Article Per Year (5 Year)
p-Index From 2021 - 2026
3.72
P-Index
This Author published in this journals
All Journal Jurnal Computer Science and Information Technology (CoSciTech) Jurnal Komtekinfo Jurnal Ilmiah Sistem Informasi dan Ilmu Komputer Populer: Jurnal Penelitian Mahasiswa Jurnal Ilmiah Teknik Informatika dan Komunikasi Jurnal Ilmiah Dan Karya Mahasiswa Jurnal Sistem Informasi dan Ilmu Komputer Jurnal Elektronika dan Teknik Informatika Terapan Jurnal Penelitian Teknologi Informasi dan Sains Saber: Jurnal Teknik Informatika, Sains dan Ilmu Komunikasi Jurnal Quancom: Jurnal Quantum Komputer Jurnal Pengabdian Masyarakat dan Riset Pendidikan Journal of Information System and Education Development
Billy Hendrik
Unknown Affiliation
Humanities Automotive Engineering Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal Computer Science and Information Technology (CoSciTech)

 1 
Implementasi Convolutional Neural Netowork Untuk Klasifikasi Citra KTP-El SATRIA, SATRIA; Sumijan; Billy Hendrik
Computer Science and Information Technology Vol 5 No 1 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v5i1.6708

Abstract

The Electronic Identity Card (e-KTP) serves as the official proof of identity for residents, issued by the relevant implementing agency across the entire territory of the Unitary State of the Republic of Indonesia. Mandatory for both Indonesian citizens (WNI) and foreigners (WNA) holding a Permanent Stay Permit (ITAP) and aged 17 or married, the e-KTP is susceptible to potential damage, often arising from factors such as prolonged usage or improper handling. Physical damage to the e-KTP can impede the document's ability to accurately verify identity, potentially impacting public services and government administration. This research aims to assess the condition of e-KTPs, determining whether they are in good or damaged condition. The study employs the Convolutional Neural Network (CNN) method, known for its significant results in image recognition by attempting to emulate the image recognition system in the human visual cortex, facilitating the processing of image information. This method comprises two architectural layers: Feature Learning and Classification. The dataset utilized in this research comprises images of e-KTPs sourced from the Population and Civil Registration Office of Bengkalis Regency, totaling 400 images categorized into two classes: 200 for good condition and 200 for damaged condition. The research findings enable the determination of the e-KTP image's condition, achieving a 90% accuracy rate.
Prediksi Penjualan Sepeda Motor Yamaha dengan Jaringan Syaraf Tiruan dan Backpropagation (Studi Kasus: CV Sinar Mas) Santriawan, Aji; Gunadi Widi Nurcahyo; Billy Hendrik
Computer Science and Information Technology Vol 5 No 1 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v5i1.6709

Abstract

Perkembangan teknologi yang begitu pesat dengan kebutuhan masyarakat tentang kendaraan pribadi untuk mempermudah segala aktivitas sehari-hari. Pertumbuhan penduduk Indonesia yang meningkat juga mempengaruhi bertambahnya jumlah kendaraan bermotor yang ada di Indonesia. Sepeda Motor Yamaha merupakan salah satu brand sepeda motor yang telah lama berada di Indonesia. Oleh karena itu konsumen menggunakan sepeda motor saat ini sangatlah tinggi. Dengan peningkatan penjualan dan minat masyarakat terhadap sepeda motor untuk tahun berikutnya. Masalah yang terjadi pada CV Sinar Mas adalah tidak ada metode untuk memprediksi bagaimana kecenderungan peningkatan/penurunan jumlah unit tertentu setiap tahun. Sehinggan dengan Jaringan Syaraf Tiruan menggunakan metode Backpropagation dengan Software Matlab dapat menjadi data prediksi penjualan sepeda motor di bulan berikutnya atau yang akan datang. Penelitian ini bertujuan untuk meningkatkan akurasi penjualan sepeda motor Yamaha pada Cv Sinar Mas. Metode yang digunakan dalam penelitian ini adalah Jaringan Saraf Tiruan Backpropagation. Algoritma Backpropagation digunakan untuk memprediksi dengan akurat berdasarkan data historis penjualan sepeda motor Yamaha dari tahun 2019-2022. Dataset yang digunakan terdiri dari 48 data penjualan. Hasil penelitian ini dapat memprediksi penjualan dengan menggunakan pola terbaik yaitu 4-25-1 dengan hasil MSE 0.00010594. Oleh karena itu penelitian ini dapat menjadi acuan untuk mempredisi penjualan sepeda motor Yamaha pada CV Sinar Mas
Vision Transformer untuk Identifikasi 15 Variasi Citra Ikan Koi Uthama, Rayhan; Yuhandri; Billy Hendrik
Computer Science and Information Technology Vol 5 No 1 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v5i1.6711

Abstract

This research aims to classify various types of koi fish using Vision Transformer (ViT). There is previous research [1] using Support Vector Machine (SVM) as a classifier to identify 15 types of koi fish with training and testing datasets respectively of 1200 and 300 images. This research was continued by research [2] which implemented a Convolutional Neural Network (CNN) as a classifier to identify 15 types of koi fish with the same amount dataset. As a result, the research achieved a classification accuracy rate of 84%. Although the accuracy obtained from using CNN is quite high, there is still room for improvement in classification accuracy. Overcoming obstacles such as limitations in classification accuracy in previous studies and further exploration of the use of new algorithms and techniques, this study proposes a ViT architecture to improve accuracy in Koi fish classification. ViT is a deep learning algorithm adopted from the Transformer algorithm which works by relying on self-attention mechanism tasks. Because the power of data representation is better than other deep learning algorithms including CNN, researchers have applied this Transformer task in the field of computer vision, one of the results of this application is ViT. This study was designed using class and number datasets retained from two previous studies. Meanwhile, the koi fish image dataset used in this research was collected from the internet and has been validated. The implementation of ViT as a classifier in koi classification in this research resulted in an accuracy level that reached an average of 89% in all classes of test data.
Co-Authors Ade Saputra Akhiruddin Pulungan Amir Salim Khairul Rijal Deti Karmanita Diffri Solihin Siregar Dwana Abdi Juliantho Firdaus Firdaus , Firdaus Fungki Wahyu Ghinaa Fadhiilah Gunadi Widi Nurcahyo Hasri Awal Juliantho, Dwana Abdi Ladyka Febby Olivia Lubis, Fitri Amelia Sari Lubis, Fitri Sari Lubis, Siti Sahara Mardhiah Masril Mardhiah Masril Ondra Eka Putra Resnawita Resnawita Resnawita Riris Agustin Ritna Wahyuni Rizqi Nusabbih Hidayatullah Gaja Roy Efendi Subarja Ruri Hartika Zain Santriawan, Aji Satria Satria, Satria Siti Sahara Lubis Sonia Indhira Sonia Indhira, Sonia Sumijan Uthama, Rayhan Yuhandri