values in the occupancy's time series which reflects an inordinate behavior.
Variational Graph Recurrent Neural Networks
- Computer ScienceNeurIPS
- 2019
A novel hierarchical variational model is developed that introduces additional latent random variables to jointly model the hidden states of a graph recurrent neural network (GRNN) to capture both topology and node attribute changes in dynamic graphs.
References
SHOWING 1-10 OF 51 REFERENCES
Latent Space Model for Road Networks to Predict Time-Varying Traffic
- Computer ScienceKDD
- 2016
This paper proposes a Latent Space Model for Road Networks (LSM-RN), a framework for real-time traffic prediction on large road networks over competitors as well as baseline graph-based LSM's and presents an incremental online algorithm which sequentially and adaptively learns the latent attributes from the temporal graph changes.
Wavelets on graphs with application to transportation networks
- Computer Science17th International IEEE Conference on Intelligent Transportation Systems (ITSC)
- 2014
The research presented in this article focuses on the detection of disruptive traffic events such as congestion, and shows that the abrupt changes in the speed can be captured by using the wavelet coefficients at the higher scales.
Utilizing Real-World Transportation Data for Accurate Traffic Prediction
- Computer Science2012 IEEE 12th International Conference on Data Mining
- 2012
This paper utilized the spatiotemporal behaviors of rush hours and events to perform a more accurate prediction of both short-term and long-term average speed on road-segments, even in the presence of infrequent events (e.g., accidents).
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
- Computer ScienceIJCAI
- 2018
This paper proposes a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain, and builds the model with complete convolutional structures, which enable much faster training speed with fewer parameters.
Traffic Flow Prediction With Big Data: A Deep Learning Approach
- Computer ScienceIEEE Transactions on Intelligent Transportation Systems
- 2015
A novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently and is applied for the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction.
Towards stationary time-vertex signal processing
- Computer Science2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2017
A novel definition of joint (time-vertex) stationarity is introduced, which generalizes the classical definition of time stationarity and the recent definition appropriate for graphs and gives rise to a scalable Wiener optimization framework for denoising, semi-supervised learning, or more generally inverting a linear operator that is provably optimal.
Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction
- Computer ScienceSensors
- 2017
The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks and outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time.
New York city taxi analysis with graph signal processing
- Computer Science2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
- 2016
Graph frequency components reveal taxi behaviors that are not obvious from the raw signal, and spectral analysis on these graph signals is performed to address the challenge of finding the eigendecomposition of the 6K-node directed Manhattan road network.
Discovering spatio-temporal causal interactions in traffic data streams
- Computer ScienceKDD
- 2011
Algorithms which construct outlier causality trees based on temporal and spatial properties of detected outliers reveal not only recurring interactions among spatio-temporal outliers, but potential flaws in the design of existing traffic networks.
The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
- Computer ScienceIEEE Signal Processing Magazine
- 2013
This tutorial overview outlines the main challenges of the emerging field of signal processing on graphs, discusses different ways to define graph spectral domains, which are the analogs to the classical frequency domain, and highlights the importance of incorporating the irregular structures of graph data domains when processing signals on graphs.