Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal E-Komtek
Fatbayani
Unknown Affiliation
Computer Science & IT Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Daily Container Volume Throughput Forecasting at Container Terminal Using Long-Short Term Memory (LSTM) Recurrent Neural Network Kasanah, Yulinda Uswatun; Miftahol Arifin; Famila Dwi Winati; Fatbayani
Jurnal E-Komtek (Elektro-Komputer-Teknik) Vol 9 No 1 (2025)
Publisher : Politeknik Piksi Ganesha Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37339/e-komtek.v9i1.2214

Abstract

Container throughput is an important indicator for measuring the efficiency of a kontainer terminal. Kontainers that enter and exit are those transported to and from the terminal, respectively. Kontainers are stacked in the kontainer yard before they leave the terminal. Handling these kontainers accounts for a major workload at the terminal. Therefore, accurate short-term forecasting of daily kontainer gate-in and Gate-Out at a kontainer terminal is crucial for operational planning. While most forecasts are made at the strategic level of overall kontainer throughput, this study focuses on the daily kontainer gate-in and Gate-Out quantities with a case study at the TPKNM Makassar Kontainer Terminal. The study results show that the Epoch for each training set and performance metrics for each feature are 10, 50, and 100. Based on this, the difference in prediction performance with different epoch sizes is quite significant. The larger the Epoch, the smaller the MSE level.
Co-Authors Famila Dwi Winati Miftahol Arifin Yulinda Uswatun Kasanah