Optimisation of Convolutional Neural Network Parameters Using the Bees Algorithm

The convolutional neural network (CNN)Convolutional Neural Network (CNN) is one of the most popular deep learningDeep learning algorithmsAlgorithms that deals mainly with image data. In this study, the application of the Bees AlgorithmBees algorithm (BA), which behaves like honeybees, was used along with the Bayesian OptimisationOptimisation (BO) approach to improve CNN performance (BA-BO-CNN). Applying the hybrid algorithmHybrid algorithm on Cifar10DataDir images increased the accuracy on the validation set from 80.72% for the existing BO-CNN to 82.22% for the hybrid algorithmHybrid algorithm. Applying BA-BO-CNN on digit datasets showed the same accuracy as the existing hybridHybrid BO-CNN, but with a computational time shortened by 3 min and 12 s. Finally, concrete crack benchmark image data yielded almost similar results to existing algorithmsAlgorithms. Similarly, a new hybridHybrid Bees Convolutional Neural Network (BA-CNN)Bees Convolutional Neural Network (BA-CNN) algorithmAlgorithms was proposed that uses BA to design better CNN topologyCNN topology by optimising its hyperparameters, which increases the network accuracy. Applying the hybrid algorithmHybrid algorithm to the Cifar10DataDir dataset yielded the same accuracy as existing CNNs and BO-CNNs. Applying it to the digits dataset produced the lowest computational time with 4 min and 14 s reductions compared to BO-CNN, so it is the best algorithmAlgorithms in terms of cost-effectiveness. Finally, applying it to concrete crack images produced similar results to the existing algorithmsAlgorithms.