Generation of CNN Architectures Using the Harmonic Search Algorithm and its Application to Classification of Damaged Sewer

When used as an image processing method, convolutional neural networks (CNNs) cannot verify conditions that can achieve high performance; however, they show sufficiently high performance and are used in various fields. The architecture of a CNN and various parameters determine its performance, and it is impossible to verify the number of all cases that determine the performance of the CNN. Therefore, well-known CNN models are generally used. Recently, various methods for adjusting the parameters of CNNs or generating CNN architectures have been studied in various ways. Methods using metaheuristic algorithms often focus on parameter tuning, or the use of simple hierarchical architectures. This paper proposes a method to create a CNN model with a complex CNN architecture that can be applied to different datasets using the harmony search (HS) algorithm from among metaheuristic algorithms. This study aimed to generate a CNN architecture using fewer computing resources and to verify the results. To make the CNN model in units of cells, the internal and hierarchical architecture of the cell was created based on the learning of the CIFAR image dataset through HS and the performance of the created CNN model was tested by applying it to the classification of a damaged sewer pipe image dataset. The 10-GPU-day computed result showed that the accuracy of classifying the damaged sewers was at least 5% higher than that of VGGNet, the highest among the existing CNN models.
Keywords:
convolutional neural network; auto machine learning; metaheuristic algorithm; harmony search algorithm; heuristic algorithm, optimization, artificial neural network, image classification.