Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : Indonesian Journal on Computing (Indo-JC)

Active Queue Management (AQM) Performance Analysis Based On Controled Delay (CoDel) Against Bufferbloat On Real-Time Aplication Satria Mandala; Muhammad Noer Iskandar
Indonesia Journal on Computing (Indo-JC) Vol. 2 No. 1 (2017): Maret, 2017
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/INDOJC.2017.2.1.139

Abstract

Bufferbloat merupakan salah satu kondisi buffer dengan ukuran besar yang cenderungselalu penuh dan menyebabkan antrian panjang didalam buffer, jika hal ini terjadi secaraterus-menerus maka dapat menyebabkan jeda transmisi yang tinggi. Bufferbloat seringterjadi pada aplikasi berbasis real-time. Active Queue Management (AQM) merupakansalah satu cara untuk menangani terjadinya bufferbloat., AQM umumnya menggunakanalgoritma Drop Tail untuk menangani kondisi antrian panjang dalam buffer router dijaringan. Namun demikian, performansi AQM berbasis Drop Tail kurang dapatdiandalkan karena jeda transmisi dalam keadaan bufferbloat masih tinggi. Telah banyakstudi dilakukan untuk menangani bufferbloat, seperti Drop Tail, Random Early Detection(RED) dan Controlled Delay (CoDel). Dari riset yang telah dilakukan tersebut masih sulitditemukan performasi algoritma terbaik dalam menangani bufferbloat. Untuk hal tersebut,paper ini menyajikan studi performansi penanganan bufferbloat menggunakan ketigaalgoritma diatas. Dalam studi ini, video streaming digunakan sebagai traffic uji untukmenentukan performansi algoritma terbaik dalam mengatasi bufferbloat. Sedangkanmetriks uji yang digunakan dalam riset ini adalah latency, throughput dan packet-loss.Analisa hasil pengujian mengambil 3 hasil terbaik dalam setiap percobaan. Hasilpengujian menunjukan performansi algoritma CoDel jauh lebih baik dalam menanganilatency yang tinggi pada kondisi bufferbloat dibandingkan RED dan Drop Tail. Namununtuk packet-loss dan throughput performansi RED dan Drop Tail masih ungguldibanding algoritma CoDel
IoT on Heart Arrhythmia Real Time Monitoring Muhammad Alif Akbar; Satria Mandala
Indonesia Journal on Computing (Indo-JC) Vol. 3 No. 2 (2018): September, 2018
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/INDOJC.2018.3.2.170

Abstract

Monitoring jantung telah populer sejak 5 tahun terakhir. Hal ini ditandai dengan munculnya berbagai produk monitoring jantung berbasis wearable sensor. Umumnya komunikasi yang digunakan pada sistem tersebut adalah menggunakan radio telemetri dengan biaya opera- sional yang mahal. Beberapa riset mencoba menggunakan konsep internet of things (IoT) untuk mengatasi hal tersebut. Namun demikian, desain komunikasi IoT yang ada belum efisien. Ini disebabkan riset yang ada hanya berfokus pada bagaimana hasil baca sensor dapat dipantau secara realtime. Untuk mengatasi hal tersebut, riset ini mengusulkan sebuah arsitektur IoT berbasis cloud untuk memonitor aritmia, salah satu jenis penyakit jantung yang umum ditemukan. Deteksi aritmia yang diusulkan adalah pengembangan algoritma deteksi aritmia berbasis Tsipuras et al, dengan menggunakan deteksi fitur R. Sistem yang diusulkan pada paper ini telah diuji menggunakan dataset MIT-BIH dan menghasilkan akurasi 93.11% terhadap 3 kelas aritmia, yaitu PAC, PVC dan VT. Menariknya, dengan penerapan IoT, efisiensi algoritma deteksi fitur R meningkat 30% dibanding yang diusulkan oleh Pan dan Tompkins. Terbukti dengan rendahnya waktu rata-rata eksekusi tiap sampel data, yaitu sekitar 0.00749 ms.
Study of Machine Learning Algorithm on Phonocardiogram Signals for Detecting of Coronary Artery Disease Satria Mandala; Miftah Pramudyo; Ardian Rizal; Maurice Fikry
Indonesia Journal on Computing (Indo-JC) Vol. 5 No. 3 (2020): December, 2020
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2020.5.3.536

Abstract

Several methods of detecting coronary artery disease (CAD) have been developed, but they are expensive and generally use an invasive catheterization method. This research provides a solution to this problem by developing an inexpensive and non-invasive digital stethoscope for detecting CAD. To prove the effectiveness of this device, twenty-one subjects consisting of 11 CAD patients and 10 healthy people from Hasan Sadikin Hospital Bandung were selected as validation test participants. In addition, auscultation was carried out at four different locations around their chests, such as the aorta, pulmonary, tricuspid, and mitral. Then the phonocardiogram data taken from the stethoscope were analyzed using machine learning. To obtain optimal detection accuracy, several types of kernels such as radial basis function kernel (RBF), polynomial kernel and linear kernel of Support Vector Machine (SVM) have been analyzed. The experimental results show that the linear kernel outperforms compared to others; it provides a detection accuracy around 66%. Followed by RBF is 56% and Polynomial is 46%. In addition, the observation of phonocardiogram signals around the aorta is highly correlated with CAD, giving an average detection accuracy for the kernel of 66%; followed by 44% tricuspid and 43% pulmonary.
Study of Denoising Method to Detect Valvular Heart Disease Using Phonocardiogram (PCG) Muhammad Yaumil Ihza Ihza; Satria Mandala; Miftah Pramudyo
Indonesia Journal on Computing (Indo-JC) Vol. 7 No. 1 (2022): April, 2022
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2022.7.1.610

Abstract

Heart sound is a very weak acoustic signal, very susceptible to external acoustic signals and electrical disturbances, especially friction caused by the subject's breathing or body movements. The heart sound signal will be recorded in a phonocardiogram (PCG) and produce heart sounds, noise, and extra sounds. The purpose of this work is to denoise the signal from the heart sounds recorded on the PCG and determine valvular heart disease (VHD). Several methods have been proposed for denoising heart sound signals, both in the time domain and in the frequency domain. Most of these methods still have problems for denoising results. In this paper, the techniques used to denoise the heart sound signal are Discrete Wavelet Transform (DWT), Short Term Fourier Transform (STFT), and Low-Pass filter.
Performance Analysis of PPG Signal Denoising Method Using DWT and EMD for Detection of PVC and AF Arrhytmias: Analisis Performansi Metode Denoising Sinyal PPG Menggunakan DWT dan EMD untuk deteksi Aritmia PVC dan AF Muhammad Aniq Wafa; Satria Mandala; Miftah Pramudyo
Indonesia Journal on Computing (Indo-JC) Vol. 7 No. 2 (2022): August, 2022
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2022.7.2.648

Abstract

In the cardiac arrhythmia detection system using a Photoplethysmography (PPG) sensor, noise is often found in the PPG signal due to internal and external factors in the signal retrieval process. So it is necessary to do a denoising process to remove noise before the signal is used. This study aims to test the Discrete wavelet transform (DWT) and Empirical Mode Decomposition (EMD) methods in removing noise from the PPG signal and to test the denoising signal on the Premature Arrhythmia Verticular Contractions (PVC) and Atrial Fibrillation (AF) detection systems. The parameters used to compare the performance of the denoising method are Mean Square Error (MSE), Signal to Noise Ratio (SNR), Accuracy, F1, Precision, and Recall. The method with the highest SNR, Accuracy, F1, Precision, and Recall values ​​and the lowest MSE values ​​is the best denoising method.
Study of Machine Learning Algorithm on Phonocardiogram Signals for Detecting of Coronary Artery Disease Mandala, Satria; Pramudyo, Miftah; Rizal, Ardian; Fikry, Maurice
Indonesian Journal on Computing (Indo-JC) Vol. 5 No. 3 (2020): December, 2020
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2020.5.3.536

Abstract

Several methods of detecting coronary artery disease (CAD) have been developed, but they are expensive and generally use an invasive catheterization method. This research provides a solution to this problem by developing an inexpensive and non-invasive digital stethoscope for detecting CAD. To prove the effectiveness of this device, twenty-one subjects consisting of 11 CAD patients and 10 healthy people from Hasan Sadikin Hospital Bandung were selected as validation test participants. In addition, auscultation was carried out at four different locations around their chests, such as the aorta, pulmonary, tricuspid, and mitral. Then the phonocardiogram data taken from the stethoscope were analyzed using machine learning. To obtain optimal detection accuracy, several types of kernels such as radial basis function kernel (RBF), polynomial kernel and linear kernel of Support Vector Machine (SVM) have been analyzed. The experimental results show that the linear kernel outperforms compared to others; it provides a detection accuracy around 66%. Followed by RBF is 56% and Polynomial is 46%. In addition, the observation of phonocardiogram signals around the aorta is highly correlated with CAD, giving an average detection accuracy for the kernel of 66%; followed by 44% tricuspid and 43% pulmonary.