FateMurphy/CEEMDAN_LSTM

CEEMDAN_LSTM is a Python project for decomposition-integration forecasting models based on EMD methods and LSTM.

60
/ 100
Established

Combines CEEMDAN signal decomposition with multi-layer LSTM networks to isolate high-frequency and low-frequency components for separate forecasting, then integrates predictions using configurable strategies (ensemble, respective, hybrid). Supports multiple decomposition modes (EMD, EEMD, VMD, OVMD, SVMD) and re-decomposition of individual IMFs, with optional re-normalization and automated parameter tuning via Keras/TensorFlow, including built-in statistical validation (ADF, Ljung-Box tests) and comparative analysis (Diebold-Mariano test).

292 stars and 139 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m No Dependents
Maintenance 0 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

292

Forks

49

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 03, 2025

Monthly downloads

139

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FateMurphy/CEEMDAN_LSTM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.