Pengenalan Gambar Botol Plastik dan Kaleng Minuman Menggunakan Metode Convolutional Neural Network

Regina Valentina, Silvia Rostianingsih, Alvin Nathaniel Tjondrowiguno

Abstract


Plastic bottles and cans are anorganic waste that cannot be decomposed by bacteria naturally and take a long time decomposed. Until now, people awareness to care about the environment is still low. Even though waste sorting is very important before the waste recycling process. According to Kediri City Environment, Hygiene and Gardening Agency, waste such as plastic and cans require special treatment for the recycling process. Until now, the process of sorting waste is still done manually by humans. This process require a lot of energy, a long time and still cannot overcome the amount of the waste nowadays.

This research uses Convolutional Neural Network (CNN) method for object recognition. There have been other research about the classification of plastic waste. Both of studies only use plastic waste as the object. There is no studies yet about cans waste. Therefore, this research will carried out an introduction to plastic bottles and cans waste.

Based on the result of the study, the activation function that suits the case is ELU. While using four convolutional layers, four max pooling layers, and three fully connected layers in total. This study uses 0.00001 for the learning rate, 0.8 for the dropout rate, and 50 times epoch. The result from test that were done by using this CNN model architecture is an accuracy rate of 86%.


Keywords


Convolutional Neural Network; waste; plastic bottle; metal can; image recognition

Full Text:

PDF

References


Dertat, A. 2017. Applied Deep Learning - Part 4: Convolutional Neural Networks. Retrieved September 4, 2019, from https://towardsdatascience.com/applied-deep-learning-part-4-convolutional-neural-networks-584bc134c1e2

Gamauf, T. 2018. Tensorflow Records? What they are and how to use them. Retrieved September 14, 2019, from 20 March 2018 website: https://medium.com/mostly-ai/tensorflow-records-what-they-are-and-how-to-use-them-c46bc4bbb564

Goodfellow, I., Yoshua, B., & Courville, A. 2016. Deep Learning. Retrieved May 27, 2019, from MIT Press website: https://www.deeplearningbook.org/

Özkan, K., Ergin, S., Işik, S., & Işikli, I. 2015. A new classification scheme of plastic wastes based upon recycling labels. Waste Management, 35, 29–35. https://doi.org/10.1016/j.wasman.2014.09.030

Saha, S. 2018. A Comprehensive Guide to Convolutional Neural Networks — the ELI5 way. Retrieved May 27, 2019, from https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53

Stanfords. 2018. Introduction to Convolutional Neural Networks. Retrieved May 27, 2019, from https://web.stanford.edu/class/cs231a/lectures/intro_cnn.pdf

Udofia, U. 2018. Basic Overview of Convolutional Neural Network (CNN). Retrieved May 27, 2019, from https://medium.com/@udemeudofia01/basic-overview-of-convolutional-neural-network-cnn-4fcc7dbb4f17

Wang, Z., Peng, B., Huang, Y., & Sun, G. 2019. Classification for plastic bottles recycling based on image recognition. Waste Management, 88, 170–181. https://doi.org/10.1016/j.wasman.2019.03.032


Refbacks

  • There are currently no refbacks.


Jurnal telah terindeks oleh :