IDENTIFIKASI DAN KLASIFIKASI OTOMATIS BOTOL PLASTIK DENGAN METODE ARTIFICIAL NEURAL NETWORK (ANN)

ROSILIANI, DINDA and Yani, Irsyadi (2019) IDENTIFIKASI DAN KLASIFIKASI OTOMATIS BOTOL PLASTIK DENGAN METODE ARTIFICIAL NEURAL NETWORK (ANN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_21201_03051181621027.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
Preview	Text RAMA_21201_03051181621027_0025127104_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB) | Preview
	Text RAMA_21201_03051181621027_0025127104_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (419kB) | Request a copy
	Text RAMA_21201_03051181621027_0025127104_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (212kB) | Request a copy
	Text RAMA_21201_03051181621027_0025127104_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_21201_03051181621027_0025127104_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11kB) | Request a copy
	Text RAMA_21201_03051181621027_0025127104_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (152kB) | Request a copy
	Text RAMA_21201_03051181621027_0025127104_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (558kB) | Request a copy
	Text RAMA_21201_03051181621027_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy

Abstract

In this practical era, plastic that has beneficial characteristics such as flexible, easy to form, heat resistant, light, and cheap is chosen to be one of the most used material to make various things. Especially to make one-time use thing such as plastic bottle. The increased use of plastic bottles start to pile up the waste, therefore the efficient processing is needed. Recycling is one of the most common plastic bottle waste processing, but it is still done manually that causes the probability of human error is still high. Automation of recycling processing needs to be done to reduce the probability of human error. In this research, artificial neural netwok (ANN) method has chosen to develop an automatic identification and classification system using MATLAB software that is connected to a webcam as a censor to make the sorting process in the recycling process of plastic bottle waste become easier. The color space that has been chosen for this research is HSV (hue, saturation and value) that the input is the characteristics of plastic bottles, that are RHSV, GHSV, BHSV, mean2, entropy and variance. And the output is the type of plastic bottle that used as the object of this research, that are PET, HDPE and PP. Based on the development of an automatic identification and classification system for plastic bottles, the database research has been through the training and testing process, and the value for the percentage of success obtained from the training process is 65.3% and the percentage of success from the testing process is 57%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	ANN, PET, HDPE, PP, Plastic Bottle, HSV, identification, classification, MATLAB
Subjects:	T Technology > TR Photography > TR925-1050 Photomechanical processes
Divisions:	03-Faculty of Engineering > 21201-Mechanical Engineering (S1)
Depositing User:	Users 3967 not found.
Date Deposited:	14 Jan 2020 02:38
Last Modified:	14 Jan 2020 02:38
URI:	http://repository.unsri.ac.id/id/eprint/23900

Actions (login required)

View Item