Claim Missing Document
Check
Articles

Found 3 Documents
Search

Klasifikasi Sinyal EKG menggunakan Ciri Statistik dan Parameter Hjorth dengan SVM dan k-NN WIJAYANTO, INUNG; HUMAIRANI, ANNISA; RIZAL, ACHMAD; HADIYOSO, SUGONDO
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 10, No 1: Published January 2022
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v10i1.132

Abstract

ABSTRAKSinyal elektrokardiogram (EKG) dapat dianalisis dengan memperhatikan bentuk, durasi, dan irama. Pada penelitian ini, dikembangkan sebuah metode ekstraksi ciri sinyal EKG dengan menggunakan parameter Hjorth dan ciri statistik. Kedua parameter tersebut diaplikasikan untuk mengekstrak ciri-ciri dari rekaman suara sinyal EKG. Terdapat tiga kondisi rekaman sinyal EKG yang menjadi masukan dari sistem, kondisi normal, atrial fibrillation (AF), dan congestive heart failure (CHF). Set ciri rekaman EKG yang didapatkan kemudian diklasifikasikan dengan menggunakan metode support vector machine (SVM) dan k-Nearest Neighbor (k-NN) untuk dibandingkan performansinya. Hasil pengujian menggunakan semua ciri sebagai prediktor menunjukkan bahwa usulan sistem mampu memberikan akurasi sebesar 100%. Sementara itu pada skenario reduksi ciri dimana hanya dua ciri yaitu skewness dan complexity, performansi sistem tidak berkurang. Komparasi dengan beberapa studi sebelumnya menunjukkan bahwa usulan metode lebih unggul dalam hal akurasi deteksi dan jumlah ciri yang digunakan.Kata kunci: EKG, atrial fibrillation, congestive heart failure, Hjorth, SVM, k-NN ABSTRACTAn electrocardiogram (ECG) signal can be analyzed by paying attention to its shape, duration, and rhythm. In this study, feature extraction for ECG signals is applied using the Hjorth parameter and statistical characteristics. These two parameters are applied to extract the characteristics of the ECG signal sound recording. There are three conditions of ECG signal recording that are used as input for the system. They are normal conditions, atrial fibrillation (AF), and congestive heart failure (CHF). The set of ECG recording features are classified using the support vector machine (SVM) and k-Nearest Neighbor (k-NN) methods. The test results using all features show that the proposed system can achieve 100% of accuracy. On the other hand, by reducing the feature using only skewness and complexity, the system’s performance is not reduced. Comparative studies with several previous studies show that the proposed method is superior in detection accuracy and the number of features used.Keywords: ECG, atrial fibrillation, congestive heart failure, Hjorth, SVM, k-NN
Optimasi Deteksi Aritmia Pada Sinyal Ekg Menggunakan Pendekatan Divergence Kullback-Leiber Fathir, Muhammad Azlam Ikhlasul; Purboyo, Tito Waluyo; Humairani, Annisa
eProceedings of Engineering Vol. 12 No. 5 (2025): Oktober 2025
Publisher : eProceedings of Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Aritmia jantung merupakan gangguan irama jantung yang berpotensi memicu kondisi kardiovaskular serius apabila tidak terdeteksi secara dini. Kompleksitas morfologi sinyal elektrokardiogram (EKG), dimensi data yang tinggi, dan ketidakseimbangan distribusi kelas pada dataset menjadi tantangan dalam pengembangan sistem deteksi berbasis kecerdasan buatan. Penelitian ini bertujuan mengembangkan sistem klasifikasi aritmia berbasis sinyal EKG dari MIT-BIH Arrhythmia Database dengan menggabungkan Discrete Wavelet Transform (DWT) dan Kullback–Leibler Divergence (KL Divergence) untuk ekstraksi fitur. Data diseimbangkan menggunakan random undersampling sebelum ekstraksi, dengan empat pendekatan distribusi pada KL Divergence, yaitu Uniform, Exponential, Gaussian, dan Combined. klasifikasi dilakukan menggunakan Support Vector Machine (SVM) dengan kernel RBF, serta dievaluasi menggunakan metrik akurasi, F1-score, ROC AUC, log loss, average precision (AP), efisiensi komputasi, dan Coefficient of Variation (CV). Hasil menunjukkan bahwa KL Combined memberikan performa terbaik dengan akurasi 0,8895, F1-score 0,9039, AUC 0,9406, dan log loss uji 0,3012. KL Combined dinilai optimal untuk implementasi klinis karena menggabungkan akurasi tinggi, kestabilan, dan efisiensi, menjadikannya pilihan unggulan dalam sistem deteksi aritmia yang konsisten dan andal. Kata kunci: Aritmia jantung, Divergence Kullback-Leibler, Discrete Wavelet Transform, EKG, MIT-BIH, Support Vector Machine
Comparative Analysis of Hybrid Wavelet Transformation and Filter Bank for  Efficient Arrhythmia Detection in ECG Signals Nurul Maulida, Amalia; Humairani, Annisa; Waluyo Purboyo, Tito; Naufal, Dziban
Jurnal Teknokes Vol. 19 No. 1 (2026): March
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jteknokes.v19i1.154

Abstract

Cardiovascular disease (CVD) is still the leading cause of death worldwide, and arrhythmia is one of its most serious forms because it can trigger sudden cardiac arrest. Given the life-threatening nature of arrhythmias, reliable automated methods for arrhythmia detection are increasingly important in both clinical and remote monitoring settings. While the electrocardiogram (ECG) is the standard tool for arrhythmia detection, its accuracy is often reduced by noise and waveform distortion, which may lead to misclassification. To address this challenge, this study proposes an arrhythmia classification framework that integrates wavelet-based feature extraction with filter bank enhancement. ECG signals from the MIT-BIH Arrhythmia Database were preprocessed and segmented from two leads (MLII and V1), followed by wavelet decomposition using Daubechies (db6), Symlet (sym7), and Biorthogonal (bior4.4) families. Three complementary feature enhancement schemes, Discrete Cosine Transform (DCT), Complex Discrete Wavelet Transform (CDWT), and Orthogonal filter bank, were applied prior to classification with Support Vector Machine (SVM) and Random Forest (RF). The experimental results further highlight that the selection of wavelet, filter bank, and classifier combinations significantly influences arrhythmia detection performance. In particular, the pairing of the bior4.4 wavelet with the orthogonal filter bank and RF classifier achieved the highest accuracy of 94.76%, outperforming other setups, including CDWT-based schemes. This outcome suggests that the linear phase property of bior4.4 yields a more stable feature representation that aligns well with the ensemble mechanism of RF. These insights reinforce the importance of considering both the mathematical properties of wavelets and classifier design when developing ECG-based diagnostic systems. Future work will extend this approach to deep learning models and larger datasets to strengthen its clinical applicability.