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
Rahmatul Bijak Nur Kholis
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 
Rancang Bangun Sistem Klasifikasi Sampah Anorganik Kantor menggunakan Deep Learning Arsitektur Xception berbasis NVIDIA Jetson Nano Rahmatul Bijak Nur Kholis; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 6 (2022): Juni 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Ineffective waste management is believed to be the reason of the piling amount of waste in landfill. There should be sorting mechanism from the source of waste before being transported to TPA. Offices are of the areas which produce waste similar to household waste and must carry out waste sorting process. Actually, there have been trash cans provided for different waste type. However, people tend to be ignorant of this and keep on throwing waste not in the right container. Thus, the trash can method is rendered ineffective. This study attempted to create a prototype of trash can that classifies office waste in the form of plastic bottles, cans, and paper. The system then automatically places those waste based on their category container. To perform its job of classifying, the deep learning Xception architecture method is used, applied to the system processor, namely the NVIDIA Jetson Nano. This system produces output, namely the movement of the sorting arm. The sorting arm moves to the left if the classification results are plastic bottles waste, it moves to the right for cans waste, and it stays in the middle for paper waste. For testing the classification of waste objects in the system, the accuracy result obtained 91.67% and the average computation time for classification was 0.06385 second. An integration testing was also carried out on the system which resulted in an accuracy of 97.22%.
Co-Authors Utaminingrum, Fitri