Search

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. [ABSTRACT FROM AUTHOR]

A method for computerized detection of heat stress is presented in this paper and tested on pre-recorded data from a range of subjects. The physiological changes that happen in the subjects are incorporated as fuzzy logic to distinguish the stress level of the subjects as chronic or acute stress. The sleep stage classification is done initially with the help of pre-established rules governed by American Academy of Sleep Medicine. After the sleep stage classification is done, data are further classified as chronic or acute stress with respect to their controlled states. The proposed algorithm employs adaptive neuro-fuzzy inference system and Mamdani fuzzy model and achieves an average classification accuracy of 89% in detecting stress levels. [ABSTRACT FROM AUTHOR]