Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal G-Tech : Jurnal Teknologi Terapan
Mochamad Imamudin
Universitas Islam Negeri Maulana Malik Ibrahim Malang, Indonesia
Computer Science & IT Decision Sciences, Operations Research & Management Energy Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Impact of Preprocessing on Indonesian Extractive Summarization Using LexRank, TextRank, DivRank, and Cosine Similarity Andri Setiawan; Zainal Abidin; Mochamad Imamudin
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.8306

Abstract

Extractive text summarization is a fundamental approach to tackle information overload, yet its quality is highly dependent on the pre-processing stage. Despite its crucial role, there is no consensus on the most optimal pre-processing scenario for the Indonesian language, which has a complex morphological structure. This study aims to fill this research gap by systematically analyzing the impact of seven pre-processing scenarios on four summarization methods: three graph-based methods (LexRank, TextRank, DivRank) and one topic-relevance method (Cosine Similarity against the title). Using a corpus of 3,000 Indonesian news articles and ROUGE evaluation metrics, the results show two key findings. First, the Cosine Similarity method significantly outperforms all graph-based methods, achieving the highest F1-Measure scores on ROUGE-1 (0.5073), ROUGE-2 (0.4018), and ROUGE-L (0.4574), which emphasizes the important role of the title in news texts. Second, a comprehensive pre-processing scenario involving Case Folding, Punctuation Removal, Tokenization, Normalization, Negation Handling, Stopword Removal and Stemming proves to be the most effective in improving the performance of all algorithms. These findings provide empirical evidence and practical recommendations that the combination of a title-relevancy approach with proper text normalization is the most effective strategy for optimizing extractive text summarization for the Indonesian language.
Probabilistic Forecasting of M≥5.0 Earthquakes in East Java: A 30-Day LSTM Approach Using Seismic Feature Data Nanang Yulianto; Totok Chamidy; Mochamad Imamudin; Suhartono Suhartono; Muhammad Ainul Yaqin
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9504

Abstract

East Java is a seismically active region where short-term earthquake forecasting remains a critical yet challenging endeavor. While deterministic prediction is inherently unfeasible, probabilistic modeling offers a practical pathway for risk mitigation. This study develops a 30-day forward-window probabilistic forecasting model for M≥5.0 earthquakes in East Java using a Long Short-Term Memory (LSTM) network framed as a binary classification task. The model is trained on 25 years of seismic data (2001–2025) from BMKG Stasiun Geofisika Pasuruan. Twenty-five seismic features were rigorously selected through correlation analysis and data-leakage prevention protocols, while class imbalance was mitigated using adaptive loss weighting. The LSTM architecture was systematically optimized via sequential hyperparameter tuning and robust validation strategies. On a hold-out test set, the model achieved an AUC-ROC of 0.752, F1-score of 0.484, and recall of 0.673, indicating the model's capacity to detect impending seismic events with reasonable sensitivity. These results confirm that deep learning can effectively capture non-linear temporal patterns in seismic sequences. The primary contribution of this work is a validated, operationally ready probabilistic forecasting framework that can be integrated into regional earthquake monitoring systems, providing actionable lead time for disaster preparedness in East Java.
Integrating Boolean Logic-Based Feature Representation and Artificial Neural Networks for Digital Divide Level Classification in Online Learning Imalatul Hidayah; Ririen Kusumawati; Mochamad Imamudin; Zainal Abidin
G-Tech: Jurnal Teknologi Terapan Vol 10 No 3 (2026): G-Tech, Vol. 10 No. 3 July 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i3.10060

Abstract

Digital divide remains a major challenge in online learning, affecting students’ ability to access and benefit from digital education. While previous studies have primarily focused on first-level digital divide factors or employed machine learning models using raw input variables, limited research has explored the integration of logical feature engineering and artificial intelligence to model the multidimensional nature of digital divide. This study proposes a hybrid classification framework that combines Boolean Logic-based feature engineering and Artificial Neural Networks (ANN) for digital divide classification in online learning. The proposed framework utilizes four variables, namely Primary Device, Internet Stability, Equity Score, and Accessibility Score. Boolean Logic operations (AND, OR, and XOR) were applied to generate additional logical representations of digital access conditions before the ANN classification process. Data were collected from 324 student respondents participating in online learning. The model was evaluated using accuracy, precision, recall, and F1-score metrics. Experimental results demonstrate that the optimized ANN model achieved 93% accuracy, 93% weighted precision, 93% weighted recall, and 93% weighted F1-score. Comparative analysis revealed that Boolean Logic features contributed additional logical representations of digital access patterns, although their impact on predictive performance was not consistently significant. The findings highlight that digital divide should be viewed as a multidimensional phenomenon and demonstrate the potential of ANN based predictive modeling to support data-driven digital inclusion strategies in education.
Comparison of Boolean OR, AND, and OR–AND Models for Monthly Rainfall Classification in Bawean Island Rudi Kasianto; Zainal Abidin; Totok Chamidy; Mochamad Imamudin
G-Tech: Jurnal Teknologi Terapan Vol 10 No 3 (2026): G-Tech, Vol. 10 No. 3 July 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i3.10298

Abstract

Rainfall classification plays an important role in climate monitoring, water resource management, agricultural planning, and hydrometeorological disaster mitigation. While machine learning techniques have been widely used for rainfall classification, they often require substantial computational resources and complex training processes. This study proposes a simple, interpretable, and computationally efficient Boolean-based framework for monthly rainfall classification on Bawean Island, East Java, Indonesia. Monthly climatological data from 1972–2023, including rainfall, rainy days, mean temperature, and minimum temperature, were analyzed, yielding 624 observations. Rainfall was classified into three categories: low (<100 mm), moderate (100–299 mm), and high (≥300 mm). Rainy days were converted into ordinal scores, while mean and minimum temperatures were transformed into binary scores. Three Boolean-based rainfall classification models were developed and evaluated using confusion matrices, accuracy, precision, recall, and F1-score. Correlation analysis showed that rainy days had the strongest relationship with rainfall (r = 0.858), followed by minimum temperature (r = −0.592) and mean temperature (r = −0.463). The hybrid OR–AND model achieved the best overall performance, with 66% accuracy, 71% precision, 62% recall, and 61% F1-score, outperforming both the OR and AND models. These results demonstrate that the proposed Boolean-based framework provides an effective, transparent, and computationally efficient approach for monthly rainfall classification.
Co-Authors Ainul Yaqin Andri Setiawan Imalatul Hidayah Nanang Yulianto Ririen Kusumawati Rudi Kasianto Suhartono Suhartono Totok Chamidy Zainal Abidin