Klasifikasi Kelainan Irama Jantung pada Sinyal Electrocardiogram Menggunakan Metode Hybrid PSO-Neural Network dengan Filter Neural ICA

Ariyati, Miftah Rahmalia (2018) Klasifikasi Kelainan Irama Jantung pada Sinyal Electrocardiogram Menggunakan Metode Hybrid PSO-Neural Network dengan Filter Neural ICA. Masters thesis, Institut Teknologi Sepuluh Nopember.

[img]
Preview
Text
02311650010203-MASTER_THESIS.pdf - Accepted Version

Download (3MB) | Preview

Abstract

Penelitian untuk mempelajari klasifikasi irama jantung dengan interpretasi sinyal Electrocardiogram (ECG) telah banyak diteliti dan dikembangkan. Terdapat penelitian terkini mengenai klasifikasi kelainan irama jantung tipe left bundle branch (LBBB), right bundle branch (RBBB) dan premature ventricular contraction (PVC) dengan menggunakan metode optimasi Taguchi dan metode klasifikasi Naïve Bayes. Hasil klasifikasi metode Naïve Bayes hasilnya lebih rendah dibandingkan dengan metode klasifikasi SVM, sehingga masih terdapat peluang pengembangan selanjutnya untuk topik tersebut. Penelitian ini mengusulkan suatu metode Hybrid PSO-Neural Network sebagai metode klasifikasi dan metode Neural-ICA sebagai filter. Filter Neural ICA bertujuan untuk memisahkan sinyal asli dan sinyal noise pada rekaman sinyal ECG. Metode ICA mengimplementasikan algoritma Neural untuk proses update bobot setelah mengalami proses filter. Metode Hybrid PSO-Neural Network merupakan metode Neural Network yang dioptimasi menggunakan PSO untuk mengoptimalkan hasil klasifikasi. Metode Hybrid PSO-NN mampu meningkatkan hasil akurasi sebesar 2%. Hasil dari pendekatan yang diusulkan diperoleh akurasi sebesar 99% dan pada metode NN diperoleh akurasi sebesar 97% dan metode SVM diperoleh akurasi sebesar 97%. ========================================================================================Studies on the classification of heart rhythms from Electrocardiogram (ECG) signal interpretation have been widely reported. Several techniques for recognizing the abnormalities on left bundle branch (LBBB), right bundle branch (RBBB) and premature ventricular contraction (PVC) using the Taguchi optimization method and the Naïve Bayes classification method have been reported. Unfortunately results from the Naïve Bayes classification method are not as good as those using method such as SVM classification method. In the paper, we propose a Hybrid PSO-Neural Network (NN) as a classification method and a Neural Independent Component Analysis (Neural-ICA) as a filter method. Neural ICA aims to separate the original signal and the noise signal on the ECG signal record. In this research, the ICA method implements the Neural algorithm for the process of updating the weights after the filter process. The Hybrid PSO-Neural Network is a Neural Network method that optimized by PSO to optimize the classification result. The hybrid PSO-NN method can improve the classification accuracy by up to 2%, i.e. 99% accuracy, in comparison to NN method 98% accuracy and SVM method 96% accuracy, respectively.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Klasifikasi sinyal ECG, ICA, Neural Network, PSO
Subjects: Q Science > Q Science (General) > Q325.78 Back propagation
Q Science > Q Science (General) > Q337.5 Pattern recognition systems
Divisions: Faculty of Industrial Technology > Physics Engineering > 30101-(S2) Master Thesis
Depositing User: miftah rahmalia ariyati
Date Deposited: 23 Jun 2021 08:26
Last Modified: 23 Jun 2021 08:26
URI: https://repository.its.ac.id/id/eprint/54857

Actions (login required)

View Item View Item