| DC Field | Value | Language |
|---|
| dc.contributor.author | AKSA, DJemai | - |
| dc.contributor.author | OMARI, FEth ALlah WAlid | - |
| dc.date.accessioned | 2022-03-31T08:35:48Z | - |
| dc.date.available | 2022-03-31T08:35:48Z | - |
| dc.date.issued | 2020 | - |
| dc.identifier.uri | https://repository.esi-sba.dz/jspui/handle/123456789/76 | - |
| dc.description | Mr A. Rahmoun Encadreur Mr H. Bensenan Co-encadreur | en_US |
| dc.description.abstract | On thisgraduationproject,weinvestigatetheuseofDSSforcardiovasculardiseasesdiag-
nostic, focusingonmultipletypesofarrhythmia.wealsoexploretheuseofLSTMasaclas-
sification modelusinglongertermECGsignal(10s),aswellasbuildingaplatformtodisplay
and acquirenewsignalsusingIoTdevice(MySignals).
The useofLSTMprovestobeperformingverywellonthetaskofclassifying17categories
of rhythm(15arrhythmia+normalsinusrhythm+pacemakerrhythm)comparedtootherstate-
of-the-art methods,yieldinganaccuracyof93%,sensitivity95%,andaspecificityof99.46%.
As wellasareal-timeresponsiveplatformallowingthevisualizationofnewlyobtainedsignals
and outputofthecomputer-aideddiagnostic.
This projectdepictsthatthetopicofstudystillfacesmanyobstacles,challengesandlim-
itations suchas(clinicalimplication,healthydata...etc)andothers.Despiteallthelater,the
LSTM anddeeplearningmechanismsdemonstratedthatitiscapableofrecognizinglong-term
patterns withinourtime-seriesdataalongwithgeneralizingthediagnosticprocess. | en_US |
| dc.language.iso | en | en_US |
| dc.subject | LSTM | en_US |
| dc.subject | Deep Learning | en_US |
| dc.subject | Arrhythmia | en_US |
| dc.subject | DSS | en_US |
| dc.subject | Visualization Platform | en_US |
| dc.subject | Iot | en_US |
| dc.subject | time-series | en_US |
| dc.title | Decision Support Systems for Cardio Vascular Disease using Deep Learning Techniques | en_US |
| dc.type | Thesis | en_US |
| Appears in Collections: | Ingénieur
|
