Article Per Year (5 Year)
p-Index From 2021 - 2026
1.513
P-Index
This Author published in this journals
All Journal Journal of the Indonesian Mathematical Society IJoICT (International Journal on Information and Communication Technology) Jurnal Aplikasi Statistika & Komputasi Statistik InPrime: Indonesian Journal Of Pure And Applied Mathematics Prosiding Seminar Nasional Official Statistics PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND OFFICIAL STATISTICS
Josaphat, Bony Parulian
Unknown Affiliation
Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Mathematics Social Sciences

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Desain dan Implementasi Sistem Monitoring Jaringan Menggunakan Zabbix dan Telegram Malik, Prasetyo Fajar; Josaphat, Bony Parulian
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.2196

Abstract

The BPS Data Center requires an integrated monitoring system to ensure the integrity and accessibility of statistical data. Currently, the system is fragmented by device type and brand, lacking the ability to send real-time alerts to mobile devices. This research focuses on designing and implementing a monitoring system at the BPS Data Center. Furthermore, this research endeavors to forward alert from the monitoring system into mobile notifications. The study employs the Network Development Life Cycle (NDLC) methodology. From the results of the analysis using Pugh matrix, it was obtained that Zabbix was the selected monitoring application service and Telegram as the mobile application that utilizes the Bot feature to send notifications using webhook method. Based on the evaluation results from Black-box testing and SUS, it was found that overall, the system features were successfully tested with expected outputs, and the system interface received an “acceptable” rating from users.
Pembangunan Chatbot Sistem Informasi KBLI dan KBJI Berbasis LLM Anassai, Bayu Rayhan; Josaphat, Bony Parulian
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.2202

Abstract

The Central Statistics Agency (BPS) collects data through censuses and surveys to provide data to the government and the public. This data is obtained from questionnaires containing open and closed questions. One of the open questions asked is about the respondent's occupation, which will later be classified with the assignment of KBLI and KBJI codes. KBLI and KBJI are classifications used by BPS to classify economic activities. BPS uses the Sibaku Mobile application to facilitate officers in filling out KBLI and KBJI codes, but this application has shortcomings for new users. This research aims to develop a chatbot that can provide the correct KBLI/KBJI codes using Large Language Models (LLM). The chatbot development was carried out using the prototyping method. Evaluation of classification objectives showed accuracy, precision, recall, and F1-score values approaching 97%. The RAG robustness evaluation obtained a hallucination rate of 0% and an error rate of 7%. Usability testing showed a chatbot acceptance rate of 87.45%.
Machine Learning for Cybersecurity: Web Attack Detection (Brute Force, XSS, SQL Injection) Irfa’issurur, Muhammad; Josaphat, Bony Parulian
InPrime: Indonesian Journal of Pure and Applied Mathematics Vol 7, No 1 (2025)
Publisher : Department of Mathematics, Faculty of Sciences and Technology, UIN Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/inprime.v7i1.41025

Abstract

Security is a top priority in system development, as web portals serve as critical entry points that are frequently targeted by cyber-attacks. Common attack methods include SQL Injection, Cross-Site Scripting (XSS), and Brute Force. The application of machine learning in cybersecurity is growing due to its effectiveness in detecting such threats. This study employs supervised machine learning with six algorithms: K-Nearest Neighbors (KNN), Random Forest, Naïve Bayes, AdaBoost, LightGBM, and XGBoost. The research utilizes the CICIDS2017 and CSE-CICIDS2018 datasets, which contain network traffic data labeled with four categories: Benign, Brute Force, XSS, and SQL Injection. To address the dataset imbalance issue, this study applies Synthetic Minority Oversampling Technique (SMOTE) in conjunction with Principal Component Analysis (PCA) for dimensionality reduction. Performance evaluation is conducted using accuracy, precision, recall, and F1-score metrics, as well as K-Fold Cross Validation, AUC-ROC, and Learning Curve analysis. The results indicate that the Random Forest algorithm achieves the highest classification performance, with an accuracy of 97.77%, precision of 84.07%, recall of 91.96%, and an F1-score of 87.28%. This research contributes by demonstrating the applicability of machine learning in real-time web attack detection, highlighting the advantages of ensemble-based models in handling cybersecurity threats. Additionally, it underscores the importance of dataset preprocessing techniques in enhancing classification performance. Future improvements should focus on optimizing hyperparameters, integrating real-time network traffic analysis, and exploring hybrid models that combine traditional machine learning with deep learning approaches to further enhance detection capabilities.Keywords: Machine learning; Cybersecurity; Web attack detection; Random forest; SMOTE; PCA. Abstrak Keamanan merupakan prioritas utama dalam pengembangan sistem, karena portal web berfungsi sebagai titik masuk penting yang sering menjadi sasaran serangan siber. Metode serangan umum meliputi SQL Injection, Cross-Site Scripting (XSS), dan Brute Force. Penerapan machine learning dalam keamanan siber semakin berkembang karena efektivitasnya dalam mendeteksi ancaman tersebut. Studi ini menggunakan supervised machine learning dengan enam algoritma: K-Nearest Neighbors (KNN), Random Forest, Naïve Bayes, AdaBoost, LightGBM, dan XGBoost. Penelitian ini memanfaatkan kumpulan data CICIDS2017 dan CSE-CICIDS2018, yang berisi data lalu lintas jaringan yang diberi label dengan empat kategori: Benign, Brute Force, XSS, dan SQL Injection. Untuk mengatasi masalah ketidakseimbangan kumpulan data, studi ini menerapkan Synthetic Minority Oversampling Technique (SMOTE) bersama dengan Principal Component Analysis (PCA) untuk pengurangan dimensionalitas. Evaluasi kinerja dilakukan dengan menggunakan metrik akurasi, presisi, recall, dan skor F1, serta K-Fold Cross Validation, AUC-ROC, dan analisis Learning Curve. Hasilnya menunjukkan bahwa algoritma Random Forest mencapai kinerja klasifikasi tertinggi, dengan akurasi 97,77%, presisi 84,07%, recall 91,96%, dan skor F1 87,28%. Penelitian ini berkontribusi dengan menunjukkan penerapan machine learning dalam deteksi serangan web real-time, menyoroti keunggulan model berbasis ensemble dalam menangani ancaman keamanan siber. Selain itu, penelitian ini menggarisbawahi pentingnya teknik praproses dataset dalam meningkatkan kinerja klasifikasi. Peningkatan di masa mendatang harus difokuskan pada pengoptimalan hiperparameter, pengintegrasian analisis lalu lintas jaringan real-time, dan eksplorasi model hybrid yang menggabungkan machine learning tradisional dengan pendekatan deep learning untuk lebih meningkatkan kemampuan deteksi.Kata Kunci: Pembelajaran mesin; Keamanan siber; Deteksi serangan web; Random forest; SMOTE; PCA. 2020MSC: 68T05
Predicting Stock Price Using Convolutional Neural Network and Long Short Term Memory (Case Study: Stock of BBCA) Pangestika, Zubaidah; Josaphat, Bony Parulian
Journal of the Indonesian Mathematical Society Vol. 31 No. 1 (2025): MARCH
Publisher : IndoMS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22342/jims.v31i1.1512

Abstract

Stocks are capital market instruments capable of creating profits for investors. However, stocks have a fluctuating nature that can lead to risk, so price predictions are needed to reduce this risk. Stock price prediction can use various methods such as deep learning. This study aims to predict stock price using Convolution Neural Network (CNN) and Long Short Term Memory (LSTM), with the application carried out at the stock price of Bank Central Asia (BBCA) for the period between July 1, 2005 and December 30, 2022. Data division uses a ratio of 70% for training and 30% for testing. To maximize prediction results, we select the best hyperparameter combinations using Grid Search. The prediction results show that CNN is better to LSTM, where CNN produces RMSE values of 488.992, R2 83.8%, and MAPE 6.5%.
Machine Learning for Cybersecurity: Web Attack Detection (Brute Force, XSS, SQL Injection) Irfa’issurur, Muhammad; Josaphat, Bony Parulian
InPrime: Indonesian Journal of Pure and Applied Mathematics Vol. 7 No. 1 (2025)
Publisher : Department of Mathematics, Faculty of Sciences and Technology, UIN Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/inprime.v7i1.41025

Abstract

Security is a top priority in system development, as web portals serve as critical entry points that are frequently targeted by cyber-attacks. Common attack methods include SQL Injection, Cross-Site Scripting (XSS), and Brute Force. The application of machine learning in cybersecurity is growing due to its effectiveness in detecting such threats. This study employs supervised machine learning with six algorithms: K-Nearest Neighbors (KNN), Random Forest, Naïve Bayes, AdaBoost, LightGBM, and XGBoost. The research utilizes the CICIDS2017 and CSE-CICIDS2018 datasets, which contain network traffic data labeled with four categories: Benign, Brute Force, XSS, and SQL Injection. To address the dataset imbalance issue, this study applies Synthetic Minority Oversampling Technique (SMOTE) in conjunction with Principal Component Analysis (PCA) for dimensionality reduction. Performance evaluation is conducted using accuracy, precision, recall, and F1-score metrics, as well as K-Fold Cross Validation, AUC-ROC, and Learning Curve analysis. The results indicate that the Random Forest algorithm achieves the highest classification performance, with an accuracy of 97.77%, precision of 84.07%, recall of 91.96%, and an F1-score of 87.28%. This research contributes by demonstrating the applicability of machine learning in real-time web attack detection, highlighting the advantages of ensemble-based models in handling cybersecurity threats. Additionally, it underscores the importance of dataset preprocessing techniques in enhancing classification performance. Future improvements should focus on optimizing hyperparameters, integrating real-time network traffic analysis, and exploring hybrid models that combine traditional machine learning with deep learning approaches to further enhance detection capabilities.Keywords: machine learning; cybersecurity; web attack detection; random forest; SMOTE; PCA. Abstrak Keamanan merupakan prioritas utama dalam pengembangan sistem, karena portal web berfungsi sebagai titik masuk penting yang sering menjadi sasaran serangan siber. Metode serangan umum meliputi SQL Injection, Cross-Site Scripting (XSS), dan Brute Force. Penerapan machine learning dalam keamanan siber semakin berkembang karena efektivitasnya dalam mendeteksi ancaman tersebut. Studi ini menggunakan supervised machine learning dengan enam algoritma: K-Nearest Neighbors (KNN), Random Forest, Naïve Bayes, AdaBoost, LightGBM, dan XGBoost. Penelitian ini memanfaatkan kumpulan data CICIDS2017 dan CSE-CICIDS2018, yang berisi data lalu lintas jaringan yang diberi label dengan empat kategori: Benign, Brute Force, XSS, dan SQL Injection. Untuk mengatasi masalah ketidakseimbangan kumpulan data, studi ini menerapkan Synthetic Minority Oversampling Technique (SMOTE) bersama dengan Principal Component Analysis (PCA) untuk pengurangan dimensionalitas. Evaluasi kinerja dilakukan dengan menggunakan metrik akurasi, presisi, recall, dan skor F1, serta K-Fold Cross Validation, AUC-ROC, dan analisis Learning Curve. Hasilnya menunjukkan bahwa algoritma Random Forest mencapai kinerja klasifikasi tertinggi, dengan akurasi 97,77%, presisi 84,07%, recall 91,96%, dan skor F1 87,28%. Penelitian ini berkontribusi dengan menunjukkan penerapan machine learning dalam deteksi serangan web real-time, menyoroti keunggulan model berbasis ensemble dalam menangani ancaman keamanan siber. Selain itu, penelitian ini menggarisbawahi pentingnya teknik praproses dataset dalam meningkatkan kinerja klasifikasi. Peningkatan di masa mendatang harus difokuskan pada pengoptimalan hiperparameter, pengintegrasian analisis lalu lintas jaringan real-time, dan eksplorasi model hybrid yang menggabungkan machine learning tradisional dengan pendekatan deep learning untuk lebih meningkatkan kemampuan deteksi.Kata Kunci: pembelajaran mesin; keamanan siber; deteksi serangan web; random forest; SMOTE; PCA. 2020MSC: 68T05
Reducing Lending Risk: SVM Model Development with SMOTE for Unbalanced Credit Data Purba, Josya Ryan Alexandro; Muftikhali, Qilbaaini Effendi; Josaphat, Bony Parulian
International Journal on Information and Communication Technology (IJoICT) Vol. 9 No. 2 (2023): Vol.9 No. 2 Dec 2023
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v9i2.860

Abstract

Lending is an important activity for banks in managing available funds. However, lending is also an activity that has a high risk, because not all customers who borrow funds can fulfill the responsibilities of the existing agreement. Because of this, it is necessary to have a method that can predict creditworthiness to customers in order to minimize the risks that arise. This research uses machine learning method, namely Support Vector Machine (SVM) in predicting creditworthiness. This method is applied and compared before and after the Synthetic Minority Oversampling Technique (SMOTE) on historical bank credit data BPR NBP 16 Rantau Prapat, North Sumatra and find the best parameters with grid search. According to the results of the analysis based on Area Under the Receiver Operating Characteristic Curve (AUC-ROC), SVM with SMOTE shows better results, namely 96%, than SVM without SMOTE, namely 56%.
Forecasting Dependent Tail Value-at-Risk by ARMA-GJR-GARCH-Copula Method and Its Application in Energy Risk Josaphat, Bony Parulian
Journal of the Indonesian Mathematical Society VOLUME 29 NUMBER 3 (NOVEMBER 2023)
Publisher : IndoMS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22342/jims.29.3.1451.382-407

Abstract

One widely known risk measure is Tail Value-at-Risk (TVaR), which isthe average of the values of random risk that exceed the Value-at-Risk (VaR). Thisclassic risk measure of TVaR does not take into account the excess of another randomrisk (associated risk) that may have an effect on target risk. Copula function expresses a methodology that represents the dependence structure of random variablesand has been used to create a risk measure of Dependent Tail Value-at-Risk (DTVaR). Incorporating copula into the forecast function of the ARMA-GJR-GARCHmodel, this article argues a novel approach, called ARMA-GJR-GARCH-copulawith Monte Carlo method, to calculate the DTVaR of dependent energy risks. Thiswork shows an implementation of the ARMA-GJR-GARCH-copula model in forecasting the DTVaR of energy risks of NYH Gasoline and Heating oil associated withenergy risk of WTI Crude oil. The empirical results demonstrate that, the simplerGARCH-Clayton copula is better in forecasting DTVaR of Gasoline energy risk thanthe MA-GJR-GARCH-Clayton copula. On the other hand, the more complicatedMA-GJR-GARCH-Frank copula is better in forecasting DTVaR of Heating oil energy risk than the GARCH-Frank copula. In this context, energy sector marketplayers should invest in Heating oil because the DTVaR forecast of Heating oil ismore accurate than that of Gasoline.
Integrating Multi-Criteria Decision Analysis and Machine Learning for Fine-Scale Mapping of Safe Drinking Water Access in Bengkulu Province, Indonesia Tampubolon, Andrew Maruli Tua; Josaphat, Bony Parulian; Asriadi Sakka; Yohanes Wahyu Trio Pramono
Jurnal Aplikasi Statistika & Komputasi Statistik Vol 17 No 2 (2025): Jurnal Aplikasi Statistika & Komputasi Statistik
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/jurnalasks.v17i2.866

Abstract

Introduction/Main Objectives: This study aims to develop a 1 km × 1 km level estimation model of safe drinking water access using multisource satellite imagery, point of interest (POI), and aquifer productivity maps. Background Problems: There is a lack of alternative data sources for estimating safe drinking water access that are cost-, time-, and labor-efficient while maintaining high accuracy and frequent updates. Novelty: This study integrates Multi-Criteria Decision Analysis (MCDA) and machine learning methods to estimate and map safe drinking water access at a 1 km × 1 km resolution. Research Methods: Multisource geospatial data were used to construct the model. Within the MCDA approach, the Weighted Product Model (WPM) was employed to develop the Safe Drinking Water Access Index (SDWAI). Meanwhile, the machine learning regression algorithms Adaptive Boosting Regression (ABR) and Gradient Boosting Regression (GBR) were applied to estimate safe drinking water access at a fine spatial scale. The study was conducted in Bengkulu Province, Indonesia. Finding/Results: WPM yielded the best MCDA performance (  = 0.3699, RMSE = 10.6566, MAE = 9.5427, MAPE = 0.1405), while ABR showed the best machine learning performance (  = 0.4361, RMSE = 10.0813, MAE = 8.3750, MAPE = 0.1333).
Development of Portal Pintar Utilization Evaluation Dashboard (Case Study: BPS Province of Bengkulu) Josaphat, Bony Parulian; Humaira, Rifka
Proceedings of The International Conference on Data Science and Official Statistics Vol. 2025 No. 1 (2025): Proceedings of 2025 International Conference on Data Science and Official St
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/icdsos.v2025i1.581

Abstract

BPS Statistics Province of Bengkulu (BPS Provinsi Bengkulu) plays a role insupporting statistical operations in Province of Bengkulu. As a vertical agency of StatisticsIndonesia (BPS), BPS Province of Bengkulu also holds an important role in providing statisticaldata at the regional level. Naturally, BPS Province of Bengkulu also requires an integratedsystem to facilitate all activities, such as providing easier and faster access to information for allemployees—both in reporting work progress and in monitoring the implementation of activitiessuch as agenda planning, facility usage, facility loan management, and cross-unit coordination.Portal Pintar is a portal used to facilitate the management of various activities in BPS Provinceof Bengkulu. By using Portal Pintar, users can access and manage various types of informationand documents, such as activity agendas, correspondence, and facility loan applications. BPSProvince of Bengkulu then produces periodic evaluations of Portal Pintar’s utilization, which aredistributed to all employees. However, the evaluations conducted are not yet visualizedautomatically and in real time, hence the need to develop a Portal Pintar Utilization EvaluationDashboard in which visualizations are generated automatically and connected to Portal Pintar’sAPI. Through the development of this dashboard, it is expected that the evaluation of PortalPintar’s utilization will become more integrated.
Co-Authors Anassai, Bayu Rayhan Asriadi Sakka Humaira, Rifka Irfa’issurur, Muhammad Malik, Prasetyo Fajar Pangestika, Zubaidah Purba, Josya Ryan Alexandro Qilbaaini Effendi Muftikhali Tampubolon, Andrew Maruli Tua Yohanes Wahyu Trio Pramono