Data-Driven Sparse Sensor Selection Based on A-Optimal Design of Experiment with ADMM

Takayuki Nagata, Taku Nonomura, Kumi Nakai, Keigo Yamada, Yuji Saito, Shunsuke Ono

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

The present study proposes a sensor selection method based on the proximal splitting algorithm and the A-optimal design of experiment using the alternating direction method of multipliers (ADMM) algorithm. The performance of the proposed method was evaluated with a random sensor problem and compared with previously proposed methods, such as the greedy and convex relaxation methods. The performance of the proposed method is better than the existing greedy and convex relaxation methods in terms of the A-optimality criterion. Although, the proposed method requires a longer computational time than the greedy method, it is quite shorter than that of convex relaxation method in large-scale problems. Then the proposed method was applied to the data-driven sparse-sensor-selection problem. The dataset adopted was the National Oceanic and Atmospheric Administration optimum interpolation sea surface temperature dataset. At a number of sensors larger than that of the latent variables, the proposed method showed similar and better performance compared with previously proposed methods in terms of the A-optimality criterion and reconstruction error.

Original languageEnglish
Article number9407001
Pages (from-to)15248-15257
Number of pages10
JournalIEEE Sensors Journal
Volume21
Issue number13
DOIs
Publication statusPublished - 2021 Jul 1

Keywords

  • Alternating direction method of multipliers
  • optimal design of experiment
  • sensor selection
  • sparse observation

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Data-Driven Sparse Sensor Selection Based on A-Optimal Design of Experiment with ADMM'. Together they form a unique fingerprint.

Cite this