DocumentCode
3061860
Title
Passive human presence detection method based on the incremental analysis of principal components from the signal strength space
Author
Nenadic, D. ; Mrazovac, Bojan
Author_Institution
Fakultet Tehnickih Nauka, Novi Sad, Serbia
fYear
2012
fDate
20-22 Nov. 2012
Firstpage
444
Lastpage
447
Abstract
This paper proposes the use of the incremental method for principal components analysis, designed for human presence detection. The algorithm extracts principal components from the matrix of signal strength samples retrieved from the pre-existing wireless electrical infrastructure, based on smart outlets and smart light switches. By proposing the additional filter based on the Shannon Entropy, the level of false detections is minimized.
Keywords
entropy; filtering theory; principal component analysis; signal detection; Shannon entropy; false detection; filter; incremental analysis; passive human presence detection method; principal component analysis; signal strength sample; signal strength space; smart light switch; smart outlet; wireless electrical infrastructure; Covariance matrix; Electronic mail; Humans; IEEE 802.15 Standards; Principal component analysis; Wireless sensor networks; Zigbee; CCIPCA; PCA; RSSI; Zigbee; pasivna detekcija prisustva čoveka;
fLanguage
English
Publisher
ieee
Conference_Titel
Telecommunications Forum (TELFOR), 2012 20th
Conference_Location
Belgrade
Print_ISBN
978-1-4673-2983-5
Type
conf
DOI
10.1109/TELFOR.2012.6419242
Filename
6419242
Link To Document