Cargando…

EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network

The use of electroencephalography (EEG) has recently grown as a means to diagnose neurodegenerative pathologies such as Alzheimer’s disease (AD). AD recognition can benefit from machine learning methods that, compared with traditional manual diagnosis methods, have higher reliability and improved re...

Descripción completa

Detalles Bibliográficos
Autores principales: Alessandrini, Michele, Biagetti, Giorgio, Crippa, Paolo, Falaschetti, Laura, Luzzi, Simona, Turchetti, Claudio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9145212/
https://www.ncbi.nlm.nih.gov/pubmed/35632105
http://dx.doi.org/10.3390/s22103696
_version_ 1784716235932434432
author Alessandrini, Michele
Biagetti, Giorgio
Crippa, Paolo
Falaschetti, Laura
Luzzi, Simona
Turchetti, Claudio
author_facet Alessandrini, Michele
Biagetti, Giorgio
Crippa, Paolo
Falaschetti, Laura
Luzzi, Simona
Turchetti, Claudio
author_sort Alessandrini, Michele
collection PubMed
description The use of electroencephalography (EEG) has recently grown as a means to diagnose neurodegenerative pathologies such as Alzheimer’s disease (AD). AD recognition can benefit from machine learning methods that, compared with traditional manual diagnosis methods, have higher reliability and improved recognition accuracy, being able to manage large amounts of data. Nevertheless, machine learning methods may exhibit lower accuracies when faced with incomplete, corrupted, or otherwise missing data, so it is important do develop robust pre-processing techniques do deal with incomplete data. The aim of this paper is to develop an automatic classification method that can still work well with EEG data affected by artifacts, as can arise during the collection with, e.g., a wireless system that can lose packets. We show that a recurrent neural network (RNN) can operate successfully even in the case of significantly corrupted data, when it is pre-filtered by the robust principal component analysis (RPCA) algorithm. RPCA was selected because of its stated ability to remove outliers from the signal. To demonstrate this idea, we first develop an RNN which operates on EEG data, properly processed through traditional PCA; then, we use corrupted data as input and process them with RPCA to filter outlier components, showing that even with data corruption causing up to 20% erasures, the RPCA was able to increase the detection accuracy by about 5% with respect to the baseline PCA.
format Online
Article
Text
id pubmed-9145212
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91452122022-05-29 EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network Alessandrini, Michele Biagetti, Giorgio Crippa, Paolo Falaschetti, Laura Luzzi, Simona Turchetti, Claudio Sensors (Basel) Article The use of electroencephalography (EEG) has recently grown as a means to diagnose neurodegenerative pathologies such as Alzheimer’s disease (AD). AD recognition can benefit from machine learning methods that, compared with traditional manual diagnosis methods, have higher reliability and improved recognition accuracy, being able to manage large amounts of data. Nevertheless, machine learning methods may exhibit lower accuracies when faced with incomplete, corrupted, or otherwise missing data, so it is important do develop robust pre-processing techniques do deal with incomplete data. The aim of this paper is to develop an automatic classification method that can still work well with EEG data affected by artifacts, as can arise during the collection with, e.g., a wireless system that can lose packets. We show that a recurrent neural network (RNN) can operate successfully even in the case of significantly corrupted data, when it is pre-filtered by the robust principal component analysis (RPCA) algorithm. RPCA was selected because of its stated ability to remove outliers from the signal. To demonstrate this idea, we first develop an RNN which operates on EEG data, properly processed through traditional PCA; then, we use corrupted data as input and process them with RPCA to filter outlier components, showing that even with data corruption causing up to 20% erasures, the RPCA was able to increase the detection accuracy by about 5% with respect to the baseline PCA. MDPI 2022-05-12 /pmc/articles/PMC9145212/ /pubmed/35632105 http://dx.doi.org/10.3390/s22103696 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Alessandrini, Michele
Biagetti, Giorgio
Crippa, Paolo
Falaschetti, Laura
Luzzi, Simona
Turchetti, Claudio
EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network
title EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network
title_full EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network
title_fullStr EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network
title_full_unstemmed EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network
title_short EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network
title_sort eeg-based alzheimer’s disease recognition using robust-pca and lstm recurrent neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9145212/
https://www.ncbi.nlm.nih.gov/pubmed/35632105
http://dx.doi.org/10.3390/s22103696
work_keys_str_mv AT alessandrinimichele eegbasedalzheimersdiseaserecognitionusingrobustpcaandlstmrecurrentneuralnetwork
AT biagettigiorgio eegbasedalzheimersdiseaserecognitionusingrobustpcaandlstmrecurrentneuralnetwork
AT crippapaolo eegbasedalzheimersdiseaserecognitionusingrobustpcaandlstmrecurrentneuralnetwork
AT falaschettilaura eegbasedalzheimersdiseaserecognitionusingrobustpcaandlstmrecurrentneuralnetwork
AT luzzisimona eegbasedalzheimersdiseaserecognitionusingrobustpcaandlstmrecurrentneuralnetwork
AT turchetticlaudio eegbasedalzheimersdiseaserecognitionusingrobustpcaandlstmrecurrentneuralnetwork