Forecasting Occurrences of Activities

Bryan Minor; Diane J Cook

doi:10.1016/j.pmcj.2016.09.010

Back

Journal article

Open access

Peer reviewed

Forecasting Occurrences of Activities

Bryan Minor and Diane J Cook

Pervasive and mobile computing, Vol.38(Pt 1), pp.77-91

07/2017

DOI: https://doi.org/10.1016/j.pmcj.2016.09.010

Handle:

https://hdl.handle.net/2376/106858

PMCID: PMC5501468

PMID: 28694746

Files and links (1)

url

https://doi.org/10.1016/j.pmcj.2016.09.010View

Published (Version of record) Open

Abstract

regression trees

activity forecasting

smart homes

activity recognition

While activity recognition has been shown to be valuable for pervasive computing applications, less work has focused on techniques for forecasting the future occurrence of activities. We present an activity forecasting method to predict the time that will elapse until a target activity occurs. This method generates an activity forecast using a regression tree classifier and offers an advantage over sequence prediction methods in that it can predict expected time until an activity occurs. We evaluate this algorithm on real-world smart home datasets and provide evidence that our proposed approach is most effective at predicting activity timings.

Metrics

15 Record Views

Details

Title: Forecasting Occurrences of Activities
Creators: Bryan Minor - Washington State University, Pullman, WA 99203, USA
Diane J Cook - Washington State University, Pullman, WA 99203 USA
Publication Details: Pervasive and mobile computing, Vol.38(Pt 1), pp.77-91
Academic Unit: Electrical Engineering and Computer Science, School of
Identifiers: 99900546937201842
Language: English
Resource Type: Journal article