Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 6 No 6 (2022): Juni 2022

Implementasi YOLO versi 3 untuk Mengidentifikasi dan Mengklasifikasi Sampah Kantor berbasis NVIDIA Jetson Nano

Onky Soerya Nugroho Utomo (Fakultas Ilmu Komputer, Universitas Brawijaya)
Fitri Utaminingrum (Fakultas Ilmu Komputer, Universitas Brawijaya)
Edita Rosana Widasari (Fakultas Ilmu Komputer, Universitas Brawijaya)



Article Info

Publish Date
25 Jul 2022

Abstract

Waste has become a problem that is always found in several big cities in Indonesia. Waste management in Indonesia has not been effective in dealing with the increasing amount of waste. One type of waste that continues to grow is office waste which is common in urban areas. Office waste is inorganic waste generated from the activities of office employees. The office waste generated can cause problems in the environment if it is not managed properly, it is necessary to manage waste by sorting waste according to its type. In this study, we design a classification of office waste in the form of paper, plastic bottles, and cans to sort waste according to categories. This office waste classification process uses the YOLO algorithm or You Only Look Once. The YOLO algorithm or You Only Look Once is one of the algorithms used to detect an object in real-time. Based on the results of the tests that have been carried out for object detection, the accuracy results are 94%. After that, the integration test for the classification system obtained an accuracy of 97.3% and for testing the computational time for the classification system the best value for the computational time was 0.271 seconds.

Copyrights © 2022






Journal Info

Abbrev

j-ptiik

Publisher

Subject

Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Description

Jurnal Pengembangan Teknlogi Informasi dan Ilmu Komputer (J-PTIIK) Universitas Brawijaya merupakan jurnal keilmuan dibidang komputer yang memuat tulisan ilmiah hasil dari penelitian mahasiswa-mahasiswa Fakultas Ilmu Komputer Universitas Brawijaya. Jurnal ini diharapkan dapat mengembangkan penelitian ...