Image of IMPLEMENTASI METODE K-NEAREST NEIGHBORS (KNN) PADA SISTEM SORTIR BOTOL PLASTIK OTOMATIS BERBASIS CITRA

Skripsi

IMPLEMENTASI METODE K-NEAREST NEIGHBORS (KNN) PADA SISTEM SORTIR BOTOL PLASTIK OTOMATIS BERBASIS CITRA

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

Environmental problems due to the accumulation of plastic waste, especially plastic bottles that are difficult to decompose naturally, encourage the need for an efficient waste management system to support a circular economy. One important step in the recycling process is the sorting of plastic bottles based on their type. This research aims to design and implement a digital image-based automatic sorting system using the K-Nearest Neighbors (KNN) method to classify three types of plastic, namely PET (Polyethylene Terephthalate), HDPE (High-Density Polyethylene), and PP (Polypropylene). The system is built in the form of a physical prototype consisting of a conveyor belt, web camera, mini computer, mini monitor, and wireless keyboard, where the camera captures real-time images of bottles and the system processes them using RGB color images converted to HSV. The dataset is 150 images, divided into 120 training images and 30 test images, and processed using Python libraries such as OpenCV, NumPy, and scikit-learn. The classification results show that the KNN method with a value of K = 1 is able to classify plastic bottle types with an accuracy of 83%. The system works in real-time and proved to be stable at a conveyor speed of 0.04 m/s, making it quite efficient for plastic bottle sorting applications. In conclusion, the system is capable of automatic and economical classification of plastic bottles with high accuracy, and can serve as a basis for the development of more sophisticated plastic waste sorting systems. Suggestions for further development include optimizing lighting and image capture, increasing sorting speed, and testing with larger and more varied datasets, so that the system can be more adaptive to real conditions in the field.

Availability
Inventory Code Barcode Call Number Location Status
2507005434T183013T1830132025Central Library (Reference)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1830132025
Publisher
Indralaya : Prodi Teknik Mesin, Fakultas Teknik Universitas Sriwijaya.,
Collation
xiii, 97 hlm.; ilus.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
621.807
Content Type
Text
Media Type
unmediated
Carrier Type
-
Edition
-
Subject(s)
Prodi Teknik Mesin
Metode K-Nearest Neighbors (KNN)
Specific Detail Info
-
Statement of Responsibility
Other version/related
File Attachment
Comments
You must be logged in to post a comment