Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Coreid Journal
Hamami, Muhammad Syamil
Unknown Affiliation
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Coreid Journal

 1 
Design and Deployment of Backend Integration System for Rumah Jurnal Using ExpressJS Hamami, Muhammad Syamil; Rifqi Syamsul Fuadi
CoreID Journal Vol. 2 No. 3 (2024): November 2024
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v2i3.74

Abstract

The design and deployment of a backend integration system for Rumah Jurnal at UIN Sunan Gunung Djati Bandung addresses the increasing complexity of journal management systems across faculties. A centralized platform enhances accessibility and operational efficiency by consolidating multiple journal databases into a unified interface. Developed using ExpressJS, the system ensures reliable data synchronization and robust management through an API-driven architecture, security measures, and deployment on a Virtual Private Server (VPS) with Nginx and PM2. Testing demonstrates significant performance improvements, including faster response times and seamless user experiences, positioning the system as an effective solution for modernizing journal management.
GreenEye: Plant Classification Using MobileNet V2 Hamami, Muhammad Syamil; Firdaus, Muhammad Rihap; Pasha, Pancadrya Yashod; Firdaus, Muhammad Raihan; Sugiarto, Awang
CoreID Journal Vol. 3 No. 3 (2025): November 2025
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v3i3.138

Abstract

Biodiversity in Indonesia includes more than 30,000 species of plantsand mushrooms, but public knowledge about these plants is still limited. The research aims to develop a mobile application called GreenEye that uses machine learning to detect and classify plants based on images. The model used is based on the MobileNet V2 architecture, a type of Convolutional Neural Network (CNN) designed for high-efficiency image classification tasks. Research data collected from PlantNet and Google Images, consisting of 2800 images covering seven plant species: Ananas comosus, Artocarpus heterophyllus, Carica papaya, Cocos nucifera, Musa spp, Nephelium lappaceum, and Salacca zalacca. Each species is categorized into four plant parts: fruit, flower, leaf, and habit. (habitus). This data is then processed through various preprocessing stages such as data cleaning, format conversion, resizing, cropping, and image augmentation. The results showed that the MobileNet V2 model was able to classify parts of plants with high accuracy, especially on fruits and leaves with accurations above 90%. However, the accuration was slightly lower for flowers and habits, which is about 70%. Classification errors occurred mainly in species with high visual similarities. To improve the performance of the model, it is recommended that further research increase the quantity and diversity of datasets.
Co-Authors Firdaus, Muhammad Raihan Firdaus, Muhammad Rihap Pasha, Pancadrya Yashod Rifqi Syamsul Fuadi Sugiarto, Awang