Article Per Year (5 Year)
p-Index From 2021 - 2026
1.116
P-Index
This Author published in this journals
All Journal Techno.Com: Jurnal Teknologi Informasi JTIULM (Jurnal Teknologi Informasi Universitas Lambung Mangkurat) Jurnal Sains Komputer dan Teknologi Informasi Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics
Rafie Rafie
Universitas Lambung Mangkurat
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Health Professions Materials Science & Nanotechnology

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Deteksi Cacat Ubin Keramik Dengan Metode K-Nearest Neighbor Riza Alamsyah; Ade Davy Wiranata; Rafie Rafie
Techno.Com Vol 18, No 3 (2019): Agustus 2019
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (711.008 KB) | DOI: 10.33633/tc.v18i3.2459

Abstract

Perusahaan industri manufaktur harus dapat menjaga kualitas dari setiap produk yang diproduksi, termasuk perusahaan industri manufaktur yang memproduksi ubin keramik. Selama beberapa tahun, inspeksi visual secara otomatis sudah diterapkan untuk menentukan kualitas ubin keramik yang diproduksi. Sulitnya mendeteksi ubin keramik yang cacat bisa berdampak pada menurunnya kualitas hasil produksi, menurunnya tingkat kepercayaan konsumen, dan penurunan laba bagi perusahaan. Masalah yang dibahas di dalam penelitian ini adalah bagaimana mendeteksi ubin keramik yang cacat sehingga model yang dibangun dapat meningkatkan akurasi untuk mendeteksi ubin keramik yang cacat. Langkah penyelesaian masalah ini adalah dengan mengumpulkan data berupa citra dari ubin keramik, kemudian data citra dilakukan preprocessing menggunakan Median Filtering untuk menghilangkan noise salt and paper dan Teknik Morfologi untuk memperbaiki hasil segmentasi citra. Setelah dilakukan preprocessing, data citra diekstraksi ciri berdasarkan tekstur dengan menggunakan metode Gray Level Co-occurrence Matrix (GLCM) yang dilanjutkan dengan mengklasifikasikan data citra menggunakan metode K-Nearest Neighbor (KNN). Hasil dari penelitian ini adalah model yang dibangun menggunakan metode K-Nearest Neighbor dapat meningkatkan akurasi untuk mendeteksi kecacatan pada ubin keramik dengan nilai akurasi sebesar 98.9474% untuk k = 3.
Klasifikasi Bunga Menggunakan Naïve Bayes Berdasarkan Fitur Warna Dan Texture Rafie Rafie
Jurnal Sains Komputer dan Teknologi Informasi Vol 4 No 1 (2021): Jurnal Sains Komputer dan Teknologi Informasi
Publisher : Institute for Research and Community Services Universitas Muhammadiyah Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33084/jsakti.v4i1.3173

Abstract

Pemrosesan gambar sangat berbeperan pernting dalam mengekstraksi informasi yang berguna dari gambar. Klasifikasi bunga diperlukan untuk mengatasi masalah klasifikasi bunga secara manual serta mempersingkat waktu dalam identifikasi bunga, dalam kasus klasifikasi bunga, pemrosesan gambar adalah langkah penting untuk identifikasi spesies tanaman yang dibantu komputer. Klasifikasi citra bunga di dasarkan pada fitur tingkat rendah seperti warna dan tekstur untuk mendefinisikan dan menggambarkan konten gambar. Penelitian ini bertujuan untuk mengklasifikasi bunga berdasarkan jenis bunga menggunakan Teknik pemrosesan citra. Ektraksi fitur yang digunakan awalnya adalah Hue, Saturation, Value untuk mendapatkan citra warna. Sedangkan untuk mendapatkan citra texture adalah GLCM (Gray Level Co-occurrence Matrik) yaiut Contrast, Correlation, Energy dan Homogenity, kemudian setelah percobaan fitur warna di tambah 3 lagi yaitu Red, Green Blue. Data latih bunga yang digunakan berjumlah 200 gambar yang terdiri dari 4 class bunga (kansas, marguerite, roses dan tulips), masing-masing bunga mewakili dari 50 gambar. Hasil percobaan pertama menunjukkan akurasi menggunakan Naïve Bayes distribusi normal sebesar 66 %, setelah beberapa kali percobaan hingga mendapatkan hasil akurasi tertinggi sebesar 77%, hasil ini diperoleh dengan menerapkan 6 fitur warna dan 4 fitur texture dan menggunakan Naïve Bayes distribusi kernel.
Real-Time K-Means Clustering with Firebase ML Kit: Segmenting Barber Shop Customers by Booking Behavior and Churn Risk Rafie Rafie; Helda Yunita; Amrul Hadiyanoor
Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM) Vol. 10 No. 1 (2025)
Publisher : Fakultas Teknik Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtiulm.v10i1.461

Abstract

This study addresses the challenges of high churn rates and the need for real-time customer behavior analysis in barber shops by developing a K-Means model integrated with Firebase ML Kit. The research analyzes 70,000 booking records from an Android application, focusing on features such as booking frequency, average cancellations, and recency day. The model achieves optimal performance with 5 clusters, validated by a Silhouette Score of 0.58 and a Davies-Bouldin Index of 0.541. Key segments like "Inactive Members" and "High Volume Churners" are successfully identified, enabling targeted business strategies such as reactivation campaigns and priority booking offers. The system is implemented in a mobile application, providing real-time customer segmentation and actionable insights. This approach offers a scalable solution to enhance customer retention and operational efficiency in the barber shop industry
Implementation of Midtrans Payment Gateway in the 81 Coffee Sales Application Ari anto; Rafie Rafie
Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM) Vol. 10 No. 2 (2025)
Publisher : Fakultas Teknik Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtiulm.v10i2.471

Abstract

81 Coffee is a coffee shop business established in Banjarmasin City that faces challenges in its conventional sales system and dependency on third-party marketplaces, which affect profit margins and operational efficiency. This study aims to design and implement a mobile-based coffee sales application to improve transaction efficiency, expand customer reach, and provide a better user experience. The research employed a software development method using the Flutter framework for mobile application development, Firebase as the cloud database, and Midtrans as the payment gateway. The system was tested through functional, integration, and field testing using various devices and network conditions to measure response time, transaction success rate, and data consistency. The results show that the application performs effectively, achieving an average UI response time of 1.2 seconds, payment success rate of 98%, and data consistency of 100%. The integration of Midtrans enables a secure and seamless digital payment process. Overall, the developed system improves operational efficiency and provides a reliable digital sales platform for 81 Coffee’s business operations.
Web-Based Contract Employee Payroll Information System at PT.Bridgestone Kalimantan Plantation Asti Yana; Rahmat Hidayat; Rafie Rafie
Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM) Vol. 10 No. 2 (2025)
Publisher : Fakultas Teknik Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtiulm.v10i2.472

Abstract

The payroll system for contract employees used by PT. Bridgestone Kalimantan Plantation has been relying on Microsoft Excel to calculate contract employee salaries. However, using Microsoft Excel has several drawbacks when it comes to payroll processing, one of which is its inefficiency when dealing with large datasets. This study aims to analyze and design a web-based payroll system for contract employees to assist and simplify the process of calculating payroll for contract employees at PT. Bridgestone Kalimantan Plantation. The methods used in this study include system requirements analysis, database design, and the implementation of a web-based system using Laragon as the database. This research was conducted by analyzing the current system, obtaining data from direct interviews with parties involved in the employee payroll system, and conducting observations. The results of this research simplify the processing of contract employee data, minimize data errors, accelerate data verification and validation, and make salary calculations easier, thereby generating more effective and efficient information.
Edge AI Using MobileNet Architecture for Driver Drowsiness Detection Rafie, Rafi e
Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM) Vol. 11 No. 1 (2026)
Publisher : Fakultas Teknik Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtiulm.v11i1.517

Abstract

Driving safety is a crucial issue significantly influenced by the driver's physical condition, where fatigue and drowsiness are major factors causing traffic accidents. This study aims to develop a real-time drowsiness detection system utilizing Edge AI technology based on the MobileNet architecture. This architecture was selected due to its efficiency in performing image classification on resource-constrained devices. The dataset used consists of 4,000 digital images balanced into open-eye and closed-eye classes. The model was trained using the TensorFlow framework and optimized through post-training quantization into the TensorFlow Lite format to reduce model size and inference latency. Performance evaluation was conducted by testing 372 new test images. The results indicate that the balanced model achieved an accuracy rate of 94%. Confusion matrix analysis showed a precision value of 1.000 for the closed-eye class and a recall of 1.000 for the open-eye class, indicating that the system is highly reliable in minimizing detection errors. With processing speeds reaching 10 to 22 Frames Per Second (FPS) on edge devices, this system is proven effective for implementation as a responsive driving safety assistant. Drowsiness detection duration indicator “Closed: 0.32s” represents part of the system logic used to trigger an alert. The system does not immediately activate an alarm during normal blinking, it measures the duration of eye closure. If the duration exceeds a predefined threshold (e.g., >0.30 seconds), an alert is triggered in the form of an audible alarm
Real-Time Drowsiness Detection Using Dual MobileNetV2 Models on Desktop and Edge Devices Rafi'e
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 8 No. 3 (2026): August
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/ijeeemi.v8i3.371

Abstract

Drowsiness is a leading cause of human error in transportation and in shift-based occupational work, yet delivering reliable real-time detection on affordable, resource-constrained hardware remains difficult. This study aims to develop and evaluate a vision-based drowsiness detection system that behaves consistently across a full-power desktop and a low-cost edge device. The system couples two independent MobileNetV2 transfer-learning classifiers — one for eye state (Open/Closed) and one for mouth state (Yawn/No_yawn) — with a temporal decision engine that converts frame-level predictions into microsleep and excessive-yawning alerts. Both classifiers were trained on a merged multi-source dataset (8,548 training images) and evaluated with a class-balanced protocol (186 images/class for the eye branch and 448 images/class for the mouth branch) to remove test-set imbalance bias. The decision engine was realised as two platform-appropriate pipelines that share an offline-first, retry-capable event architecture: a duration-based, two-tier hysteresis alert on a desktop application (Haar-cascade detection, H5/float32 models) and a frame-count alert designed for a Raspberry Pi 5 edge board (MediaPipe detection, quantised TensorFlow Lite models). On the class-balanced test set the eye branch reached 95.16% (H5) / 95.97% (TFLite) accuracy and the mouth branch reached 96.65% for both formats, with above-99% cross-format prediction agreement. Converting to TFLite cut model size by 73.4% (8.99 to 2.39 MB) and single-frame model inference latency roughly thirteen-fold (about 25 to 1.9 ms, measured on the development machine). Real-time desktop sessions sustained 6.9–12.0 FPS, and the Haar detector located a face in only 15.8% of off-angle frames versus 96.9–98.6% of frontal frames. This single-session result offers a preliminary, rather than definitive, indication of the detector's pose sensitivity. A lightweight dual-MobileNetV2 design with platform-appropriate detectors shows promise for delivering consistent real-time drowsiness alerts across heterogeneous hardware tiers.
Co-Authors Ade Davy Wiranata Amrul Hadiyanoor Ari anto Asti Yana Helda Yunita Rahmat Hidayat Riza Alamsyah