CD Skripsi

Sistem Klasifikasi Sampah Plastik Menggunakan Pencitraan Multispektral Dan Jaringan Syaraf Tiruan

---

ABSTRACT
Sorting plastic covering is crucial before plastic waste has brought into landfill. Manual sorting doesn’t recognized due to limitation of human vision, subjective, and time consuming. Multispectral imaging has advantages for plastic waste classification, because it can cover only visible range of electromagnetic spectrum, but also infrared range (700 – 2500 nm). Plastic waste has better response in Near-Infrared range. Reflectance intensity is obtained for each pixel in Region of Interest to classify plastics category. Results show that average reflectance intensity are different for each plastic category which is 0.170, 0.671, and 0.109 for Polyethielene terephthalate (PET), High Density Polyethilene (HDPE), and Polypropylene (PP) plastic, respectively. Backpropagation Neural Network with one input layer, two hidden layer, and one output layer was used for classification each plastic category. Accuracy in training and testing data reach 0.9 and 0.8667 with 800 epoch, respectively. Confusion matrix method has used for prediction accuracy with 86.67%.
Keywords: Multispectral imaging, plastic waste type, Infrared Range, classification, Artificial Neural Network.

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

1803111112

Penerbit

Pekanbaru : Universitas Riau - FISIP -FISIKA., 2023

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

1803111112

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

FISIKA

Info Detail Spesifik

-

Pernyataan Tanggungjawab

tethi

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar