|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Spatio-temporal transportations have various issues like traffic congestion, weather and wind direction. The measure problem is to prevent from traffic based accidents. The traffic may be in homogenous and heterogeneous format. In this paper the complete focus is based on heterogeneous traffic flow. In first stage we studied various research and we studied deep convolution network for identifying and measures the traffic accidents and developed a unique spatiotemporal graph-based model for predicting the probability of future traffic accidents. We used hybrid approach to improve the reliability and sustainability of large-scale networks through improving both recurrent and non-recurrent traffic conditions.
Keyword
Fully Connected traffic, K-hop neighbours, Dynamic Spatial Attention, Autonomous Vehicle, Deep Convolution Network
PDF Download (click here)
|
|
|
|
|