Waste classification using AutoEncoder network with integrated feature selection method in convolutional neural network models

[Display omitted] •Classification of organic and recyclable wastes with deep learning models.•We extracted and combined the features from the layer of 1000-features of CNN models.•Feature selection method was applied to the combined feature set to reduce features.•The dataset was rebuilt with the Au...

Full description

Saved in:
Bibliographic Details
Published in:Measurement : journal of the International Measurement Confederation Vol. 153; p. 107459
Main Authors: Toğaçar, Mesut, Ergen, Burhan, Cömert, Zafer
Format: Journal Article
Language:English
Published: London Elsevier Ltd 01.03.2020
Elsevier Science Ltd
Subjects:
Artificial intelligence
Artificial neural networks
AutoEncoder network
Classification
Datasets
Deep learning
Ecological monitoring
Feature extraction
Feature selection
Neural networks
Recycling
Recycling waste
Support vector machines
Waste containers
Waste disposal
Deep learning
Recycling waste
AutoEncoder network
Feature selection
ISSN:0263-2241, 1873-412X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] •Classification of organic and recyclable wastes with deep learning models.•We extracted and combined the features from the layer of 1000-features of CNN models.•Feature selection method was applied to the combined feature set to reduce features.•The dataset was rebuilt with the AutoEncoder model and the above steps were repeated.•The two feature sets obtained by feature selection were combined and classified. Unless adequate measures are taken for waste litter, the ecological balance may deteriorate over time. The wastes disposed of the trash can be divided into two classes that are organic and recycling types. In recent years, artificial intelligence is frequently mentioned in all areas of technology. In this study, the dataset used for the classification of waste is reconstructed with the AutoEncoder network. The feature sets are then extracted using two datasets by Convolutional Neural Network (CNN) architectures and these feature sets are combined. The Ridge Regression (RR) method performed on the combined feature set reduced the number of features and also revealed the efficient features. Support Vector Machines (SVMs) were used as classifiers in all experiments. The most successful classification accuracy in the experiments was 99.95%. In this study, it is seen that the proposed approach is successful in the classification of waste types.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0263-2241
1873-412X
DOI:10.1016/j.measurement.2019.107459