Article Per Year (5 Year)
p-Index From 2021 - 2026
2.286
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer dan Informasi Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JIKO (Jurnal Informatika dan Komputer) J I M P - Jurnal Informatika Merdeka Pasuruan Compiler Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi bit-Tech Jurnal Indonesia : Manajemen Informatika dan Komunikasi Djtechno: Jurnal Teknologi Informasi Jurnal Informatika dan Multimedia
Muhammad Fachrie
Universitas Teknologi Yogyakarta
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Engineering Library & Information Science

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
Pengembangan Aplikasi Penyewaan Lapangan Futsal di Tiki-Taka Barcelona Futsal Berbasis Android dan Web Aziz Nur Rohman; Muhammad Fachrie
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 5 No. 1 (2024): Jurnal Indonesia : Manajemen Informatika dan Komunikasi (JIMIK)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) AMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v5i1.545

Abstract

Tiki-taka Barcelona Futsal is one of the places to rent futsal fields in Prambanan. The data collection and rental system at Tiki-taka Barcelona Futsal is still classified as manual, where renters must first ask for empty schedules via the WhatsApp application or come directly. This manual system has an impact on tenants and groundskeepers. Renters have to WhatsApp or come directly to the place which takes quite a long time because the guards or field admins are not always online on WhatsApp and the guards or field admins have to answer one by one if many people ask questions and not all renters have to travel distance to Tiki-taka Barcelona Futsal. near. By creating an Android and web-based futsal field rental application, it can make it easier for tenants to rent the field and for keepers to manage the field. This application can also carry out online transactions using Midtrans.
Pengembangan Aplikasi Penjualan Tiket Acara Berbasis Website dan Mobile Muhammad Abdurrasyid Nugroho; Muhammad Fachrie
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 5 No. 1 (2024): Jurnal Indonesia : Manajemen Informatika dan Komunikasi (JIMIK)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) AMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v5i1.552

Abstract

This research presents innovation in the form of web-based and mobile event ticket sales applications using the PHP and Kotlin programming languages. The goal is to provide convenience to users in booking event tickets and registering events themselves from their homes. The application is designed to simplify the ticket booking process, improve accessibility, and provide an optimal user experience. Key features include a responsive user interface, being able to register new events, book desired events, view booked events, view registered events. By combining the advantages of PHP and Kotlin programming languages, this research has the potential to provide a more efficient and satisfying event ticket booking and sales experience for users.
Pengembangan Aplikasi Jasa Service Peralatan Elektronik Berbasis Android Menggunakan Payment Gateways Rasid Ferdinan; Muhammad Fachrie
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 5 No. 1 (2024): Jurnal Indonesia : Manajemen Informatika dan Komunikasi (JIMIK)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) AMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v5i1.563

Abstract

Along with the development of current technology such as TV repair, fans, refrigerators, washing machines, irons, air conditioners do not always function properly. There are times when a device is damaged and the user of the device will try to fix it by visiting a service or repair shop for televisions, fans, refrigerators, washing machines, irons and air conditioners. Of course, in this case the user will waste time and energy to go to the service place. Therefore, online booking services such as Grab and Gojek are needed. This online booking service specifically accepts the repair of televisions, fans, refrigerators, washing machines, irons, air conditioners, directly so that device users can save time and costs. With the selection of categories based on electronic products, it is easier for users if they want to find a service based on the electronic equipment that the user wants to repair. This application will be equipped with an online payment system integrated with Midtrans as a payment gateway service provider so that the transaction process becomes faster, easier and more practical.
Real-Time Identification of Potholes and Road Damage Using Yolov11 Muh Ryamizard Albasith; Muhammad Fachrie
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3371

Abstract

Road surface deterioration poses increasing risks to transportation safety and operational efficiency, prompting the need for automated, real-time detection systems suitable for mobile deployment. This study develops and evaluates a YOLOv11-based road damage detection model implemented on Android devices, targeting four defect classes: potholes, cracks, surface waviness, and patched roads. Unlike previous YOLO-based approaches (e.g., YOLOv5, YOLOv8), YOLOv11 integrates a C2PSA attention mechanism and an anchor-free architecture, offering enhanced detection accuracy and computational efficiency critical for resource-limited environments. A total of 2,989 images were collected and annotated from public datasets and organized in standard YOLO format. Model evaluation was conducted using metrics such as AP@0.5, confidence curves, confusion matrix analysis, and latency benchmarks. YOLOv11 achieved high AP@0.5 scores of 0.849 and 0.850 for cracked and patched roads, with a real-time inference latency of 2.6 ms per image and an end-to-end latency of 3.8 ms faster than YOLOv8 in comparable mobile settings. The model was successfully integrated into an Android application, demonstrating robust performance during real-time deployment. However, the system showed reduced accuracy in detecting subtle or low-contrast defects such as shallow potholes and wavy surfaces, often due to background-texture similarity. These limitations suggest the need for improved data diversity and feature refinement. Overall, the findings confirm YOLOv11’s suitability for mobile-based road monitoring, combining speed, accuracy, and lightweight deployment. Future research should address generalization challenges under varied lighting and environmental conditions.
Hamisfera: Sistem Rekomendasi Progresi Chord Berbasis Sentimen Lirik Melalui Studi Komparatif Arsitektur Transformer dan Mixture of Experts Fara Daud Ibra; Muhammad Fachrie
Jurnal Informatika dan Multimedia Vol. 17 No. 2 (2025): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v17i2.9057

Abstract

Abstrak – Proses penciptaan lagu sering kali memerlukan penyelarasan antara nuansa emosional lirik dengan harmoni musik yang tepat. Namun, penerjemahan sentimen lirik menjadi progresi chord secara manual merupakan tantangan yang berarti. Penelitian ini bertujuan untuk mengidentifikasi arsitektur deep learning yang optimal bagi sistem Hamisfera, sebuah kerangka dua tahap yang dirancang untuk memberikan rekomendasi progresi chord yang relevan secara emosional berdasarkan lirik multibahasa. Metodologi melibatkan studi komparatif antara arsitektur Transformer dan Mixture of Experts menggunakan model pralatih XLM-R, yang dievaluasi pada dataset 73.369 entri, diperluas dari 12.000 entri data orisinal melalui augmentasi dan pembersihan. Temuan penelitian menunjukkan hasil yang berbeda per tugas, untuk klasifikasi emosi, arsitektur MoE pralatih menunjukkan keunggulan kecil dengan F1-Score sebesar 0,844. Sebaliknya, untuk generasi chord, arsitektur Transformer pralatih unggul secara keseluruhan berkat kefasihan generasi yang lebih baik, dengan BLEU-4 sebesar 0,608, serta efisiensi sumber daya yang lebih tinggi. Oleh karena itu, konfigurasi hibrida MoE untuk klasifikasi dan Transformer untuk generasi ditentukan sebagai solusi paling optimal.
SISTEM PREDIKSI TINGKAT KEMATANGAN BUAH TOMAT MENGGUANAKAN ARSITEKTUR VGG16 Rayhan Dzikri Fauzi; Muhammad Fachrie
Djtechno: Jurnal Teknologi Informasi Vol 5, No 3 (2024): Desember
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v5i3.5005

Abstract

Penelitian ini bertujuan mengembangkan sistem prediksi kematangan buah tomat menggunakan metode Convolutional Neural Networks (CNN). Sistem ini dirancang untuk menggantikan penilaian manual yang sering kali kurang efisien dan akurat akibat subjektivitas manusia. Data penelitian berupa gambar buah tomat yang diperoleh dari platform Kaggle, dengan kategori matang, mentah, dan setengah matang. Dua model CNN, yaitu Simple CNN dan VGG16, diterapkan untuk melakukan klasifikasi. Setelah melalui proses pra-pemrosesan dan augmentasi data, kedua model dibor dan diuji. Hasil menunjukkan bahwa model VGG16 memberikan kinerja terbaik dengan akurasi 97,17% pada data latih dan 95,56% pada validasi data. Kesimpulannya, model VGG16 lebih unggul dalam prediksi kematangan buah tomat dan diharapkan mampu meningkatkan efisiensi serta akurasi penilaian kematangan buah di industri pertanian.
Sistem Reservasi Berbasis Android dengan Dasbor Analitik Tito Zaki Saputro; Muhammad Fachrie
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 14, No 3: Desember 2025
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v14i3.3302

Abstract

The conventional reservation process at Ema Mom Kids Baby Spa has led to various operational issues, such as scheduling errors and inefficient queues. This research aims to address these challenges through the development of an integrated digital reservation system. This study successfully produced a dual-platform system (a mobile application for the business owner and a web platform for customers) that manages booking, schedule, and service data. Testing using the black-box method demonstrated that all core system functionalities from booking to schedule management performed validly. The system also features a descriptive analytics dashboard that serves as a data-driven decision-making tool for the business owner. The developed system has proven effective in improving operational efficiency, minimizing operational errors, and providing strategic business insights.Keywords: Reservation system; Analytics dashboard; Baby spa; Schedule management; Android  AbstrakProses reservasi konvensional di Ema Mom Kids Baby Spa memicu antrean yang tidak efisien dan kesalahan jadwal. Untuk mengatasi masalah itu, sebuah sistem reservasi digital terintegrasi dikembangkan. Penelitian ini berhasil menghasilkan sistem dua platform (aplikasi mobile untuk pemilik usaha dan platform web untuk pelanggan) yang mampu mengelola seluruh fungsionalitas utama. Validasi fungsional menggunakan metode black box testing membuktikan bahwa seluruh fitur inti, dari alur pemesanan hingga pengelolaan jadwal, telah berjalan sesuai harapan. Aplikasi ini juga menyediakan dasbor analitik deskriptif yang berfungsi sebagai alat bantu pengambilan keputusan berbasis data bagi pemilik usaha. Implementasi sistem ini terbukti tidak hanya meningkatkan efisiensi dan meminimalkan galat (error) operasional, tetapi juga menyediakan wawasan bisnis strategis bagi pemilik. 
Intelligent Document Processing Berbasis OCR + Transformers dan CNN untuk Verifikasi Dokumen Bantuan Pangan David Bagas Santoso; Muhammad Fachrie
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 14, No 3: Desember 2025
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v14i3.3351

Abstract

The rice assistance program is a government initiative to alleviate poverty by distributing rice to low-income households. This study aims to design and implement an Intelligent Document Processing system based on Convolutional Neural Networks (CNN) and hybrid Optical Character Recognition (OCR) to facilitate the verification of social assistance documents. The system integrates the LayoutLMv3 model for text entity extraction and a ResNet-18 CNN for signature-box classification, supported by conventional OCR and TrOCR for challenging text regions. The research methodology covers system design and model development. Experimental results show that the system can successfully convert PDF documents into images and accurately recognize key entities such as names and national ID numbers using LayoutLMv3 (validation accuracy 96.78%). Although ResNet-18 achieves a validation accuracy of 99.04%, it remains biased toward majority classes and is not yet reliable for verification decisions. The proposed system has the potential to accelerate and standardize document verification, with future work focusing on dataset rebalancing and improving the signature classification model. Keywords: LayoutLMv3; ResNet-18; Optical Character Recognition; TrOCR AbstrakProgram bantuan pangan beras merupakan upaya pemerintah dalam menanggulangi kemiskinan melalui distribusi beras kepada masyarakat kurang mampu. Penelitian ini bertujuan merancang dan mengimplementasikan Intelligent Document Processing berbasis Convolutional Neural Network (CNN) dan OCR hibrida untuk mempermudah proses verifikasi dokumen bantuan pangan. Sistem ini mengintegrasikan model machine learning LayoutLMv3 untuk ekstraksi entitas teks serta CNN ResNet-18 untuk klasifikasi tanda tangan, dengan dukungan Optical Character Recognition (OCR) dan TrOCR. Metode penelitian mencakup perancangan sistem dan pengembangan perangkat. Hasil pengujian menunjukkan bahwa sistem mampu mengekstraksi dokumen PDF menjadi citra, mengenali entitas seperti nama dan NIK dengan akurasi tinggi menggunakan LayoutLMv3 (val_accuracy 96,78%), serta mengklasifikasikan kotak tanda tangan dengan ResNet-18 (val_accuracy 99,04%). Namun, ResNet-18 masih bias terhadap kelas mayoritas sehingga belum dapat dianggap andal untuk keputusan verifikasi. Sistem yang diusulkan berpotensi mempercepat pemeriksaan dokumen bantuan pangan, sementara pengembangan lanjut difokuskan pada penyeimbangan data dan penyempurnaan model klasifikasi tanda tangan. 
Co-Authors Adityo Permana Wibowo Alfin Andrias Wardoyo Aziz Nur Rohman Bayu Ajiwicaksana Bilal Nurul Fauzi Dadang Heksaputra David Bagas Santoso Fadil Indra Sanjaya Fara Daud Ibra Hadi Wiyono Muh Ryamizard Albasith Muhammad Abdurrasyid Nugroho Nur Hidayati Nuzula Afini Rasid Ferdinan Rayhan Dzikri Fauzi Sulistyo Dwi Sancoko Tito Zaki Saputro Waluyo, Anita Fira Zahra Septa Hati