Please use this identifier to cite or link to this item:
https://dspace.univ-ouargla.dz/jspui/handle/123456789/37209
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | BENSID, Khaled | - |
dc.contributor.author | MEBROUKI, Zine EL Abidine | - |
dc.contributor.author | BENTADJ, Ouissal | - |
dc.contributor.author | BENAMEUR, Maroua | - |
dc.contributor.author | DARRAGI, Amira Asma | - |
dc.contributor.author | IDJA, Sarah | - |
dc.date.accessioned | 2024-10-09T09:09:07Z | - |
dc.date.available | 2024-10-09T09:09:07Z | - |
dc.date.issued | 2024 | - |
dc.identifier.citation | FACULTY OF NEW TECHNOLOGIES OF INFORMATION AND COMMUNICATION | en_US |
dc.identifier.uri | https://dspace.univ-ouargla.dz/jspui/handle/123456789/37209 | - |
dc.description | Electronics and Embedded system | en_US |
dc.description.abstract | In this master’s thesis, we aim to develop a diagnostic support system that enables the detection of heart failure using a medical dataset. Accurate diagnosis of heart failure is a complex task that requires a series of clinical examinations and tests to verify the signs and symptoms of the disease. Therefore, the objective of this project is to design an automated diagnostic system for the early detection of heart failure using a medical dataset, focusing on distinguishing between heart failure patients and healthy individuals. The proposed system relies on two main stages: the first is feature extraction, and the second is classification using artificial intelligence. The selected discriminative features in- clude two main parameters: the feature extraction process and the neural network model parameters. The classification process employs several deep learning models and classi- fiers such as Convolutional Neural Networks (CNN), Support Vector Machines (SVM), Long Short-Term Memory networks (LSTM), hybrid CNN-LSTM models, and Artificial Neural Networks (ANN). Feature extraction and the classification process were implemented using Visual Studio Code. The heart failure database used in our experiments was manually structured from a previous database. Performance measures used in this study include accuracy, loss curve, and accuracy curve. The results obtained showed varying performance across different models. | en_US |
dc.description.sponsorship | Department of Electronic and Telecommunication | en_US |
dc.language.iso | en | en_US |
dc.publisher | UNIVERSITY OF KASDI MERBAH OUARGLA | en_US |
dc.subject | Heart failure disease | en_US |
dc.subject | Medical dataset | en_US |
dc.subject | Accurate diagnosis | en_US |
dc.subject | Early detection | en_US |
dc.subject | Fea- ture extraction | en_US |
dc.title | Heart failure analysis using Artificial Intelligence | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | Département d'Electronique et des Télécommunications - Master |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
MEBROUKI-BENAMEUR-BENTADJ-DERRADJI-IDJA.pdf | Electronics and Embedded system | 4,5 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.