PCA-Aided FCM Identifies Stressful Events of Sleep EEG Under Hot Environment

Abstract

In this study, Principal Component Analysis (PCA) uses a vector space transform to reduce the dimensionality of large datasets for sleep EEG. Fuzzy C means (FCM) clustering approach has been used to classify the three stages of sleep EEG – Awake, SWS and REM under the chronic and acute hot environment. Sleep data are acquired by exposing the subjects to environmental heat stress. Performance of the system in stress classification of EEG signals under acute and chronic environmental heat conditions has achieved the accuracy of 91.6%. Overall performance of the algorithm shows that subjects under acute exposure of heat are detected with 93.2% accuracy as compared to the subjects exposed to chronic heat stress. The first two components alone accounted for almost half of the total variance. The first principle component comprising delta, alpha and beta powers explains about 28% of the total variance with an eigenvalue of 3.195. Relative powers of delta, alpha and beta seem to be significant as compared to that of theta. The second principal component consisted of approximately 22% of the total variance with an eigenvalue of 2.15.

KEYWORDS:

• Awake
• FCM
• Heat stress
• PCA
• Rapid eye movement
• Sleep EEG
• SWS

Additional information

Notes on contributors

Prabhat Kumar Upadhyay

Prabhat Kumar Upadhyay is an assistant professor in Electrical & Electronics Engineering Department, Birla Institute of Technology, Ranchi, India. He obtained his PhD (in technology) degree from BIT Mesra in 2011. He has been working as a Faculty in the EEE Department of BIT Mesra main campus and its offshore campuses in the UAE and Oman since the last 19 years. He has published many research papers in various journals and conferences. His current research interest include brain signals, signal processing and soft computing. Corresponding author. E-mail: [email protected]

Chetna Nagpal

Chetna Nagpal completed MTech in electronics and communication from Maharishi Dayananad University, Rohtak,India in 2008 and PhD from Banasthali Vidyapith, in 2019. She is having 8 years of teaching experience at various renowned universities in the UAE and India. Her research area includes signal processing with soft computing techniques. She has published several research papers in international journals and international and national conferences. E-mail: [email protected]