Automatic Acoustic Localization in Sensor Networks Using Environmental Natural Acoustic Phenomena

Please enable javascript in your browser.

This page was sent successfuly

Bookmark

1207 viewed

مکان یابی خودکار آکوستیک در شبکه های حسگر بی سیم با استفاده از صداهای طبیعی محیط

1207 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 39474 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Abolhassani, Hassan
Abstract:
We propose a range-free localization framework in which a network of randomly deployed acoustic sensors can passively use natural acoustic phenomena within its environment to localize itself. We introduce a novel approach for registration of sensors observations which takes advantage of a clustering technique on triplets of associated observations. A Bayesian filtering method is employed to incrementally improve system state estimation as more observations become available. To the best of our knowledge this is the first work done on range-free passive acoustic localization. Furthermore, we have proposed a simple but effective and efficient acoustic detection method which can be used to extract acoustic events against the noise background in the environment. Simulation experiments as well as small-scale physical experiments demonstrate the liability of the proposed algorithms
Keywords:
Sensor Network ; Location ; Detecting Voice ; Parallel Processing ; Bayesian Filtering

No TOC