cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ismail Puji Saputra
Contact Email
ismailpujisaputra@gmail.com
Phone
+6281379119607
Journal Mail Official
ismailpujisaputra@gmail.com
Editorial Address
Jl. Cut Nyak Dien 15 B Barat, Metro, Provinsi Lampung, 34111
Location
Unknown,
Unknown
INDONESIA
Bulletin of Network Engineer and Informatics (BUFNETS)
Published by GWEX NET PUBLISHER
ISSN : 29874858     EISSN : 29868017     DOI : https://doi.org/10.59688/bufnets
Core Subject : Science,
Computer Science & IT
The Journal invites original articles and is not simultaneously submitted to another journal or conference. Scopes: Information Technology: Software Engineering, Knowledge and Data Mining, Multimedia Technologies, Mobile Computing, Parallel/Distributed Computing, Computer Graphics, Virtual Reality, Data and Cyber Security. Computer Network: Management and Protocol Network, Telecommunication Systems, Wireless Communications, Fuzzy Sensor and Network, Internet of Things, Data Communication and Networking.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 95 Documents
 6   7   8   9   10 
AURA: ADAPTIVE UI RECOVERY ARCHITECTURE FOR ANDROID TEST AUTOMATION M Ilham Yusuf Gumai; Suhendro Yusuf Irianto; RZ Abdul Aziz; Rahmalia Syahputri
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/738290

Abstract

User interface (UI) test automation on Android frequently breaks when developers rename element attributes during refactoring, rendering previously valid locators unresolvable and imposing significant maintenance overhead. Existing self-healing approaches predominantly target web DOM and lack post-action validation, risking false healing where a wrong element is silently accepted. This study introduces AURA, a runtime self-healing layer for Appium-WebdriverIO that chains five deterministic recovery strategies, a widget-family post-action validator, and an optional machine-learning reranker. A controlled benchmark comprising 490 refactoring scenarios across five synthetic Android applications and six mutator types demonstrates that AURA achieves a 99.39% correct action rate with only 0.61% false-healing rate, significantly outperforming the adapted Similo baseline (95.71% / 4.29%) at p < 0.0001 (McNemar exact test). External validation on six production Google Android applications (130 scenarios) confirms a 100% correct rate with a bounds-IoU enhanced validator. Cache learning reduces per-find latency by 95.1% from the second session onward.
Evaluating the Limitations of English Lexicon-Based Sentiment Analysis for Indonesian E-Wallet Reviews: A Comparison of VADER and Indonesian RoBERTa Imam asrowardi; Septafiansyah Dwi Putra; Nadia Nabiha Dziqra
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/738289

Abstract

Sentiment analysis of mobile application reviews supports service evaluation in the fast-growing Indonesian digital finance sector. This study compared an English lexicon-based method (VADER) with a fine-tuned Indonesian RoBERTa model on 1,000 reviews of the DANA e-wallet application collected from Google Play. Following best practice for transformer models, reviews were classified primarily from their original (raw) text, and a preprocessed variant was used to assess the effect of text cleaning. On raw text, VADER labelled 903 reviews as neutral, 78 as positive, and 19 as negative, whereas Indonesian RoBERTa produced 494 positive, 385 negative, and 121 neutral, a positive-leaning distribution consistent with the sample's mean rating of 4.06. Inter-method agreement was negligible (Cohen's kappa = 0.008). Removing stopwords and numbers before classification changed 30.2% of the RoBERTa labels and flattened its distribution, confirming that such preprocessing degrades the contextual input transformers rely on, while leaving VADER almost unchanged. Because no human-annotated gold standard was used, the reported figures reflect inter-method agreement rather than absolute accuracy against human labels. The findings show that VADER is unsuitable for Indonesian reviews and that language-specific transformers should be applied to unprocessed text.
SONG POPULARITY PREDICTION ON THE SPOTIFY PLATFORM USING MULTIPLE LINEAR REGRESSION WITH MIN-MAX NORMALIZATION Rismaria Sipayung; Mutaqin Akbar
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/738832

Abstract

This study critically investigates whether three commonly used audio-level features of a song, duration, tempo, and energy, are by themselves, statistically capable of predicting song popularity on the Spotify platform. Using a multiple linear regression model estimated via Ordinary Least Squares (OLS) on 849 songs retrieved from Kaggle 'Spotify Tracks Dataset', a publicly available collection spanning multiple genres and release periods, filtered to exclude duplicate records and songs with a popularity score of zero, we show that this is not the case. Prior to modeling, Min-Max normalization was applied to standardize variable scales. The model yields the equation Y = 42.4073 + (-5.2462)*X1 + (1.0306)*X2 + (-4.1247)*X3, but the overall F-test is not significant (F = 1.1789, less than F-table = 2.6154, p = 0.3167), and none of the three predictors reach individual significance (all |t| less than 1.53, p greater than 0.12). Pairwise correlations between each predictor and popularity are negligible (r = -0.037 for duration, r = -0.006 for tempo, r = -0.053 for energy), confirming that the linear structure captures essentially no signal in this dataset. We conclude that duration, tempo, and energy have effectively zero standalone predictive capability for Spotify popularity, and that normalization, while statistically inert with respect to R^2 and RMSE, remains necessary for producing comparable, interpretable coefficients. As a secondary, practical contribution, the analysis pipeline was deployed as an interactive web application (SpotiPredict, built with Python Flask) that exposes the full normalization and regression computation transparently to the user.
LINEAR INTERPOLATION AS A BASELINE TOOL FOR ONLINE RIDE-HAILING FARE ESTIMATION DURING PEAK HOURS Prima Yalesta Sarumaha; Mutaqin Akbar
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/738830

Abstract

The dynamic pricing system on Grab causes frequent fare fluctuations, complicating travel budget planning. This study analyzesGrabBikeReguler fare patterns from Campus 3 of Universitas Mercu Buana Yogyakarta (UMBY) to Mirota Kampus Babarsari. It implements linear interpolation as a lightweight numerical baseline for rough estimation, rather than a robust predictive model. Primary data were collected through direct observation over seven days at 15-minute intervals during morning (07:00–09:00 WIB), noon (12:00–13:00 WIB), and evening (16:00–19:00 WIB) peak periods, noting rainy and non-rainy conditions. This method was deployed via a Python-Flask web application. Results indicate the morning fare stabilizes at IDR 12,000 after a peak of IDR 14,500, while the noon fare remains constant at IDR 12,000. The evening period shows the highest volatility, peaking at IDR 14,342 (17:30 WIB, non-rainy) and IDR 21,250 (18:45 WIB, rainy). Accuracy evaluation across 21 paired data points from morning and evening sessions yielded MAE = IDR 1,047.62, MSE = 4,117,767.24, and RMSE = IDR 2,029.23, representing an 8.7% average error relative to the IDR 12,000 base fare. This margin confirms linear interpolation serves only as a rough baseline reference tool, not a reliable predictive model.
A DIGITALIZATION MODEL FOR NEW STUDENT ADMISSION SERVICES THROUGH A WEB-BASED INFORMATION SYSTEM IN PRIMARY SCHOOLS Arif Rahman; Arabiatul Adawiyah; Surahmat surahmat; Delta Khairunnisa; Rahul Sabilillah; Panisah Panisah; Zalsabila Herawaty
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/738299

Abstract

Digital transformation in education has encouraged schools to modernize administrative services, including new student admissions. However, many primary schools still rely on manual registration processes that often lead to inefficiencies, data inaccuracies, and limited access to information. This study aims to develop a digitalization model for new student admission services through a web-based information system in primary schools. A qualitative case study was conducted at SD Islam Al-Asri Palembang using observation, semi-structured interviews, and documentation techniques. The study employed a prototype-based development approach to analyze existing admission processes and formulate a digitalization model that integrates registration, data management, verification, and reporting services. Model validation was carried out through practitioner review involving the school principal, administrative staff, and IT personnel, using three evaluation parameters: model practicality, completeness of the five service components, and contextual applicability within the primary school setting. The results show that the proposed model consists of five key components: digital registration, data validation, document management, admission status notification, and reporting services. The model simplifies administrative workflows, improves data accuracy, accelerates the admission process, and enhances transparency and accessibility for both parents and school administrators. The study concludes that the proposed digitalization model can support the modernization of primary school admission services and serve as a replicable reference for schools seeking to implement digital transformation in educational administration.
Implementation of E-Monitoring Development and Sales Reports As A Support For Digitalization Of Pt. Amelia Putratama Mandiri's Business Processes Lailatur Rahmi; Robinson Robinson; Ade Sukma Wati
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/738300

Abstract

Digitalization has become a strategic necessity for improving company efficiency and competitiveness. PT. Amelia Putratama Mandiri, a cement company, faces crucial challenges such as delayed sales reporting, limited real-time operational monitoring, and a high reliance on manual processes. These challenges pose a risk of information delays and recording errors, which impact business decision-making. This research aims to develop and implement an integrated e-monitoring and sales reporting system to support the digitalization of the company's business processes. This system is designed to improve transparency, speed data access, and reporting accuracy, while also facilitating real-time monitoring of operational and sales activities. The development method used is Agile Development, which emphasizes an iterative and collaborative approach between the development team and users. Development is carried out through several sprint stages, starting from needs identification, interface design, system development, and testing and implementation. This approach allows the system to be flexibly developed according to field needs and continuous user input. The implementation results show that the developed e-monitoring and sales reporting system successfully integrated sales and monitoring processes into a single web-based platform. User testing indicated that the system improved reporting accuracy, accelerated information access, and enhanced operational monitoring efficiency at PT. Amelia Putratama Mandiri.
MULTI-TENANT ACCREDITATION SIMULATION PLATFORM WITH HRBAC, FEDERATED INSTRUMENT BANK, AND LLM-ASSISTED FORM REVIEW Muhammad Reza Redo Islami Islami; Dewi Kania Widyawati Widyawati; Rima Maulini Maulini; Tri Sandhika Jaya Sandhika Jaya; Akhmad Jayadi Jayadi; Ahmad Rofi'i Rofi'i; Kurniawan Saputra Saputra
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/738301

Abstract

The accreditation preparation process for study programs in Indonesian higher education remains largely manual, making it prone to data inconsistencies and absent audit trails. Existing information systems are generally single-tenant and do not support complex access hierarchies. In this study, we design, implement, and evaluate a multi-tenant web-based accreditation preparation simulation platform using an SDLC cycle. The platform introduces four novelty layers: (1) a multi-tenant architecture with triple-layer data isolation; (2) a four-level-scope Hierarchical Role-Based Access Control (HRBAC); (3) a centralized instrument bank for distributing accreditation instrument templates; and (4) LLM-assisted form content checking. We evaluate the platform through PHPUnit functional testing (207 test methods, 23 files) on a GitHub Actions pipeline and a System Usability Scale (SUS) study with 15 respondents from six user roles. All 207 tests passed (100%) and the mean SUS score was 83.3 (Excellent category, formative reading given n = 15). We state upfront that the LLM-assisted review is currently validated at the functional and infrastructure level only; its accuracy against accreditation rubrics has not yet been evaluated and is staged as follow-up work. Within that boundary, the combination of all four novelty layers has not been reported in any previously published accreditation system research.
Design of a Hybrid SVM Ensemble and Large Language Model Chatbot for Multi-Class Intent Classification in Clinic Information Services Vina Rahmadiany; Lindawati Lindawati; Aryanti Aryanti
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/a3kdjj55

Abstract

Clinical information service chatbots require an accurate multiclass intent classification mechanism to handle informal language variations, medical abbreviations, service-related inquiries, and health complaints in Indonesian. This study aims to develop a hybrid chatbot architecture that integrates a Support Vector Machine ensemble for intent classification with Meta-Llama-3.1-8B-Instruct to generate relevant, natural, and context-aware responses. The dataset consisted of 3,293 utterance patterns across 66 intent classes. The proposed approach employed an 80:20 stratified split; semantic augmentation on the training data; preprocessing via abbreviation normalization, stopword removal, and Sastrawi stemming; TF-IDF feature extraction using unigram and bigram word n-grams and character n-grams; chi-squared feature selection; and hyperparameter optimization via grid search. The classification model was constructed by combining three calibrated LinearSVC classifiers via probability-based soft voting. Experimental results achieved an accuracy of 89.83%, a weighted F1-score of 89.90%, a kappa of 0.8966, a macro AUC of 0.9942, and an average response time of 61.87 ms. McNemar's test indicated statistically significant improvements over Complement Naïve Bayes, Logistic Regression, and Decision Tree, while no significant difference was observed compared with Single SVM. Therefore, the proposed architecture is effective at supporting multiclass intent classification and delivering fast, relevant chatbot responses for clinical information services.
Development and Performance Evaluation of an Embedded Magnetic Field Measurement System for River Sediment Monitoring Megastin Massang Lumembang; Ferdy Ferdy; Berton M. Siahaan; Jorjie Abigael Sumanti; Geraldy J. C Pilat; Giovanny Paeh; Brian B. Mambu
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/q1xmy902

Abstract

River sediment monitoring plays an important role in environmental and geophysical investigations, yet conventional magnetic characterization generally relies on laboratory-based instruments that are expensive, non-portable, and unsuitable for rapid field measurements. This study aimed to develop and evaluate an embedded magnetic field measurement system for river sediment monitoring using an HMC5883L magnetic sensor integrated with an Arduino Uno microcontroller. The developed system underwent performance evaluation under controlled laboratory conditions using a solenoid-generated magnetic field before being applied to river sediment samples collected from three different sampling locations. The performance evaluation was conducted at measurement distances of 1–7 cm, with three repeated measurements at each distance. The measured Z-axis magnetic field response decreased from 13.56 µT at 1 cm to -0.33 µT at 7 cm, and linear regression analysis yielded a coefficient of determination of R2 = 0.9632, indicating a consistent distance-dependent response within the evaluated range. The average magnetic field responses of the river sediment samples ranged from 54.5 µT to 245.6 µT across the three sampling locations, with a maximum difference of 197.7 µT. The developed embedded system provides a compact, portable, and low-cost platform for preliminary comparative assessment of magnetic field responses in river sediments. The measured values represent the sensor response obtained under the established experimental configuration and may include contributions from ambient magnetic fields; therefore, they should not be interpreted as direct measurements of the intrinsic magnetic properties or magnetic susceptibility of the sediment. The proposed system is intended for preliminary field screening and comparative magnetic response assessment, while quantitative characterization of magnetic minerals requires conventional laboratory-based magnetic measurement techniques
COMPARISON OF BAYESIAN MARKOV CHAIN MONTE CARLO AND MACHINE LEARNING ALGORITHMS FOR STUDENT CUMULATIVE GRADE POINT AVERAGE PREDICTION WITH FEATURE ENGINEERING Husni Hidayat Malik; Indra Surya Permana; Alva Hendi Muhammad; Kusnawi Kusnawi
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/vfk6qw80

Abstract

Prediksi Indeks Prestasi Kumulatif (IPK) merupakan salah satu tantangan penting dalam manajemen akademik perguruan tinggi. Penelitian ini mengusulkan penerapan algoritma Markov Chain Monte Carlo (MCMC) berbasis inferensi Bayesian untuk memprediksi IPK mahasiswa berdasarkan Indeks Prestasi Semester (IPS) 1-8, dilengkapi dengan tiga fitur rekayasa: rata-rata IPS, variabilitas IPS (standar deviasi), dan tren IPS. Keunggulan utama pendekatan Bayesian adalah kemampuannya menghasilkan kuantifikasi ketidakpastian (uncertainty quantification) berupa interval kepercayaan 95% untuk setiap prediksi, yang tidak dapat dilakukan metode machine learning konvensional. Model MCMC dibandingkan secara komprehensif dengan tujuh algoritma machine learning: Random Forest, XGBoost, Gradient Boosting, SVM, KNN, AdaBoost, dan Bagging, menggunakan dataset 543 mahasiswa dari Institut Teknologi dan Kesehatan Mahardika periode 2017-2021. Evaluasi dilakukan melalui train-test split (80:20) dan 5-fold cross-validation menggunakan metrik RMSE, MAE, MAPE, dan R². Hasil pada data testing menunjukkan MCMC Bayesian memperoleh RMSE 0.0792 dan R² 0.867, berada pada peringkat kedua setelah Gradient Boosting. Namun pada evaluasi cross-validation yang lebih robust, MCMC Bayesian unggul dengan RMSE terendah 0.0832±0.0162 dan R² tertinggi 0.848. Temuan ini menunjukkan MCMC Bayesian tidak hanya kompetitif dari sisi akurasi, tetapi juga memberikan nilai tambah unik berupa estimasi ketidakpastian prediksi yang sangat berguna untuk sistem peringatan dini akademik.   Predicting Cumulative Achievement Index (GPA) is a key challenge in higher education academic management. This study proposes the application of Markov Chain Monte Carlo (MCMC) Bayesian inference for predicting student GPA based on Semester Achievement Index (IPS) from semesters 1-8, enriched with three engineered features: IPS mean, IPS variability (standard deviation), and IPS trend. The primary advantage of the Bayesian approach is its ability to produce uncertainty quantification in the form of 95% credible intervals for each prediction, which conventional machine learning methods cannot provide. The MCMC model was comprehensively compared against seven machine learning algorithms: Random Forest, XGBoost, Gradient Boosting, SVM, KNN, AdaBoost, and Bagging, using a dataset of 543 students from Institut Teknologi dan Kesehatan Mahardika for the period 2017-2021. Evaluation was conducted through an 80:20 train-test split and 5-fold cross-validation using RMSE, MAE, MAPE, and R² metrics. Test set results show MCMC Bayesian achieved RMSE 0.0792 and R² 0.867, ranking second after Gradient Boosting. However, in the more robust cross-validation evaluation, MCMC Bayesian outperformed all competitors with the lowest RMSE of 0.0832±0.0162 and highest R² of 0.848. These findings demonstrate that MCMC Bayesian is not only competitive in accuracy but also provides the unique value of prediction uncertainty estimation, which is highly useful for early academic warning systems

Page 8 of 10 | Total Record : 95

 6   7   8   9   10 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 2 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) October 2026 Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026 Vol. 3 No. 2 (2025): BUFNETS (Bulletin of Network Engineer and Informatics) October 2025 Vol. 3 No. 1 (2025): BUFNETS (Bulletin of Network Engineer and Informatics) April 2025 Vol. 2 No. 2 (2024): BUFNETS (Bulletin of Network Engineer and Informatics) October 2024 Vol. 2 No. 1 (2024): BUFNETS (Bulletin of Network Engineer and Informatics) April 2024 Vol. 1 No. 2 (2023): BUFNETS (Bulletin of Network Engineer and Informatics) October 2023 Vol. 1 No. 1 (2023): BUFNETS (Bulletin of Network Engineer and Informatics) April 2023