Fast Data-Driven Greedy Sensor Selection for Ridge Regression

We propose a data-driven sensor-selection algorithm for accurate estimation of the target variables from the selected measurements. The target variables are assumed to be estimated by a ridge-regression estimator, which is trained based on the data. The proposed algorithm greedily selects sensors fo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal Vol. 25; no. 6; pp. 10030 - 10045
Main Authors: Sasaki, Yasuo, Yamada, Keigo, Nagata, Takayuki, Saito, Yuji, Nonomura, Taku
Format: Journal Article
Language:English
Published: New York IEEE 15.03.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accuracy
Algorithms
Computational modeling
Cost function
Datasets
Estimation
Greedy algorithms
Intelligent sensors
Keywords Greedy algorithm
Linear programming
Linear systems
Overfitting
Parameters
Regularization
ridge regression
sensor selection
Sensors
Training
Vectors
ISSN:1530-437X, 1558-1748
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a data-driven sensor-selection algorithm for accurate estimation of the target variables from the selected measurements. The target variables are assumed to be estimated by a ridge-regression estimator, which is trained based on the data. The proposed algorithm greedily selects sensors for minimizing the cost function of the estimator. Sensor selection that prevents overfitting of the resulting estimator can be realized by setting a positive regularization parameter. The greedy solution is computed in quite a short time by using some recurrent relations that we derive. The effectiveness of the proposed algorithm is verified for artificial datasets that are generated from linear systems and a real-wold dataset that is aimed for the selection of pressure-sensor locations for estimating the yaw angle of a ground vehicle. The demonstration for the datasets reveals that the proposed algorithm computes a sensor set, resulting in more accurate estimation than existing data-driven selection algorithms in some conditions. Furthermore, it is confirmed that setting a positive regularization parameter in the proposed algorithm leads to accurate estimation when overfitting is problematic.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2025.3537702