RANCANG BANGUN TEMPAT SAMPAH PINTAR DENGAN SISTEM PEMILAH OTOMATIS BERBASIS FASTER REGION CONVOLUTIONAL NEURAL NETWORK (FASTER R-CNN)

Rizky Kamila Sari, . (2025) RANCANG BANGUN TEMPAT SAMPAH PINTAR DENGAN SISTEM PEMILAH OTOMATIS BERBASIS FASTER REGION CONVOLUTIONAL NEURAL NETWORK (FASTER R-CNN). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (11kB)
[img] Text
AWAL.pdf
Download (2MB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (136kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (421kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (702kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (986kB)
[img] Text
BAB 5.pdf
Download (124kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (234kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (19kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (3MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (12MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (750kB)

Abstract

The large variety of waste types encountered in daily life requires the public to sort waste correctly to prevent pollution and improper waste management. However, low public awareness and education regarding waste sorting often lead to improperly mixed disposal. Therefore, this research presents the design and development of a smart trash bin capable of automatically sorting four types of waste: organic, anorganic, hazardous (B3), and paper. The system is powered by a Raspberry Pi 4B and a camera using the Faster Region Convolutional Neural Network (Faster R-CNN) for object detection. It is equipped with a Computer Numerical Control (CNC)-based actuator system that uses a stepper motor to direct a waste-carrying box to the appropriate disposal compartment. Based on testing, the smart trash bin successfully sorted 75 out of 80 waste samples, achieving a detection accuracy of 96.25% and a CNC system accuracy of 98.42%. Additionally, the system includes a waste level detection feature that alerts when the trash bin is nearly full by using ultrasonic sensors to detect waste within 10 cm of the sensor. This device has demonstrated efficient sorting performance with high accuracy and shows strong potential to assist the community in properly disposing of waste by type.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2010314023] [Pembimbing: Ni Putu Devira Ayu Martini] [Penguji 1: Silvia Anggraeni] [Penguji 2: Yosy Rahmawati]
Uncontrolled Keywords: Automatic Waste Sorter, Camera Pi, CNC System, Faster R-CNN, Raspberry Pi 4B
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User: RIZKY KAMILA SARI
Date Deposited: 15 Aug 2025 03:10
Last Modified: 15 Aug 2025 03:10
URI: http://repository.upnvj.ac.id/id/eprint/38233

Actions (login required)

View Item View Item