Predicting room occupancy with a single passive infrared (PIR) sensor through behavior extraction
- Submitting institution
-
Aston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 21359230
- Type
- E - Conference contribution
- DOI
-
10.1145/2971648.2971746
- Title of conference / published proceedings
- UbiComp 2016 - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
- First page
- 1016
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- September
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
A - Aston Institute of Urban Technology and the Environment (ASTUTE)
- Citation count
- 29
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work introduces a novel approach to occupancy estimation which requires a simple Passive InfraRed sensor with an analog setting and an ARM mbed microcontroller board. The developed system demonstrates that by using advanced machine learning algorithms, we are able to compensate for the lack of privacy-invading image data in occupancy estimation and obtain competitive outcomes. The system was patented by ARM (US10607147B2) and developed into a stand-alone device. Follow up deals were subject to confidentiality, but the new passive monitoring device led to discussions with manufacturers from Fujitsu and Sony.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
