# A Method for Explainable Epileptic Seizure Detection Through Wavelet Transforms Obtained by Electroencephalogram-Based Audio Recordings

## TL;DR

This paper introduces an explainable deep learning method for detecting epileptic seizures by converting EEG signals into audio and using wavelet transforms for analysis.

## Contribution

The novelty lies in using wavelet-based spectrograms and class activation mapping to enhance transparency in seizure detection models.

## Key findings

- Wavelet-based preprocessing improves seizure detection accuracy to 0.922.
- Class activation mapping techniques highlight salient regions in wavelet images for model transparency.
- The method effectively captures temporal and spectral characteristics of EEG signals.

## Abstract

Accurate classification of brain activity from electroencephalogram signals is essential for diagnosing neurological disorders such as epilepsy. In this paper, we propose an explainable deep learning method for epileptic seizure detection. The proposed approach converts electroencephalogram signals into audio waveforms, which are then transformed into time–frequency representations using two distinct continuous wavelet transforms, i.e., the Morlet and the Mexican Hat. These wavelet-based spectrograms effectively capture both temporal and spectral characteristics of the electroencephalogram signal data and serve as inputs to a set of convolutional neural network models with the aim to detect seizure activity. To improve model transparency, the proposed method integrates three class activation mapping techniques aimed to visualize the salient regions in the wavelet images that influence each prediction. Experimental evaluation on a real-world dataset emphasizes the efficacy of wavelet-based preprocessing in electroencephalogram signal analysis in prompt epileptic seizure detection, showing an accuracy equal to 0.922.