| dc.description.abstract | Nowadays, stress is one of the major issues where too much stress may lead to depression, fatigue and insomnia. Stress can be divided into two types called Eustress
and Distress. Eustress or positive stress refers to the positive stress which helps to
improve the performance of an individual. In contrast, Distress or negative stress can
devastate a person by creating depression and damage the quality of life. It is essential to comprehend and to figure out the state of current stress in numerical index. The development of a reliable data acquisition protocol is a crucial part to elicit mental stress in different level of stress. In this study, some modification on the existing Mental Arithmetic Task (MAT) has been made to ensure the designed protocol is capable to induce the different intensity of stress such as low, moderate and high. The dynamical excitation protocol and time pressure concept are proposed in this work. There are three validation methods have been used, namely, K Nearest Neighbor (KNN), Alpha Brain Asymmetry and statistical analysis (Paired T-test). As a result of this study, it was
found that the proposed experimental protocol is comparable as the verification has
been made with the following: (i) The t-test result based on physiological changes
during pre and post experiment were found to be statistically significant (p<0.01) (ii)
The mean value of Alpha Brain Asymmetry are comparable and have a potential to
discriminate between levels and (iii) the classification accuracy of 84% confirmed that
the proposed protocol have potential in classifying the mental stress level. Besides that,
the preprocessing technique applying elliptic filters with 256 data per frame is the most suitable technique. Five types of spectral estimator (Welch, Burg, Yule Walker,
Modified Covariance and Multiple Signal Classification) based feature extraction is
performed on the normalized signals. The extracted features are cross validated using
10-fold cross validation and classified using KNN and have been proved using
statistical analysis (ANOVA). The maximum mean classification rate of 86.75% is
achieved using Modified Covariance feature derived from alpha waves using KNN.
Besides that, this study found that F3 and F4 are the most informative electrodes with
the classification rate of 93.50%. Last but not least, a new algorithm has been proposed
based on the more established index, Alpha Asymmetry Score (AAS), as a reference.
Modifications have been made in term of the frequency band as a variable in the stress
index. The classification accuracy of the proposed Stress Asymmetry Score (SAS) is
approximately 96% which is 10% higher than AAS. The development of the stress
index promises new era of stress brain related research for future people’s benefit. | en_US |
