Tami, Mohammad, Masri, Sari, Hasasneh, Ahmad et Tadj, Chakib.
2024.
« Transformer-based approach to pathology diagnosis using audio spectrogram ».
Information, vol. 15, nº 5.
Prévisualisation |
PDF
Tadj-C-2024-28768.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (3MB) | Prévisualisation |
Résumé
Early detection of infant pathologies by non-invasive means is a critical aspect of pediatric healthcare. Audio analysis of infant crying has emerged as a promising method to identify various health conditions without direct medical intervention. In this study, we present a cutting-edge machine learning model that employs audio spectrograms and transformer-based algorithms to classify infant crying into distinct pathological categories. Our innovative model bypasses the extensive preprocessing typically associated with audio data by exploiting the self-attention mechanisms of the transformer, thereby preserving the integrity of the audio’s diagnostic features. When benchmarked against established machine learning and deep learning models, our approach demonstrated a remarkable 98.69% accuracy, 98.73% precision, 98.71% recall, and an F1 score of 98.71%, surpassing the performance of both traditional machine learning and convolutional neural network models. This research not only provides a novel diagnostic tool that is scalable and efficient but also opens avenues for improving pediatric care through early and accurate detection of pathologies.
Type de document: | Article publié dans une revue, révisé par les pairs |
---|---|
Professeur: | Professeur Tadj, Chakib |
Affiliation: | Génie électrique |
Date de dépôt: | 05 juin 2024 18:38 |
Dernière modification: | 07 juin 2024 17:01 |
URI: | https://espace2.etsmtl.ca/id/eprint/28768 |
Actions (Authentification requise)
![]() |
Dernière vérification avant le dépôt |