Trace-back Depth in Distributed Sensing HMM

This work addresses the problem of presence detection as Distributed Sensing of a Hidden Markov Model (DS-HMM). We propose an efficient communication strategy to limit sensor communication. For optimum detection under constrained communication, it does not suffice to just send only the latest sensor...

Full description

Saved in:
Bibliographic Details
Main Authors: Papatsimpa, C., Linnartz, J. P. M. G.
Format: Conference Proceeding
Language:English
Subjects:
distributed sensing
Hidden Markov models
History
HMM
Pragmatics
Sensor fusion
Smart buildings
Time measurement
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work addresses the problem of presence detection as Distributed Sensing of a Hidden Markov Model (DS-HMM). We propose an efficient communication strategy to limit sensor communication. For optimum detection under constrained communication, it does not suffice to just send only the latest sensor observations. It requires tracing back in the HMM algorithm to the latest moment that all data from all sensors was available. Alternatively, we investigate a more pragmatic approach, that is, to send a few recent observations in every message (packet) instead of the full history. The effect of unreliable communication, subject to channel erasure, is also investigated.
ISSN:2166-9589
DOI:10.1109/PIMRC.2018.8580870