Claim Missing Document
Check
Articles

Found 7 Documents
Search

Potensi akurasi Convolutional Neural Network (CNN) dalam mengenali pakaian adat Herwinsyah, Herwinsyah; Yuswanto Jaya, Dery
IT Journal Research and Development Vol. 8 No. 2 (2024)
Publisher : UIR PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25299/itjrd.2023.12690

Abstract

The diversity of cultures in Indonesia is proof that Indonesia is a country that is rich in cultural diversity. Many foreign tourists who want to know about culture in Indonesia are not directly proportional to the media to introduce culture in Indonesia. Therefore, this study aims to classify images of traditional clothing by detecting images of traditional clothing sent to the application to determine the name of the traditional soldier. These images will be converted into vectors and processed to find the closest similarity level. The Deep Learning method which currently has the most significant results in image recognition is the Convolutional Neural Network (CNN). The analysis carried out resulted in an accuracy of 0.7934 with an epoch of 20 and a data set of 700 data. The accuracy value is 0.7934 which is a large enough number to determine the correct classification of image objects. This is proven by testing on 10 different images and only 1 image is inaccurate with 90% accuracy.
IoT-Based Driver Health Monitoring System with Location Based Service Feature for Fast Treatment at Nearest Health Facilities Jaya, Dery Yuswanto
International Journal of Health Engineering and Technology Vol. 3 No. 6 (2025): IJHET MARCH 2025
Publisher : CV. AFDIFAL MAJU BERKAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55227/ijhet.v3i6.263

Abstract

This research aims to develop and test an Internet of Things (IoT)-based driver health monitoring system with Location Based Service (LBS) features for quick response to the nearest health facility. The system uses health sensors (heart rate, body temperature, SpO2, and fatigue), GPS module, and Wi-Fi/GSM-based communication to monitor the driver's condition in real-time. The research method includes system design, sensor testing, field testing with 25 drivers, and system performance analysis. The results show that the health sensor has an accuracy above 90%, with detection of critical conditions within 3-5 seconds and sending emergency notifications within 10 seconds. The LBS feature successfully provided health facility recommendations with 98% accuracy. Field tests detected several cases of critical conditions and proved the effectiveness of the system in real conditions. Ninety percent of participants expressed satisfaction with the system. The research conclusion confirms that the system can improve driver safety, reduce the risk of accidents due to health problems, and has the potential for wide application in the transportation and logistics sectors. However, there are limitations such as dependence on the internet and the accuracy of fatigue sensors that need to be improved in future research.
Komparasi Fungsionalitas EVE-NG dan GNS3: Simulasi Protokol Jaringan Sholeha, Eka Wahyu; Jaya, Dery Yuswanto; Supriyanto, Arif; Utomo, Hendrik Setyo
Algoritma: Jurnal Ilmu Komputer dan Informatika Vol 9, No 1 (2025): April 2025
Publisher : Universitas Islam Negeri Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/algoritma.v9i1.23864

Abstract

The development of network technology drives the need for efficient, flexible, and economical simulation tools for learning and testing network architectures. This research compares two popular platforms, GNS3 (Graphical Network Simulator-3) and EVE-NG (Emulated Virtual Environment - Next Generation), in terms of functionality, network performance, and resource consumption. Testing was carried out through network protocol simulations with identical topologies, and parameters such as throughput, delay, jitter, packet loss, convergence time, and CPU, RAM, and disk I/O usage were measured. The results show that EVE-NG is more stable with high throughput, low jitter, and optimal transmission efficiency, making it suitable for complex simulations. Meanwhile, GNS3 is more resource-efficient and has faster convergence, ideal for basic learning. The conclusion of this research emphasizes that the choice of platform depends on the needs: EVE-NG for large scale, GNS3 for education. These findings provide guidance for educators, professionals, and researchers in choosing simulation tools according to the context. Keywords: Network Simulation, GNS3, EVE-NG, Protocol Emulation, Performance Evaluation
Analisis Perbandingan Learnability antara Framework dan Native PHP pada Mahasiswa Informatika Universitas XYZ Jaya, Dery Yuswanto; Ulfah Siregar, Maria
Journal Information Technology Trends (JITRENDS) Vol 2 No 02 (2025): Journal Information Technology Trends Volume 02. No 02 Juni 2025
Publisher : mijournal.org

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51817/jitrends.v2i2.34

Abstract

Aplikasi tersebut merupakan salah satu syarat penyelesaian skripsi Mahasiswa Informatika Universitas XYZ. Dalam menyelesaikan skripsi, pengajuan skripsi harus cepat dan mudah karena waktu pengerjaan yang cukup singkat. Penelitian diperlukan karena akan membantu memberikan pemahaman tentang pembuatan website. Memiliki itu dapat membantu dalam mengimplementasikan situs web dengan cepat dan efektif. Dalam mencapai hal itu, siswa yang dituju akan dikonsep dan diarahkan dengan metode yang lebih tepat. Metode penelitian dilakukan dengan tinjauan pustaka, penyusunan instrumen, pengumpulan data, dan analisis data. Hasil yang diperoleh dari penelitian ini adalah secara umum Native PHP mempunyai tingkat Learnability yang lebih baik dibandingkan Framework. Namun perbedaannya praktis tidak signifikan. Dapat disimpulkan bahwa hasil penelitian perbandingan tingkat Learnability Framework dan Native PHP pada mahasiswa informatika menghasilkan sedikit perbedaan dikarenakan populasi yang sama yaitu mahasiswa informatika yang mempunyai pengalaman membuat aplikasi website dan sistem informasi dengan menggunakan keduanya platform.
OPTIMASI JARINGAN WI-FI DI KANTOR DESA BUMI JAYA MELALUI PEMBATASAN AKSES GAME ONLINE Dery, Dery Yuswanto Jaya; Eka Wahyu Sholeha; H, Herpendi; Dewi Indra Anggraeni
Jurnal Widya Laksmi: Jurnal Pengabdian Kepada Masyarakat Vol. 5 No. 1 (2025): Jurnal WIDYA LAKSMI (Jurnal Pengabdian Kepada Masyarakat) - Inpress
Publisher : Yayasan Lavandaia Dharma Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59458/jwl.v5i1.157

Abstract

Optimasi jaringan Wi-Fi di kantor publik telah menjadi sangat penting untuk memastikan penggunaan yang produktif dan efisien. Di Desa Bumi Jaya, yang terletak di Pelaihari, Kabupaten Tanah Laut, Kalimantan Selatan, penyalahgunaan akses internet untuk aktivitas game online oleh pemuda setempat menyebabkan gangguan di lingkungan kantor, mempengaruhi fokus dan kenyamanan pegawai negeri. Studi ini menerapkan fitur Queue Tree pada perangkat Mikrotik untuk mengatasi masalah tersebut, dengan tujuan untuk mengelola alokasi bandwidth secara efektif dan memprioritaskan aktivitas penting seperti administrasi dan pelayanan publik. Penelitian dimulai dengan survei dan observasi untuk mengidentifikasi pola penggunaan jaringan dan kualitas infrastruktur. Sistem Queue Tree dirancang dan diimplementasikan untuk mengurangi bandwidth untuk aktivitas yang tidak relevan, seperti game online, tanpa sepenuhnya memblokir akses. Hasil menunjukkan peningkatan signifikan dalam efisiensi bandwidth, dengan prioritas dialokasikan untuk tugas administratif, meningkatkan kinerja jaringan dan pengalaman pengguna. Inisiatif ini juga mengurangi tingkat kebisingan dan meningkatkan kebersihan di area kantor, menciptakan lingkungan kerja yang lebih kondusif. Kegiatan ini memberikan pengetahuan dan keterampilan yang diperlukan kepada pejabat setempat untuk memelihara dan mengoptimalkan jaringan secara mandiri di masa mendatang, memastikan pengelolaan yang berkelanjutan. Implementasi Queue Tree berhasil mengatasi tantangan teknis sekaligus mendorong lingkungan kerja yang produktif dan tertib.
PERANCANGAN JARINGAN MENGGUNAKAN ROUTING OSPF PADA SMPN 4 BANJARBARU Maharani, Monica Rahayu; Arrahimi, Ahmad Rusadi; Jaya, Dery Yuswanto
JEIS: Jurnal Elektro dan Informatika Swadharma Vol 5, No 1 (2025): JEIS EDISI JANUARI 2025
Publisher : Institut Teknologi dan Bisnis Swadharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56486/jeis.vol5no1.550

Abstract

SMPN 4 Banjarbaru is one of the schools that uses technology in its learning process. Because of this, a poor internet network is a big problem that can disrupt the learning process. This research aims to create a network design using OSPF routing. This research uses the PPDIOO cycle network design method (prepare, plan, design, implement, operate, optimize). The research resulted in a new network configuration at SMPN 4 Banjarbaru, which implemented OSPF routing. Apart from increasing the efficiency of the internet network in schools, OSPF routing technology will make it easier to manage routes without the need for complicated manual configuration because OSPF can quickly adapt to changes in network topology, such as adding or removing network devices, so that the network continues to operate efficiently.SMPN 4 Banjarbaru merupakan salah satu sekolah yang sudah menggunakan teknologi dalam proses pembelajarannya. Karena hal tersebut, jaringan internet yang kurang bagus menjadi masalah besar yang dapat menganggu proses pembelajaran. Penelitian ini bertujuan membuat rancangan jaringan menggunakan routing OSPF. Penelitian ini menggunakan metode perancangan jaringan siklus model PPDIOO (prepare, plan, design, implement, operate, optimize). Penelitian menghasilkan konfigurasi baru jaringan di SMPN 4 Banjarbaru yang menerapkan routing OSPF. Teknologi routing OSPF selain meningkatkan efisiensi jaringan internet di sekolah, akan memudahkan manajemen rute tanpa perlu konfigurasi manual yang rumit karena OSPF dapat dengan cepat beradaptasi terhadap perubahan topologi jaringan, seperti penambahan atau pengurangan perangkat jaringan, sehingga jaringan tetap beroperasi dengan efisien.
Quantum-Safe Evaluation of TLS 1.3 Hybrid with ML-DSA Jaya, Dery Yuswanto; Jakaria
Bahasa Indonesia Vol 17 No 09 (2025): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v17i09.428

Abstract

Quantum computing poses a significant threat to classical cryptographic schemes widely used in modern networks, particularly RSA and ECC, which are vulnerable to Shor’s algorithm. To address this challenge, this study conducts a post-quantum security evaluation of TLS 1.3 by implementing hybrid X25519+Kyber key exchange and ML-DSA digital signatures. The objective is to assess the performance, overhead, and effectiveness of hybrid TLS in ensuring long-term data confidentiality within enterprise environments. The research method involves building a server–client testbed using OpenSSL with the oqs-provider, applying network load simulations under various latencies, and measuring key metrics including handshake latency, CPU utilization, certificate size, and client compatibility. The results indicate that hybrid TLS 1.3 with X25519+Kyber introduces only moderate handshake latency, while ML-DSA increases certificate size but remains manageable for deployment in modern enterprise systems. The conclusion of this study is that combining X25519+Kyber with ML-DSA offers an effective transition path towards quantum-safe networks without significantly sacrificing system performance..