Titre :	Deep Vision Transformer for Heart Disease Classification and Prediction
Type de document :	texte imprimé
Auteurs :	Oualid Akkouche, Auteur ; Adlene Bekhouche, Auteur ; Abdelouahab Moussaoui, Auteur
Année de publication :	2023
Importance :	1 vol (76 f .)
Format :	29cm
Langues :	Français (fre)
Catégories :	Thèses & Mémoires:Informatique
Mots-clés :	Machine learning
Index. décimale :	004 Informatique
Résumé :	The field of computer vision has for years been dominated by Convolutional Neural Networks (CNNs) and Recurrent Neural Network (RNN) in the medical domain . However, there are various other Deep Learning (DL) techniques that have became very popular in this space. Transformers are an example of the deep learning technique that has been gaining popularity in the recent years. In this work, we studied the performance of Vision Transformers on Heart Disease classification tasks and we have proposed a new model depending on ViTs. We also proposed other models and architectures such as, CNN, MLP, ResNet-1D, AlexNet-1D,LSTM,GRU... . Finally, we trained the proposed models on PTB-XL dataset and evaluated them. We compared the performance of ViTs to that of others and the later showed an accuracy higher than the others (98%).
Côte titre :	MAI/0713
En ligne :	https://drive.google.com/file/d/1bN4NBnFcNpT_47naBdw-aAmzCUIrZhBW/view?usp=drive [...]
Format de la ressource électronique :	pdf

Deep Vision Transformer for Heart Disease Classification and Prediction [texte imprimé] / Oualid Akkouche, Auteur ; Adlene Bekhouche, Auteur ; Abdelouahab Moussaoui, Auteur . - 2023 . - 1 vol (76 f .) ; 29cm.
Langues : Français (fre)

Catégories :	Thèses & Mémoires:Informatique
Mots-clés :	Machine learning
Index. décimale :	004 Informatique
Résumé :	The field of computer vision has for years been dominated by Convolutional Neural Networks (CNNs) and Recurrent Neural Network (RNN) in the medical domain . However, there are various other Deep Learning (DL) techniques that have became very popular in this space. Transformers are an example of the deep learning technique that has been gaining popularity in the recent years. In this work, we studied the performance of Vision Transformers on Heart Disease classification tasks and we have proposed a new model depending on ViTs. We also proposed other models and architectures such as, CNN, MLP, ResNet-1D, AlexNet-1D,LSTM,GRU... . Finally, we trained the proposed models on PTB-XL dataset and evaluated them. We compared the performance of ViTs to that of others and the later showed an accuracy higher than the others (98%).
Côte titre :	MAI/0713
En ligne :	https://drive.google.com/file/d/1bN4NBnFcNpT_47naBdw-aAmzCUIrZhBW/view?usp=drive [...]
Format de la ressource électronique :	pdf