[AAAI 2024] ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting
Code for our paper: "[ ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting]".
data -> metr-la and pems-bay raw data and processed data
Datasets -> dataset preprocessing code
Model -> model implementation
pip install -r requirements.txt
more details: cudnn==8.2.1, cudatoolkit==11.3.1
Alterbatively, the datasets can be found as follows:
- METR-LA and PEMS-BAY: These datasets were released by DCRNN[1]. Data can be found in its GitHub repository. Please put these two files metr-la.h5 and pems-bay.h5 in the data folder
The hyperparameters of ModWaveMLP can be changed in the Parameters.py
python run_MoDWaveMLP.py --dataset metr-la --horizon 12 --history_length 12
python run_MoDWaveMLP.py --dataset pems-bay --horizon 12 --history_length 12