Show simple item record

dc.contributor.authorKhaldi, Belkacem
dc.contributor.authorHarrou, Fouzi
dc.contributor.authorBenslimane, Sidi Mohammed
dc.contributor.authorSun, Ying
dc.date.accessioned2021-06-08T06:24:55Z
dc.date.available2021-06-08T06:24:55Z
dc.date.issued2021-06-08
dc.identifier.citationKhaldi, B., Harrou, F., Benslimane, S. M., & Sun, Y. (2021). A Data-Driven Soft Sensor for Swarm Motion Speed Prediction using Ensemble Learning Methods. IEEE Sensors Journal, 1–1. doi:10.1109/jsen.2021.3087342
dc.identifier.issn2379-9153
dc.identifier.doi10.1109/JSEN.2021.3087342
dc.identifier.urihttp://hdl.handle.net/10754/669445
dc.description.abstractMachine Learning (ML) for swarm motion prediction is a relatively unexplored area that could help sustain and monitor daily swarm robotics collective tasks. This paper focuses on a specific application of swarm robotics which is pattern formation, to demonstrate the ability of Ensemble Learning (EL) approaches to predict the motion speed of swarm robots. Specifically, the boosted trees (BST) and bagged trees (BT) algorithms are introduced to predict the motion speed of a swarm of miniature two-wheels differential driver mobile robots performing a circle-formation via the viscoelastic control model. This choice’s motivation is due to EL-based models’ ability to improve the performance of ML models by combining multiple learners versus single regressors. Both BST and BT algorithms’ performances are compared to ten commonly known prediction models based on Support Vector Regressors (SVRs) and Gaussian Process Regressors (GPRs) with different kernel functions. Using simulated measurements recorded every 0.1 second from the robots’ sensors, we demonstrate the effectiveness of the developed methods over conventional ML models (SVR and GPR) in a free/non-free obstacles environment. Results showed that the BST and BT regression models reached the highest prediction performance with fully and partially connected swarms and even when involving different swarm sizes.
dc.publisherIEEE
dc.relation.urlhttps://ieeexplore.ieee.org/document/9448037/
dc.relation.urlhttps://ieeexplore.ieee.org/document/9448037/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9448037
dc.rightsArchived with thanks to IEEE Sensors Journal
dc.subjectSwarm Robotics
dc.subjectSwarm Motion Speed Prediction
dc.subjectEnsemble Learning
dc.subjectboosted trees
dc.subjectbagged trees
dc.subjectSupport Vector Regressors
dc.subjectGaussian Process Regressors
dc.titleA Data-Driven Soft Sensor for Swarm Motion Speed Prediction using Ensemble Learning Methods
dc.typeArticle
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.contributor.departmentEnvironmental Statistics Group
dc.contributor.departmentStatistics Program
dc.identifier.journalIEEE Sensors Journal
dc.eprint.versionPost-print
dc.contributor.institutionLaboratoire de Recherche en Informatique de Sidi Bel Abbes (Lab RI-SBA) Sidi Bel Abess, Algeria and École Supérieure en Informatique 8 Mai 1945, Sidi Bel-Abbés, Algeria.
kaust.personHarrou, Fouzi
kaust.personSun, Ying
refterms.dateFOA2021-06-08T06:37:33Z
dc.date.published-online2021-06-08
dc.date.published-print2021-09-01


Files in this item

Thumbnail
Name:
Sensors2021.pdf
Size:
8.884Mb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record