EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network

EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network

Objective: Classification of sleep-wake states using multichannel electroencephalography (EEG) data that reliably work for neonates. Methods: A deep multilayer perceptron (MLP) neural network is developed to classify sleep-wake states using multichannel bipolar EEG signals, which takes an input vect...

Full description

Bibliographic Details
Main Authors: Saadullah Farooq Abbasi, Jawad Ahmad, Ahsen Tahir, Muhammad Awais, Chen Chen, Muhammad Irfan, Hafiza Ayesha Siddiqa, Abu Bakar Waqas, Xi Long, Bin Yin, Saeed Akbarzadeh, Chunmei Lu, Laishuan Wang, Wei Chen
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Neonatal sleep staging
electroencephalogram
classification
multilayer perceptron
neural network
Online Access:https://ieeexplore.ieee.org/document/9210487/
id doaj-d91922f5ffec4c74b4f2f6b88e9a2cd4
record_format Article
spelling doaj-d91922f5ffec4c74b4f2f6b88e9a2cd42021-03-30T04:20:55ZengIEEEIEEE Access2169-35362020-01-01818302518303410.1109/ACCESS.2020.30281829210487EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural NetworkSaadullah Farooq Abbasi0https://orcid.org/0000-0001-9814-3023Jawad Ahmad1https://orcid.org/0000-0001-6289-8248Ahsen Tahir2Muhammad Awais3https://orcid.org/0000-0002-0379-0744Chen Chen4https://orcid.org/0000-0001-7587-3314Muhammad Irfan5Hafiza Ayesha Siddiqa6Abu Bakar Waqas7Xi Long8https://orcid.org/0000-0001-9505-1270Bin Yin9https://orcid.org/0000-0001-9612-2376Saeed Akbarzadeh10https://orcid.org/0000-0001-6750-7971Chunmei Lu11Laishuan Wang12https://orcid.org/0000-0002-4126-0701Wei Chen13https://orcid.org/0000-0003-3720-718XDepartment of Electronic Engineering, School of Information Science and Technology, Center for Intelligent Medical Electronics, Fudan University, Shanghai, ChinaSchool of Computing, Edinburgh Napier University, Edinburgh, U.K.School of Computing, Engineering, and Built Environment, Glasgow Caledonian University, Glasgow, U.K.Department of Electronic Engineering, School of Information Science and Technology, Center for Intelligent Medical Electronics, Fudan University, Shanghai, ChinaDepartment of Electronic Engineering, School of Information Science and Technology, Center for Intelligent Medical Electronics, Fudan University, Shanghai, ChinaDepartment of Electronic Engineering, School of Information Science and Technology, Center for Intelligent Medical Electronics, Fudan University, Shanghai, ChinaDepartment of Electronic Engineering, School of Information Science and Technology, Center for Intelligent Medical Electronics, Fudan University, Shanghai, ChinaDepartment of Electronic Engineering, School of Information Science and Technology, Center for Intelligent Medical Electronics, Fudan University, Shanghai, ChinaDepartment of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The NetherlandsConnected Care and Personal Health Department, Philips Research, Shanghai, ChinaDepartment of Electronic Engineering, School of Information Science and Technology, Center for Intelligent Medical Electronics, Fudan University, Shanghai, ChinaDepartment of Neonatology, Children’s Hospital of Fudan University, Shanghai, ChinaDepartment of Neonatology, Children’s Hospital of Fudan University, Shanghai, ChinaDepartment of Electronic Engineering, School of Information Science and Technology, Center for Intelligent Medical Electronics, Fudan University, Shanghai, ChinaObjective: Classification of sleep-wake states using multichannel electroencephalography (EEG) data that reliably work for neonates. Methods: A deep multilayer perceptron (MLP) neural network is developed to classify sleep-wake states using multichannel bipolar EEG signals, which takes an input vector of size 108 containing the joint features of 9 channels. The network avoids any post-processing step in order to work as a full-fledged real-time application. For training and testing the model, EEG recordings of 3525 30-second segments from 19 neonates (postmenstrual age of 37 ± 05 weeks) are used. Results: For sleep-wake classification, mean Cohen's kappa between the network estimate and the ground truth annotation by human experts is 0.62. The maximum mean accuracy can reach up to 83% which, to date, is the highest accuracy for sleep-wake classification.https://ieeexplore.ieee.org/document/9210487/Neonatal sleep stagingelectroencephalogramclassificationmultilayer perceptronneural network
collection DOAJ
language English
format Article
sources DOAJ
author Saadullah Farooq Abbasi
Jawad Ahmad
Ahsen Tahir
Muhammad Awais
Chen Chen
Muhammad Irfan
Hafiza Ayesha Siddiqa
Abu Bakar Waqas
Xi Long
Bin Yin
Saeed Akbarzadeh
Chunmei Lu
Laishuan Wang
Wei Chen
spellingShingle Saadullah Farooq Abbasi
Jawad Ahmad
Ahsen Tahir
Muhammad Awais
Chen Chen
Muhammad Irfan
Hafiza Ayesha Siddiqa
Abu Bakar Waqas
Xi Long
Bin Yin
Saeed Akbarzadeh
Chunmei Lu
Laishuan Wang
Wei Chen
EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network
IEEE Access
Neonatal sleep staging
electroencephalogram
classification
multilayer perceptron
neural network
author_facet Saadullah Farooq Abbasi
Jawad Ahmad
Ahsen Tahir
Muhammad Awais
Chen Chen
Muhammad Irfan
Hafiza Ayesha Siddiqa
Abu Bakar Waqas
Xi Long
Bin Yin
Saeed Akbarzadeh
Chunmei Lu
Laishuan Wang
Wei Chen
author_sort Saadullah Farooq Abbasi
title EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network
title_short EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network
title_full EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network
title_fullStr EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network
title_full_unstemmed EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network
title_sort eeg-based neonatal sleep-wake classification using multilayer perceptron neural network
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2020-01-01
description Objective: Classification of sleep-wake states using multichannel electroencephalography (EEG) data that reliably work for neonates. Methods: A deep multilayer perceptron (MLP) neural network is developed to classify sleep-wake states using multichannel bipolar EEG signals, which takes an input vector of size 108 containing the joint features of 9 channels. The network avoids any post-processing step in order to work as a full-fledged real-time application. For training and testing the model, EEG recordings of 3525 30-second segments from 19 neonates (postmenstrual age of 37 ± 05 weeks) are used. Results: For sleep-wake classification, mean Cohen's kappa between the network estimate and the ground truth annotation by human experts is 0.62. The maximum mean accuracy can reach up to 83% which, to date, is the highest accuracy for sleep-wake classification.
topic Neonatal sleep staging
electroencephalogram
classification
multilayer perceptron
neural network
url https://ieeexplore.ieee.org/document/9210487/
work_keys_str_mv AT saadullahfarooqabbasi eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT jawadahmad eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT ahsentahir eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT muhammadawais eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT chenchen eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT muhammadirfan eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT hafizaayeshasiddiqa eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT abubakarwaqas eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT xilong eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT binyin eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT saeedakbarzadeh eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT chunmeilu eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT laishuanwang eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
AT weichen eegbasedneonatalsleepwakeclassificationusingmultilayerperceptronneuralnetwork
_version_ 1724182026246946816

Similar Items