A statistical approach to distributed edge sensor detection

Duckdong Hwang; Chien-Hwa Hwang; C.-C. Jay Kuo

doi:10.1117/12.512805

8 August 2003 A statistical approach to distributed edge sensor detection

Duckdong Hwang, Chien-Hwa Hwang, C.-C. Jay Kuo

Proceedings Volume 5245, Internet Quality of Service; (2003) https://doi.org/10.1117/12.512805
Event: ITCom 2003, 2003, Orlando, Florida, United States

Abstract

Edge sensor detection is often used in identifying regions that are affected by various factors in wireless sensor networks. A statistical methodology based on distributed detection theory and the Neyman-Pearson criterion is developed for edge sensor detection in this research. The input sensor statistics are assumed to be identically independently distributed in our framework. Edge regions and sensors are determined using a hypothesis test, where the observation model for each hypothesis is derived. A sub-optimal distributed detection scheme, which is optimal among detectors having the same test at all local sensors, and the way of choosing the optimal operating point are described. The condition under which the proposed scheme outperforms the optimum detector based on a single sensor is presented. Furthermore, the noisy channel effect is considered, and a method to overcome this noisy effect is addressed. The performance of the proposed distributed edge sensor detection scheme is studied via computer simulation, where the ROC curves are used to demonstrate the tradeoff between the cost (in terms of the sensor density) and detection accuracy.

Citation Download Citation

Duckdong Hwang, Chien-Hwa Hwang, and C.-C. Jay Kuo "A statistical approach to distributed edge sensor detection", Proc. SPIE 5245, Internet Quality of Service, (8 August 2003); https://doi.org/10.1117/12.512805

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available