Estimating inhomogeneous fields using wireless sensor networks

Sensor networks have emerged as a fundamentally new tool for monitoring spatial phenomena. This paper describes a theory and methodology for estimating inhomogeneous, two-dimensional fields using wireless sensor networks. Inhomogeneous fields are composed of two or more homogeneous (smoothly varying) regions separated by boundaries. The boundaries, which correspond to abrupt spatial changes in the field, are nonparametric one-dimensional curves. The sensors make noisy measurements of the field, and the goal is to obtain an accurate estimate of the field at some desired destination (typically remote from the sensor network). The presence of boundaries makes this problem especially challenging. There are two key questions: 1) Given n sensors, how accurately can the field be estimated? 2) How much energy will be consumed by the communications required to obtain an accurate estimate at the destination? Theoretical upper and lower bounds on the estimation error and energy consumption are given. A practical strategy for estimation and communication is presented. The strategy, based on a hierarchical data-handling and communication architecture, provides a near-optimal balance of accuracy and energy consumption.

[1]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[2]  A. Tsybakov,et al.  Minimax theory of image reconstruction , 1993 .

[3]  Andrew R. Barron,et al.  Mixture Density Estimation , 1999, NIPS.

[4]  D. Donoho.  Wedgelets: nearly minimax estimation of edges , 1999 .

[5]  K. Ramchandran,et al.  Distributed source coding using syndromes (DISCUS): design and construction , 1999, Proceedings DCC'99 Data Compression Conference (Cat. No. PR00096).

[6]  E. Candès,et al.  Curvelets: A Surprisingly Effective Nonadaptive Representation for Objects with Edges , 2000 .

[7]  Anna Scaglione,et al.  On the Interdependence of Routing and Data Compression in Multi-Hop Sensor Networks , 2002, MobiCom '02.

[8]  Sergio D. Servetto.  Sensing lena-massively distributed compression of sensor images , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[9]  Mingyan Liu,et al.  On the Many-to-One Transport Capacity of a Dense Wireless Sensor Network and the Compressibility of Its Data , 2003, IPSN.

[10]  Kannan Ramchandran,et al.  Distributed source coding using syndromes (DISCUS): design and construction , 2003, IEEE Trans. Inf. Theory.

[11]  Deborah Estrin,et al.  An evaluation of multi-resolution storage for sensor networks , 2003, SenSys '03.

[12]  Deborah Estrin,et al.  An evaluation of multi-resolution search and storage in resource-constrained sensor networks - eScholarship , 2003 .

[13]  Ramesh Govindan,et al.  Localized edge detection in sensor fields , 2003, Ad Hoc Networks.

[14]  Urbashi Mitra,et al.  Boundary Estimation in Sensor Networks: Theory and Methods , 2003, IPSN.

[15]  Deborah Estrin,et al.  An implementation of multi-resolution search and storage in resource-constrained sensor networks , 2003 .

[16]  R. Nowak,et al.  Backcasting : A New Approach to Energy Conservation in Sensor Networks , 2003 .

[17]  Bhaskar Krishnamachari,et al.  Applications of localized image processing techniques in wireless sensor networks , 2003, SPIE Defense + Commercial Sensing.

[18]  Robert D. Nowak,et al.  Platelets: a multiscale approach for recovering edges and surfaces in photon-limited medical imaging , 2003, IEEE Transactions on Medical Imaging.

[19]  R. Nowak,et al.  Backcasting: adaptive sampling for sensor networks , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[20]  Feng Zhao,et al.  Information processing in sensor networks (IPSN'04) , 2004, SIGBED.

[21]  R. Nowak,et al.  Multiscale likelihood analysis and complexity penalized estimation , 2004, math/0406424.