EnergyLens
Authors:
Open Access
- 11 June 2014
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 289-300
Abstract
Inferring human activity is of interest for various ubiquitous computing applications, particularly if it can be done using ambient information that can be collected non intrusively. In this paper, we explore human activity inference, in the context of energy consumption within a home, where we define an "activity" as the usage of an electrical appliance, its usage duration and its location. We also explore the dimension of identifying the occupant who performed the activity. Our goal is to answer questions such as "Who is watching TV in the Dining Room and during what times?". This information is particularly important for scenarios such as the apportionment of energy use to individuals in shared settings for better understanding of occupant's energy consumption behavioral patterns. Unfortunately, accurate activity inference in realistic settings is challenging, especially when considering ease of deployment. One of the key differences between our work and prior research in this space is that we seek to combine readily available sensor data (i.e. home level electricity meters and sensors on smartphones carried by the occupants) and metadata information (e.g. appliance power ratings and their location) for activity inference. Our proposed EnergyLens system intelligently fuses electricity meter data with sensors on commodity smartphones -- the Wifi radio and the microphone -- to infer, with high accuracy, which appliance is being used, when its being used, where its being used in the home, and who is using it. EnergyLens exploits easily available metadata to further improve the detection accuracy. Real world experiments show that EnergyLens significantly improves the inference of energy usage activities (average precision= 75.2%, average recall= 77.8%) as compared to traditional approaches that use the meter data only (average precision = 28.4%, average recall = 22.3%).Keywords
Funding Information
- Department of Electronics and Information Technology, Ministry of Communications and Information Technology (ITRA/15(57)/Mobile/HumanSense/01)
- National Science Foundation (SHF-1018632)
This publication has 29 references indexed in Scilit:
- iSleep2013
- Auditeur2013
- SocioPhone2013
- FixtureFinder2013
- MachineSenseACM SIGMOBILE Mobile Computing and Communications Review, 2013
- ARIEL2012
- Managing plug-loads for demand response within buildings2011
- Acoustic environment classificationACM Transactions on Speech and Language Processing, 2006
- Computational auditory scene analysisComputer Speech & Language, 1994
- Nonintrusive appliance load monitoringProceedings of the IEEE, 1992