zhangzw16/SageFormer

Code for IoTJ 2024 paper "SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting".

37
/ 100
Emerging

This helps researchers and data scientists predict future trends from complex sensor data or other interconnected measurements over long periods. It takes in historical multivariate time-series data, such as readings from multiple IoT devices, and outputs accurate long-term forecasts. This is useful for anyone needing to anticipate future behavior in systems with many interacting variables.

No commits in the last 6 months.

Use this if you need to make accurate long-term predictions from data where many different measurements influence each other, such as in smart grids or industrial IoT.

Not ideal if you only need to forecast a single variable, have very short-term prediction needs, or prefer models that don't require handling complex inter-series dependencies.

IoT data analytics predictive maintenance smart grid management environmental monitoring sensor data forecasting
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

86

Forks

8

Language

Python

License

MIT

Last pushed

Mar 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zhangzw16/SageFormer"

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