Home // eKNOW 2023, The Fifteenth International Conference on Information, Process, and Knowledge Management // View article

Prediction Pipeline on Time Series Data Applied for Usage Prediction on Household Devices

Authors:
Raluca Portase
Ramona Tolas
Camelia Lemnaru
Rodica Potolea

Keywords: Time series; data filtering; processing pipeline; home appliances data; forecasting devices usage

Abstract:
Processing time series is wildly used for many real-world applications such as financial market prediction, resource demand forecasting, device maintenance prediction, or environmental state prediction. In this work, we propose a general time series prediction pipeline with a hybrid unit for the relevance intervals on the processing part. The granularity unit is separated based on the intermittency level of the time series. We further apply the pipeline to real data from household appliances for non-intrusive usage pattern modeling and multistep-ahead prediction using machine learning methods.

Pages: 44 to 49

Copyright: Copyright (c) IARIA, 2023

Publication date: April 24, 2023

Published in: conference

ISSN: 2308-4375

ISBN: 978-1-68558-082-7

Location: Venice, Italy

Dates: from April 24, 2023 to April 28, 2023