Design and Implementation of a Robust Sensor Data Fusion System for Unknown Signals

In this work, we present a robust sensor fusion system for exploratory data collection, exploiting the spatial redundancy in sensor networks. Unlike prior work, our system design criteria considers a heterogeneous correlated noise model and packet loss, but no prior knowledge of signal characteristics. The former two assumptions are both common signal degradation sources in sensor networks, while the latter allows exploratory data collection of unknown signals. Through both a numerical example and an experimental study on a large military site, we show that our proposed system reduces the noise in an unknown signal by 58.2% better than a comparable algorithm.

[1]  S. Kay.  Fundamentals of statistical signal processing: estimation theory , 1993 .

[2]  Edward J. Wegman,et al.  Statistical Signal Processing , 1985 .

[3]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[4]  Saurabh Ganeriwal,et al.  Timing-sync protocol for sensor networks , 2003, SenSys '03.

[5]  Steven Kay,et al.  Fundamentals Of Statistical Signal Processing , 2001 .

[6]  S. Mallat,et al.  Adaptive covariance estimation of locally stationary processes , 1998 .

[7]  Stephen P. Boyd,et al.  Distributed average consensus with least-mean-square deviation , 2007, J. Parallel Distributed Comput..

[8]  A. Dimakis,et al.  Geographic gossip: efficient aggregation for sensor networks , 2006, 2006 5th International Conference on Information Processing in Sensor Networks.

[9]  Ramesh Govindan,et al.  Understanding packet delivery performance in dense wireless sensor networks , 2003, SenSys '03.

[10]  R. Olfati-Saber,et al.  Consensus Filters for Sensor Networks and Distributed Sensor Fusion , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[11]  Eduardo F. Nakamura,et al.  Information fusion for wireless sensor networks: Methods, models, and classifications , 2007, CSUR.

[12]  C. Guestrin,et al.  Near-optimal sensor placements: maximizing information while minimizing communication cost , 2006, 2006 5th International Conference on Information Processing in Sensor Networks.

[13]  Carlo Fischione,et al.  A distributed minimum variance estimator for sensor networks , 2008, IEEE Journal on Selected Areas in Communications.

[14]  Stephen P. Boyd,et al.  Gossip algorithms: design, analysis and applications , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[15]  Gene F. Franklin,et al.  Feedback Control of Dynamic Systems , 1986 .

[16]  Nageswara S. V. Rao,et al.  N-learners Problem: Fusion Of Concepts , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Nageswara S. V. Rao,et al.  On Fusers that Perform Better than Best Sensor , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  R. Bellman.  Dynamic programming. , 1957, Science.

[19]  Don Coppersmith,et al.  Matrix multiplication via arithmetic progressions , 1987, STOC.

[20]  Carlo Fischione,et al.  Adaptive distributed estimation over wireless sensor networks with packet losses , 2007, 2007 46th IEEE Conference on Decision and Control.

[21]  Robert N. McDonough,et al.  Detection of signals in noise , 1971 .

[22]  Carlo Fischione,et al.  Peer-to-peer estimation over wireless sensor networks via Lipschitz optimization , 2009, 2009 International Conference on Information Processing in Sensor Networks.

[23]  L. Balzano,et al.  Blind Calibration of Sensor Networks , 2007, 2007 6th International Symposium on Information Processing in Sensor Networks.

[24]  Nabendu Pal,et al.  Estimation Of A Multivariate Normal Mean Vector And Local Improvements , 1995 .

[25]  Stephen P. Boyd,et al.  A scheme for robust distributed sensor fusion based on average consensus , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..