A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data Classification
This paper proposes a novel data classification framework, combining sparse auto-encoders (SAEs) and a post-processing system consisting of a linear system model relying on Particle Swarm Optimization (PSO) algorithm. All the sensitive and high-level features are extracted by using the first auto-en...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/21/6378 |
id |
doaj-0144acaf05264d2c855c045f64fd6a67 |
---|---|
record_format |
Article |
spelling |
doaj-0144acaf05264d2c855c045f64fd6a672020-11-25T03:57:09ZengMDPI AGSensors1424-82202020-11-01206378637810.3390/s20216378A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data ClassificationAhmad M. Karim0Hilal Kaya1Mehmet Serdar Güzel2Mehmet R. Tolun3Fatih V. Çelebi4Alok Mishra5Computer Engineering Department, AYBU, Ankara 06830, TurkeyComputer Engineering Department, AYBU, Ankara 06830, TurkeyComputer Engineering Department, Ankara University, Ankara 06830, TurkeyComputer Engineering Department, Konya Food and Agriculture University, Konya 42080, TurkeyComputer Engineering Department, AYBU, Ankara 06830, TurkeyFaculty of Logistics, Molde University College-Specialized University in Logistics, 6402 Molde, NorwayThis paper proposes a novel data classification framework, combining sparse auto-encoders (SAEs) and a post-processing system consisting of a linear system model relying on Particle Swarm Optimization (PSO) algorithm. All the sensitive and high-level features are extracted by using the first auto-encoder which is wired to the second auto-encoder, followed by a Softmax function layer to classify the extracted features obtained from the second layer. The two auto-encoders and the Softmax classifier are stacked in order to be trained in a supervised approach using the well-known backpropagation algorithm to enhance the performance of the neural network. Afterwards, the linear model transforms the calculated output of the deep stacked sparse auto-encoder to a value close to the anticipated output. This simple transformation increases the overall data classification performance of the stacked sparse auto-encoder architecture. The PSO algorithm allows the estimation of the parameters of the linear model in a metaheuristic policy. The proposed framework is validated by using three public datasets, which present promising results when compared with the current literature. Furthermore, the framework can be applied to any data classification problem by considering minor updates such as altering some parameters including input features, hidden neurons and output classes.https://www.mdpi.com/1424-8220/20/21/6378deep sparse auto-encodersmedical diagnosislinear modeldata classificationPSO algorithm |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ahmad M. Karim Hilal Kaya Mehmet Serdar Güzel Mehmet R. Tolun Fatih V. Çelebi Alok Mishra |
spellingShingle |
Ahmad M. Karim Hilal Kaya Mehmet Serdar Güzel Mehmet R. Tolun Fatih V. Çelebi Alok Mishra A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data Classification Sensors deep sparse auto-encoders medical diagnosis linear model data classification PSO algorithm |
author_facet |
Ahmad M. Karim Hilal Kaya Mehmet Serdar Güzel Mehmet R. Tolun Fatih V. Çelebi Alok Mishra |
author_sort |
Ahmad M. Karim |
title |
A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data Classification |
title_short |
A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data Classification |
title_full |
A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data Classification |
title_fullStr |
A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data Classification |
title_full_unstemmed |
A Novel Framework Using Deep Auto-Encoders Based Linear Model for Data Classification |
title_sort |
novel framework using deep auto-encoders based linear model for data classification |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-11-01 |
description |
This paper proposes a novel data classification framework, combining sparse auto-encoders (SAEs) and a post-processing system consisting of a linear system model relying on Particle Swarm Optimization (PSO) algorithm. All the sensitive and high-level features are extracted by using the first auto-encoder which is wired to the second auto-encoder, followed by a Softmax function layer to classify the extracted features obtained from the second layer. The two auto-encoders and the Softmax classifier are stacked in order to be trained in a supervised approach using the well-known backpropagation algorithm to enhance the performance of the neural network. Afterwards, the linear model transforms the calculated output of the deep stacked sparse auto-encoder to a value close to the anticipated output. This simple transformation increases the overall data classification performance of the stacked sparse auto-encoder architecture. The PSO algorithm allows the estimation of the parameters of the linear model in a metaheuristic policy. The proposed framework is validated by using three public datasets, which present promising results when compared with the current literature. Furthermore, the framework can be applied to any data classification problem by considering minor updates such as altering some parameters including input features, hidden neurons and output classes. |
topic |
deep sparse auto-encoders medical diagnosis linear model data classification PSO algorithm |
url |
https://www.mdpi.com/1424-8220/20/21/6378 |
work_keys_str_mv |
AT ahmadmkarim anovelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT hilalkaya anovelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT mehmetserdarguzel anovelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT mehmetrtolun anovelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT fatihvcelebi anovelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT alokmishra anovelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT ahmadmkarim novelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT hilalkaya novelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT mehmetserdarguzel novelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT mehmetrtolun novelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT fatihvcelebi novelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification AT alokmishra novelframeworkusingdeepautoencodersbasedlinearmodelfordataclassification |
_version_ |
1724461659787886592 |