Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Technologia: Jurnal Ilmiah RISTEC : Research in Information Systems and Technology
Rudy Sofian
Universitas Satu
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
KLASIFIKASI KERUSAKAN MESIN MOTOR MENGGUNAKAN 2D-CNN DENGAN FITUR MFCC DAN SPECTRAL CONTRAST Rudy Sofian; Heri Purwanto; Rikky Wisnu Nugraha; Ghanim Kanugrahan; Alamsyah Wirayudha Hidayat
Technologia : Jurnal Ilmiah Vol 17 No 2 (2026): Technologia (April)
Publisher : Universitas Islam Kalimantan Muhammad Arsyad Al Banjari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31602/tji.v17i2.22487

Abstract

Sepeda motor memiliki peran penting dalam mobilitas masyarakat, namun banyak pengguna yang belum mampu mengenali tanda-tanda awal kerusakan mesin, sehingga sering terjadi kesalahan diagnosis saat perawatan. Penelitian ini bertujuan untuk mengembangkan model klasifikasi kerusakan mesin sepeda motor menggunakan 2D Convolutional Neural Network (2D-CNN) dengan fitur ekstraksi Mel-Frequency Cepstral Coefficients (MFCC) dan Spectral Contrast. MFCC digunakan untuk merepresentasikan sinyal audio dalam bentuk dua dimensi, sedangkan Spectral Contrast menonjolkan perbedaan antara puncak dan lembah spektrum. Dataset terdiri atas rekaman suara mesin normal dan mesin dengan kerusakan pada timing chain, masing-masing lima sampel per label. Data melalui tahapan praproses, ekstraksi fitur, augmentasi, pelatihan, dan evaluasi. Hasil pelatihan awal menunjukkan adanya overfitting, dengan akurasi pelatihan mencapai 100% pada epoch ke-8, sementara akurasi validasi hanya sekitar 50%. Setelah dilakukan augmentasi data melalui penambahan noise, pitch shifting, dan time stretching hingga total data menjadi 20 sampel per label, kinerja model meningkat dengan akurasi pelatihan sebesar 94,73% dan hasil validasi yang lebih stabil. Secara keseluruhan, model yang diusulkan mencapai akurasi 75%, dengan kemampuan yang lebih baik dalam mengenali kerusakan timing chain dibandingkan kelas lainnya.
Implementation of Hybrid LSTM-Light GBM and XG Boost Algorithm for Stock Increase Prediction Rudy Sofian; Melly Diyani; Fahmi Reza Ferdiansyah; Heri Purwanto; Rikky Wisnu Nugraha
RISTEC : Research in Information Systems and Technology Vol. 6 No. 2 (2025): RISTEC: Research in Information Systems and Technology
Publisher : Institut Pendidikan Indonesia Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31980/3hjjvt46

Abstract

The advancement of machine learning, particularly in time-series analysis, has created significant opportunities for improving the accuracy of stock price prediction. However, the volatile nature of financial markets and the complexity of temporal patterns often hinder the ability of single models to deliver consistent and optimal results. To address these limitations, this study proposes a hybrid approach by integrating three popular algorithms—Long Short-Term Memory (LSTM), XGBoost, and LightGBM—through a stacking ensemble method. The dataset used consists of daily stock prices of Apple Inc. (AAPL) for the period 2014–2024, obtained from Yahoo Finance. The research process includes preprocessing, the construction of time-series datasets using windowing techniques, training of single models, and the application of ensemble stacking. Experimental results reveal that LSTM achieved the best performance among the single models, with a MAPE of 3.70% and R² of 0.9204, demonstrating its ability to capture long-term temporal dependencies. In contrast, XGBoost and LightGBM performed poorly in recognizing sequential patterns, resulting in negative R² values. The combination of all three models through stacking ensemble significantly improved prediction accuracy, achieving a MAPE of 2.57% and R² of 0.9693. These findings confirm that integrating LSTM, XGBoost, and LightGBM not only enhances predictive accuracy but also improves model stability, while contributing to the scientific development of hybrid machine learning methods in stock market analysis.
Co-Authors Alamsyah Wirayudha Hidayat Fahmi Reza Ferdiansyah Ghanim Kanugrahan Heri Purwanto Melly Diyani Rikky Wisnu Nugraha