González-Vidal, A., Jiménez, F., & Gómez-Skarmeta, A. F have provided an article: “A methodology for energy multivariate time series forecasting in smart buildings based on feature selection” to Energy and Buildings, 196, 71-82.

The abstract reads.
The massive collection of data via the Internet of Things (IoT) requires finding optimal ways to reduce the features used in the machine learning process. The paper “A Methodology for Energy Multivariate Time Series Forecasting in Smart Buildings Based on Feature Selection” proposes a methodology to create features based on lagged variables and then, apply different types of feature selection methods for regression tasks. We successfully applied our methodology for energy consumption forecasting in smart buildings.

The article is available in our repository.

WordPress Appliance - Powered by TurnKey Linux