scholarly journals Dual-Stage Attention Based Spatio-Temporal Sequence Learning for Multi-Step Traffic Prediction

2020 ◽  
Vol 53 (2) ◽  
pp. 17035-17040
Author(s):  
Ziqiang Cui ◽  
Chunhui Zhao
Keyword(s):  
Sequence Learning ◽  
Temporal Sequence ◽  
Traffic Prediction ◽  
Dual Stage ◽  
Spatio Temporal

MDTP

2021 ◽  
Vol 14 (8) ◽  
pp. 1289-1297
Author(s):  
Ziquan Fang ◽  
Lu Pan ◽  
Lu Chen ◽  
Yuntao Du ◽  
Yunjun Gao
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Temporal Dynamics ◽  
Real Life ◽  
Feature Modeling ◽  
Traffic Prediction ◽  
Interactive System ◽  
Trajectory Data ◽  
Spatio Temporal ◽  
Prediction Approach

Traffic prediction has drawn increasing attention for its ubiquitous real-life applications in traffic management, urban computing, public safety, and so on. Recently, the availability of massive trajectory data and the success of deep learning motivate a plethora of deep traffic prediction studies. However, the existing neural-network-based approaches tend to ignore the correlations between multiple types of moving objects located in the same spatio-temporal traffic area, which is suboptimal for traffic prediction analytics. In this paper, we propose a multi-source deep traffic prediction framework over spatio-temporal trajectory data, termed as MDTP. The framework includes two phases: spatio-temporal feature modeling and multi-source bridging. We present an enhanced graph convolutional network (GCN) model combined with long short-term memory network (LSTM) to capture the spatial dependencies and temporal dynamics of traffic in the feature modeling phase. In the multi-source bridging phase, we propose two methods, Sum and Concat, to connect the learned features from different trajectory data sources. Extensive experiments on two real-life datasets show that MDTP i) has superior efficiency, compared with classical time-series methods, machine learning methods, and state-of-the-art neural-network-based approaches; ii) offers a significant performance improvement over the single-source traffic prediction approach; and iii) performs traffic predictions in seconds even on tens of millions of trajectory data. we develop MDTP + , a user-friendly interactive system to demonstrate traffic prediction analysis.

Retrieval of spatio-temporal sequence in asynchronous neural network

1990 ◽  
Vol 41 (6) ◽  
pp. 3346-3354 ◽  
Author(s):  
Hidetoshi Nishimori ◽  
Tota Nakamura ◽  
Masatoshi Shiino
Keyword(s):  
Neural Network ◽  
Temporal Sequence ◽  
Spatio Temporal

scholarly journals Theta oscillations promote temporal sequence learning

2018 ◽  
Vol 153 ◽  
pp. 92-103 ◽  
Author(s):  
Jordan Crivelli-Decker ◽  
Liang-Tien Hsieh ◽  
Alex Clarke ◽  
Charan Ranganath
Keyword(s):  
Sequence Learning ◽  
Temporal Sequence ◽  
Theta Oscillations

Spatial and Temporal Sequence Learning in Patients with Parkinson's Disease or Cerebellar Lesions

2003 ◽  
Vol 15 (8) ◽  
pp. 1232-1243 ◽  
Author(s):  
Jacqueline C. Shin ◽  
Richard B. Ivry
Keyword(s):  
Sequence Learning ◽  
Functional Role ◽  
Phase Relationship ◽  
Reaction Time Task ◽  
Training Sequence ◽  
Temporal Sequence ◽  
General Role ◽  
Cerebellar Damage ◽  
Patient Groups

The functional role of different subcortical areas in sequence learning is not clear. In the current study, Parkinson's patients, patients with cerebellar damage, and age-matched control participants performed a serial reaction time task in which a spatial sequence and a temporal sequence were presented simultaneously. The responses were based on the spatial sequence, and the temporal sequence was incidental to the task. The two sequences were of the same length, and the phase relationship between them was held constant throughout training. Sequence learning was assessed comparing performance when both sequences were present versus when the dimension of interest was randomized. In addition, sequence integration was assessed by introducing phase-shift blocks. A functional dissociation was found between the two patient groups. Whereas the Parkinson's patients learned the spatial and temporal sequences individually, they did not learn the relationship between the two sequences, suggesting the basal ganglia play a functional role in sequence integration. In contrast, the cerebellar patients did not show any evidence of sequence learning at all, suggesting the cerebellum might play a general role in forming sequential associations.

Somite abnormalities caused by short heat shocks to pre-neurula stages of Xenopus laevis

Development ◽  
1978 ◽  
Vol 45 (1) ◽  
pp. 283-294
Author(s):  
Jonathan Cooke
Keyword(s):  
High Temperature ◽  
Xenopus Laevis ◽  
Temporal Sequence ◽  
Embryonic Stage ◽  
Regular Pattern ◽  
Tail Bud ◽  
Heat Shocks ◽  
Similar Temperature ◽  
Spatio Temporal ◽  
Small Disturbances

This paper describes the small disturbances, in the regular pattern of the somites and the fissures between them, that are seen following short (around 300 s) heat shocks at 37·5 °C delivered to pre-neurula stages of Xenopus laevis. Affected groups of cells still finally differentiate as somite muscle, but the normally precise spatio-temporal sequence in which they move beforehand to give rise to the actual pattern of somite blocks, is disrupted. Examination of the position and sizes of patches of disrupted morphogenesis, in relation to the precise embryonic stage at shock, leads to certain conclusions about the nature of the disturbance induced by a brief period at high temperature, in cells due to form somites. The pattern of results is compared with that produced by similar temperature shocks given to tail-bud (later) staged embryos. The discussion includes a brief consideration of how the various results of heat shocks, given at different embryonic stages, might be understood in terms of one particular model (Cooke & Zeeman, 1976) for the spatio-temporal control of the developing somite pattern.

Sign in / Sign up

Export Citation Format

Share Document