Traffic Representation

Traffic representation research focuses on developing efficient and accurate methods to model traffic data for various applications, such as accident prediction, platooning optimization, and encrypted traffic classification. Current research emphasizes the development of novel model architectures, including self-supervised learning frameworks, graph neural networks (particularly those incorporating attention mechanisms), and optimized transformer-based models, to improve both the accuracy and real-time performance of traffic prediction and classification systems. These advancements are crucial for improving transportation efficiency, enhancing network security, and enabling the development of more robust intelligent transportation systems.

Papers

September 9, 2024

Self-Supervised State Space Model for Real-Time Traffic Accident Prediction Using eKAN Networks
Xin Tan, Meng Zhao
Network Programming Kolmogorov Arnold Network Self Supervised Auxiliary Task Traffic Accident Prediction Traffic Representation

August 14, 2024

A Nested Graph Reinforcement Learning-based Decision-making Strategy for Eco-platooning
Xin Gao, Xueyuan Li, Hao Liu, Ao Li, Zhaoyang Ma, Zirui Li
Traffic Management Graph Reinforcement Learning Platoon Control Traffic Representation

June 3, 2024

Non-uniformity is All You Need: Efficient and Timely Encrypted Traffic Classification With ECHO
Shilo Daum, Tal Shapira, Anat Bremler-Barr, David Hay
Hyperparameter Optimization Non Uniform Encrypted Traffic Classification Fast Classification Traffic Representation Hyperparameter OPtimization

May 19, 2024

NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba
Tongze Wang, Xiaohui Xie, Wenduo Wang, Chuyi Wang, Youjian Zhao, Yong Cui
Traffic Data Mamba Based Traffic Classification Traffic Representation

March 25, 2024

LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
Qinyao Luo, Silu He, Xing Han, Yuhan Wang, Haifeng Li
Traffic Data Temporal Transformer Traffic Flow Prediction Traffic Flow Forecasting Accurate Traffic Forecasting Traffic Representation

December 7, 2022

Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction
Jiahao Ji, Jingyuan Wang, Chao Huang, Junjie Wu, Boren Xu, Zhenhe Wu, Junbo Zhang, Yu Zheng
Self Supervised Learning Traffic Prediction Traffic Data Temporal Correlation Traffic Flow Prediction Traffic Representation

February 13, 2022

ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification
Xinjie Lin, Gang Xiong, Gaopeng Gou, Zhen Li, Junzheng Shi, Jing Yu
Transformer Megatron Decepticons Contextual Representation Bidirectional Encoder Representation Traffic Classification Encrypted Traffic Classification Traffic Representation

December 30, 2021

Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization
Liang Zhang, Shubin Xie, Jianming Deng
Reinforcement Learning Attention Mechanism Traffic Signal Control Traffic Representation

December 19, 2021

Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control
Liang Zhang, Qiang Wu, Jun Shen, Linyuan Lü, Bo Du, Jianqing Wu
Reinforcement Learning Reinforcement Learning Algorithm Traffic Signal Control Urban Traffic Human Expression Pressure Matching Video Game Demand Traffic Representation

Traffic Representation

Papers

Self-Supervised State Space Model for Real-Time Traffic Accident Prediction Using eKAN Networks

A Nested Graph Reinforcement Learning-based Decision-making Strategy for Eco-platooning

Non-uniformity is All You Need: Efficient and Timely Encrypted Traffic Classification With ECHO

NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba

LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting

Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction

ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification

Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization

Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control