Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Data Science and Its Applications

Classification of Electrocardiogram Signals using Principal Component Analysis and Levenberg Marquardt Backpropagation for Detection Ventricular Tachyarrhythmia Astrima Manik; Adiwijaya Adiwijaya; Dody Qori Utama
Journal of Data Science and Its Applications Vol 2 No 1 (2019): Journal of Data Science and Its Applications
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/jdsa.2019.2.12

Abstract

Abstract Ventricular Tachyarrhythmia (VT) are the primary arrhythmias which are cause of sudden death. For someone who already has symptoms of VT should immediately perform an examination of one of them by using an electrocardiogram (ECG). An electrocardiogram is a recording of the heart's electrical results in a waveform. However, limited ability in analysis and diagnosis of ECG reading is still difficult to do. Therefore, the classification of ECG signals is needed to detect a person, especially those with VT or not. In this research focuses on the classification of VT heartbeats from ECG signals by using median filter method in preprocessing, Principal Component Analysis (PCA) as feature extraction and modified Backpropagation (MBP) as classification. This research used machine learning method that is a neural network with backpropagation modification that is Levenberg Marquardt to speed up network training process. The best VT detection performance results were based on the average accuracy of the overall scheme of 91.67% with the best parameters that principal component=10 and 20, hidden neuron=4, and µ value=0.001 as well training time 1 seconds with a comparison of train data and test data that is 80:20 percent. Keywords: Electrocardiogram, Levenberg Marquardt Backpropagation, Median filter, Principal Component Analysis, and Ventricular Tachyarrhythmia
Snakebite Classification Using Active Contour Model and K Nearest Neighbor Chiara Janetra Cakravania; Dody Qori Utama
Journal of Data Science and Its Applications Vol 3 No 1 (2020): Journal of Data Science and Its Applications
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/jdsa.2020.3.38

Abstract

Indonesia is categorized as one of tropical countries that have a high risk of snakebites. This surely may endanger rural citizens’ lives for there are still many snakes found in rural areas. The main cause of death from snakebite cases is by reason of the venom squirted from snake’s canine teeth. Others causes are errors in identifying the bite marks visually. There are anatomical differences between puncture wounds from venomous and non-venomous snakes. This study established a snakebite identification system using Active Contour Model and K Nearest Neighbor (KNN) methods. By performing some tests related to the parameters used in the method, the highest accuracy value on K Nearest Neighbor method was obtained by using the correlation distance rule, the K value = 3, without using distance weight in the classification system.