ARCHIVES
VOL. 10, ISSUE 2 (2025)
Hyper-heuristic firefly algorithm-based convolutional neural network for handwritten identification system
Authors
Locksley EA, Olabiyisi SO, Ganiyu RA, Omidiora EO, Taiwo CY
Abstract
The goal of this study is to create a
convolutional neural network for a handwritten identification system based on
the hyper-heuristic firefly algorithm. Samples of handwriting were gathered
from Ladoke Akintola University employees and students in Ogbomoso, Nigeria.
The CNN's hyperparameter is chosen by the Hyper Heuristic Firefly Algorithm
(HHFA). The MATLAB 2020 environment was used to implement the improved model.
False Positive Rate (FPR), accuracy, sensitivity, specificity, precision, and
computation time were used to assess the created model. The efficacy of the CNN
model based on the hyperheuristic firefly algorithm was evaluated using the
paired-sample t-test. To determine the performance differences between the
hyper-heuristic firefly method and the current CNN at P < 0.5, a hypothesis
was established. It was discovered that there is a notable distinction between
HHFA-CNN and the existing CNN algorithms. The hyper-heuristic firefly algorithm
was therefore suggested as an effective tool in the handwritten identification
system.
Download
Pages:1-9
How to cite this article:
Locksley EA, Olabiyisi SO, Ganiyu RA, Omidiora EO, Taiwo CY "Hyper-heuristic firefly algorithm-based convolutional neural network for handwritten identification system". International Journal of Advanced Science and Research, Vol 10, Issue 2, 2025, Pages 1-9
Download Author Certificate
Please enter the email address corresponding to this article submission to download your certificate.