cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Rizki Wahyudi
Contact Email
rizki.key@gmail.com
Phone
+6281329125484
Journal Mail Official
jcse@icsejournal.com
Editorial Address
Perum Pasir Indah Blok K. No. 22, Pasir Lor, Kec. Karanglewas, Kabupaten Banyumas, Jawa Tengah 53161, Indonesia
Location
Unknown,
Unknown
INDONESIA
Journal of Computer Science and Engineering (JCSE)
Published by Institute of Computer Science and Engineering
ISSN : -     EISSN : 27210251     DOI : https://doi.org/10.36596/jcse
Core Subject : Science,
Computer Science & IT
Computer Architecture, Processor design, operating systems, high-performance computing, parallel processing, computer networks, embedded systems, theory of computation, design and analysis of algorithms, data structures and database systems, theory of computation, design and analysis of algorithms, data structures and database systems, artificial intelligence, machine learning, data science, Information System
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 4 Documents
 1 
Search results for , issue "Vol 6, No 2: August (2025)" : 4 Documents clear
Comparative Analysis of Parameter-Efficient-Fine-Tuning and Full Fine-Tuning Approaches for Indonesian Dialogue Summarization using mBART Aji, Ananda Bayu; Purnamasari, Detty
Journal of Computer Science and Engineering (JCSE) Vol 6, No 2: August (2025)
Publisher : ICSE (Institute of Computer Sciences and Engineering)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study addresses the urgent need for efficient Indonesian dialogue summarization systems in remote working contexts by adapting the multilingual mBART-large-50 model. The DialogSum dataset was translated into Indonesian using Opus-MT, and two fine-tuning approaches—full fine-tuning and Parameter-Efficient Fine-Tuning (PEFT) with LoRA—were evaluated. Experiments on 1,500 test samples revealed that full fine-tuning achieved superior performance (ROUGE-1: 0.3726), while PEFT reduced energy consumption by 68.7% with a moderate accuracy trade-off (ROUGE-1: 0.2899). A Gradio-based interface demonstrated practical utility, enabling direct comparison of baseline, fine-tuned, and PEFT models. Critical findings include translation-induced terminology inconsistencies (e.g., "Hebes" vs. "Hebei") and context retention challenges in long dialogues. This work contributes a scalable framework for low-resource language NLP and provides actionable insights for optimizing computational efficiency in real-world applications.This study addresses the urgent need for efficient Indonesian dialogue summarization systems in remote working contexts by adapting the multilingual mBART-large-50 model. The DialogSum dataset was translated into Indonesian using Opus-MT, and two fine-tuning approaches, full fine-tuning and Parameter-Efficient Fine-Tuning (PEFT) with LoRA, were evaluated. Experiments on 1,500 test samples revealed that full fine-tuning achieved superior performance (ROUGE-1: 0.3726), while PEFT reduced energy consumption by 68.7% with a moderate accuracy trade-off (ROUGE-1: 0.2899). A Gradio-based interface demonstrated practical utility, enabling direct comparison of baseline, fine-tuned, and PEFT models. Critical findings include translation-induced terminology inconsistencies (e.g., "Hebes" vs. "Hebei") and context retention challenges in long dialogues. This work contributes a scalable framework for low-resource language NLP and provides actionable insights for optimizing computational efficiency in real-world applications.
Hyperband‑Optimized LightGBM and Ensemble Learning for Web Phishing Detection with SHAP‑Based Interpretability Wahyudi, Rizki
Journal of Computer Science and Engineering (JCSE) Vol 6, No 2: August (2025)
Publisher : ICSE (Institute of Computer Sciences and Engineering)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study evaluates the performance of three tree boosting algorithms, Random Forest (RF), XGBoost (XGB), and LightGBM (LGBM), in detecting phishing websites using a phishing dataset based on HTML, URLs, and network features. Two hyperparameter optimization strategies were tested: Hyperband search (HalvingRandomSearchCV) and stacking ensemble combining all three models. The evaluation was conducted based on five main metrics: accuracy, precision, recall, F1-score, and AUC‑ROC. The results indicate that LightGBM tuned via Hyperband achieved the highest performance (accuracy 0.9724; AUC‑ROC 0.9702), followed by ensemble tuned (accuracy 0.9697; AUC‑ROC 0.9684). SHAP analysis was used to interpret the contribution of key features in predicting phishing websites. The AUC‑ROC difference of 0.0034 points from the XGBoost baseline (0.9668) confirms the effectiveness of Hyperband tuning and stacking ensembles for phishing detection
Statistical Analysis of Adaptive Thresholding Algorithms for Denoising Signature Images Choudhury, Ruhiteswar; Deb Roy, Tanusree
Journal of Computer Science and Engineering (JCSE) Vol 6, No 2: August (2025)
Publisher : ICSE (Institute of Computer Sciences and Engineering)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study explores the efficacy of adaptive thresholding techniques in denoising signature images captured under varying lighting conditions. Signature images from multiple individuals were obtained in different illumination scenarios, and three prominent adaptive thresholding algorithms, namely histogram thresholding, Otsu’s method, and the Gaussian Mixture Model (GMM), were applied to the noisy images. The performance of each technique was rigorously evaluated using root mean square error (RMSE) and correlation coefficient metrics. The findings reveal that the Gaussian Mixture Model significantly outperformed both histogram thresholding and Otsu’s method, achieving superior noise reduction and better preservation of essential information. This was evidenced by lower RMSE values and higher correlation coefficients. These results suggest that the Gaussian Mixture Model is a highly effective technique for denoising signature images, particularly under varying lighting conditions. Its superior performance underscores its potential as a robust tool for enhancing the clarity and accuracy of signature verification systems. This study provides valuable insights into the application of adaptive thresholding techniques in image processing, highlighting the advantages of the Gaussian Mixture Model over traditional methods. The implications of this research are substantial for fields that rely on precise signature recognition and verification, such as banking, legal documentation, and security systems. This study specifically focuses on signature segmentation as a preprocessing step for signature verification systems. It does not directly address full document verification but aims to improve segmentation accuracy under varying lighting conditions, which is a foundational component in document authentication pipelines.    
Monte Carlo Simulation Application for Meteorological Parameter Prediction Rizqi, Muhammad Nur; Sugiarto, Cahya; Afifah, Ghaitsa
Journal of Computer Science and Engineering (JCSE) Vol 6, No 2: August (2025)
Publisher : ICSE (Institute of Computer Sciences and Engineering)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Rainfall in Indonesia, particularly in southern coastal regions such as Cilacap Regency, is strongly influenced by the interaction of multiple meteorological variables. This study aims to predict monthly meteorological parameters consisting of rainfall, air temperature, wind speed, humidity, and solar radiation intensity using the Monte Carlo simulation method based on historical data from 2022 to 2024 obtained from the Tunggul Wulung Cilacap Class III Meteorological Station. The simulation process involved probability distribution fitting and random number generation for 10,000 iterations for each parameter. Model performance was evaluated using the Mean Absolute Percentage Error (MAPE). The results show that air temperature and humidity achieved the highest predictive accuracy, with MAPE values of 4.04 percent and 3.18 percent. These values indicate high model consistency. Solar radiation intensity and wind speed produced moderate accuracy with MAPE values of 38.83 percent and 44.44 percent. In contrast, rainfall exhibited low predictive performance with a MAPE of 53.13 percent. This low performance is primarily caused by high temporal variability and limited data length. The findings demonstrate that Monte Carlo simulation is effective for predicting meteorological variables with stable patterns but less suitable for parameters with extreme fluctuations such as rainfall 

Page 1 of 1 | Total Record : 4

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 6, No 2: August (2025) Vol 6, No 1: February (2025) Vol 5, No 2: August (2024) Vol 5, No 1: February (2024) Vol 4, No 2: August (2023) Vol 4, No 1: February (2023) Vol 3, No 2: August (2022) Vol 3, No 1: February (2022) Vol 2, No 2: August (2021) Vol 2, No 1: February (2021) Vol 1, No 2: August (2020) Vol 1, No 1: February (2020) More Issue