Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal G-Tech : Jurnal Teknologi Terapan Journal of Electrical Engineering and Computer (JEECOM)
Kevin Harlis Oktaviano
Politeknik Internasional Tamansiswa Mojokerto, Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Pencarian Visual Berbasis Jaringan Convolutional Neural Network untuk Platform Pemasaran Digital Produk UMKM Oktaviano, Kevin Harlis; Nasution, Arman Hakim
Journal of Electrical Engineering and Computer (JEECOM) Vol 6, No 2 (2024)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v6i2.9178

Abstract

Usaha Mikro, Kecil, dan Menengah (UMKM) memainkan peran penting dalam perekonomian Indonesia. Namun, UMKM seringkali menghadapi tantangan dalam hal manajemen produk dan interaksi dengan pelanggan terutama dalam pemasaran digital dan E-commerce. Penelitian ini bertujuan untuk mengembangkan platform pencarian visual berbasis Deep Learning untuk identifikasi produk UMKM guna mengatasi tantangan tersebut. Metode penelitian diawali dengan studi literatur tentang Deep Learning dan CNN (Convolutional Neural Network). Selanjutnya dilakukan pengumpulan data berupa gambar produk UMKM, diikuti pra-pemrosesan dan augmentasi data. Kemudian dirancang model menggunakan arsitektur CNN VGG16 yang terdiri dari 16 lapisan untuk pencarian visual dan klasifikasi produk UMKM. Model terbaik yang memenuhi target performa kemudian diintegrasikan pada prototipe platform berbasis web. Platform pencarian visual ini diharapkan dapat membantu pengelolaan produk UMKM serta meningkatkan pengalaman pelanggan dalam mencari dan menemukan produk yang mereka butuhkan. Secara keseluruhan, penelitian ini bertujuan mendukung pertumbuhan UMKM di Indonesia melalui adopsi teknologi Deep Learning
Design and Implementation of a Web-Based Visual Search System for MSME E-Commerce Using the Flask Framework Kevin Harlis Oktaviano; Kevin Ilham Apriandy; M. Sholahudin Sunardiyanta
G-Tech: Jurnal Teknologi Terapan Vol 10 No 1 (2026): G-Tech, Vol. 10 No. 1 January 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i1.8942

Abstract

This research presents the design and implementation of an end-to-end web-based visual search system for MSME e-commerce using the Flask framework and a VGG16-based convolutional neural network. The system addresses two critical challenges commonly faced by MSME digital platforms: product tagging errors during product uploads by sellers and limitations of text-based search for customers. A dual-model architecture is implemented, consisting of a visual search module for similarity-based image retrieval and a backend classification module for automatic product categorization. The system is evaluated using a locally collected MSME product image dataset from the Tapal Kuda region, achieving a classification accuracy of 89.17% and visual search performance with a macro precision of 0.85, macro recall of 1.0, and macro F1-score of 0.91. To support real-time deployment, visual features are pre-extracted and stored, enabling efficient query processing with response times under 2 seconds during concurrent usage testing. The results demonstrate that the proposed system provides effective and practical visual search functionality within a localized MSME context while maintaining feasible computational requirements, making it suitable for deployment in resource-constrained MSME environments.
Identifying Financial Literacy and Asset Participation Segments among Young Adults in Indonesia Using K-Means Clustering Oktavia Citra Resmi Rachmawati; Kevin Ilham Apriandy; Kevin Harlis Oktaviano; Zakha Maisat Eka Darmawan
G-Tech: Jurnal Teknologi Terapan Vol 10 No 3 (2026): G-Tech, Vol. 10 No. 3 July 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i3.10684

Abstract

Financial literacy is crucial in influencing asset ownership decisions among young adults; yet, the variability of financial literacy and asset involvement in Indonesia has not been adequately examined. This research seeks to categorize young Indonesian individuals based on financial literacy and asset participation using the K-Means clustering technique. The research employed a quantitative methodology, incorporating exploratory data analysis of a survey dataset comprising 952 participants and 13 variables related to financial literacy, asset involvement, demographic traits, economic education, and financial behavior. Missing values were addressed by group-based mode imputation for categorical variables and mean imputation for numerical variables, followed by encoding and data standardization utilizing StandardScaler. The ideal number of clusters was assessed by the Elbow Method, Silhouette Score, and Davies–Bouldin Index. Despite achieving the highest Silhouette Score at k = 2, the k = 9 model was chosen due to its lower Davies–Bouldin Index and its ability to enable more nuanced responder segmentation. The findings identified nine categories exhibiting varying levels of basic and advanced financial literacy, ranging from very low to very high. These findings offer significant insights for the formulation of targeted financial education initiatives and financial inclusion policies customized to the attributes of various young adult demographics.
Co-Authors Arman Hakim Nasution Darmawan, Zakha Maisat Eka Kevin Ilham Apriandy M. Sholahudin Sunardiyanta Oktavia Citra Resmi Rachmawati