Claim Missing Document
Check
Articles

Performance Comparison of Random Forest, XGBoost, and SVM for Flood Risk Prediction Using BNPB GIS Data Muhammad Amanulloh Mz; Oky Dwi Nurhayati; Jatmiko Endro Suseno
Journal of Information System and Informatics Vol 8 No 1 (2026): February
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i1.1461

Abstract

This study compares the performance of three machine learning algorithms—Random Forest, XGBoost, and Support Vector Machine (SVM)—for predicting flood risk using spatial and non-spatial data from BNPB GIS. The analysis focuses on disaster records from January 3 to 15, 2026, with district-city as the spatial unit of observation. Following data cleaning, exploratory analysis, and feature preparation, the models were evaluated using ROC-AUC, PR-AUC, F1-Score, Precision, Recall, and Accuracy. XGBoost demonstrated the highest ROC-AUC (0.675), indicating strong overall performance in distinguishing flood from non-flood events. Random Forest achieved the highest Recall (0.947), showing superior sensitivity in detecting flood events, while SVM exhibited fluctuating performance with a lower ROC-AUC (0.496). Visualizations of model behavior and spatial flood patterns were provided to support model interpretability. The study’s results suggest that ensemble models, particularly XGBoost and Random Forest, can significantly enhance flood risk prediction, improving the accuracy and sensitivity of early warning systems. These findings contribute to the development of more effective data-driven flood mitigation strategies in Indonesia, enabling better disaster preparedness and response.
Analysis of Naïve Bayes and K-Nearest Neighbors Algorithms for Classifying Fishermen Aid Eligibility Muhammad Nasrullah; Bayu Surarso; Oky Dwi Nurhayati
Jurnal Penelitian Pendidikan IPA Vol 10 No 10 (2024): October
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v10i10.8818

Abstract

This article analyzes the use of data mining with Naïve Bayes and K-Nearest Neighbor (KNN) algorithms to build classification models and evaluate their performance in identifying fishermen eligible for aid. The study aims to compare the effectiveness of these algorithms in handling imbalanced datasets using the Synthetic Minority Over-sampling Technique (SMOTE). The research applies SMOTE to improve the balance of the dataset before classification. Without SMOTE, Naïve Bayes achieved an accuracy of 97.01%, precision of 94.16%, recall of 96.67%, and F1-score of 95.39%. KNN, on the other hand, reached an accuracy of 94.04%, precision of 94.53%, recall of 86.00%, and F1-score of 90.06%. After applying SMOTE, both algorithms improved: Naïve Bayes attained an accuracy of 98.33%, precision of 96.86%, recall of 100.00%, and F1-score of 98.49%, while KNN reached an accuracy of 96.90%, precision of 97.72%, recall of 96.19%, and F1-score of 96.94%. The results show that Naïve Bayes, with SMOTE, outperforms KNN in managing data imbalance and accurately classifying eligible fishermen for aid.
User Satisfaction Analysis of SUS Method of Virtual Tours Website for Semarang Chinatown Tourism Experience Muhammad Reza Setiawan; Dinar Mutiara Kusumo Nugraheni; Oky Dwi Nurhayati
Jurnal Penelitian Pendidikan IPA Vol 11 No 1 (2025): January
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v11i1.9891

Abstract

This article analyzes the satisfaction of website-based virtual tour users using the usability scale system method for tourism experiences in Chinatown Semarang for respondents who use the virtual tour application both in the initial and final applications. This research aims to compare user satisfaction by analyzing the score calculation results from 80 respondents from each virtual tour application using the system usability scale method where the virtual tour in the initial application and the virtual tour in the final application have differences in the addition of a simple interactive website and a guide in the form of a manual book and video tutorial in the final application. The system usability scale d calculation score was obtained with an increase in value of 7.875. This proves that modifying the application and adding a guide feature in the form of a manual book and video tutorial can help respondents use a virtual tour in Semarang's Chinatown village. The advice obtained in this research is that it is hoped that for future research, you can use paid hosting because, in the study here, the virtual tour application still uses free hosting, which still has limitations in processing files, so it takes longer for users to access the virtual tour in Semarang Chinatown Village.
Information Security Architecture for Pesantren: The Synergy of ISO/IEC 27001 and TOGAF ADM in Supporting Sustainable Quality Education yussrizal Asygaf; Dinar Mutiara Kusumo Nugraheni; Oky Dwi Nurhayati
Jurnal Penelitian Pendidikan IPA Vol 12 No 4 (2026)
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v12i4.14712

Abstract

Digital transformation in Islamic boarding schools (pesantren) presents new challenges in protecting information assets and student data privacy. This study aims to perform an information security analysis in a pesantren currently undergoing a crucial digital transition, aligned with the institutional vision to implement digital administrative services and science-and-technology-based learning. The research methodology integrates the ISO/IEC 27001:2022 information security standard as an audit instrument into the TOGAF ADM framework, limited to Phase D (Technology Architecture). This approach aims to establish a foundational infrastructure and critical technical governance that complies with security standards prior to the architecture implementation phase. A selection of 41 security controls was made through asset identification and risk assessment to represent the specific operational needs of the pesantren for effective mitigation. Research findings reveal significant gaps in identity management, backup protocols, and cryptography, stemming from a governance approach that remains reactive. This study concludes that strengthening information security through policy standardization, the implementation of Role-Based Access Control (RBAC), and data recovery procedures is urgent to ensure the integrity and sustainability of digital services. The synergy between regulatory compliance and resilient technology architecture serves as the primary determinant in protecting data sovereignty within traditional educational institutions.
Evaluating the Success Factors of a Tourism Management Information System Using the DeLone and McLean Model: A User Perspective Hidayat Syah, Rizqi Mulyantara; Oky Dwi Nurhayati; Bayu Surarso
Journal of Information Technology and Computer Science Vol. 11 No. 1: April 2026
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.111925

Abstract

This study evaluates the success factors of a tourism management information system implemented by startup XYZ using the DeLone and McLean Information Systems Success Model. Startups in the tourism industry are becoming more dependent on digital platforms, which prompted this research because there has been little user-centered evaluation of tourism information systems. Involving 75 active users of the system, a quantitative explanatory method was used. A systematic questionnaire with 44 questions was used to gather data. The questions covered topics such as system quality, information quality, service quality, use, user satisfaction, and net benefits. Research methods encompassed creating instruments, collecting data, analyzing it statistically, checking reliability using Cronbach's Alpha, and expert validation with Aiken's V. The instrument demonstrated strong validity and reliability with an overall Aiken's V value of 0.8247. Additionally, all constructs attained Cronbach's Alpha values above 0.70, further supporting these findings. Descriptive statistics, construct correlation, multiple regression, coefficient of determination (R²), and F-test analyses were used to examine the data. All descriptive factors had high mean values, suggesting that users had a good impression of the system. System quality and service quality had a substantial impact on user happiness, according to regression analysis, but information quality and system quality had a substantial impact on system usage. Perceived net benefits were also heavily impacted by system utilization and user satisfaction. The results show that the DeLone and McLean model may be used to evaluate TISs. Making the system more responsive, making the information more accurate, and improving the user support services should be the goals of future enhancements.
Governance in Samarinda City Using TOGAF (The Open Group Architecture Framework): Literature Review Rizki Galang Rahmadani; Oky Dwi Nurhayati; Dinar Mutiara Kusumo Nugraheni
Proceedings of the 1st International Conference on Social Science (ICSS) Vol. 4 No. 1 (2025): Proceedings of the 6th International Conference on Social Science (ICSS)
Publisher : Green Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/icss.v4i1.226

Abstract

Effective governance is essential for ensuring the efficient delivery of public services and fostering community development. In Samarinda City, addressing administrative and developmental challenges requires the implementation of a robust governance framework. This research explores the application of TOGAF (The Open Group Architecture Framework) to improve the efficiency and effectiveness of local governance in Samarinda City. The study aims to analyze how TOGAF can strengthen strategic alignment, decision-making, and operational efficiency within local government frameworks. This research employs a qualitative approach through a literature review of academic articles, case studies, and industry reports on the application of TOGAF in governance contexts. The findings indicate that TOGAF facilitates strategic alignment of IT resources with governance goals, improves decision-making through structured methodologies, enhances operational efficiency through resource optimization, and promotes interoperability between government departments. However, challenges such as the framework's complexity, resource demands, and adaptability to local contexts must be addressed. The results suggest that adopting TOGAF incrementally, investing in capacity building, and ensuring stakeholder engagement are crucial for successful implementation. These findings have important implications for the Samarinda City Government, providing practical recommendations to enhance governance through TOGAF, and contributing to the broader literature on IT frameworks in public sector governance. Further research could explore case studies of TOGAF implementation in other cities with similar challenges to offer additional insights into its practical applications.
Benchmarking Lightweight Machine Learning for Disaster Prediction: Accuracy, Latency, and Readiness Muhammad Amanulloh Mz; Oky Dwi Nurhayati; Jatmiko Endro Suseno
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 4 (2026): August 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i4.7570

Abstract

Natural disaster early warning systems are often constrained by high computational latency, which impedes the timely dissemination of critical information. This study proposes a disaster impact prediction framework designed to optimize inference speed through a lightweight machine learning approach. Utilizing a comprehensive historical dataset from the Indonesian National Board for Disaster Management (BNPB) comprising 28,773 disaster records across 34 provinces from January 2018 to May 2024, this research evaluates the performance of XGBoost and LightGBM against a Gated Recurrent Unit (GRU) model for predicting infrastructure damage. SMOTE was applied exclusively during the training phase to address class imbalance without affecting inference speed. The results demonstrate that tree-based models significantly outperform GRU in both accuracy and speed. XGBoost achieved the lowest Mean Absolute Error (MAE of 1.1649) and the fastest inference latency (0.0026 ms per sample), followed by LightGBM (MAE of 1.4006, latency of 0.0064 ms), while GRU yielded a substantially higher error (MAE of 1.4189) and latency (0.2493 ms). Statistical validation via the Wilcoxon signed-rank test confirmed the significance of these performance differences (p < 0.001). Beyond technical benchmarking, these findings support the development of Intelligent Decision Support Systems for disaster mitigation, where organizational readiness and technology acceptance are critical for successful adoption. This study discusses practical implications for deploying lightweight models on resource-constrained edge computing devices such as Raspberry Pi 4, demonstrating sub-millisecond response speed, horizontal scalability, and affordability under $100 per node.
A Socio-Technical Assessment of Information Security Management Using KAMI Index, ISO/IEC 27001:2022, and User Awareness Nur Wachid Hidayatulloh; Dinar Mutiara Kusumo Nugraheni; Oky Dwi Nurhayati
Journal of Information System and Informatics Vol 8 No 4 (2026): August
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i4.1746

Abstract

ISO/IEC 27001:2022 is one of the certifications for Information Security Management Systems (ISMS). The study employs a mixed descriptive approach, analyzing maturity using the KAMI Index 5.0, ISO/IEC 27001:2022 clause implementation as a gap assessment, and user awareness of the ISMS, examined through socio-technical system theory at a university in Semarang. The results reveal a gap between the two subsystems: the technical subsystem shows high overall readiness but is not fully optimal, with weaker domain in Personal Data Protection (level II). The KAMI Index places the university's overall maturity at level V, while the ISO/IEC 27001:2022 gap assessment shows several clauses still unimplemented. Meanwhile, the social subsystem for user awareness revealed that the ISMS was less than optimal according to user interviews, even though the test achieved a score of 81.2% and was rated Very Worthy. Suitable standard operating procedures (SOPs) were also found lacking for several clauses and indicators. Socio-technical systems theory emphasizes joint consideration of social and technical elements in designing and implementing complex organizational systems such as information security; applying it here shows both subsystems must be evaluated holistically rather than separately.
Real-time Monitoring and Remote Control of Laboratory Furnaces using MQTT and Role-Based Access Control Adilia Getia Haqia Ilmi; Linda Ratna Kholifah; Syada Saleha; Oky Dwi Nurhayati; Agung Budi Prasetijo; Abdul Manab; Andre Rabiula; Edi Saputra; Samratul Fuady; Nazrizawati Ahmad Tajuddin; Nazarudin Nazarudin
AMPLITUDO : Journal of Science and Technology Innovation Vol. 5 No. 2 (2026): August
Publisher : Balai Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56566/amplitudo.v5i2.628

Abstract

The modernization of laboratory infrastructure requires secure, reliable remote monitoring systems to replace inefficient manual supervision. This study presents the design and implementation of a Web-based Supervisory Control and Data Acquisition (SCADA) system for laboratory furnaces, incorporating Proportional-Integral-Derivative (PID) control for precise temperature regulation and the Message Queuing Telemetry Transport (MQTT) protocol for efficient wireless data transmission. A key feature of the proposed architecture is the integration of Role-Based Access Control (RBAC), which systematically classifies user permissions into Administrator, Operator, and Viewer roles to ensure operational safety and prevent unauthorized actions. The system employs an Arduino Uno R4 Wi-Fi as a gateway, interfacing industrial-grade sensors with a React.js and Node.js web platform, enabling real-time monitoring and supervisory control. Performance evaluation demonstrates robust communication stability, achieving 0% packet loss and consistent throughput, with an average latency of approximately 0.5 seconds for remote monitoring and under 0.2 seconds for control commands. While functional testing confirms that the RBAC mechanism effectively manages user permissions, load testing indicates that concurrent, multi-user access on the current shared hosting configuration introduces performance bottlenecks, highlighting a need for dedicated infrastructure to ensure scalability. This research contributes to the field of physics instrumentation by providing a scalable, secure, and cost-efficient architectural model for remote laboratory experimentation within academic environments
SISTEM PAKAR MENDETEKSI GANGGUAN OBSESSIVE COMPULSIVE DISORDER MENGGUNAKAN METODE BACKWARD CHAINING Hammas Zulfikar Ikhsan; Oky Dwi Nurhayati; Yudi Eko Windarto
Jurnal Transformatika Vol. 17 No. 1 (2019): July 2019
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v17i1.1276

Abstract

Obsessive Compulsive Disorder (OCD) adalah salah satu jenis gangguan psikologi yang berasal dari rasa cemas dan takut yang muncul secara tiba-tiba dan tidak dapat dikendalikan oleh penderitanya. Jika gangguan ini dibiarkan maka akan mengganggu aktivitas sehari-hari penderita dan menyebabkan depresi. Dalam proses diagnosa oleh dokter, pasien menggunakan kata yang tidak pasti seperti jarang , lumayan, dan cukup dalam menjawab pertanyaan dari dokter. Hal ini menyebabkan dokter kesulitan dalam melakukan diagnosa. Dari permasalahan diatas, maka dibuatlah aplikasi sistem pakar mendeteksi gangguan obsessive compulsive disorder menggunakan metode backward chaining dan certainty factor untuk memudahkan dan meningkatkan tingkat kepercayaan dokter dalam mendeteksi gangguan obsessive compulsive disorder pasien. Aplikasi ini menggunakan ilmu kecerdasan buatan yaitu metode backward chaining dan certainty factor yang digunakan dalam perancangan dan pembuatan aplikasi sistem pakar. Aplikasi yang dibuat berbasis website menggunakan bahasa PHP dan MySQL. Dari penelitian ini, dihasilkan sistem pakar yang dapat menampilkan kemungkinan dideritanya tipe gangguan OCD. Hasil pengujian aplikasi telah sesuai dengan pengetahuan dari pakar. Pengujian sistem aplikasi menggunakan pengujian black box yang menunjukan semua fungsi yang ada pada aplikasi dapat berjalan sesuai yang diharapkan.  
Co-Authors Abdul Manab Achmad Hidayatno Adhi Susanto Adi Mora Tunggul Adi, Yudi Restu Adilia Getia Haqia Ilmi Agung Budi Prasetijo Agung Budi Prasetijo Agus Subhan Akbar, Agus Subhan Agus Subkhi Hermawan Agus Supriyanto Ahmad Aviv Mahmudi Ahmad Muzami Aji Yudha Al Iman, Yusraka Dimas Alim Muadzani Ambrina Kundyanirum Amrina Rosyada Andre Rabiula Anggi Anugraha Putra Anggit Sri Herlambang Anggoro Mukti Anisa Eka Utami Annisa Hedlina Hendraputri Aria Hendrawan, Aria Arief Puji Eka Prasetya Atik Zilziana Muflihati Noor Aulia Medisina Ramadhan Bayu Surarso Bayu Surarso Budi Warsito Catur Edi Widodo Christine Dewi Damar Wicaksono Danal Meizantaka Daeanza Dania Eridani Dania Eridani Deryan Gelrandy Diana Nur Afifah, Diana Nur Dinar Mutiara Kusumo Nugraheni Dinar Mutiara Kusumo Nugraheni Dwiana Okviandini Dwiyanasari, Desty Edi Saputra Eggy Listya Sutigno Eko Didik Widianto Eko Sediyono Fardana, Nouvel Izza Febi Andrea Renatha Galuh Boy Hertantyo Gayuh Nurul Huda Gumay, Naretha Kawadha Pasemah Hadi Hilmawan Hammas Zulfikar Ikhsan Hanna Mariana Baun, Hanna Mariana Harits Fathuddin hastuti, Isti Pudji Hendra Pria Utama Hengki Hengki Hidayat Syah, Rizqi Mulyantara Ike Pertiwi Ike Pertiwi Windasari Ike Pertiwi Windasari Imaduddin Abdul Rahim Indra Aditia Indra Permana Isti Pudjihastuti Jatmiko Endro Suseno Jatmiko Endro Suseno Julce Adiana Sidette, Julce Adiana Juwanda, Farikhin Keszya Wabang Kurniawan Teguh Martono Kusworo Adi Lazuardi Arsy Lia Dorothy Linda Ratna Kholifah M Irfan Syarif Hidayatullah M. Rizki Kurniawan Maesadji Tjokronagoro Menur Wahyu Pangestika, Menur Wahyu Merdekawati, Utami Mey Fenny Wati Simanjuntak Mifta Ardianti Migunani Migunani Muhammad Amanulloh Mz Muhammad Nasrullah Muhammad Naufal Prasetyo Muhammad Reza Setiawan Muhammad Ridwan Asad Mustafid Mustafid Nazarudin Nazarudin Nazrizawati Ahmad Tajuddin Ningrum, Alifvia Arvi Ninik Rustanti Nofiyati Nofiyati, Nofiyati Nugraheni, Dinar Nugroho Adhi Santoso Nur Wachid Hidayatulloh Nurazizah Nurazizah Nurhuda Maulana Nurul Arifa Nuryanto . Otong Saeful Bachri Prio Pambudi R Rizal Isnanto R. Rizal Isnanto R. Rizal Isnanto Rahmat Gernowo Rahmawati, Nurhita Reza Najib Hidayat Rian Haris Muda Nasution Rinta Kridalukmana Risma Septiana Rismawan Fajril Falah Riyadhi Sholikhin Rizki Galang Rahmadani Rizki Galang Rahmadani Samratul Fuady Satriaji Cahyo Nugroho Siswo Sumardiono Sri Widodo, Thomas Suryo Mulyawan Raharjo Suryono Suryono Syada Saleha Teguh Hananto Widodo Thomas Sri Widodo Tristy Meinawati Tsalavin, Muhammad Hafiz Tyas Panorama Nan Cerah Ulinuha, Ajik Wahyul Amien Syafei Wijaya Wahyudi Akbar Yessy Kurniasari Yudhi Kasih Pasaribu Yudi Eko Windarto Yudi Restu Adi yussrizal Asygaf Yusuf Arya Yudanto Zaskia Wiedya Sahardevi