Impact of Tuning Parameters in Deep Convolutional Neural Network Using a Crack Image Dataset
This work addresses parameter optimization for crack detection in images, but it is incremental as it applies standard methods to a specific dataset without introducing new techniques.
The study investigated how tuning parameters like pooling, activation functions, and optimizers affect the performance of a deep convolutional neural network on a crack image dataset, finding that maxpooling with the Adam optimizer and tanh activation function yielded the best results.
The performance of a classifier depends on the tuning of its parame ters. In this paper, we have experimented the impact of various tuning parameters on the performance of a deep convolutional neural network (DCNN). In the ex perimental evaluation, we have considered a DCNN classifier that consists of 2 convolutional layers (CL), 2 pooling layers (PL), 1 dropout, and a dense layer. To observe the impact of pooling, activation function, and optimizer tuning pa rameters, we utilized a crack image dataset having two classes: negative and pos itive. The experimental results demonstrate that with the maxpooling, the DCNN demonstrates its better performance for adam optimizer and tanh activation func tion.