Title: Diagnosing lung cancer with the aid of BPN in associate with AFSO-EA

Authors: C. Rahul; R. Gopikakumari

Addresses: Electronics and Communication Engineering, CUSAT, Errnakulam, India ' Division of Electronics Engineering, School of Engineering, CUSAT, Errnakulam, India

Abstract: This work aims at modelling an optimum back propagation network (BPN) model, by reducing the input feature count and by optimising the number of neurons in each layer of the BPN classifier without compromising the accuracy. This work incorporates artificial fish swarm optimisation (AFSO) and evolutionary algorithm (EA) and proposes a hybrid AFSO-EA for reducing the input feature set. This work also configures a BPN model, where the number of neurons in each hidden layer is optimised using the same hybrid method. The investigation results reveal that the proposed hybrid AFSO-EA technique generates a BPN model, which can achieve 97.5% classification accuracy, with much less computational overhead, than the existing methods.

Keywords: lung cancer; back propagation network; BPN; Levenberg-Marquardt; LM; artificial fish swarm optimisation; AFSO; evolutionary algorithm; EA; hybrid artificial fish swarm optimisation-evolutionary algorithm; AFSO-EA.

DOI: 10.1504/IJMEI.2021.118767

International Journal of Medical Engineering and Informatics, 2021 Vol.13 No.6, pp.534 - 551

Received: 23 Dec 2019
Accepted: 25 Jan 2020
Published online: 05 Nov 2021 *

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