KLASIFIKASI GELOMBANG PQRST PADA SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN METODE LONG SHORT-TERM MEMORY

DINA, TIARA ANNISA and Nurmaini, Siti (2021) KLASIFIKASI GELOMBANG PQRST PADA SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN METODE LONG SHORT-TERM MEMORY. Undergraduate thesis, Sriwijaya University.

[img] Text
RAMA_52601_09011381722124.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (10MB) | Request a copy
[img] Text
RAMA_52601_09011381722124_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (35MB) | Request a copy
[img]
Preview
Text
RAMA_52601_09011381722124_0002085908_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[img] Text
RAMA_56201_09011381722124_0002085908_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (651kB) | Request a copy
[img] Text
RAMA_56201_09011381722124_0002085908_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (359kB) | Request a copy
[img] Text
RAMA_56201_09011381722124_0002085908_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (8MB) | Request a copy
[img] Text
RAMA_56201_09011381722124_0002085908_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (48kB) | Request a copy
[img] Text
RAMA_56201_09011381722124_0002085908_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (115kB) | Request a copy
[img] Text
RAMA_56201_09011381722124_0002085908_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (86kB) | Request a copy

Abstract

Elektrokardiogram (EKG) merupakan alat diagnosis non-invasif yang paling umum digunakan untuk merekam aktivitas fisiologis jantung selama periode waktu tertentu. Didalam EKG terdapat sinyal QRS-complex, Gelombang P dan T merupakan bentuk gelombang karakteristik utama dalam EKG, merepresentasikan berbagai kegiatan jantung. Penelitian ini menggunakan dataset dari Lobachevsky University Database (LUDB). Metode Long Short-Term Memory digunakan untuk mengatasi masalah vanishing gradient. Kemudian dilakukan perbandingan menggunakan metode LSTM untuk mendapatkan hasil model yang terbaik. . Hasil klasifikasi menggunakan metode LSTM tersebut menunjukkan hasil yang baik pada kasus 4 kelas gelombang PQRST yaitu nilai akurasi sebesar 97,53%, nilai presisi sebesar 93,44%, nilai sensitivitas sebesar 93,27%, nilai spesifisitas sebesar 98,45% serta nial f1-score sebesar 93,35%. Selanjutnya hasil klasifikasi pada kasus 7 kelas gelombang PQRST juga mendapatkan hasil yang baik yaitu nilai akurasi sebesar 99,18%, nilai presisi sebesar 93,76%, nilai sensitivitas sebesar 94,51%, nilai spesifisitas sebesar 99,54%, dan nilai F1-score sebesar 94.12%.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: ECG Classification, PQRST Waves, Recurrent Neural Network, Long Short-Term Memory, Deep Learning
Subjects: T Technology > T Technology (General) > T1-995 Technology (General)
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Tiara Annisa Dina
Date Deposited: 26 Aug 2021 03:22
Last Modified: 26 Aug 2021 03:22
URI: http://repository.unsri.ac.id/id/eprint/52647

Actions (login required)

View Item View Item