Paper Info
Title
Sensor Placement In Arbitrarily Restricted Region For Field Estimation Based On Gaussian Process
Abstract
A sensor placement method that enables us to arbitrarily set a region of candidate positions independently of a region of estimation is proposed. Field estimation aims to estimate and interpolate the physical quantities of fields, e.g., temperature and sound pressure, in an entire region of interest, where Gaussian processes are typically used for modeling. Although a number of sensor placement methods are proposed in the literature, in most of the methods, an optimization criterion is evaluated only at the candidate positions of the sensors. However, a region in which sensors are placed is sometimes restricted in practical applications of field estimation. To overcome this issue, we formulate a cost function on the basis of the expected squared error inside the target region for field estimation, which is derived by Gaussian process regression. We also propose two algorithms, the greedy algorithm and convex relaxation method, to efficiently solve this optimization problem. Numerical simulation results indicated that our proposed method achieves accurate field estimation even when the placement region of sensor candidates is restricted.
Year
DOI
Venue
2020
10.23919/Eusipco47968.2020.9287222
28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020)
Keywords
DocType
ISSN
sensor placement, Gaussian process, field estimation, greedy algorithm, convex optimization
Conference
2076-1465
Citations 
PageRank 
References 
0
0.34
0
Authors
4
Name
Order
Citations
PageRank
Nishida Tomoya141.23
Natsuki Ueno2125.59
Shoichi Koyama36817.76
Saruwatari, H.465290.81