Source of Publication
Procedia Computer Science
© 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the Conference Program Chairs. The efficiency of heating, ventilation and cooling operations in a home are improved when they are controlled by a system that takes into account an accurate forecast of temperature in the house. Temperature forecasts are informed by data from sensors that report on activities and conditions in and around the home. Using publicly available data, we apply linear models based on LASSO regression and our recently developled MIDFEL LASSO regression. These models take into account the past 24 hours of the sensors' data. We have previously identified the most influential sensors in a forecast over the next 48 hours. In this paper, we compute 48 separate one-hour forecast and for each hour we identify the sensors that are most influential. This improves forecast accuracy and reveals which sensors are most valuable to install .
Energy Efficiency, Feature Selection, Home Sensor Network, Internet of Things, LASSO regression, Model Predictive Control, Temperature Forecasting
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Spencer, Bruce; Alfandi, Omar; and Al-Obeidat, Feras, "Forecasting Temperature in a Smart Home with Segmented Linear Regression" (2019). All Works. 1698.
Indexed in Scopus
Open Access Type
Gold: This publication is openly available in an open access journal/series