scholarly journals Multicomponent Spatial-Temporal Graph Attention Convolution Networks for Traffic Prediction with Spatially Sparse Data

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Shaohua Liu ◽  
Shijun Dai ◽  
Jingkai Sun ◽  
Tianlu Mao ◽  
Junsuo Zhao ◽  
...  
Keyword(s):  
Sparse Data ◽  
Superior Performance ◽  
Traffic Prediction ◽  
Traffic Data ◽  
Convolutional Networks ◽  
Learning Framework ◽  
Spatial Dependencies ◽  
Temporal Graph ◽  
Correlation Information ◽  
Temporal Periodicity

Predicting traffic data on traffic networks is essential to transportation management. It is a challenging task due to the complicated spatial-temporal dependency. The latest studies mainly focus on capturing temporal and spatial dependencies with spatially dense traffic data. However, when traffic data become spatially sparse, existing methods cannot capture sufficient spatial correlation information and thus fail to learn the temporal periodicity sufficiently. To address these issues, we propose a novel deep learning framework, Multi-component Spatial-Temporal Graph Attention Convolutional Networks (MSTGACN), for traffic prediction, and we successfully apply it to predicting traffic flow and speed with spatially sparse data. MSTGACN mainly consists of three independent components to model three types of periodic information. Each component in MSTGACN combines dilated causal convolution, graph convolution layer, and the weight-shared graph attention layer. Experimental results on three real-world traffic datasets, METR-LA, PeMS-BAY, and PeMSD7-sparse, demonstrate the superior performance of our method in the case of spatially sparse data.

scholarly journals Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting

2019 ◽  
Vol 33 ◽  
pp. 890-897 ◽  
Author(s):  
Zulong Diao ◽  
Xin Wang ◽  
Dafang Zhang ◽  
Yingru Liu ◽  
Kun Xie ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Tensor Decomposition ◽  
Laplacian Matrix ◽  
Traffic Data ◽  
Theoretical Derivation ◽  
Traffic Forecasting ◽  
Learning Framework ◽  
Spatial Dependencies

Graph convolutional neural networks (GCNN) have become an increasingly active field of research. It models the spatial dependencies of nodes in a graph with a pre-defined Laplacian matrix based on node distances. However, in many application scenarios, spatial dependencies change over time, and the use of fixed Laplacian matrix cannot capture the change. To track the spatial dependencies among traffic data, we propose a dynamic spatio-temporal GCNN for accurate traffic forecasting. The core of our deep learning framework is the finding of the change of Laplacian matrix with a dynamic Laplacian matrix estimator. To enable timely learning with a low complexity, we creatively incorporate tensor decomposition into the deep learning framework, where real-time traffic data are decomposed into a global component that is stable and depends on long-term temporal-spatial traffic relationship and a local component that captures the traffic fluctuations. We propose a novel design to estimate the dynamic Laplacian matrix of the graph with above two components based on our theoretical derivation, and introduce our design basis. The forecasting performance is evaluated with two realtime traffic datasets. Experiment results demonstrate that our network can achieve up to 25% accuracy improvement.

scholarly journals Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting

2018 ◽  
Author(s):  
Bing Yu ◽  
Haoteng Yin ◽  
Zhanxing Zhu
Keyword(s):  
Deep Learning ◽  
Traffic Control ◽  
Time Series Prediction ◽  
Urban Traffic ◽  
Traffic Forecasting ◽  
Convolutional Networks ◽  
Learning Framework ◽  
Temporal Correlations ◽  
Temporal Graph ◽  
Spatio Temporal

Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies. In this paper, we propose a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain. Instead of applying regular convolutional and recurrent units, we formulate the problem on graphs and build the model with complete convolutional structures, which enable much faster training speed with fewer parameters. Experiments show that our model STGCN effectively captures comprehensive spatio-temporal correlations through modeling multi-scale traffic networks and consistently outperforms state-of-the-art baselines on various real-world traffic datasets.

scholarly journals Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography

Algorithms ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 144
Author(s):  
Yuexing Han ◽  
Xiaolong Li ◽  
Bing Wang ◽  
Lu Wang
Keyword(s):  
Image Segmentation ◽  
Spatial Information ◽  
Medical Images ◽  
Tumor Segmentation ◽  
Convolutional Networks ◽  
Learning Framework ◽  
Fully Convolutional Networks ◽  
Segmentation Accuracy ◽  
Boundary Information

Image segmentation plays an important role in the field of image processing, helping to understand images and recognize objects. However, most existing methods are often unable to effectively explore the spatial information in 3D image segmentation, and they neglect the information from the contours and boundaries of the observed objects. In addition, shape boundaries can help to locate the positions of the observed objects, but most of the existing loss functions neglect the information from the boundaries. To overcome these shortcomings, this paper presents a new cascaded 2.5D fully convolutional networks (FCNs) learning framework to segment 3D medical images. A new boundary loss that incorporates distance, area, and boundary information is also proposed for the cascaded FCNs to learning more boundary and contour features from the 3D medical images. Moreover, an effective post-processing method is developed to further improve the segmentation accuracy. We verified the proposed method on LITS and 3DIRCADb datasets that include the liver and tumors. The experimental results show that the performance of the proposed method is better than existing methods with a Dice Per Case score of 74.5% for tumor segmentation, indicating the effectiveness of the proposed method.

scholarly journals HMD-ARG: hierarchical multi-task deep learning for annotating antibiotic resistance genes

Microbiome ◽  
2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Yu Li ◽  
Zeling Xu ◽  
Wenkai Han ◽  
Huiluo Cao ◽  
Ramzan Umarov ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Deep Learning ◽  
Resistance Genes ◽  
Antibiotic Resistance Genes ◽  
Third Party ◽  
Superior Performance ◽  
Beta Lactamase ◽  
Learning Framework ◽  
Sequence Encoding ◽  
Global Threat

Abstract Background The spread of antibiotic resistance has become one of the most urgent threats to global health, which is estimated to cause 700,000 deaths each year globally. Its surrogates, antibiotic resistance genes (ARGs), are highly transmittable between food, water, animal, and human to mitigate the efficacy of antibiotics. Accurately identifying ARGs is thus an indispensable step to understanding the ecology, and transmission of ARGs between environmental and human-associated reservoirs. Unfortunately, the previous computational methods for identifying ARGs are mostly based on sequence alignment, which cannot identify novel ARGs, and their applications are limited by currently incomplete knowledge about ARGs. Results Here, we propose an end-to-end Hierarchical Multi-task Deep learning framework for ARG annotation (HMD-ARG). Taking raw sequence encoding as input, HMD-ARG can identify, without querying against existing sequence databases, multiple ARG properties simultaneously, including if the input protein sequence is an ARG, and if so, what antibiotic family it is resistant to, what resistant mechanism the ARG takes, and if the ARG is an intrinsic one or acquired one. In addition, if the predicted antibiotic family is beta-lactamase, HMD-ARG further predicts the subclass of beta-lactamase that the ARG is resistant to. Comprehensive experiments, including cross-fold validation, third-party dataset validation in human gut microbiota, wet-experimental functional validation, and structural investigation of predicted conserved sites, demonstrate not only the superior performance of our method over the state-of-art methods, but also the effectiveness and robustness of the proposed method. Conclusions We propose a hierarchical multi-task method, HMD-ARG, which is based on deep learning and can provide detailed annotations of ARGs from three important aspects: resistant antibiotic class, resistant mechanism, and gene mobility. We believe that HMD-ARG can serve as a powerful tool to identify antibiotic resistance genes and, therefore mitigate their global threat. Our method and the constructed database are available at http://www.cbrc.kaust.edu.sa/HMDARG/.

Multi-stage attention spatial-temporal graph networks for traffic prediction

2021 ◽  
Vol 428 ◽  
pp. 42-53
Author(s):  
Xueyan Yin ◽  
Genze Wu ◽  
Jinze Wei ◽  
Yanming Shen ◽  
Heng Qi ◽  
...  
Keyword(s):  
Traffic Prediction ◽  
Multi Stage ◽  
Temporal Graph

scholarly journals Tensor Decomposition for Spatial—Temporal Traffic Flow Prediction with Sparse Data

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6046
Author(s):  
Funing Yang ◽  
Guoliang Liu ◽  
Liping Huang ◽  
Cheng Siong Chin
Keyword(s):  
Traffic Flow ◽  
Prediction Method ◽  
Sparse Data ◽  
Time Of Day ◽  
Traffic Prediction ◽  
Traffic Surveillance ◽  
Data Sparsity ◽  
Traffic Flow Prediction ◽  
Flow Prediction ◽  
Sparsity Problem

Urban transport traffic surveillance is of great importance for public traffic control and personal travel path planning. Effective and efficient traffic flow prediction is helpful to optimize these real applications. The main challenge of traffic flow prediction is the data sparsity problem, meaning that traffic flow on some roads or of certain periods cannot be monitored. This paper presents a transport traffic prediction method that leverages the spatial and temporal correlation of transportation traffic to tackle this problem. We first propose to model the traffic flow using a fourth-order tensor, which incorporates the location, the time of day, the day of the week, and the week of the month. Based on the constructed traffic flow tensor, we either propose a model to estimate the correlation in each dimension of the tensor. Furthermore, we utilize the gradient descent strategy to design a traffic flow prediction algorithm that is capable of tackling the data sparsity problem from the spatial and temporal perspectives of the traffic pattern. To validate the proposed traffic prediction method, case studies using real-work datasets are constructed, and the results demonstrate that the prediction accuracy of our proposed method outperforms the baselines. The accuracy decreases the least with the percentage of missing data increasing, including the situation of data being missing on neighboring roads in one or continuous multi-days. This certifies that the proposed prediction method can be utilized for sparse data-based transportation traffic surveillance.

Two-Stream Spatial-Temporal Graph Convolutional Networks for Driver Drowsiness Detection

2021 ◽  
pp. 1-13
Author(s):  
Jing Bai ◽  
Wentao Yu ◽  
Zhu Xiao ◽  
Vincent Havyarimana ◽  
Amelia C. Regan ◽  
...  
Keyword(s):  
Drowsiness Detection ◽  
Convolutional Networks ◽  
Driver Drowsiness ◽  
Temporal Graph

scholarly journals Hybrid Spatial–Temporal Graph Convolutional Networks for On-Street Parking Availability Prediction

2021 ◽  
Vol 13 (16) ◽  
pp. 3338
Author(s):  
Xiao Xiao ◽  
Zhiling Jin ◽  
Yilong Hui ◽  
Yueshen Xu ◽  
Wei Shao
Keyword(s):  
Smart Cities ◽  
Convolutional Networks ◽  
Temporal Correlations ◽  
Spatial Features ◽  
Temporal Features ◽  
Prediction Scheme ◽  
Temporal Graph ◽  
Real World Datasets ◽  
The Internet Of Things

With the development of sensors and of the Internet of Things (IoT), smart cities can provide people with a variety of information for a more convenient life. Effective on-street parking availability prediction can improve parking efficiency and, at times, alleviate city congestion. Conventional methods of parking availability prediction often do not consider the spatial–temporal features of parking duration distributions. To this end, we propose a parking space prediction scheme called the hybrid spatial–temporal graph convolution networks (HST-GCNs). We use graph convolutional networks and gated linear units (GLUs) with a 1D convolutional neural network to obtain the spatial features and the temporal features, respectively. Then, we construct a spatial–temporal convolutional block to obtain the instantaneous spatial–temporal correlations. Based on the similarity of the parking duration distributions, we propose an attention mechanism called distAtt to measure the similarity of parking duration distributions. Through the distAtt mechanism, we add the long-term spatial–temporal correlations to our spatial–temporal convolutional block, and thus, we can capture complex hybrid spatial–temporal correlations to achieve a higher accuracy of parking availability prediction. Based on real-world datasets, we compare the proposed scheme with the benchmark models. The experimental results show that the proposed scheme has the best performance in predicting the parking occupancy rate.

Sign in / Sign up

Export Citation Format

Share Document