**6. Discussion**

The presented work is concerned with the development of novel methodology for fully automated analysis of images of the inside of the examined concrete elements obtained from an ultrasonic tomograph. The proposed methodology is based on the combination of the ultrasound tomography technique and the convolutional neural network (CNN). The CNN model is applied at the final stage of the developed methodology for classifying images into two categories: "element without a flaw" and "element with a flaw."

Because the main challenge was to collect enough data, instead of building the CNN model from scratch, we applied a pre-trained convolutional neural network called VGG-16 trained on the ImageNet dataset. The parameters of the pre-trained model were fine-tuned by using the collected images and the transfer learning technique. Moreover, two regularization techniques were applied to avoid problems with overfitting and obtain a satisfactory generalization property of the final CNN model. The first technique was image data augmentation by using basic transformations of an image-like rotation, horizontal flipping, and shifts. The second technique was network weights pruning called dropout. In the process of building the neural model, only 246 RGB images were used. After 100 epochs of training, the network achieved 98% accuracy on the training set with a loss of 0.05. The validation accuracy was 97% with a loss of 0.09. Lastly, the generalization accuracy was close to 99%, which confirms that the CNN model was built properly.

Analysis of the obtained results shows that it is very possible to detect defects in concrete samples with very high accuracy. In the provided example, the concrete cubic laboratory specimens were tested using ultrasonic tomography and the trained convolutional neural network. The experiments were carried out according to the proposed testing approach.
