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

Abbasi, Saadullah Farooq; Ahmad, Jawad; Tahir, Ahsen; Awais, Muhammad; Chen, Chen; Irfan, Muhammad; Siddiqa, Hafiza Ayesha; Waqas, Abu Bakar; Long, Xi; Yin, Bin; Akbarzadeh, Saeed; Lu, Chunmei; Wang, Laishuan; Chen, Wei

Abstract

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.

Citation

Abbasi, S. F., Ahmad, J., Tahir, A., Awais, M., Chen, C., Irfan, M., Siddiqa, H. A., Waqas, A. B., Long, X., Yin, B., Akbarzadeh, S., Lu, C., Wang, L., & Chen, W. (2020). EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network. IEEE Access, 8, 183025-183034. https://doi.org/10.1109/access.2020.3028182

• Journal Article Type: Article
• Acceptance Date: Sep 23, 2020
• Online Publication Date: Oct 1, 2020
• Publication Date: 2020
• Deposit Date: Oct 29, 2020
• Publicly Available Date: Oct 29, 2020
• Journal: IEEE Access
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 8
• Pages: 183025-183034
• DOI: https://doi.org/10.1109/access.2020.3028182
• Keywords: Neonatal sleep staging, electroencephalogram, classification, multilayer perceptron, neural network
• Public URL: http://researchrepository.napier.ac.uk/Output/2696656