Claim Missing Document
Check
Articles

Pengembangan Model Deep Learning LSTM dan CNN untuk Peramalan Penjualan Sepeda Motor di Indonesia Yohanes Anton Nugroho; Hotma Antoni Hutahaean
Jupiter: Publikasi Ilmu Keteknikan Industri, Teknik Elektro dan Informatika Vol. 3 No. 2 (2025): Maret: Publikasi Ilmu Keteknikan Industri, Teknik Elektro dan Informatika
Publisher : Asosiasi Riset Ilmu Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/jupiter.v3i2.795

Abstract

Accurate sales forecasting is essential for stakeholders to make strategic decisions. This study aims to compare the performance of two deep learning models, namely Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), in forecasting domestic motorcycle sales produced by AISI member manufacturers. The forecast is based on historical data from January 2021 to December 2024. The model was trained using time series data and the forecasting results for the period January to March 2025 were evaluated using the metrics Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results show that the LSTM model produces lower MAE and MAPE values than CNN, which shows its superiority in providing more accurate and consistent predictions. On the other hand, the CNN model has lower RMSE and MSE values, thus being able to reduce large prediction errors. By comparing the results of LSTM, CNN, and actual data forecasting, the LSTM model is more suitable for forecasting motorcycle sales in Indonesia
Re-Layout Tata Letak Bagian Percetakan Menggunakan Calullar Manufacturing System Yohanes Anton Nugroho
Jurnal Penelitian Rumpun Ilmu Teknik Vol. 1 No. 4 (2022): November : Jurnal Penelitian Rumpun Ilmu Teknik
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1595.868 KB) | DOI: 10.55606/juprit.v1i4.613

Abstract

Material handling in the production division of publisher X encountered several obstacles, including the transfer of material between production processes having cross-movement flows. This condition occurs as a result of an irregular engine layout. The impact of the conditions in the transfer of material in the production process is the distance of the transfer to be 968.6 m/day. This condition causes some machines to be repositioned, so that material transfer can run faster and more efficiently. One of the efforts to reduce material transfer is to re-plan the placement of production facilities by adopting the concept of a cellular manufacturing system or cellular manufacturing system that is feasible to be applied to the production process of publisher X. The cellular manufacturing system was chosen because it is in accordance with the number of characteristics of the publishing industry that requires the ability to anticipate changes. This rapid demand suits a particular market. This article describes how the results of rearranging and minimizing the distance of moving raw materials in the production section of publisher X by adopting the concept of a cellular manufacturing system and rearranging the layout of production facilities by using sorting using Sorting Algorithms. The selection of the Sorting Algorithms is based on consideration of the order of the output which is not coherent, so it needs to be sorted. Efficient sorting is needed to determine the part-machine incidence matrix which is then used in the development of cellular manufacturing systems. Program development on Visual Studio 2012 software shows the results of facility layout planning by grouping 20 machines and 11 products with this layout change, the total material handling distance is reduced by 371.8 m or by 61.61%