@Article{cmc.2020.09903,
AUTHOR = {Jinyuan Li, Hao Li, Guorong Cui, Yan Kang, Yang Hu, Yingnan Zhou},
TITLE = {GACNet: A Generative Adversarial Capsule Network for Regional Epitaxial Traffic Flow Prediction},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {64},
YEAR = {2020},
NUMBER = {2},
PAGES = {925--940},
URL = {http://www.techscience.com/cmc/v64n2/39337},
ISSN = {1546-2226},
ABSTRACT = {With continuous urbanization, cities are undergoing a sharp expansion within 
the regional space. Due to the high cost, the prediction of regional traffic flow is more 
difficult to extend to entire urban areas. To address this challenging problem, we present
a new deep learning architecture for regional epitaxial traffic flow prediction called 
GACNet, which predicts traffic flow of surrounding areas based on inflow and outflow 
information in central area. The method is data-driven, and the spatial relationship of 
traffic flow is characterized by dynamically transforming traffic information into images 
through a two-dimensional matrix. We introduce adversarial training to improve
performance of prediction and enhance the robustness. The generator mainly consists of 
two parts: abstract traffic feature extraction in the central region and traffic prediction in 
the extended region. In particular, the feature extraction part captures nonlinear spatial 
dependence using gated convolution, and replaces the maximum pooling operation with 
dynamic routing, finally aggregates multidimensional information in capsule form. The 
effectiveness of the method is evaluated using traffic flow datasets for two real traffic 
networks: Beijing and New York. Experiments on highly challenging datasets show that 
our method performs well for this task.},
DOI = {10.32604/cmc.2020.09903}
}