Claim Missing Document
Check
Articles

Found 2 Documents
Search

Evaluasi Sistem Proteksi dan Koordinasi Relai Arus lebih Gedung Mall XYZ Menggunakan ETAP 19.0.1 Fuad Djauhari; Idris Kusuma; Endang Retno Nugroho
Jurnal Ilmiah Giga Vol 25, No 2 (2022): Volume 25 Edisi 2 Tahun 2022
Publisher : Universitas Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47313/jig.v25i2.1915

Abstract

Large buildings require optimal electrical protection. Short-circuit events are the most common occurrences. If there is a short-circuit fault on one of the feeders, the circuit breaker whose position is upstream from the fault center must work ahead of the circuit breaker whose position is upstream from the short-circuit fault center. The problem that occurs in the XYZ Mall Building is the opposite. When there is a short circuit current, it will cut off the main connector. As a result, some of the building's electricity will also go out. The purpose of this study is to regulate the coordination of relay protection repeatedly in this building. The study will evaluate the existing electrical Single Line Diagram of the XYZ Mall Building and perform simulations with the help of ETAP 19.0.1 software. The simulation results get the value of the protection system that has been adjusted where the curves of each relay do not intersect with each other so that the coordination of each relay is safe, with the standard time delay setting of 0.2 to 0.4 seconds. To overcome the problem in the XYZ Mall building, the relay that is not suitable must be set manually according to the simulation results to prevent tripping some of the buildings in the event of a short circuit fault.
IDENTIFIKASI KELAINAN JANTUNG DARI DATA EKG MENGGUNAKAN BACKPROPAGATION NEURAL NETWORK Sumiati Sumiati; Haris Triono Sigit; Wahyudin Nor Achmad; Idris Kusuma
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 8 No. 2 (2025): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v8i2.3937

Abstract

This study is one of the initial approaches in implementing Backpropagation Neural Network for ECG signal classification. The condition of the human heart can be known based on the results of electrocardiogram medical records, so that with the results of electrocardiogram medical records it can be known whether the heart is normal or abnormal. Symptoms of abnormal heart disease in the heart often come suddenly. Early recognition of heart disease with further procedures and treatment can prevent an increase in the risk of fatal heart attacks. This study has a very important goal in an effort to detect and classify heart abnormalities more efficiently. By utilizing artificial neural networks (ANN) and backpropagation methods, it can utilize computing capabilities to analyze patterns in electrocardiogram (ECG) data. The results show that the classification of heart abnormalities with an epoch value of 2000, a learning rate of 0.01 with normal and abnormal targets, obtained the number of Hidden Neurons as many as 25, the number of weight patterns 44 and a mean squared error (MSE) value of with an accuracy of 0.61364 from 25 inputs.