Article Per Year (5 Year)
p-Index From 2021 - 2026
2.57
P-Index
This Author published in this journals
All Journal EDUMATIC: Jurnal Pendidikan Informatika METIK JURNAL JATI (Jurnal Mahasiswa Teknik Informatika) Jurnal Informatika dan Rekayasa Perangkat Lunak Arcitech: Journal of Computer Science and Artificial Intelligence Jurnal Ilmiah Informatika dan Ilmu Komputer CHAIN: Journal of Computer Technology, Computer Engineering and Informatics Journal of Data Science and Information System Journal of Artificial Intelligence and Technology Information Jurnal Media Jawadwipa
Nuroji Nuroji
Universitas Muhammadiyah Prof. DR. HAMKA
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Engineering Library & Information Science

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Analisis Sentimen Pengguna Aplikasi Byond BSI Pada Google Play Store Menggunakan Algoritma SVM Dan Random Forest Firzatullah, Firdaus Naifah; Nuroji, Nuroji
METIK JURNAL (AKREDITASI SINTA 3) Vol. 9 No. 2 (2025): METIK Jurnal
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/6vtc4567

Abstract

The development of digital technology has encouraged banks to provide application-based financial services, one of which is BYOND by BSI, which carries the concept of Islamic banking. However, various technical obstacles such as service disruptions and application errors in using this application have caused dissatisfaction among users. Therefore, sentiment analysis is needed to understand user responses comprehensively. This study aims to classify user sentiment towards the BYOND by BSI application by utilizing the Support Vector Machine (SVM) and Random Forest algorithms. The data used are 35,000 user reviews collected from the Google Play Store through crawling techniques, then automatically labeled using a rule-based method based on rating values. The analysis process was carried out using the SEMMA approach, which includes the stages of text cleaning, word weighting using TF-IDF, and dividing the data into 80% training data and 20% test data. The test results showed that the SVM algorithm had the best performance with an accuracy of 93.16%, while Random Forest obtained an accuracy of 90.33%. The majority of the analyzed reviews showed negative sentiment. These findings are expected to provide input in improving the quality of the BYOND by BSI application service.
Perancangan Sistem Presensi Wajah (SIWAJA) Berbasis Internet of Things dengan Notifikasi Telegram Muhammad Bagas Adi Pangestu; Nuroji, Nuroji
METIK JURNAL (AKREDITASI SINTA 3) Vol. 9 No. 2 (2025): METIK Jurnal
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/88ctdw53

Abstract

Manual student attendance administration is prone to human error, inefficient, and hinders communication between schools and parents. This study aims to develop the Face Presence System (SIWAJA), an innovative solution integrating face recognition technology and the Internet of Things (IoT) to provide live attendance notifications to parents via Telegram. A key technological advantage of this system is the implementation of the YOLOv8 algorithm, which is emphasized for its high precision in face detection. The development method used is the prototype model, which includes stages of requirements identification, design, implementation, and evaluation. The system was built using an Orange Pi 5 Pro, the Python programming language with the OpenCV library, and the YOLOv8 algorithm for face detection. The research results show that the SIWAJA system was successfully developed and functions as expected, where the IoT-based design supports potential scalability for broader implementation. Black Box Testing validated all main functionalities, from presence-taking to notification delivery. The face detection model showed highly reliable performance with a precision (P) value of 0.97, recall (R) of 0.99, and mAP@.5 of 0.99. In conclusion, SIWAJA proves to be an effective and accurate solution for modernizing student attendance management and enhancing real-time parental involvement, offering significant contributions to the application of IoT in education.
Kombinasi Metode Pembobotan Rank Reciprocal dan Simple Additive Weighting Dalam Pemilihan Tempat Servis Kendaraan Nuroji Nuroji
CHAIN: Journal of Computer Technology, Computer Engineering, and Informatics Vol. 2 No. 2 (2024): Volume 2 Number 2 April 2024
Publisher : PT. Tech Cart Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/chain.v2i2.117

Abstract

The choice of vehicle service place is an important decision for vehicle owners because it will affect the quality of maintenance and service received by their vehicle. Some of the problems that may arise in the selection of vehicle service places include uncertainty in service quality, unaffordable prices, lack of availability of spare parts, and communication problems between customers and mechanics. The combination of reciprocal rank weighting (RR) and simple additive weighting (SAW) methods in vehicle service site selection can improve accuracy and objectivity in decision making. The RR method is used to derive the relative ranking of each alternative based on the decision maker's preference for certain criteria, while the SAW method is used to weigh and combine the weights of criteria in a structured manner. The ranking results gave a rank 1 result with a value of 0.9256 obtained by TR Service Place, rank 2 with a value of 0.8291 obtained by the AS Service Place, and rank 3 with a value of 0.7884 obtained by DW Service Place.
Perbandingan Tingkat Kesesuaian Algoritma SMART dan MOORA dalam Evaluasi Pelanggan Terbaik Very Hendra Saputra; Nuroji Nuroji
CHAIN: Journal of Computer Technology, Computer Engineering, and Informatics Vol. 3 No. 2 (2025): Volume 3 Number 2 April 2025
Publisher : PT. Tech Cart Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/chain.v3i2.220

Abstract

Penentuan pelanggan terbaik adalah suatu proses kritis dalam manajemen pelanggan di mana perusahaan berupaya mengidentifikasi dan menilai pelanggan yang memberikan kontribusi paling signifikan terhadap keberhasilan bisnis. Penelitian ini bertujuan untuk menerapakan dan membandingkan penentuan pelanggan terbaik dengan menggunakan metode SMART dan MOORA sehingga memberikan wawasan yang lebih baik kepada pengambil keputusan tentang pilihan metode yang paling sesuai dengan karakteristik dan kompleksitas keputusan yang dihadapi. Hasil perangkingan menunjukkan pelanggan terbaik didapatkan oleh Sulistia dengan peringkat 1 baik dengan menggunakan metode SMART ataupun dengan metode MOORA. Perbandingan hasil perangkingan antara metode SMART dan MOORA dapat memberikan wawasan yang berguna tentang sejauh mana kedua metode tersebut efektif dalam menangani pengambilan keputusan multi-kriteria. Berdasarkan hasil perbandingan perangkingan dari metode SMART dan MOORA terdapat perbedaan rangking pada 2 data yaitu atas nama Handoko dengan metode SMART mendapatkan rangking 3 dan dengan metode MOORA mendapatkan peringkat 2, serta atas nama Subagio dengan metode SMART mendapatkan rangking 2 dan dengan metode MOORA mendapatkan peringkat 3. Hasil perbandingan antara metode SMART dan MOORA dalam penentuan pelanggan terbaik merekomendasikan metode MOORA dibandingkan dengan metode SMART, karena hasil tingkat kesesuaian metode MOORA mendapatkan nilai 99,996% lebih tinggi dibandingkan dengan metode SMART yang mendapatkan nilai 99,995%.
Klasifikasi Serangan Web Berdasarkan Log Web Application Firewall (WAF) Menggunakan Support Vector Machine (SVM) Nuroji Nuroji; Tirta Anhari
Journal of Artificial Intelligence and Technology Information (JAITI) Vol. 4 No. 2 (2026): Volume 4 Number 2 June 2026
Publisher : PT. Tech Cart Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jaiti.v4i2.262

Abstract

Pertumbuhan aplikasi web yang semakin pesat turut meningkatkan risiko ancaman keamanan siber terhadap layanan berbasis internet. Berbagai jenis serangan seperti SQL Injection (SQLi) dan Cross-Site Scripting (XSS) masih menjadi ancaman utama yang dapat mengganggu keamanan maupun ketersediaan sistem web. Penelitian ini bertujuan menerapkan pendekatan machine learning untuk melakukan klasifikasi serangan web menggunakan data log dari Web Application Firewall (WAF) berbasis ModSecurity. Data penelitian diperoleh dari audit log ModSecurity dalam format JSON yang berisi aktivitas request dan response pada web server. Tahapan penelitian meliputi pengumpulan data, preprocessing, ekstraksi fitur, labeling, feature engineering menggunakan TF-IDF, pembagian dataset dengan train-test split, pemodelan menggunakan algoritma Support Vector Machine (SVM), serta evaluasi performa model menggunakan confusion matrix, accuracy, precision, recall, dan F1-score. Dataset yang digunakan terdiri atas 3467 data traffic web dengan kategori SQL Injection, XSS, dan Normal. Berdasarkan hasil pengujian, model SVM mampu menghasilkan tingkat akurasi sebesar 94,52% dalam proses klasifikasi traffic web. Model menunjukkan performa sangat baik pada pendeteksian serangan SQL Injection dengan recall sebesar 1,00 dan nilai F1-score sebesar 0,97. Akan tetapi, performa pada kategori Normal masih relatif rendah karena distribusi data yang tidak seimbang. Hasil penelitian menunjukkan bahwa analisis log ModSecurity yang dipadukan dengan machine learning dapat dimanfaatkan sebagai pendekatan alternatif untuk mendukung deteksi serangan web secara otomatis.
Co-Authors Alim, Endi Sjaiful Alita, Debby Anhari, Tirta Fadillah, Bagas Firzatullah, Firdaus Naifah Harlian Navi Isnain, Auliya Rahman M. Asep Rizkiawan Muhammad Bagas Adi Pangestu Pasaribu, A. Ferico Octaviansyah Sobari, Bahar Taufiq Martiwansyah Tirta Anhari Very Hendra Saputra Yusuf Widsono, Maulana