Modelling of a surface marine vehicle with kernel ridge regression confidence machine



Downloads per month over past year

Moreno Salinas, David and Moreno Salinas, Raúl and Pereira, Augusto and Aranda, Joaquín and Cruz García, Jesús Manuel de la (2019) Modelling of a surface marine vehicle with kernel ridge regression confidence machine. Applied soft computing, 76 . pp. 237-250. ISSN 1568-4946

[thumbnail of cruzgarcia73postprint+EMB_01_mar_2020.pdf]
Creative Commons Attribution Non-commercial No Derivatives.


Official URL:


This paper describes the use of Kernel Ridge Regression (KRR) and Kernel Ridge Regression Confidence Machine (KRRCM) for black box identification of a surface marine vehicle. Data for training and test have been obtained from several manoeuvres typically used for marine system identification. Thus, a 20/20 degrees Zig-Zag, a 10/10 degrees Zig-Zag, and different evolution circles have been employed for the computation and validation of the model. Results show that the application of conformal prediction provides an accurate model that reproduces with large accuracy the actual behaviour of the ship with confidence margins that ensure that the model response is within these margins, making it a suitable tool for system identification.

Item Type:Article
Additional Information:

©2019 Elsevier B.V.
We express our appreciation to the late Prof. Jesus Manuel de la Cruz, whose contribution to this work was of great significance.
The work of D. Moreno-Salinas was supported by “Ministerio de Economia y Competitividad” under project CICYT DPI2014-55932-C2-2-R.
The work of R. Moreno has been supported by Science Foundation Ireland under Grant No. SFI/12/RC/2289.

Uncontrolled Keywords:System-identification; Ship; System identification; Marine systems; Kernel ridge regression (KRR); Conformal predictors (CP); Kernel ridge regression confidence machine (KRRCM)
Subjects:Sciences > Computer science > Artificial intelligence
ID Code:55046
Deposited On:23 Apr 2019 14:53
Last Modified:01 Mar 2021 23:00

Origin of downloads

Repository Staff Only: item control page