000			02495nam a22001937a 4500
003			BML
082			_a006.3 _bPHU
100			_aPhutela, Nishtha
245			_aDevelopment of stress induction and detection system to study its effect on brain
260			_aGurgaon _bBML Munjal University _c2022
300			_a139p.
502			_aThesis submitted in the fulfillment of the requirement for the degree of Doctor of Philosophy by Nishtha Phutela Under the supervision of Dr. Devanjali Relan, Prof. Goldie Gabrani and Prof. Ponnurangam Kumaraguru _bDoctor of Philosophy _d2022
520			_aStress has become a significant mental health problem of the 21st century. The number of people suffering from stress is increasing rapidly. Thus, easy-to-use, inexpensive, and accurate biomarkers are needed to detect stress during its inception. Early detection of stress-related diseases allows people to access healthcare services. This thesis focuses on the development of stress stimuli and the detection of stress induced by these stimuli. Identifying brain regions affected while exposing the subject to these stressful stimuli has also been done. Three different stimuli, viz. videos, gamified application, and a game, are investigated to study their effect as stress induction stimuli. To this end, in this thesis, a system is proposed to classify participants into stressed and non-stressed categories using machine learning, deep learning, and statistical techniques. The statistical significance between stressed and non-stressed was found using Higuchi Fractal Dimensions (HFD) feature extracted from EEG. This feature also helped identify the brain s most affected region due to stress. Another outcome of this thesis is the extra annotation of the ground truth which further helps to validate the participant s experience under the influence of stressful stimuli. This annotation was performed by evaluating participant performance under time pressure. In addition, a technique based on in-game analytics is presented to complement the betterment of self-reported data. Further, another dimension utilizing signatures from WiFi Media Access Control (MAC) layer traffic is presented to detect stress indicators in a device-agnostic way.
650			_aEngineering and Technology
650			_aComputer Science Artificial Intelligence
856			_uhttps://shodhganga.inflibnet.ac.in/handle/10603/444027
856			_uhttp://drc.bml.edu.in:8080/jspui/handle/123456789/2836
942			_2ddc _cTH
999			_c10139 _d10139