SlideShare a Scribd company logo
1 of 17
Traffic Speed Prediction
Model Comparison
Hyunwook Lee
Contents
• Introduction
• Method for feature extraction
• Summary of Models
• Additional Experiments
• ToDo
Introduction
• Motivation: In traffic speed prediction domain, there exists survey paper
that summarize the models in high-level, but there are no paper that
investigate the deep learning models deeply
• Contribution: Deep investigation of deep learning models + Find the
contribution of all model and validate the contribution
2
Method for feature extraction: spatial
• Convolutional Neural Network
 Simply apply Convolution on grid map
 Cannot model the road network correctly
 Task will be easy(input is mapped to grid map)
• Graph-Convolutional Network
 Can capture the road network
 Limitation: only capture the neighbors in K-steps
 Spectral Domain(Similar to frequency domain)
• apply the filter to the graph signal
• should convert adjacency matrix to Laplacian matrix
 Spatial Domain
• Aggregation of the neighborhood node
• Directly use adjacency matrix without transform
3
Method for feature extraction: temporal
• Recurrent Neural Network
 LSTM
• Standard model in RNN
• Model complexity is in both memory and time(6 calculations per unit, with hidden/cell state)
 GRU
• Modified version of LSTM
• Simple than LSTM(4 calculations per unit, no cell state)
4
LSTM unit GRU unit
Method for feature extraction: temporal
• Convolutional Neural Network
 simple architecture – Faster than RNN
 without dilation
• Default CNN, convolution to time sequence
(e.g. shape=(time sequence, node)  filter=(m,1))
• Only capture the field with same size to filters
 with dilation
• Zero padding to filter
• Can check more field than default CNN
 Can extract overall features in long-term
5
Method for feature extraction: temporal
• Graph-Convolutional Network
 Song et al. proposed localized spatial-temporal
adjacency matrix  can model both spatial and
temporal in one graph convolution
 Adjacency matrix shape (3N,3N)  much slower
• Attention
 Apply attention mechanisms + some type of neural networks
 Can validate importance of the sequence
6
C. Song, Y. Lin, S. Guo, and H. Wan, “Spatial-temporal sychronous graph convolutional networks: A new framework
for spatialtemporal network data forecasting."
Summary of Models: DCRNN
• Spatial: GCN(Diffusional convolutional network)
• Temporal: RNN(sequence to sequence, GRU)
• Most basic model in this area
• Simply change concatenate operation to GCN
7
GCN applied
Y. Li, R. Yu, C. Shahabi, and Y. Liu, “Diffusion convolutional recurrent neural networks: data-driven traffic
forecasting,” in Proceedings of the International Conference on Learning Representations, 2018.
Summary of Models: STGCN
• Spatial: GCN
• Temporal: Default CNN
• To predict 12 sequences, use many-to-one architecture 12 times
8
B. Yu, H. Yin, and Z. Zhu, “Spatio-temporal graph convolutional networks: a deep learning framework for traffic
forecasting,” in Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018, pp. 3634–3640
Summary of Models: ASTGCN
• Spatial: Attention + GCN
• Temporal: Attention + CNN
• Using attention
 capture the features with attention weights
• Blending Spatial/Temporal attention
(Spatial attention=SAttn(TAttn(x)))
• Use 3 type of input – recent, daily, weekly
9
S. Guo, Y. Lin, N. Feng, C. Song, and H. Wan, “Attention based spatialtemporal graph convolutional networks for traffic
flow forecasting,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 2019, pp. 922–929.
Summary of Models: STSGCN
• Spatial: GCN
• Temporal: GCN
• Use Localized Spatial-Temporal Graph
to catch spatial-temporal correlation
• By using that, model can simultaneously
capture both spatial and temporal features
• To capture the heterogeneity in long-term spatial temporal dependency,
use individual modules for different time step
10
C. Song, Y. Lin, S. Guo, and H. Wan, “Spatial-temporal sychronous graph convolutional
networks: A new framework for spatialtemporal network data forecasting”
Summary of Models: STSGCN
• Spatial: GCN
• Temporal: GCN
• Use Localized Spatial-Temporal Graph
to catch spatial-temporal correlation
• By using that, model can simultaneously capture both spatial and
temporal features
• To capture the heterogeneity in long-term spatial temporal dependency,
use individual modules for different time step
11
C. Song, Y. Lin, S. Guo, and H. Wan, “Spatial-temporal sychronous graph convolutional
networks: A new framework for spatialtemporal network data forecasting”
Summary of Models: Graph-WaveNet
• Spatial: GCN
• Temporal: dilated CNN
• To capture the hidden graph structure, add adaptive adjacency matrix
that can be trained
• Simple and fast
12
Z. Wu, S. Pan, G. Long, J. Jiang, and C. Zhang, “Graph wavenet for deep spatial-temporal graph modeling,” in
Proceedings of the 28th International Joint Conference on Artificial Intelligence. AAAI Press, 2019, pp. 1907–1913
Additional Experiments: Model Comparison
• Temporal: RNN-based(DCRNN) is much slower than CNN-based
• Sequence to sequence model is slow(DCRNN, STGRAT)
• All of these models are evaluated in same epoch and batch size, but not
fair because of the model architecture(e.g. ASTGCN use 3 types of inputs,
but other models only use 1 type)
 should conduct more experiment with fair setting
• To evaluate the contribution of model, should modify the model
13
Additional Experiments
• At first, DCRNN and STGCN is not considered in this experiment
 DCRNN: First model that utilizes GCN in traffic domain
 STGCN: Bad architecture – many to one recursion 12 times
• ASTGCN
 Fairness: modify the model to get only recent 12 sequences as input
 Contribution: change spatial-temporal blending method to other methods
(e.g. CNN, simple concat, do spatial and temporal in linear(no blend))
• STSGCN
 Contribution:
• change individual module to shared one
• Localized spatial-temporal graph to only spatial graph
• Graph-WaveNet
 Contribution: Use trained adaptive adjacency matrix to other models
14
ToDo
• Experiment
 STSGCN is not reproduced as paper shows – hyperparameter tuning needed
 Additional Experiments - STSGCN
 with other models – ST-MetaNet, ST-ResNet, GMAN, STGRAT
• Write model summary + contribution discussion documents
• Find
15
[Seminar] hyunwook 0624

More Related Content

What's hot

Using topological analysis to support event guided exploration in urban data
Using topological analysis to support event guided exploration in urban dataUsing topological analysis to support event guided exploration in urban data
Using topological analysis to support event guided exploration in urban data
ivaderivader
 
Paper2_CSE6331_Vivek_1001053883
Paper2_CSE6331_Vivek_1001053883Paper2_CSE6331_Vivek_1001053883
Paper2_CSE6331_Vivek_1001053883
Vivek Sharma
 
TurnerBottoneStanekNIPS2013
TurnerBottoneStanekNIPS2013TurnerBottoneStanekNIPS2013
TurnerBottoneStanekNIPS2013
Clay Stanek
 

What's hot (20)

Temporal Network
Temporal NetworkTemporal Network
Temporal Network
 
ETA Prediction with Graph Neural Networks in Google Maps
ETA Prediction with Graph Neural Networks in Google MapsETA Prediction with Graph Neural Networks in Google Maps
ETA Prediction with Graph Neural Networks in Google Maps
 
SROP_Poster
SROP_PosterSROP_Poster
SROP_Poster
 
Using topological analysis to support event guided exploration in urban data
Using topological analysis to support event guided exploration in urban dataUsing topological analysis to support event guided exploration in urban data
Using topological analysis to support event guided exploration in urban data
 
(Icca 2014) shortest path analysis in social graphs
(Icca 2014) shortest path analysis in social graphs(Icca 2014) shortest path analysis in social graphs
(Icca 2014) shortest path analysis in social graphs
 
Prediction of traveller information and route choice
Prediction of traveller information and route choicePrediction of traveller information and route choice
Prediction of traveller information and route choice
 
Distributed approximate spectral clustering for large scale datasets
Distributed approximate spectral clustering for large scale datasetsDistributed approximate spectral clustering for large scale datasets
Distributed approximate spectral clustering for large scale datasets
 
DEEP LEARNING NEURAL NETWORK APPROACHES TO LAND USE-DEMOGRAPHIC- TEMPORAL BA...
 DEEP LEARNING NEURAL NETWORK APPROACHES TO LAND USE-DEMOGRAPHIC- TEMPORAL BA... DEEP LEARNING NEURAL NETWORK APPROACHES TO LAND USE-DEMOGRAPHIC- TEMPORAL BA...
DEEP LEARNING NEURAL NETWORK APPROACHES TO LAND USE-DEMOGRAPHIC- TEMPORAL BA...
 
Determining the k in k-means with MapReduce
Determining the k in k-means with MapReduceDetermining the k in k-means with MapReduce
Determining the k in k-means with MapReduce
 
20180308 coptra wac_pub
20180308 coptra wac_pub20180308 coptra wac_pub
20180308 coptra wac_pub
 
Fractal analysis for reduced reference
Fractal analysis for reduced referenceFractal analysis for reduced reference
Fractal analysis for reduced reference
 
Paper2_CSE6331_Vivek_1001053883
Paper2_CSE6331_Vivek_1001053883Paper2_CSE6331_Vivek_1001053883
Paper2_CSE6331_Vivek_1001053883
 
Benchmarking Link Discovery Systems for Geo-Spatial Data - BLINK ISWC2017.
Benchmarking Link Discovery Systems for Geo-Spatial Data - BLINK  ISWC2017. Benchmarking Link Discovery Systems for Geo-Spatial Data - BLINK  ISWC2017.
Benchmarking Link Discovery Systems for Geo-Spatial Data - BLINK ISWC2017.
 
Distributed web systems performance forecasting
Distributed web systems performance forecastingDistributed web systems performance forecasting
Distributed web systems performance forecasting
 
Masters Thesis
Masters ThesisMasters Thesis
Masters Thesis
 
Spatial spectrum access game
Spatial spectrum access gameSpatial spectrum access game
Spatial spectrum access game
 
(Paper note) Real time rgb-d camera relocalization via randomized ferns for k...
(Paper note) Real time rgb-d camera relocalization via randomized ferns for k...(Paper note) Real time rgb-d camera relocalization via randomized ferns for k...
(Paper note) Real time rgb-d camera relocalization via randomized ferns for k...
 
Nonlinear filtering approaches to field mapping by sampling using mobile sensors
Nonlinear filtering approaches to field mapping by sampling using mobile sensorsNonlinear filtering approaches to field mapping by sampling using mobile sensors
Nonlinear filtering approaches to field mapping by sampling using mobile sensors
 
TurnerBottoneStanekNIPS2013
TurnerBottoneStanekNIPS2013TurnerBottoneStanekNIPS2013
TurnerBottoneStanekNIPS2013
 
An Efficient Cluster Tree Based Data Collection Scheme for Large Mobile With ...
An Efficient Cluster Tree Based Data Collection Scheme for Large Mobile With ...An Efficient Cluster Tree Based Data Collection Scheme for Large Mobile With ...
An Efficient Cluster Tree Based Data Collection Scheme for Large Mobile With ...
 

Similar to [Seminar] hyunwook 0624

final_project_1_2k21cse07.pptx
final_project_1_2k21cse07.pptxfinal_project_1_2k21cse07.pptx
final_project_1_2k21cse07.pptx
shwetabhagat25
 
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
Edge AI and Vision Alliance
 

Similar to [Seminar] hyunwook 0624 (20)

[20240422_LabSeminar_Huy]Taming_Effect.pptx
[20240422_LabSeminar_Huy]Taming_Effect.pptx[20240422_LabSeminar_Huy]Taming_Effect.pptx
[20240422_LabSeminar_Huy]Taming_Effect.pptx
 
Coupled Layer-wise Graph Convolution for Transportation Demand Prediction
Coupled Layer-wise Graph Convolution for Transportation Demand PredictionCoupled Layer-wise Graph Convolution for Transportation Demand Prediction
Coupled Layer-wise Graph Convolution for Transportation Demand Prediction
 
[20240325_LabSeminar_Huy]Spatial-Temporal Fusion Graph Neural Networks for Tr...
[20240325_LabSeminar_Huy]Spatial-Temporal Fusion Graph Neural Networks for Tr...[20240325_LabSeminar_Huy]Spatial-Temporal Fusion Graph Neural Networks for Tr...
[20240325_LabSeminar_Huy]Spatial-Temporal Fusion Graph Neural Networks for Tr...
 
230727_HB_JointJournalClub.pptx
230727_HB_JointJournalClub.pptx230727_HB_JointJournalClub.pptx
230727_HB_JointJournalClub.pptx
 
NS-CUK Seminar: S.T.Nguyen, Review on "Hierarchical Graph Convolutional Netwo...
NS-CUK Seminar: S.T.Nguyen, Review on "Hierarchical Graph Convolutional Netwo...NS-CUK Seminar: S.T.Nguyen, Review on "Hierarchical Graph Convolutional Netwo...
NS-CUK Seminar: S.T.Nguyen, Review on "Hierarchical Graph Convolutional Netwo...
 
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion NetworkTraffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
 
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...
 
Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling Deep learning for 3-D Scene Reconstruction and Modeling
Deep learning for 3-D Scene Reconstruction and Modeling
 
20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks
 
final_project_1_2k21cse07.pptx
final_project_1_2k21cse07.pptxfinal_project_1_2k21cse07.pptx
final_project_1_2k21cse07.pptx
 
[20240429_LabSeminar_Huy]Spatio-Temporal Graph Neural Point Process for Traff...
[20240429_LabSeminar_Huy]Spatio-Temporal Graph Neural Point Process for Traff...[20240429_LabSeminar_Huy]Spatio-Temporal Graph Neural Point Process for Traff...
[20240429_LabSeminar_Huy]Spatio-Temporal Graph Neural Point Process for Traff...
 
[Seminar] 20210122 Kyunghwan Moon
[Seminar] 20210122 Kyunghwan Moon[Seminar] 20210122 Kyunghwan Moon
[Seminar] 20210122 Kyunghwan Moon
 
5438-Article Text-8663-1-10-20200511.pdf
5438-Article Text-8663-1-10-20200511.pdf5438-Article Text-8663-1-10-20200511.pdf
5438-Article Text-8663-1-10-20200511.pdf
 
Pedestrian behavior/intention modeling for autonomous driving IV
Pedestrian behavior/intention modeling for autonomous driving IVPedestrian behavior/intention modeling for autonomous driving IV
Pedestrian behavior/intention modeling for autonomous driving IV
 
Predict Traffic flow with KNN and LSTM
Predict Traffic flow with KNN and LSTMPredict Traffic flow with KNN and LSTM
Predict Traffic flow with KNN and LSTM
 
[20240408_LabSeminar_Huy]PivotalSTGNN.pptx
[20240408_LabSeminar_Huy]PivotalSTGNN.pptx[20240408_LabSeminar_Huy]PivotalSTGNN.pptx
[20240408_LabSeminar_Huy]PivotalSTGNN.pptx
 
Traffic Prediction from Street Network images.pptx
Traffic Prediction from  Street Network images.pptxTraffic Prediction from  Street Network images.pptx
Traffic Prediction from Street Network images.pptx
 
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En..."Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...
 

More from ivaderivader

Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
ivaderivader
 
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
ivaderivader
 

More from ivaderivader (20)

Argument Mining
Argument MiningArgument Mining
Argument Mining
 
Papers at CHI23
Papers at CHI23Papers at CHI23
Papers at CHI23
 
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph KernelsDDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
 
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
 
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
 
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
 
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
 
A Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial NetworksA Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial Networks
 
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
 
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for VisualizationPerception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
 
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
 
Neural Approximate Dynamic Programming for On-Demand Ride-Pooling
Neural Approximate Dynamic Programming for On-Demand Ride-PoolingNeural Approximate Dynamic Programming for On-Demand Ride-Pooling
Neural Approximate Dynamic Programming for On-Demand Ride-Pooling
 
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
 
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTubeBad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
 
Invertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise RemovalInvertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise Removal
 
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural NetworkTraffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
 
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training  MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
 
Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI ComponentsScreen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
 
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
 
Natural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine TranslationNatural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine Translation
 

Recently uploaded

Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 

Recently uploaded (20)

Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 

[Seminar] hyunwook 0624

  • 1. Traffic Speed Prediction Model Comparison Hyunwook Lee
  • 2. Contents • Introduction • Method for feature extraction • Summary of Models • Additional Experiments • ToDo
  • 3. Introduction • Motivation: In traffic speed prediction domain, there exists survey paper that summarize the models in high-level, but there are no paper that investigate the deep learning models deeply • Contribution: Deep investigation of deep learning models + Find the contribution of all model and validate the contribution 2
  • 4. Method for feature extraction: spatial • Convolutional Neural Network  Simply apply Convolution on grid map  Cannot model the road network correctly  Task will be easy(input is mapped to grid map) • Graph-Convolutional Network  Can capture the road network  Limitation: only capture the neighbors in K-steps  Spectral Domain(Similar to frequency domain) • apply the filter to the graph signal • should convert adjacency matrix to Laplacian matrix  Spatial Domain • Aggregation of the neighborhood node • Directly use adjacency matrix without transform 3
  • 5. Method for feature extraction: temporal • Recurrent Neural Network  LSTM • Standard model in RNN • Model complexity is in both memory and time(6 calculations per unit, with hidden/cell state)  GRU • Modified version of LSTM • Simple than LSTM(4 calculations per unit, no cell state) 4 LSTM unit GRU unit
  • 6. Method for feature extraction: temporal • Convolutional Neural Network  simple architecture – Faster than RNN  without dilation • Default CNN, convolution to time sequence (e.g. shape=(time sequence, node)  filter=(m,1)) • Only capture the field with same size to filters  with dilation • Zero padding to filter • Can check more field than default CNN  Can extract overall features in long-term 5
  • 7. Method for feature extraction: temporal • Graph-Convolutional Network  Song et al. proposed localized spatial-temporal adjacency matrix  can model both spatial and temporal in one graph convolution  Adjacency matrix shape (3N,3N)  much slower • Attention  Apply attention mechanisms + some type of neural networks  Can validate importance of the sequence 6 C. Song, Y. Lin, S. Guo, and H. Wan, “Spatial-temporal sychronous graph convolutional networks: A new framework for spatialtemporal network data forecasting."
  • 8. Summary of Models: DCRNN • Spatial: GCN(Diffusional convolutional network) • Temporal: RNN(sequence to sequence, GRU) • Most basic model in this area • Simply change concatenate operation to GCN 7 GCN applied Y. Li, R. Yu, C. Shahabi, and Y. Liu, “Diffusion convolutional recurrent neural networks: data-driven traffic forecasting,” in Proceedings of the International Conference on Learning Representations, 2018.
  • 9. Summary of Models: STGCN • Spatial: GCN • Temporal: Default CNN • To predict 12 sequences, use many-to-one architecture 12 times 8 B. Yu, H. Yin, and Z. Zhu, “Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting,” in Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018, pp. 3634–3640
  • 10. Summary of Models: ASTGCN • Spatial: Attention + GCN • Temporal: Attention + CNN • Using attention  capture the features with attention weights • Blending Spatial/Temporal attention (Spatial attention=SAttn(TAttn(x))) • Use 3 type of input – recent, daily, weekly 9 S. Guo, Y. Lin, N. Feng, C. Song, and H. Wan, “Attention based spatialtemporal graph convolutional networks for traffic flow forecasting,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 2019, pp. 922–929.
  • 11. Summary of Models: STSGCN • Spatial: GCN • Temporal: GCN • Use Localized Spatial-Temporal Graph to catch spatial-temporal correlation • By using that, model can simultaneously capture both spatial and temporal features • To capture the heterogeneity in long-term spatial temporal dependency, use individual modules for different time step 10 C. Song, Y. Lin, S. Guo, and H. Wan, “Spatial-temporal sychronous graph convolutional networks: A new framework for spatialtemporal network data forecasting”
  • 12. Summary of Models: STSGCN • Spatial: GCN • Temporal: GCN • Use Localized Spatial-Temporal Graph to catch spatial-temporal correlation • By using that, model can simultaneously capture both spatial and temporal features • To capture the heterogeneity in long-term spatial temporal dependency, use individual modules for different time step 11 C. Song, Y. Lin, S. Guo, and H. Wan, “Spatial-temporal sychronous graph convolutional networks: A new framework for spatialtemporal network data forecasting”
  • 13. Summary of Models: Graph-WaveNet • Spatial: GCN • Temporal: dilated CNN • To capture the hidden graph structure, add adaptive adjacency matrix that can be trained • Simple and fast 12 Z. Wu, S. Pan, G. Long, J. Jiang, and C. Zhang, “Graph wavenet for deep spatial-temporal graph modeling,” in Proceedings of the 28th International Joint Conference on Artificial Intelligence. AAAI Press, 2019, pp. 1907–1913
  • 14. Additional Experiments: Model Comparison • Temporal: RNN-based(DCRNN) is much slower than CNN-based • Sequence to sequence model is slow(DCRNN, STGRAT) • All of these models are evaluated in same epoch and batch size, but not fair because of the model architecture(e.g. ASTGCN use 3 types of inputs, but other models only use 1 type)  should conduct more experiment with fair setting • To evaluate the contribution of model, should modify the model 13
  • 15. Additional Experiments • At first, DCRNN and STGCN is not considered in this experiment  DCRNN: First model that utilizes GCN in traffic domain  STGCN: Bad architecture – many to one recursion 12 times • ASTGCN  Fairness: modify the model to get only recent 12 sequences as input  Contribution: change spatial-temporal blending method to other methods (e.g. CNN, simple concat, do spatial and temporal in linear(no blend)) • STSGCN  Contribution: • change individual module to shared one • Localized spatial-temporal graph to only spatial graph • Graph-WaveNet  Contribution: Use trained adaptive adjacency matrix to other models 14
  • 16. ToDo • Experiment  STSGCN is not reproduced as paper shows – hyperparameter tuning needed  Additional Experiments - STSGCN  with other models – ST-MetaNet, ST-ResNet, GMAN, STGRAT • Write model summary + contribution discussion documents • Find 15