A hybrid deep neural network for classification of schizophrenia using EEG Data

Abstract Schizophrenia is a serious mental illness that causes great harm to patients, so timely and accurate detection is essential. This study aimed to identify a better feature to represent electroencephalography (EEG) signals and improve the classification accuracy of patients with schizophrenia...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jie Sun, Rui Cao, Mengni Zhou, Waqar Hussain, Bin Wang, Jiayue Xue, Jie Xiang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/9b412826c98341fc94e5e087f0c1c1b8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9b412826c98341fc94e5e087f0c1c1b8
record_format	dspace
spelling	oai:doaj.org-article:9b412826c98341fc94e5e087f0c1c1b82021-12-02T11:35:41ZA hybrid deep neural network for classification of schizophrenia using EEG Data10.1038/s41598-021-83350-62045-2322https://doaj.org/article/9b412826c98341fc94e5e087f0c1c1b82021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83350-6https://doaj.org/toc/2045-2322Abstract Schizophrenia is a serious mental illness that causes great harm to patients, so timely and accurate detection is essential. This study aimed to identify a better feature to represent electroencephalography (EEG) signals and improve the classification accuracy of patients with schizophrenia and healthy controls by using EEG signals. Our research method involves two steps. First, the EEG time series is preprocessed, and the extracted time-domain and frequency-domain features are transformed into a sequence of red–green–blue (RGB) images that carry spatial information. Second, we construct hybrid deep neural networks (DNNs) that combine convolution neural networks and long short-term memory to address RGB images to classify schizophrenic patients and healthy controls. The results show that the fuzzy entropy (FuzzyEn) feature is more significant than the fast Fourier transform (FFT) feature in brain topography. The deep learning (DL) method that we propose achieves an average accuracy of 99.22% with FuzzyEn and an average accuracy of 96.34% with FFT. These results show that the best effect is to extract fuzzy features as input features from EEG time series and then use a hybrid DNN for classification. Compared with the most advanced methods in this field, significant improvements have been achieved.Jie SunRui CaoMengni ZhouWaqar HussainBin WangJiayue XueJie XiangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jie Sun Rui Cao Mengni Zhou Waqar Hussain Bin Wang Jiayue Xue Jie Xiang A hybrid deep neural network for classification of schizophrenia using EEG Data
description	Abstract Schizophrenia is a serious mental illness that causes great harm to patients, so timely and accurate detection is essential. This study aimed to identify a better feature to represent electroencephalography (EEG) signals and improve the classification accuracy of patients with schizophrenia and healthy controls by using EEG signals. Our research method involves two steps. First, the EEG time series is preprocessed, and the extracted time-domain and frequency-domain features are transformed into a sequence of red–green–blue (RGB) images that carry spatial information. Second, we construct hybrid deep neural networks (DNNs) that combine convolution neural networks and long short-term memory to address RGB images to classify schizophrenic patients and healthy controls. The results show that the fuzzy entropy (FuzzyEn) feature is more significant than the fast Fourier transform (FFT) feature in brain topography. The deep learning (DL) method that we propose achieves an average accuracy of 99.22% with FuzzyEn and an average accuracy of 96.34% with FFT. These results show that the best effect is to extract fuzzy features as input features from EEG time series and then use a hybrid DNN for classification. Compared with the most advanced methods in this field, significant improvements have been achieved.
format	article
author	Jie Sun Rui Cao Mengni Zhou Waqar Hussain Bin Wang Jiayue Xue Jie Xiang
author_facet	Jie Sun Rui Cao Mengni Zhou Waqar Hussain Bin Wang Jiayue Xue Jie Xiang
author_sort	Jie Sun
title	A hybrid deep neural network for classification of schizophrenia using EEG Data
title_short	A hybrid deep neural network for classification of schizophrenia using EEG Data
title_full	A hybrid deep neural network for classification of schizophrenia using EEG Data
title_fullStr	A hybrid deep neural network for classification of schizophrenia using EEG Data
title_full_unstemmed	A hybrid deep neural network for classification of schizophrenia using EEG Data
title_sort	a hybrid deep neural network for classification of schizophrenia using eeg data
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/9b412826c98341fc94e5e087f0c1c1b8
work_keys_str_mv	AT jiesun ahybriddeepneuralnetworkforclassificationofschizophreniausingeegdata AT ruicao ahybriddeepneuralnetworkforclassificationofschizophreniausingeegdata AT mengnizhou ahybriddeepneuralnetworkforclassificationofschizophreniausingeegdata AT waqarhussain ahybriddeepneuralnetworkforclassificationofschizophreniausingeegdata AT binwang ahybriddeepneuralnetworkforclassificationofschizophreniausingeegdata AT jiayuexue ahybriddeepneuralnetworkforclassificationofschizophreniausingeegdata AT jiexiang ahybriddeepneuralnetworkforclassificationofschizophreniausingeegdata
_version_	1718395834875248640

A hybrid deep neural network for classification of schizophrenia using EEG Data

Ejemplares similares