# MicrocrackAttentionNext: Advancing Microcrack Detection in Wave Field Analysis Using Deep Neural Networks Through Feature Visualization

## TL;DR

This paper introduces a new deep learning method for detecting microcracks in materials using wave field data, improving accuracy despite challenges like class imbalance.

## Contribution

The study proposes an asymmetric encoder-decoder network with adaptive feature reuse for improved microcrack detection.

## Key findings

- An optimized architecture achieved 87.74% accuracy in microcrack detection.
- Feature space visualization using MDA helped analyze the impact of activation and loss functions.
- The method addresses class imbalance and high-dimensional data challenges in microcrack detection.

## Abstract

Microcrack detection using deep neural networks (DNNs) through an automated pipeline using wave fields interacting with the damaged areas is highly sought after. However, these high-dimensional spatio–temporal crack data are limited. Moreover, these datasets have large dimensions in the temporal domain. The dataset presents a substantial class imbalance, with crack pixels constituting an average of only 5% of the total pixels per sample. This extreme class imbalance poses a challenge for deep learning models with different microscale cracks, as the network can be biased toward predicting the majority class, generally leading to poor detection accuracy for the under-represented class. This study proposes an asymmetric encoder–decoder network with an adaptive feature reuse block for microcrack detection. The impact of various activation and loss functions are examined through feature space visualisation using the manifold discovery and analysis (MDA) algorithm. The optimized architecture and training methodology achieved an accuracy of 87.74%.