DeepSTD: Mining Spatio-temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction

Last update: Sep 26, 2022

Overview

DeepSTD: Mining Spatio-temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction

This is the implementation of DeepSTD in the following paper:
Chuanpan Zheng, Xiaoliang Fan, Chengwu Wen, Longbiao Chen, Cheng Wang, and Jonathan Li. "DeepSTD: Mining Spatio-temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction", published in IEEE Transactions on Intelligent Transportation Systems (T-ITS).

Data

The Chengdu dataset with 500m*500m grid size and 15-minute time interval is provided in the './data' folder.

Requirements

Python 3.7.10, tensorflow 1.14.0, numpy 1.16.4, pandas 0.24.2

Results

We provide a pre-trained model, which achieve the following performance:

Chengdu	Workday	Weekend	All days
DeepSTD	10.36	10.78	10.48

Citation

If you find this repository useful in your research, please cite the following paper:

@article{ DeepSTD:TITS,
  author   = "Chuanpan Zheng and Xiaoliang Fan and Chenglu Wen and Longbiao Chen and Cheng Wang and Jonathan Li"
  title    = "DeepSTD: Mining Spatio-temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction",
  journal  = "IEEE Transactions on Intelligent Transportation Systems",
  volume   = "21",
  number   = "9",
  pages    = "3744--3755",
  year     = "2020"
}

DeepSTD: Mining Spatio-temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction

Related tags

Overview

DeepSTD: Mining Spatio-temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction

Data

Requirements

Results

Citation

Owner

Predict halo masses from simulations via graph neural networks

A simple pygame dino game which can also be trained and played by a NEAT KI

This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.

The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.

Gas detection for Raspberry Pi using ADS1x15 and MQ-2 sensors

EfficientNetv2 TensorRT int8

Conservative Q Learning for Offline Reinforcement Reinforcement Learning in JAX

Implementation and replication of ProGen, Language Modeling for Protein Generation, in Jax

A simple baseline for 3d human pose estimation in PyTorch.

Official repo for BMVC2021 paper ASFormer: Transformer for Action Segmentation

A PyTorch Implementation of "SINE: Scalable Incomplete Network Embedding" (ICDM 2018).

The code release of paper 'Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization' NIPS 2020.

Code, environments, and scripts for the paper: "How Private Is Your RL Policy? An Inverse RL Based Analysis Framework"

The official implementation of CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

An implementation of the [Hierarchical (Sig-Wasserstein) GAN] algorithm for large dimensional Time Series Generation

dualPC.R contains the R code for the main functions.

Code for the paper "M2m: Imbalanced Classification via Major-to-minor Translation" (CVPR 2020)

PyTorch reimplementation of the Smooth ReLU activation function proposed in the paper "Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations" [arXiv 2022].

CLNTM - Contrastive Learning for Neural Topic Model

Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.