Article: Fitness approximation with RF algorithm dedicated to WSN node deployment for a soil monitoring application Journal: International Journal of Ad Hoc and Ubiquitous Computing (IJAHUC) 2023 Vol.43 No.2 pp.72 - 86 Abstract: In order to solve the wireless sensor network (WSN) node deployment optimisation for an agricultural application, a hybridised strength Pareto evolutionary algorithm II with the random forest regressor (RF-SPEA II) was used. The SPEA II intended to optimise the deployment according to the classical constraints of coverage, over-coverage, connectivity and node number, in addition to the nodes separating distance constraint, which affects the predicted physical parameters models quality. Furthermore, the RF regressor was applied as a fitness approximation surrogate model, with the use of evolutionary control rate to avoid convergence to false optimums. Moreover, the application of RF features selection skill that helped to only keep important characteristics and gain more time. Consequently, this hybridisation allowed finding results that exceeded the unaltered SPEA II in terms of solutions qualities and computational time. For example, for an agricultural plot of 400 m<SUP align="right"><SMALL>2</SMALL></SUP> of surface, the RF-SPEA II hybridised algorithm gave better constraint rates and was 5.82 times faster than the unaltered SPEA II. Inderscience Publishers - linking academia, business and industry through research

Title: Fitness approximation with RF algorithm dedicated to WSN node deployment for a soil monitoring application

Authors: Soumaya Ferhat Taleb; Nour El-Houda Benalia; Rabah Sadoun

Addresses: Department of Electronics, Polytechnic National School, Algiers, Algeria ' Department of Electronics, Polytechnic National School, Algiers, Algeria ' Department of Electronics, Polytechnic National School, Algiers, Algeria

Abstract: In order to solve the wireless sensor network (WSN) node deployment optimisation for an agricultural application, a hybridised strength Pareto evolutionary algorithm II with the random forest regressor (RF-SPEA II) was used. The SPEA II intended to optimise the deployment according to the classical constraints of coverage, over-coverage, connectivity and node number, in addition to the nodes separating distance constraint, which affects the predicted physical parameters models quality. Furthermore, the RF regressor was applied as a fitness approximation surrogate model, with the use of evolutionary control rate to avoid convergence to false optimums. Moreover, the application of RF features selection skill that helped to only keep important characteristics and gain more time. Consequently, this hybridisation allowed finding results that exceeded the unaltered SPEA II in terms of solutions qualities and computational time. For example, for an agricultural plot of 400 m² of surface, the RF-SPEA II hybridised algorithm gave better constraint rates and was 5.82 times faster than the unaltered SPEA II.

Keywords: precise agriculture; wireless sensor network; WSN; node deployment; fitness approximation; random forest; strength Pareto evolutionary algorithm II; SPEA II.

DOI: 10.1504/IJAHUC.2023.131359

International Journal of Ad Hoc and Ubiquitous Computing, 2023 Vol.43 No.2, pp.72 - 86

Received: 23 May 2022
Received in revised form: 14 Sep 2022
Accepted: 28 Sep 2022
Published online: 07 Jun 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Fitness approximation with RF algorithm dedicated to WSN node deployment for a soil monitoring application

Keep up-to-date