Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Aditia Reza Nugraha
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Sistem Deteksi Hama Babi menggunakan CNN (Convolutional Neural Network) berbasis Raspberry Pi Aditia Reza Nugraha; Fitri Utaminingrum; Hurriyatul Fitriyah
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 9 (2021): September 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Indonesia is an agricultural country, part of which contains the agricultural sector, such as maize, rice, oil palm and other food crops. The area of ​​agricultural land increases every year by cutting down forests as an additional resource. Forest encroachment for the agricultural sector has an impact on the environment in which agriculture is located, where agriculture is in direct contact with forest areas. Agricultural areas adjacent to plantations cause wild animals such as wild boar to become pests that can damage plantation products and are also dangerous if they come into direct contact with humans who are present while doing activities in the area. As a pest repellent prevention, it is usually carried out by conventional means such as pig traps, poison, or nets in the affected area. As an innovation using smart technology, a solution to this problem requires a system that functions as a security supervisor for plantations. The system that will be created serves to monitor the situation when the plantation is invaded by pests such as wild boars. The surveillance system uses a webcam that is attached to the Raspberry pi model 4 which functions to see the state of the garden when there are objects of pig pests. The monitoring system on the camera will classify wild boar and farmer objects on plantations using the Convolutional Neural Network method by YOLOv3 architecture with an accuracy rate of the data model for a value of 97%. The system will also be built using a buzzer notification as a notification when a pest is detected on hardware with a success of 100% buzzer output.
Co-Authors Fitriyah, Hurriyatul Utaminingrum, Fitri