Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction

Zhang, Junbo; Zheng, Yu; Qi, Dekang

doi:10.48550/arxiv.1610.00081

Cited by 32 publications

(21 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among their many applications, trajectory data mining algorithms search for pa erns to cluster, forecast or classify a variety of moving objects, including animals, human, cars, and vessels [2,12,15,27,31,33,49,50]. Such applications include time series forecasting tasks such as predicting the ow of crowds [47,48] and time series classi cation tasks such as detecting human transportation modes [51] and shing activities [9,23,25]. ese applications allow us to improve tra c management, public safety, and environmental sustainability.…”

Section: Introductionmentioning

confidence: 99%

TrajectoryNet: An Embedded GPS Trajectory Representation for Point-based Classification Using Recurrent Neural Networks

Jiang¹,

Souza²,

Pesaranghader³

et al. 2017

Preprint

View full text Add to dashboard Cite

Understanding and discovering knowledge from GPS (Global Positioning System) traces of human activities is an essential topic in mobility-based urban computing. We propose TrajectoryNet-a neural network architecture for point-based trajectory classi cation to infer real world human transportation modes from GPS traces. To overcome the challenge of capturing the underlying latent factors in the low-dimensional and heterogeneous feature space imposed by GPS data, we develop a novel representation that embeds the original feature space into another space that can be understood as a form of basis expansion. We also enrich the feature space via segment-based information and use Maxout activations to improve the predictive power of Recurrent Neural Networks (RNNs). We achieve over 98% classi cation accuracy when detecting four types of transportation modes, outperforming existing models without additional sensory data or location-based prior knowledge.

show abstract

Section: Introductionmentioning

confidence: 99%

TrajectoryNet: An Embedded GPS Trajectory Representation for Point-based Classification Using Recurrent Neural Networks

Jiang¹,

Souza²,

Pesaranghader³

et al. 2017

Preprint

View full text Add to dashboard Cite

show abstract

“…The method based on deep learning has shown a superior ability for traffic flow forecasting in recent years. The LSTM [10], [11], [20] based methods demonstrates strong performance on capturing long-term temporal dependencies, and other directions of studies applied convolution neural network to capture spatial correlation [4], [21] when the deep residual convolutional structure [22] was proposed. However, while these studies only focus on spatial correlation or temporal dependency in their methods, none of them without pay close attention to both aspects simultaneously.…”

Section: Traffic Flow Predictionmentioning

confidence: 99%

Spatial-temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction

Liu,

Zhang,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

In an intelligent transportation system, the key problem of traffic forecasting is how to extract the periodic temporal dependencies and complex spatial correlation. Current state-of-the-art methods for traffic flow forecasting are based on graph architectures and sequence learning models, but they do not fully exploit spatial-temporal dynamic information in the traffic system. Specifically, the temporal dependence of the short-range is diluted by recurrent neural networks, and the existing sequence model ignores local spatial information because the convolution operation uses global average pooling. Besides, there will be some traffic accidents during the transitions of objects causing congestion in the real world that trigger increased prediction deviation. To overcome these challenges, we propose the Spatial-Temporal Conv-sequence Learning (STCL), in which a focused temporal block uses unidirectional convolution to effectively capture short-term periodic temporal dependence, and a spatial-temporal fusion module is able to extract the dependencies of both interactions and decrease the feature dimensions. Moreover, the accidents features impact on local traffic congestion, and position encoding is employed to detect anomalies in complex traffic situations. We conduct a large number of experiments on real-world tasks and verify the effectiveness of our proposed method.

show abstract

“…This is a problem when dealing with its probabilistic formulation which is difficult to tune, scale and it adds exogenous variables, i.e., other variables outside the existing variables [44]. • The simultaneous forecasting of the inflow and outflow of crowds in regions of a city is complex because of spatial dependencies, temporal dependencies and external influence factors [42]. • The complexity of sequential stock price datasets which require extensive analysis resources [40].…”

Section: 21mentioning

confidence: 99%

“…The art of improving the performance of any deep-learning framework is a process of iterated refinements. Currently, there is no single ideal framework that addresses the discontinuous, impulsive and irregular patterns of behaviour associated with irregular-patterned complex sequential datasets [19,42]. These extreme datasets can be found in many different domains, including: health care, traffic, finance, such as stock prices, meteorology, such as rainfall data and so forth.…”

Section: Introductionmentioning

confidence: 99%

Complex Sequential Data Analysis: A Systematic Literature Review of Existing Algorithms

Dandajena

Venter

Ghaziasgar

et al. 2020

Conference of the South African Institute of Computer Scientists and Information Technologists 2020

View full text Add to dashboard Cite

This paper provides a review of past approaches to the use of deep-learning frameworks for the analysis of discrete irregularpatterned complex sequential datasets. A typical example of such a dataset is financial data where specific events trigger sudden irregular changes in the sequence of the data. Traditional deep-learning methods perform poorly or even fail when trying to analyse these datasets. The results of a systematic literature review reveal the dominance of frameworks based on recurrent neural networks. The performance of deep-learning frameworks was found to be evaluated mainly using mean absolute error and root mean square error accuracy metrics. Underlying challenges that were identified are: lack of performance robustness, non-transparency of the methodology, internal and external architectural design and configuration issues. These challenges provide an opportunity to improve the framework for complex irregular-patterned sequential datasets.

show abstract

Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction

Cited by 32 publications

References 8 publications

TrajectoryNet: An Embedded GPS Trajectory Representation for Point-based Classification Using Recurrent Neural Networks

TrajectoryNet: An Embedded GPS Trajectory Representation for Point-based Classification Using Recurrent Neural Networks

Spatial-temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction

Complex Sequential Data Analysis: A Systematic Literature Review of Existing Algorithms

Contact Info

Product

Resources

About