Temporal Hierarchical Graph Attention Network for Traffic Prediction

2021 ◽  
Vol 12 (6) ◽  
pp. 1-21
Author(s):  
Ling Huang ◽  
Xing-Xing Liu ◽  
Shu-Qiang Huang ◽  
Chang-Dong Wang ◽  
Wei Tu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Spatial Dependence ◽  
Road Network ◽  
Rapid Development ◽  
Traffic Prediction ◽  
Regional Structure ◽  
Attention Network ◽  
Hierarchical Graph ◽  
Temporal Dependencies

As a critical task in intelligent traffic systems, traffic prediction has received a large amount of attention in the past few decades. The early efforts mainly model traffic prediction as the time-series mining problem, in which the spatial dependence has been largely ignored. As the rapid development of deep learning, some attempts have been made in modeling traffic prediction as the spatio-temporal data mining problem in a road network, in which deep learning techniques can be adopted for modeling the spatial and temporal dependencies simultaneously. Despite the success, the spatial and temporal dependencies are only modeled in a regionless network without considering the underlying hierarchical regional structure of the spatial nodes, which is an important structure naturally existing in the real-world road network. Apart from the challenge of modeling the spatial and temporal dependencies like the existing studies, the extra challenge caused by considering the hierarchical regional structure of the road network lies in simultaneously modeling the spatial and temporal dependencies between nodes and regions and the spatial and temporal dependencies between regions. To this end, this article proposes a new Temporal Hierarchical Graph Attention Network (TH-GAT). The main idea lies in augmenting the original road network into a region-augmented network, in which the hierarchical regional structure can be modeled. Based on the region-augmented network, the region-aware spatial dependence model and the region-aware temporal dependence model can be constructed, which are two main components of the proposed TH-GAT model. In addition, in the region-aware spatial dependence model, the graph attention network is adopted, in which the importance of a node to another node, of a node to a region, of a region to a node, and of a region to another region, can be captured automatically by means of the attention coefficients. Extensive experiments are conducted on two real-world traffic datasets, and the results have confirmed the superiority of the proposed TH-GAT model.

scholarly journals Region-Level Traffic Prediction Based on Temporal Multi-Spatial Dependence Graph Convolutional Network from GPS Data

2022 ◽  
Vol 14 (2) ◽  
pp. 303
Author(s):  
Haiqiang Yang ◽  
Xinming Zhang ◽  
Zihan Li ◽  
Jianxun Cui
Keyword(s):  
Deep Learning ◽  
Spatial Dependence ◽  
Learning Model ◽  
Urban Traffic ◽  
Model Verification ◽  
Traffic Information ◽  
Traffic Prediction ◽  
Gps Data ◽  
Convolutional Network ◽  
Deep Learning Model

Region-level traffic information can characterize dynamic changes of urban traffic at the macro level. Real-time region-level traffic prediction help city traffic managers with traffic demand analysis, traffic congestion control, and other activities, and it has become a research hotspot. As more vehicles are equipped with GPS devices, remote sensing data can be collected and used to conduct data-driven region-level-based traffic prediction. However, due to dynamism and randomness of urban traffic and the complexity of urban road networks, the study of such issues faces many challenges. This paper proposes a new deep learning model named TmS-GCN to predict region-level traffic information, which is composed of Graph Convolutional Network (GCN) and Gated Recurrent Unit (GRU). The GCN part captures spatial dependence among regions, while the GRU part captures the dynamic change of traffic within the region. Model verification and comparison are carried out using real taxi GPS data from Shenzhen. The experimental results show that the proposed model outperforms both the classic time series prediction model and the deep learning model at different scales.

scholarly journals Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction

2019 ◽  
Vol 33 ◽  
pp. 5668-5675 ◽  
Author(s):  
Huaxiu Yao ◽  
Xianfeng Tang ◽  
Hua Wei ◽  
Guanjie Zheng ◽  
Zhenhui Li
Keyword(s):  
Real World ◽  
Spatial Dependence ◽  
Large Scale ◽  
Temporal Dynamics ◽  
Dynamic Network ◽  
Research Field ◽  
Traffic Prediction ◽  
Unified Framework ◽  
Gating Mechanism ◽  
Spatial Dependencies

Traffic prediction has drawn increasing attention in AI research field due to the increasing availability of large-scale traffic data and its importance in the real world. For example, an accurate taxi demand prediction can assist taxi companies in pre-allocating taxis. The key challenge of traffic prediction lies in how to model the complex spatial dependencies and temporal dynamics. Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i.e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical. However, in practice the spatial dependence could be dynamic (i.e., changing from time to time), and the temporal dynamics could have some perturbation from one period to another period. In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. To address these two issues, we propose a novel Spatial-Temporal Dynamic Network (STDN), in which a flow gating mechanism is introduced to learn the dynamic similarity between locations, and a periodically shifted attention mechanism is designed to handle long-term periodic temporal shifting. To the best of our knowledge, this is the first work that tackle both issues in a unified framework. Our experimental results on real-world traffic datasets verify the effectiveness of the proposed method.

scholarly journals LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks

2020 ◽  
Author(s):  
Rongzhou Huang ◽  
Chuyin Huang ◽  
Yubao Liu ◽  
Genan Dai ◽  
Weiyang Kong
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Traffic Management ◽  
Route Planning ◽  
Traffic Prediction ◽  
Learning Approaches ◽  
Short Term ◽  
Temporal Prediction ◽  
Convolutional Networks ◽  
Short Term Prediction

Traffic prediction is a classical spatial-temporal prediction problem with many real-world applications such as intelligent route planning, dynamic traffic management, and smart location-based applications. Due to the high nonlinearity and complexity of traffic data, deep learning approaches have attracted much interest in recent years. However, few methods are satisfied with both long and short-term prediction tasks. Target at the shortcomings of existing studies, in this paper, we propose a novel deep learning framework called Long Short-term Graph Convolutional Networks (LSGCN) to tackle both traffic prediction tasks. In our framework, we propose a new graph attention network called cosAtt, and integrate both cosAtt and graph convolution networks (GCN) into a spatial gated block. By the spatial gated block and gated linear units convolution (GLU), LSGCN can efficiently capture complex spatial-temporal features and obtain stable prediction results. Experiments with three real-world traffic datasets verify the effectiveness of LSGCN.

Real-world environment affects the color appearance of virtual stimuli produced by augmented reality

2019 ◽  
Vol 2019 (1) ◽  
pp. 237-242
Author(s):  
Siyuan Chen ◽  
Minchen Wei
Keyword(s):  
Augmented Reality ◽  
Real World ◽  
Mixed Reality ◽  
Rapid Development ◽  
Light Level ◽  
Color Appearance ◽  
Chromatic Adaptation ◽  
Lighting Condition ◽  
The Real ◽  
World Environment

Color appearance models have been extensively studied for characterizing and predicting the perceived color appearance of physical color stimuli under different viewing conditions. These stimuli are either surface colors reflecting illumination or self-luminous emitting radiations. With the rapid development of augmented reality (AR) and mixed reality (MR), it is critically important to understand how the color appearance of the objects that are produced by AR and MR are perceived, especially when these objects are overlaid on the real world. In this study, nine lighting conditions, with different correlated color temperature (CCT) levels and light levels, were created in a real-world environment. Under each lighting condition, human observers adjusted the color appearance of a virtual stimulus, which was overlaid on a real-world luminous environment, until it appeared the whitest. It was found that the CCT and light level of the real-world environment significantly affected the color appearance of the white stimulus, especially when the light level was high. Moreover, a lower degree of chromatic adaptation was found for viewing the virtual stimulus that was overlaid on the real world.

Vignettes

2018 ◽  
Author(s):  
Marc J. Stern
Keyword(s):  
Real World ◽  
Environmental Sustainability ◽  
National Park ◽  
Public Involvement ◽  
Energy Savings ◽  
Rapid Development ◽  
Environmental Problems ◽  
Persuasive Communications ◽  
For Profit ◽  
The Face

Chapter 9 contains five vignettes, each based on real world cases. In each, a character is faced with a problem and uses multiple theories within the book to help him or her develop and execute a plan of action. The vignettes provide concrete examples of how to apply the theories in the book to solving environmental problems and working toward environmental sustainability in a variety of contexts, including managing visitors in a national park, developing persuasive communications, designing more collaborative public involvement processes, starting up an energy savings program within a for-profit corporation, and promoting conservation in the face of rapid development.

scholarly journals Deep Learning Classification of Canine Behavior Using a Single Collar-Mounted Accelerometer: Real-World Validation

Animals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1549
Author(s):  
Robert D. Chambers ◽  
Nathanael C. Yoder ◽  
Aletha B. Carson ◽  
Christian Junge ◽  
David E. Allen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Real World ◽  
Learning Algorithm ◽  
Drinking Behavior ◽  
True Positive Rate ◽  
Training Dataset ◽  
Activity Levels ◽  
Accelerometer Data ◽  
Activity Monitors

Collar-mounted canine activity monitors can use accelerometer data to estimate dog activity levels, step counts, and distance traveled. With recent advances in machine learning and embedded computing, much more nuanced and accurate behavior classification has become possible, giving these affordable consumer devices the potential to improve the efficiency and effectiveness of pet healthcare. Here, we describe a novel deep learning algorithm that classifies dog behavior at sub-second resolution using commercial pet activity monitors. We built machine learning training databases from more than 5000 videos of more than 2500 dogs and ran the algorithms in production on more than 11 million days of device data. We then surveyed project participants representing 10,550 dogs, which provided 163,110 event responses to validate real-world detection of eating and drinking behavior. The resultant algorithm displayed a sensitivity and specificity for detecting drinking behavior (0.949 and 0.999, respectively) and eating behavior (0.988, 0.983). We also demonstrated detection of licking (0.772, 0.990), petting (0.305, 0.991), rubbing (0.729, 0.996), scratching (0.870, 0.997), and sniffing (0.610, 0.968). We show that the devices’ position on the collar had no measurable impact on performance. In production, users reported a true positive rate of 95.3% for eating (among 1514 users), and of 94.9% for drinking (among 1491 users). The study demonstrates the accurate detection of important health-related canine behaviors using a collar-mounted accelerometer. We trained and validated our algorithms on a large and realistic training dataset, and we assessed and confirmed accuracy in production via user validation.

scholarly journals A Lower Bound for the Query Phase of Contraction Hierarchies and Hub Labels and a Provably Optimal Instance-Based Schema

Algorithms ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 164
Author(s):  
Tobias Rupp ◽  
Stefan Funke
Keyword(s):  
Lower Bound ◽  
Lower Bounds ◽  
Real World ◽  
Road Network ◽  
Upper And Lower Bounds ◽  
Bounded Degree ◽  
Shortest Path Routing ◽  
Graph Classes ◽  
Speed Up ◽  
To Come

We prove a Ω(n) lower bound on the query time for contraction hierarchies (CH) as well as hub labels, two popular speed-up techniques for shortest path routing. Our construction is based on a graph family not too far from subgraphs that occur in real-world road networks, in particular, it is planar and has a bounded degree. Additionally, we borrow ideas from our lower bound proof to come up with instance-based lower bounds for concrete road network instances of moderate size, reaching up to 96% of an upper bound given by a constructed CH. For a variant of our instance-based schema applied to some special graph classes, we can even show matching upper and lower bounds.

scholarly journals A Survey on Bias and Fairness in Machine Learning

2021 ◽  
Vol 54 (6) ◽  
pp. 1-35
Author(s):  
Ninareh Mehrabi ◽  
Fred Morstatter ◽  
Nripsuta Saxena ◽  
Kristina Lerman ◽  
Aram Galstyan
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Deep Learning ◽  
Real World ◽  
State Of The Art ◽  
Future Directions ◽  
Discriminatory Behavior ◽  
Real World Applications ◽  
Near Future ◽  
Different Sources

With the widespread use of artificial intelligence (AI) systems and applications in our everyday lives, accounting for fairness has gained significant importance in designing and engineering of such systems. AI systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that these decisions do not reflect discriminatory behavior toward certain groups or populations. More recently some work has been developed in traditional machine learning and deep learning that address such challenges in different subdomains. With the commercialization of these systems, researchers are becoming more aware of the biases that these applications can contain and are attempting to address them. In this survey, we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and ways they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.

Sign in / Sign up

Export Citation Format

Share Document