RT info:eu-repo/semantics/article
T1 A hybrid machine learning system to impute and classify a component-based robot
A1 Basurto Hornillos, Nuño
A1 Arroyo Puente, Ángel
A1 Cambra Baseca, Carlos
A1 Herrero Cosío, Álvaro
K1 Hybrid Artificial Intelligence System
K1 Machine learning
K1 Clustering
K1 Regression
K1 Missing values
K1 Component-Based Robot
K1 Informática
K1 Computer science
AB In the field of cybernetic systems and more specifically in robotics, one of the fundamental objectives is the detection of anomalies in order to minimize loss of time. Following this idea, this paper proposes the implementation of a Hybrid Intelligent System in four steps to impute the missing values, by combining clustering and regression techniques, followed by balancing and classification tasks. This system applies regression models to each one of the clusters built on the instances of data set. Subsequently, a variety of balancing techniques are applied to improve the classifier’s ability to discern whether it is in an error or a normal state. These techniques support to obtain better classification ratios in which a robot is close to error and allow us to bring the behavior back to a normal state. The experimentation is performed using a modern and public data set, which has been extracted from a component-based robotic system, in which different anomalies are induced by software in their components.
PB Oxford University Press
SN 1367-0751
YR 2022
FD 2022-02
LK http://hdl.handle.net/10259/8248
UL http://hdl.handle.net/10259/8248
LA eng
DS Repositorio Institucional de la Universidad de Burgos
RD 09-may-2024